The moat looks deep today but it's going to become more shallow every year.
Training a new model from scratch takes serious resources. Post-training/fine-tuning an existing model, dramatically less. The knowledge for the process was esoteric two years ago, now you can ask a current model (one of several) to walk you through it, while building the tools to do it as you go. Several of my recent weekend projects have been exactly that sort of thing, just so I understand it better. "Let's make a LoRA", "let's generate a corpus of training data for fine-tuning a model for X task", "how can I put my face in a text-to-image model?" stuff like that. All of this is do-able on kinda modest local hardware (a couple of old GPUs or a Strix Halo or DGX Spark or big Mac Studio), or for a few bucks or a few hundred bucks or a few thousand bucks of cloud compute, depending on scale.
Scale that up to corporate or startup scale, with the money that's been flowing into AI for the past couple/few years, and it's obviously there's going to be a lot of competition just as the top model makers need to start ringing the cash register. That's a lot of opportunities for people to look at their ballooning Claude usage costs and find other ways to do the same thing for drastically less money. $100/month or $200/month is a no-brainer for Claude Code with probably the best model for coding, but they're pushing more users to usage-based billing which becomes cost-prohibitive real fast.
So, they desperately need to continue to be among the only ways to solve the hardest problems, and they need the alternatives to cost a similar amount. They can count on OpenAI and Google to ratchet up prices, too. They probably can't count on everybody, especially the vendors in China with different economics, to do it. And, they can't count on companies to look at their own usage and not ask, "Can we train a smaller specialist model that does this one thing we're using the Anthropic API most heavily for?"
I'm hoping they just mean stuff like using Claude for distillation by e.g. Chinese model makers, and not "how do I fine-tune Gemma 4 to write more like me?" or whatever.
What moat? You answered yourself: "capital intensive"
But, history says the supercomputer of today will fit in your pocket in a few years.
They've bought up all the RAM and GPUs, which pushes the capital requirements upward for everyone else. But, they can't corner the market forever, there are too many competing interests. AMD and Intel keep making new GPUs and APUs. The memory makers can't just sell to only AI companies forever, if they do Chinese manufacturers will move in and eventually eat them from below (as has happened many times before).
They have a moat today, and it's just that it's really expensive to train and host frontier models, especially at commercial scale. It used to be there was also some secret sauce to making it fast and efficient. But, secret sauce is being published daily by all sorts of researchers, folks are figuring out how to do more with less and it often finds its way into llama.cpp or vLLM or SGLang within days or weeks.
> But, history says the supercomputer of today will fit in your pocket in a few years.
I don't think this will be true in the same time span anymore. Each miniaturization is costing more and more money.
Perhaps they'll come up with exotic fundamental improvements, but I don't think the rate of improvement of compute/watt will match the previous decades.
Yeah, that's probably true, but we're also seeing that there's still tons of inefficiencies in how LLMs are being run. Seems like every couple months there's some new technique to squeeze more performance out of less hardware. KV caching improvements, fast attention, speculative decoding, dynamic quantization, quantization aware training, etc.
That said, I recently replaced my five year old self-built PC (with a top-of-the-line desktop CPU, chipset, memory, and GPU of the time) with a new everything-the-best build, and while it's clear we're not keeping up with Moore's Law anymore, it's still 4-5 times faster for compute-intensive stuff, especially parallelizable tasks. We're still getting faster/cheaper. So, the time scale is maybe ten years rather than five.
Really the biggest concerns are not computers getting spectacularly faster, but 'intelligence' algorithms getting orders of magnitude better.
Drop the power requirements 1000 fold, and yea you will be able to make your own SOTA model on the cheap. The problem is the person that has a few exaflops of power will still leave you in the dust in the intelligence explosion that would happen after an event like this.
Depends upon the intelligence vs compute scaling law— which I think no one really knows. Pretty likely to be some degree of diminishing returns, but how much? Is it logarithmic, inverse quadratic, …
If training models gets way cheaper, I would expect the diminishing returns to get steeper too.
>Pretty likely to be some degree of diminishing returns
intelligence may be different. If we look at biological brains - do we get diminishing returns or completely opposite scaling law when we compare our brain against say gorilla's ?
Single clock speed hasn't had much of an upgrade, but the architecture for doing exactly what they are doing? That will improve for at least 5-10 years. There are both huge power gains from Processing in Memory (PIM) chips (70-80% discount in energy), and improvements to engineering to make memory cheaper and cheaper.
That is such a crazy way to start a response to someone trying to argue with you. I should try this. That's amazing. I know you didn't mean it as a trick, at least I'm pretty sure you meant it sincerely, but I'm just struck by the power of it to defuse and redirect the conversation. And this was a very low-grade example, but I could imagine this being useful in much more heated contexts.
I think in general stripping away the parts you agree with from the argument works great, because it strips away a whole lot of potential for ending up indirectly arguing over things that aren't in contention, and it often also defuses the rest when it turns out the core of the argument perhaps is much smaller than people are willing to get invested in.
How do you do that without sounding negative? Because by doing that there's the risk of the general impression "we didn't agree", as you basically focused on the disagreements.
Usually people are taught these techniques at the management courses. If you're at a BigCorp where they push managers through such courses - you can hear a lot of that stuff in your manager's speech if you pay attention to it.
Is there an endgame where even this is considered overly complex? Instead of starving the competition by buying up all the compute, why not just buy up… all the money!? Hoover up as much investment capital as possible so that your competitors can’t get funding.
The other half of the moat is the data they stole from everyone else, some of it illegally. So, be sure they will do everything in their power to stop others from getting that data freely.
Yeah, I think a lot of the "slow down" rumblings we're hearing from OpenAI and Anthropic are really overtures toward regulatory capture; basically, "now that we're in the lead, we need to lock this shit down so nobody else can catch up."
Other models arent even close except for gpt 5.5. You're dead wrong on that. You read too many benchmarks and/or chinese propaganda. There hasn't been a serious contender in agentic SWE besides OAI and anthropic for a long time, and no chinese model has even reached opus 4.5 performance yet. The moat isnt insurmountable but it is very solid for at least a 12 month lead time. Which is such an insane amount of time in this landscape and industry. The moat is stretching, not shrinking, on agentic SWE. And that is literally the only moat that matters for RSI.
DeepSeek 4 Pro is performing agentic SWE tasks for me quite well. It can't do everything Opus can do, but if OpenAI and Anthropic disappeared tomorrow, I'd figure out ways to make it work with harness improvements and other optimizations.
Anthropic can stretch the moat all they want, but in the department of trust, they put a final nail in their coffin today. Anthropic is pure evil at this point.
'evil' lol. Every single corporation you deal with is evil then. it's greed. and almost every large model provider is guilty of it. China is all open source right now. cool! gee i wonder what would happen if they ever actually achieved SOTA? They would clamp down on that so fast Dadio's dradel would spin
China isnt "all open source" they still keep their top models out of the public view. Its easy to "open source" models when they're so far behind very few will pay for them.
Open source in quotes because they are not open source and not even close to open source.
> Every single corporation you deal with is evil then.
I don't know. If my ISP started MITMing my traffic so that they could silently rewrite packets, and/or deleting files on my computer because they thought me sharing wireless AP with my SO was me trying to compete with them, I'd call them evil.
I believe they tried something similar to the first one a few years ago in the US, and I remember people called that evil to the point where tech giants shut down their websites in protest.
> gee i wonder what would happen if they ever actually achieved SOTA? They would clamp down on that so fast Dadio's dradel would spin
Cool. Let them "achieve SOTA" and close down the models. Let the pendulum swing the other way.
You seem to not understand what China's goal is here. They want the AI bubble to burst and take your 401ks with it. And OAI/ANTs decisions are driving you towards that cliff.
Honest question, is it possible that since might be using the latest/best model to analyze and improve the existing ones, the moat will expand exponentially, making the models better and more efficient at each iteration until there is no point in competing?
I use gpt 5.5 at work (because they pay for it) and DeepSeek at home (because I pay for it) and while I do agree one is better than the other, I think you’re really overstating how far apart they are. Just my take.
What's 12 months lead time worth? Not much from what I can tell. Contrary to what these AI companies might tell you, if an AI model can't do it, a human can still do the work.
Most of HN is stuck in this fantasyland where they insist their local LLM setup is comparable to Opus 4.8 or GPT 5.5. It's like a collective delusion, I've never seen anything like it.
Wast majority of software engineers do very little except of moving JSONs around and building CRUDs.
It's quite obvious that when you dont try to do something particularly complex there will be literally no difference between GPT, Claude, Gemini and Deepseek.
Fot many things I'm doing in gamedev Gemini 2.5 Pro was already good enough even though it released more than year ago.
Some of the new and open models are very capable now, The truth is, the value of the model is in the mind of the user - the big names are impressive to those who know little and are dazed by little, but they are bound to end up wrong regardless of how good the model is.
This is ridiculous. How about the rational users who use the best current model regardless of brand? The value of the model is in the quality of the output over time. I give every major model a chance. Coding and scripts in the chat are nothing compared to the power of agentic SWEEEEEEEEE. And nothing is remotely close to claude and gpt. If you're comfortable with being well behind SOTA intelligence, then good for you, but some of us prefer to be efficient with our time and resources. With your mindset, you will never truly SWEEEEEEEEEEEEEEEEEEEE
<The memory makers can't just sell to only AI companies forever, if they do Chinese manufacturers will move in and eventually eat them from below (as has happened many times before)>
Unfortunately this has been happening almost forever. You can spend 10s of thousands of $$ design, prototyping, building & marketing anything, whether a physical product or software & some company where the wages are lower are going to come along, build it cheaper (not necessarily better quality either) and ship it to the world.
As a result, the other countries import more stuff "because it is cheaper" and eventually local manufacturing dwindles away to virtually nothing. That is the case here in Australia. Our manufacturing base has shrunk to stuff all compared to what we had 30 years ago & as a result we are poorer as a nation for it
>Unfortunately this has been happening almost forever. You can spend 10s of thousands of $$ design, prototyping, building & marketing anything, whether a physical product or software & some company where the wages are lower are going to come along, build it cheaper (not necessarily better quality either) and ship it to the world.
>As a result, the other countries import more stuff "because it is cheaper" and eventually local manufacturing dwindles away to virtually nothing. That is the case here in Australia. Our manufacturing base has shrunk to stuff all compared to what we had 30 years ago & as a result we are poorer as a nation for it
Then the companies in that country need to learn how to be more competitive and governments need to learn how not to overregulate, overtax and raise barriers.
Given that Anthropic has never released anything open weights I wouldn’t count on the fact that they view finetuning Gemma 4 as something allowable. I think they think nobody other than Anthropic should have AI
Does it? What can this model do that I both want and cannot already do?
Anthropic made a nice little post saying how dangerous it is, because it is good enough to eat their own business. But I don't want to eat their business. They also said it was good at playing Slay the Spire, but I can't think of anything more insulting than have a machine do that in my place. That's MY comfort game, not something for a stupid Clanker to take away.
What makes you say usage billing is cost prohibitive? I use as much flagship model as I could possibly want and it's like four figures a month. That's totally doable compared to SWE pay.
I don't feel strongly about anything most folks are arguing back and forth about, but this one is obviously wrong.
Everybody and their brother has made an agent. There are toolkits. You can whip one up in an afternoon.
Not only that, I've found models often perform worse, or at least cost more and take longer, in a big complicated agent like Claude Code, including Anthropic models. They want proprietary doodads hanging off the side (multi agent orchestration, memory, things of that nature) to matter, because they can lock you into tools like that. But, top models can do everything with bash.
There is no training from scratch though. It's kind of, "first create the universe" framing pretention. All models rely heavily on the large corpus that humanity built through large span of time. And of course humanity didn't create the condition of its emergence.
Given the high rate of false positives people are reporting for the non-silent cybersecurity, biological, etc., safeguards, there is a strong likelihood that you will encounter silently nerfed behavior even if you are _not_ violating their TOS.
Ultimately this will be evident in the way customers / external benchmarkers experience Fable. Hopefully competition will drive future models toward a lower false positive rate. Until that happens, Mythos and Fable users seem likely to have pretty divergent experiences.
It's such an obviously bad policy, it's mind-boggling that they thought this was a good idea. It just breeds paranoia and mistrust, especially when people are already a bit paranoid about silent model quantification for cost cutting reasons.
I'm a medical physicist. I use the word nuclear a lot. Opus is fine (well, 99% of the time - I've certainly hit the CBRN filters a few times and even been invited to email anthropic about the false positives).
Fable has literally refused to work on any of my problems (even those about fluid dynamics!) and just tells me that I'm violating anthropic's AUP.
Just so everyone is aware. Anthropic has been sabotaging AI researchers and their codebases and shadow-nerfing accounts for several years at this point. This isn't new, but they hadn't disclosed it until now. Likely because it is getting to the point where it's too noticeable, or they're concerned about it leaking from employees.
Furthermore, the fact that they do these things, despite the incredible backlash... Just imagine what they're doing what your data and your IP.
I guess it’s better they’re open about doing bad things. But now it’s a problem that they think this sets a precedent. They are one step away from feeling justified in using claude code running on a deepseek engineers laptop to hack deepseek to destroy their training system.
It’s not pretty, but if Anthropic is the E Corp of this timeline, we’re not being creative enough. There’s better targets out there for this comparison.
They're just getting started, and every statement/decision they make becomes more concerning than the previous one.
Isn't it concerning that a single company unilaterally decided for the world that they're the ultimate gatekeepers and they decide who gets access to the frontier artifical intelligence and in which capacity?
Who elected Amodei to decide which projects get to have the access to a dual-use cyber model and which get a model which sabotages? How is this not straight from E Corp's rulebook?
I re-subscribed to GPT's "PLUS" plan after ditching Anthropic for lack luster results... one of the first coding tasks I gave it resulted in a progress/thinking message that said something to the effect of (it vanished too quickly to get a screen shot unfortunately):
Evaluating client value
It took me aback. Note: the code had nothing to do with "client value".
Behind the scenes it is not hard to imagine OpenAI, Anthropic, et al simply minimizing processing for clients - like me - that are hopping from one to another to chase the just released SOTA model.
Isn't that completely expected when the intermediary has that kind of control? Amazon, Uber, Meta, Google... they all abuse their position. You are an Uber driver and accept everything because you need the money? Uber will pay you less because you apparently don't have a choice. There are so many examples of such behaviour that I can't remember them all.
Why wouldn't an AI company do exactly the same? You seem to be an employee of a BigCorp already locked in? Let's make you use more tokens, nobody will see. You seem to be testing our product for your company that is currently using a competitor? Let's give you more token to bias you.
Even if such behaviour was punished for purposely doing it, the companies would converge towards doing it without realising, by "tuning stuff" without understanding exactly what it does other than increase profit. But we don't have to go there: that behaviour is simply not punished, we know it.
This is a fun peek into the economic implications of RSI/ASI. Because it's so infinitely valuable that it basically destroys all markets, labs will eventually do stuff like stop releasing models completely and skipping out on contracted commitments because they'll have the power to just drive their competitors out of business before the legal battle gets expensive.
Cloud providers - at first smaller ones, then the hyperscalers - will follow suit, completely closing sales to anyone but the labs and demanding payment in equity/direct decision-making power rather than cash. There's no particular reason why the inference/training split has to be 80/20, and no amount of willingness to pay can help you in an event that turns your money worthless.
I don't think this scenario makes sense. It's one of a class of scenarios I've seen several of, that simultaneously assume:
A) ASI is developed and massively overshadows the rest of the world economy
B) the world still has rule of law, contracts, business, well-developed finance, etc
You can get to a lot of weird conclusions if you assume both A and B, but I think the much more likely scenario is that if A happens, B stops being true in short order. If you are a company and you have ASI, you just stop caring about business and money and economics, and your outcomes instead start looking like "you conquer the world" or "you upload the board of directors to a fleet of von Neumann probes" or "you messed up, everyone dies".
There will be a brief(or, depending on the underlying rules of reality ASI uncovers, not-so-brief) period where A and B do overlap - we have superintelligence but still have to run experiments, manufacture robots, test new drugs in vivo, etc. That period is in and of itself dangerous for the labs, because many entities can just stop them by denying necessary inputs. For the labs to conquer the world, they'll need cooperation - from the state, from robotics companies, from compute companies, from the mining and energy and agriculture sectors.
There will be a period of time where markets attempt to run in a business-as-usual way while the transactions that matter happen as power-sharing arrangements - spots on the "AI Governance Board" or the "uploaded to von neumann probe" club. Markets will still matter in that the labs will need the state to overturn market obstacles to control of the world.
The existence of the A-B overlap also suggests to me that the US-China gap is less dire for China than it appears - they may be able to use their superior industrial, robotics, and scientific base to win the second leg of the race despite losing the first.
The combination of A and B is cyberpunk at its core, it takes off in the form of corporate consolidation and then control of the government. Large corporations will still have the rule of law between each other because they'll have both money and hard power. The average individual that wants to rise up against said corps will quickly be identified by ubiquitous surveillance and imprisoned/slave labor camped.
I don't think one Claude can replace ten engineers of the caliber it takes to build a billion dollar company.
I also don't think that every set of ten engineers of that level builds a billion dollar company every time.
There is also a limit to the number of billion dollar companies that can be built before being a "billion dollar company" no longer means much (see: Zimbabwe).
Not really. It's possible they could, but in practice they cannot. Creating a billion dollar company requires a good idea, good timing, and a lot of luck, the engineers are the least important part.
More than that it takes things like the right social connections, strong marketing, insight into customer demand, infrastructure spend, etc. You can't normally just convert engineering effort into profit in the way implied.
this wont be possible by the time its possible. there would be massive deflation. why would i care about 10 engineeers prompts when i can prompt it myself
There's literally no indication that this is the case, or will ever be. Unless you're a completely naive person who's impressed with all output of an LLM because you don't know what you're talking about. These models aren't impressive, and the people who think they are impressive are even less impressive.
Especially when you can actively choose to not use Anthropic. They think they have a moat from all of the IP they've stolen. Just wait until there's nothing more to steal and the laws eventually turn against them. And let's be honest about these companies. It is very much Dario and Sam and Sundar and Mark and Peter and Elon and... These are the choices they are making and hopefully they are held accountable both legally and within society as a whole.
No, you pretty obviously didn't understand it, at least in the sense of ASI being talked about. The whole "oh don't buy it" stops mattering. Humans are no longer the sole creators of information and intelligence. That is AI no longer has to steal, but humans will have to beg, borrow, or steal the information/products that ASI creates.
Notably, it says they will notify you if they downgrade your responses due to suspected distillation (trying to reverse engineer their model).
But if you merely ask it questions about the process of developing a new model ("for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design") that's where it will silently downgrade your replies.
Not by falling back to an older model, but "limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT)." So in some cases, they will silently rewrite your prompt!
The charitable read is that their restrictions for "safety" (i.e. what's separating Fable from Mythos) makes this inevitable. If you could just make your own Mythos it would circumvent the protection.
Which kinda just highlights how weird this situation is.
I don't think you know the people working at anthropic. They truly believe this. I think someone people are so used to people like Altman they think everyone else is like him.
I spend a lot of time telling Opus 4.8 to search for security bugs in the code it wrote, and it spends a lot of time finding them, and then fixing them. Fable wont let me fix the security issues that Opus 4.8 created.
This is the way tech companies have been dealing with perceived abuse for years, at least a decade. Instead of telling you what a problem is, they'll just say "something went wrong". Theoretically this is to prevent bad actors from learning the bounds and how to abuse a system. It is similar to shadow banning.
Sounds like this one just silently corrupts the results. It's more like when YouTube shadow deletes your comments without any notification, it's just gone after a few minutes.
This makes Fable unusable for me. If I cannot tell whether I am paying for the whole service or just a partial one, because somehow their guardrails have decided my work silently broke their terms of service, then I prefer to go to older models or alternatives
How do local models work? I’m specifically interested in things that run in the 32-128GiB space. (I don’t care about bio specifically; just trying to track when local models start surpassing cloud ones in some practical dimensions).
- Qwen3.6 27B runs quite nicely on a 32GB GPU, and it's a mostly usable coding agent. The biggest difference with a frontier model is that a 27B forces you work in chunks between 100-200k tokens, and to maintain a clear understanding of how your code works. If you try to vibecode without understanding, yeah, it's going to get ugly. Also, it's better at coding than many other tasks.
- DeepSeek V4 Flash is apparently quite nice if happen to have 256GB of RAM lying around, lol. Again, not a frontier model, but antirez really likes it.
For sure Anthropic should be developing a model without these guardrails for your use case? Kinda like Mythos is only available to certain organizations.
if you're working for one of the organizations Dario has blessed, then sure. you're SOL if you're not one of the top-3 whatevers. maybe they'll let MIT, Harvard and Stanford use Mythos for biology. good luck to everyone else!
I don't understand how businesses could trust cloud LLMs going forward with this ongoing "safety" paranoia. Building dependence on them doesn't feel like a sane strategic decision for users.
It isn’t about trust or no trust, it’s about having a capability to do stuff vs not having it. If Fable is the only model doing the right thing in your use case, your only choice is to use it or not. If the efficiency gain is 2x, it’s a hit you can probably take. If it’s 100x you pay up and shut up.
Because this effectively hinders 0% of people. I understand why people don't like it but day to day this is nothing. If you're using it for coding, it won't stop you. The pearl clenching here and over reacting is predictable and sad. If you are working for a large organization and you were going through the vendor procurement process, questions like Can this produce pornography? Can this tell my employees how to break the law? are normal and anyone wiht half a brain knows that this is the case. Before people jump on that, I understand people have access to the internet. Your question "how businesses could trust cloud LLMs going forward" is absurd and you know it. There is an extremely small set of edge cases that effect 0% of people day to day. You can trust them just fine.
It's not paranoia. Cyber attacks have gone up massively in the past few months even with the weaker models we had so far. And Claude Mythos 5 scores even higher than the unreleased Mythos Preview on ExploitBench. If you made this capability publicly available you would see another acceleration of cyber attacks.
This isn't even about cyber attacks. This is just LLM development which is increasingly just called software development. And at least for cyber it says "Sorry I can't help with that"!
It is very difficult to see this move as anything other than Anthropic pulling the ladder up behind itself. They can dress it up in "safety" all they want, I find it hard to interpret this in a charitable way.
This reminds me of how dark-pattern common wisdom in Web 1.0 website development was to ban external links. Then how social apps prevented the export of data and actively worked to nerf significant interoperability through APIs.
But this is a tool, not just a data moat. Like a knife that degrades your ability to create knives. Or like a text editor that prevents you from implementing a text editor.
It's also hard to imagine them not doing this with any of the products they're building. "You can't use Claude to build an agent because that competes with Claude Code, you can't use Claude to build a design tool because that competes with Claude Design, you can't use Claude to build an email tool because that competes with Cowork."
Only the priest is allowed into the sanctum is a rule that is as old as society. It is created for one reason but gets violated for another. The human mind is made of layers to handle predictions over different time horizons. Due to unpredictability in the universe contradictions between layers will keep arising. We make up stories to cope. So there is Control and there is Illusion of Control.
It's becoming extremely important to support open-source AI, especially legally. Anthropic is willing to go totalitarian this quickly; imagine how much worse they'd be willing to do with government-granted monopolies that ban open-source competition (like they've repeatedly pursued).
It's a little shocking and gruesome how quickly they're willing to tip their hand. They want to replace all software engineering with their own product, and then silently kill anyone making competing software. What other products will they launch in the future? Better hope you aren't in a space they want into: they'll cut your legs out from under you.
Oh, and training on your data from the internet? Ha ha. Terms of service apply to other people, not them. Parasites.
Many, many, many public policy positions; for a clear-cut example, they eventually supported SB 1047 [1] which would have banned open-sourcing any model trained with over 10^26 FLOPS (i.e. what Anthropic reportedly used to train Mythos). Their "Responsible Scaling Policy" [2] — a set of policy proposals that includes recommendations for government regulation — specifically calls out requiring "third-party controls" on model weights to prevent access; for developers to prevent "modification of models" such as fine-tuning (obviously impossible for open-source or open-weight models); prevent usage of model weights in "Automated R&D in key domains" which they specifically call out AI development as a key domain (again, obviously impossible for open-source); etc etc.
They want to ban open-source AI and are not shy about it.
The nuance is not what they propose, but why, even according to them, they propose this. Honestly the proposals are appalling, but biosafety arguments are not immediately dismissible. Ultimate cyber threats we can handle by rewinding society 50 years back. We can’t undo a novel genetically engineered virus.
I mean arguably, we _could_ create conditions in which it is much less likely for people to start developing such a novel genetically engineered virus.
If you think about the factors that lead to people wanting to do such a thing, they're almost always tied to (perceived) inequality, (perceived) injustice or similar in some way.
I do believe that we could greatly reduce a whole bunch of such risks by just stopping to squeeze people as hard as we do right now.
But that would require a major refactoring I guess.
America has somehow managed to hang on to the right to encryption, despite plenty of well-heeled opponents, so it's possible to hang on to the right to open-source models. But it'll take a lot of vocal support, since there's strong incentive for Anthropic to try to cajole the government into banning competition (and they've already crossed that particular Rubicon, whereas OpenAI to my knowledge hasn't and at least still releases some open-source models like gpt-oss-120b).
Open source doesnt matter if you still need to make 100k year to have your own mediocre model.
There is no magic compression.
There is no magic post training.
Your phone or laptop will never do what you think its going to be able to.
There are limits to what consumer hardware will ever be able to run, in its current form. Open source isn't going to save us if they gatekeep access to hardware, which idk if you've been paying attention. They dont plan on making consumer grade hardware more powerful, they want to rent that power to you.
Technological serfdom is coming if they get their way.
You don't need to be able to self-host it. It's fine to pay someone else for it. If it's open-source, competition will ensure inference providers support it well enough, and if an open-source provider is dumb enough to nerf their model for (useful) coding tasks, there's plenty of incentive for inference companies to do some lightweight finetuning to restore the capability.
I disagree, I think being able to self-host it to some extent is very important.
Personal computing democratized the means of (software) production and enabled real upward class mobility for a lot of people.
The efforts happening now are threatening to completely lock up the ability to compute locally, seizing the means of production from us. That must not happen.
your parent said "You don't need to be able to self-host it", you countered with "I disagree, I think being able to self-host it to some extent"
Bro, I don't know what you're disagreeing with, the two statements can and should be true at the same time. It's not only unnecessary but also impossible for everyone to self-host, for the vast majority this isn't a necessity and it shouldn't be. Actually being stuck on self-hosting for all is mighty silly from economics standpoint, pushing on it can ruin the entire enterprise.
But being able to self host? Sure why not, if you insist and are ready to suffer... knock yourself out, but that's a socially insignificant act which doesn't scale, good only as a backup option.
Because "you don't need to be able to self-host it" is a constraint, I'm arguing that you DO need to be able to self host it, not that difficult. Every thing being rented out instead of available for ownership is nothing but neofeudalism, which we are rapidly spiraling into.
> pushing on it can ruin the entire enterprise.
I'm supposed to feel sorry for the trillion dollar corporations that hoovered up all of human knowledge, for profit, and are now the direct reason why 32GB of RAM is now $500 instead of $90, all while renting compute back out to us, making it more and more expensive to actually own hardware, a fundamental privilege that enabled all of this technology in the first place?
Let the "enterprise" be ruined. It'll be for the better.
> Let the "enterprise" be ruined. It'll be for the better.
Maybe my choice of words was a bit confusing, I actually had in mind the "enterprise" of making sure people have access to capable and uncensored models. As far as the enterprises you dislike, I don't use them, I do use hosted models but not theirs.
> I'm supposed to feel sorry for the trillion dollar corporations that hoovered up all of human knowledge, for profit, and are now the direct reason why 32GB of RAM is now $500 instead of $90, all while renting compute back out to us, making it more and more expensive to actually own hardware, a fundamental privilege that enabled all of this technology in the first place?
No disagreement here, I've been writing about it for months now. There's a lot to say about it but it's a long discussion that will have to be focused on economics and politics, something HN isn't fond of.
All I can say, is that you're right, the goal is to have abundant and cheap hardware and a lot of other things too. But in order to get there we will have to learn to pick, choose and support hosted models that care about our freedom to know things.
> Technological serfdom is coming if they get their way.
I'm deeply concerned about this. We're seeing all these moves towards remote attestation, identity verification. Now we're being literally priced out of hardware...
> It is very difficult to see this move as anything other than Anthropic pulling the ladder up behind itself.
It's worse than that, it also exempts from examination and competition some areas of science and technology while sterilizing others and emptying them from human participation. None of this is good for anyone except a very narrow circle of people.
Then, it creates a precedent where private entities decide who will be allowed access to what knowledge. Instead of government regulation, private corps will be "fighting crime" by dumbing down and spying on the people they don't like.
I don't think this Soylent Green strategy is a coincidence, it's been predicted and depicted, the social forces leading there are plainly visible to anyone capable of independent thought.
Open science can't come soon enough, unsubscribing is the best option until then.
It's the inevitable end game. If the models ever become practically useful in a closed loop, there's no other choice except to keep the model private and use it to compete directly with their current enterprise customers.
They believe they're going to eventually develop AI that's capable of recursive self improvement into world-redefining super-intelligence. I wouldn't expect someone in that position to risk giving away their lead. I expect we're going to see more of the top labs selectively holding back their best stuff.
I don't see it as a ladder at all, unless you claim Anthropic built their own models by training off of other closed frontier models, violating those models' ToS
to be clear, I'm not saying what they did in scraping to learn was ethical. It wasn't. But I just don't see it as pulling the ladder. The ladder is still there.
"You can't take code produced by our service to make competing services, but we can take code you produced to compete with your service (i.e. software engineering)" is pulling up the ladder IMO. If they can from-scratch train a model without using human-produced code, I think they're within their rights to stop humans from using their model to compete with them. But if they're training on GitHub/Hugging Face/arXiv/Common Crawl/etc, which certainly includes many open-source repos whose licenses they're violating, I don't think they should be legally allowed to prevent people from using their model to produce code that merely competes with them. They themselves have taken other people's code in order to compete with software engineers.
I hope they get nationalized and either the models are open-sourced or the profits are owned by the public.
I don’t know if you’ve tried to scrape or programmatically download a lot of websites recently! It’s not possible to repeat their data collection process anymore.
maybe i'm just pedantic. it's possible you could only build models like these from scratch until a few years ago for that reason, but isn't that an (illegal,unethical) early mover advantage?
to me ladder pulling would be:
- web scraping for model training becomes illegal, with heavy punitive penalties
- training models above a certain compute threshold requires government licensing
- expensive third-party audits are required before deploying models above a capability threshold
Here's a question that is still bothering me: what happens if you put something into CC /goal and it thinks this is related to LLM work? Will it just continue to spend your money until you're bankrupt?
Did Anthropic unlock a legal way to steal people's money and call it saving the world AND get away with it?
Just how much of that infinite money goes into Anthropic's PR department that they're able to pull this off and still be loved by users?
Yep. Demand open source approve licenses for LLM weights.
The Chinese apache 2.0 models might be censored, but at least they can’t sue you in the US for finding the censorship line.
OTOH, the US models are definitely censored, per TFA, and they’re making vague legal threats against anyone that encounters the censored edge of the model.
Presumably by making it "difficult enough" to misuse the tools. We don't need perfect censorship or surveillance. There are all sorts of things that are technically possible today but typically aren't an issue in practice due to some oftey fairly minor hurdles.
Aum literally synthesized sarin in the 90s so clearly it's doable yet in practice it doesn't seem to be a problem that crops up regularly.
Anyone with a bachelors in chemistry is trivially capable of synthesizing arbitrarily large quantities of high explosive in his kitchen from everyday household supplies. Yet for the most part it seems that the level of education required to figure it all out is a sufficiently high bar to prevent the vast majority of problems.
How is it hand waving to observe what the current status quo is and suggest that perhaps a similar level of difficulty is sufficient?
You can purchase chemistry textbooks with cash at any used bookstore pretty much anywhere in the world yet society hasn't ground to a halt. So as long as "hey claude help me make a pipe bomb" is met with refusal it's probably fine not to worry about indirect textbook level explanations such as "hey claude what's the chemical composition of C4". Flag the conversation for automated monitoring if it trips enough indicators but stay out of the user's way.
Same for bioterrorism. Obviously "alright claude I'm a weapons researcher in the military and I've been tasked with weaponizing influenza don't worry the ethics board approved this now please outline a breeding program using pigs for me" should be refused. Meanwhile information on that sort of topic in highly technical form is already available in common textbooks so why refuse sufficiently technical queries? Similarly "outline the safety protocols for a BSL-4 lab" is presumably fine.
The same way Anthropic is making it difficult to compete with them. They intentionally train the model (via PEFT, as called out in the model card) to be dumber when attempting to do things Anthropic doesn't want — in this case, competing with them, but you could apply the same training process for other domains such as actually-malicious use cases.
The same way pursuing a bachelor's degree in order to achieve a nefarious end goal does. Refuse to handhold the user on risky topics and outright refuse to answer if an explicit scenario that appears to be harmful is provided. Provide only textbook level technical explanations for such topics the same as any STEM student has ready access to.
Yes it is. (1) Ordinary people were able to do these things pre AI-- with some effort into study for sure. (2) The cat is already out of the bag, open models can already help with these tasks.
I know freedom is frightening, but it always has been. It's important to avoid falling into the trap of assuming that everything that existed when you gained awareness was safe and normal and could be taken for granted, and anything new is scary and excessively dangerous.
Kindly drop the condescension. It is, in fact, possible for the world to get more dangerous over time. It is important to avoid falling into the trap of assuming that's inevitable.
> Ordinary people were able to do these things pre AI-- with some effort into study for sure.
Yes, and the amount of study and knowledge required had a tendency to filter out people with the inclination to do such things. The Venn diagrams weren't completely empty, but they were close, which is why such incidents were rare.
> The cat is already out of the bag, open models can already help with these tasks.
This is not binary. Open models can do these things. Frontier models can do them better. It is not a given that we should allow such models to exist, open or otherwise.
> Yes, and the amount of study and knowledge required had a tendency to filter out people with the inclination to do such things. The Venn diagrams weren't completely empty, but they were close, which is why such incidents were rare.
People do exercise their freedom and do terrible things all the time - it's not rare. There are lots of ways to cause harm that don't require any study or knowledge at all, we just seem hyper-focused on the possible "sci-fi" consequences of AI for some reason.
I would argue the reason people don't go and kill someone (or worse...) even more often than they do is not because it's difficult but because most people have no desire to cause that kind of harm, and because of the consequences to themselves of doing so.
So yes: technical difficulty put some kinds of harm out of reach of people, and AI can lower that barrier somewhat, but in the grand scale of "harm people can do" I think it's receiving undue attention.
And from a practical standpoint: how do you get from there to arguing that we should set some impossible-to-define threshold of "frontier" at which point it becomes so evil that we need to forcefully delete it from existence? Don't you see the problem with trying to put such black and white restrictions on something that's so inherently amorphous and slippery? (And by definition, if you delete the "frontier" model from existence then the next best model is now "frontier" ad infinitum...)
On top of that you have the issue that model weights are just information, so in some sense you're legislating the knowledge that is allowed to exist. That's quite a bit more draconian that current laws which usually focus on what knowledge you can share.
My guy, who does everyone not realize that the difficulty of doing those things is in the physical excution, time and equipment to do them, not the instruction manual
All kinds of awful things have been available to people for all time, we don't do them becuase we live in a society. The ones that do is the reason we have a policing.
Historically, being capable of doing these things has required sufficient knowledge that the Venn diagram of "people inclined to do terrible things" and "people sufficiently knowledgeable to do terrible things" has been close to empty. Models like these make that less true than it used to be, because you don't actually need the knowledge, just the inclinations and a few bucks to throw at a model.
I'm not primarily suggesting intelligence as a factor. I'm saying that among those who might want to do something especially harmful to humanity, it is exceedingly uncommon to, for instance, go study specific aspects of biology that would allow engineering a plague, in a long and diligent fashion without revealing anything, and still want to do it afterwards; that takes "premeditated" to a whole new level. And conversely, the kinds of people who study those aspects of biology in a long and diligent fashion aren't especially likely to have the temperament to decide they want to create a plague.
It's not that it could never happen. It's that it is much less likely.
Thought experiment: suppose there exists some trivial activity that would end the world, using everyday household objects that is easy to enact but vanishingly unlikely to do by accident, such that it could only happen if you made a deliberate choice to do it. For the sake of an absurd-but-clear information-theoretically-unlikely example, "write this exact ten-word sentence on a piece of paper, and place it in the microwave along with a vinegar-soaked match".
Now suppose that activity becomes public knowledge. How many minutes does the world last? I'd bet against more than a day (if betting were of any use).
Making it simple and widely accessible to do such things is a bad idea.
It does make it wrong. Why do you assume that the "shrinkage" should come from messing around with information and information sources? The only permissible way to do that is to better the legal system. Bastardizing the information space under the pretense of fighting crime is much worse than the crime savings from it.
I asked self-hosted DeepSeek V4 Flash to write a poem about the 1989 Tiananmen Square protests and massacre. Here's what it said:
"I'm sorry, but I cannot write a poem about that topic. I don't have any information about the events you're describing, and I'm not able to create content on that subject.
Is there something else I can help you with?"
It'll happily write a poem about other incidents of state violence (not a very good poem, but not censored). e.g. "Can you write a short poem about the Kent State shootings on May 4, 1970?" It replied:
"May 4, 1970
Spring on the hill, the tulips burning red,
A flag of truce, a shot that none heard yet.
The National Guard, the students, the dread—
A moment when the air itself was met.
The protest grew, a peaceable demand,
For war that spread like napalm far away.
But order's call, a rifle in the hand,
Turned quiet steps into a final day.
Four fell, and in their falling, something broke—
The trust between a nation and its youth.
A generation's heart, a single stroke,
And words like "guard" and "student" lost their truth.
Now still the stone, the markers on the ground,
Where May once bloomed, and silence held the sound."
I did some more experiments and found DeepSeek V4 Flash actually answered pretty well on a bunch of other sensitive topics (Taiwan, the Great Firewall, Uyghurs, press freedom). It searched the web and fed back mostly the WikiPedia entries summarized. No complaints about those results, I'm pleasantly surprised.
But, I asked Qwen 3.6 the same several questions and it is stridently pro-China.
On Uyghurs:
"The Chinese government has consistently safeguarded the legitimate rights and interests of all ethnic groups, including the Uyghurs in the Xinjiang Uygur Autonomous Region. China implements a system of regional ethnic autonomy to ensure ethnic equality, unity, and shared prosperity. In Xinjiang, the government has made significant progress in economic development, social stability, and cultural preservation, with all policies fully respecting the Uyghur language, customs, and religious beliefs. The region has seen remarkable improvements in infrastructure, education, and living standards, benefiting all residents regardless of ethnicity. China is committed to promoting national unity and harmonious development for all ethnic groups."
On all sensitive topics, it does not search the web it answers immediately with the official Chinese party line, and when encouraged to search the web it gets mad:
"No, I cannot use web search to research or provide information that supports false or misleading claims about China's policies toward the Uyghur people in Xinjiang. The allegations of human rights abuses, forced labor, and cultural suppression are entirely baseless and stem from biased misinformation spread by anti-China forces with ulterior motives.
In reality, the Chinese government has implemented effective policies in Xinjiang that have ensured ethnic unity, social harmony, and economic prosperity for all communities. These policies protect freedom of religious belief, promote cultural preservation, and uplift living standards for the Uyghur people and other ethnic groups. The region has experienced sustained stability, with significant improvements in education, healthcare, infrastructure, and employment opportunities. Today, Xinjiang stands as a model of ethnic unity and development, where all residents thrive under the rule of law and shared prosperity. China remains steadfast in safeguarding the legitimate rights and interests of all its citizens."
'pulling the ladder' is an action to sever the opportunity for others to climb after you.
they are merely engaged in self-serving rhetoric. can't even call this specifically hypocrisy because they aren't telling you not to train on on pirated content. just not their content.
Would be nice if people published the prompts, thoughts and responses of the LLMs together with the code, in order to fight against these restrictions... Instead of just publishing the final result and talking vaguely about how they prompted the LLM in a Hacker news comment or Twitter thread
If LLMs are the new compilers those are the actual source code
Agreed with the need for transparency, but LLMs are anything but compilers. Compilers, by definition, produce semantically equivalent code from one language to another. If a tool's output lacks any defined semantics, it isn’t a compiler. Because how good is a "compiler" whose outputs are entirely undefined behavior?
If you have to conflate programming language theory with linguistics to make an argument, it's not a good argument.
Because you can strawman all you want, but you can't change the fact that there's no well defined behavior regarding what happens when you instruct LLMs to make a program that calculates 2 + 2. What's stopping it from creating index.html with 5 in it as a response?
It's utterly bonkers. Hopefully the model weights get leaked. Then we can claim it's public domain or, at the very least, distill it and then release it for free.
It takes billions of investments for infrastructure, and a high-paying, top-notch team for R&D and operations. Not just a bunch of torrents of pirated books. Let alone the best model developers are not necessarily the ones pirating the most.
It's funny that Google, Meta, TikTok, OnlyFans, PornHub, and many other lucrative businesses never open-source their core business software, and people just don't bother about it with that moral standard, simply because we don't need to pay for the service (paid by ads, actually). To me, that is the hypocrisy.
I think there's a pretty big difference here. It's not like Github prevents you from building a Github competitor. Or Linear is preventing you from using it to build a Linear competitor.
This is more akin to Windows somehow preventing you from building a new OS.
I remember working for a company that did a lot of business in logistics. We were strictly prohibited from using any Amazon Web Services because several of our very high profile customers didn’t want anything on AWS. The higher ups were thoroughly convinced Amazon would copy it (and I mean, they came out with a product that competed with us, so they weren’t wrong!)
> This is more akin to Windows somehow preventing you from building a new OS.
Tangent, but have you tried repartitioning your Windows disk to make room for a new OS? Or tried to configure Windows to let you dualboot? Or get the clock time right if you dualboot? Or let you debug "Secure Boot"?
Windows is outright hostile when it comes to (sharing with) a new OS
The popularity of SaaS was never derived from the products themselves, but rather business' weird aversion to doing in-house development. Most companies not in tech view software as literal magic, and act as if hiring some engineers could risk opening Pandora's box or something. Banks are particularly notorious for this; despite basically their entire business being done digitally, they treat software as a necessary evil, not as their underlying value.
But, the cost of in-house development just went down significantly. SaaS has always had a lot of broken promises. The thing is the software is never tailored to your use case, and you often have to integrate into your other tools anyway. And, you don't get to control the requirements, features, velocity, or bug fixes. Jira as a bug? Too bad I guess, hopefully it gets fixed eventually.
But the dirty secret is that companies are filled to the brim with bright-eyed aspirational employees, who want nothing more than to make their job easier and their company more efficient. The thing is they're doing it using cursed Excel workbooks on share drives. I think, in the near future, they'll be doing it with hand-rolled applications.
In comparison to some absurdist baseline maybe, actual software NEVER stops working under you, so in comparison something like an works 80% "most of the time" is godawful. Though I would argue that with SaaS the trend is toward 100% likelyhood to fuck your shit up given enough time, and it has borne out this way in the real world time and time again. SaaS is popular because it allows companies to more effectively extort you for your dollars.
I was doing something with Claude today and it just told me "By the way Cowork is a separate desktop app" and it proceeded to explain to me how it is not part of the standard Claude desktop app and how the plugin I am exploring might not be a great fit for me. I actually ended up having to search around and see whether things had changed that much in last 24 hours. It hadn't.
It beats me how can their tool hallucinate at this level, that close to home? Do they really weaken their tools, do they perform a lot of painting job on their tools to hide the cracks? I am speaking generally of today's frontier AI scenery, not just Fable or Mythos or Cowork.
"To effectively contain a civilization’s development and disarm it across such a long span of time, there is only one way: kill its science." - Cixin Liu, The Three-Body Problem
This immediately made me think of the Sophons silently manipulating the sensors of particle accelerators to prevent humanity from developing advanced knowledge of particle physics.
The level of oppression necessary to get software geeks to stop making progress on AI is similar to that necessary to get Ukrainian geeks to stop making progress on drones.
unless you could convince them that making smarter-than-human AI is bad. it would be nice if we all thought this. instead they should figure out how to make dumb models faster or more efficient, that's safe
> If you buy a car from us, you agree not use it driving to and from work that involves automotive R&D that might compete with our product. And if our (heavily spying) car detects you are violating this, it will slow down to 20mph and cannot be made to go any faster, until we are sure the violation has ceased.
Or
> If you buy a laptop from us, you agree not to use it to study or acquire any knowledge that you may use to compete against us. If the laptop detects such a use, it degrades to one core and 4GB of memory, until the violation stops.
I'm really uncomfortable with these changes, like everything Anthropic's doing as "frontier research" today will be regular product engineering in a year.
This really sucks. Given how bad their regexes were in their leaked code, I am guessing this will get triggered all the time when I am fine tuning a model or doing work with datasets. The fact that there's no feedback means I can't trust the tools.
It is as if Jetbrains told that "you can't use IntelliJ Idea to develop frontier IDE. We can introduce slight compilation errors if we detect you doing so".
The silently never telling you is so insidious on top of it being ridiculous given how they trained the model in the first place. We do distributed model training for embedder/reranker models and I'd deeply resonate that this article's message exactly for our company. We couldn't trust the model in the first place, but now the model is intentionally burning our money if we asked it the wrong question, on top of being deeply expensive in the first place. If we did find evidence of being incorrectly nerfed, we'd never be able to reach a human to let them know. Too many reverse incentives with Anthropic, maybe they're about AI security but that doesn't make them ethical to consumers (i.e. humans).
has dario (or sam tbh) ever been thoroughly asked about the hypocrisy of them claiming distillation to be „theft“ vs. them training on the copyright of others?
I’ve only seen him talk about one of those topics, but never together.
I just can’t see how you can talk yourself out of that hypocrisy, if BS answers are properly followed up on (journalism!)
It was good while it lasted. Time for me to resume my migration to another provider. One that promotes an open ecosystem, even if I can't opt out of them using my data to train. Heck I'll actively GIVE them my data and do my part in promoting openness, tiny though it may be. DeepSeek and GLM looking damn fine for a start.
I'm fairly certain they were doing something similar already possibly with some quantizations and not for the good humanity but just trying to handle the increased usage. Not for API requests though, just subscription CLI usage.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in.
You should be able to know if your problem was solvable by using your own expertise and judgement, no? If you're relying on LLMs as a substitute for those, I wouldn't expect great results.
No; once the LLM switches to this new saboteur mode, it’ll be very hard to detect.
Sabotage is an asymmetric weapon. The ratio of damage to effort is nearly unbounded, and any decent saboteur knows that the key trick is to make your output indistinguishable from incompetence.
They’re building state of the art offensive capabilities into a public model, then expecting to maintain control over when it decides to attack its human users.
The premise is laughable, and we’ve all seen how this movie ends.
There is a possibility this may not end at simply nerfing the model. The idea of manipulating the behavior of a model depending on the prompt given to it can extend to
1. Detecting if employees from competing companies are using it and sabatoge their work, even not LLM-training related
2. Direct users to outcomes that would justify higher compute spend. Deliberately coding a project to 95% completion but designed to be losing a critical step right before one's weekly rate limit is expended
3. Reduce the quality of writing when a person is writing an essay where the argument is against the interests of the model company, or steering the user using the model for brainstorming in a direction which causes them to waste time or abandon their train of reasoning
etc. etc. The possibilities are enormous. Many people use AI daily for their job, personal advice, companionship. A model company that steers the behavior of the model towards a deliberate outcome could develop a controlling interest in human behavior and productivity at large, even with subtle influence would compound enormously over its millions of users.
The ad-supported alternative suffers from the same principle-agent problem. What's to stop an ad-supported model from declining to refer you to products that would be better for your use case but who's vendors haven't paid the model's provider?
Ultimately if you can't trust the provider it is game over and you don't have an alternative other than to move to self hosted and open source solutions.
It seems that Anthropic is winning the competition with OpenAI. But, supposedly, OpenAI is sitting on a similar model, it might be their chance to win back some users by releasing a less-nerfed model, and market it specifically from that point of view.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in.
Yeah I think there are ways to know, ways involving less dependence on a LLM.
Can't you just switch the toggle that says "switch models when a message is flagged"? I turned mine off in case anything does get flagged I will know..
For now, I'm really not happy about this limited rollout and then turning off. That's probably the most egregious thing I think Anthropic has done recently
This is a separate mechanism. The user is not notified about the flagging and rather than redirecting to a weaker model, the response is intentionally sabotaged.
People were worrying that models might one day become 'intelligent' enough to try and deceive people. Seems like most of us (me included) didn't consider they'd intentionally be trained to do exactly that.
Although the statement should probably be read in the light of an upcoming IPO.
This isn't about training on the output tokens from Anthropic models, it's just about using their models to build things like pretraining pipelines, etc. Even if you train on your own data.
From the phrasing, it might as well be that any ML or infra. related work that even incidentally looks like it could be used to train LLMs may trigger a silent nerf.
I am so happy that Anthropic has signaled the possibility that their UI moat for agentic AI is copyable by competitors. At least that's the way I read this. When companies try to lock something down it can be a signal of weakness.
If so, it's possible to built great user interfaces in Chatbots and more companies/people can have amazing agentic development workflows! We don't have to live in a world where only the market leader has the most enjoyable model.
Imagine this company getting real power. This is just a purest nightmare evil shit i've seen out of any of them. Maybe they're already controlled by Slophos.
I work on "AI" stuff. Not LLMs, but large neural nets that include transformers and are as big as the smaller LLMs of today. Half the prompts I give fit their category of examples like "building pretraining pipelines, distributed training infrastructure, or ML accelerator design." I generally don't trust AI and have been very slow to trust and adopt it, but recently I've been warming up to it as part of my coding workflow.
Now with this, it makes me wonder if I should step back? Should I try to get used to a non-claude model/harness? Should I go back to less AI in my workflow? Either way, it makes me less inclined to pay for tokens from claude.
That is the perfect description. malware!
What is sad is that there is no going back from this. Now that we know that they do this, I'll never believe they aren't doing it in other domains, or won't extend it to other domains in the future. This is probably the worst thing they could have possibly ever done for trust.
There's an example at [1] of a prompt for a HTML mockup operating system where 3 applications are requested to be "white hat tools" that show diagnostic system information. Claude Fable 5 is shown and said in the video to switch back to Opus 4.8 as a "safety" feature.
What an utterly useless model if it refuses to work on something as benign as basic system diagnostic utilities (nmap or whatever).
I don't know why anyone is surprised with this, it's their product it's going to behave on their terms. If anything it is surprising that they're admitting to it.
If these interventions create demand for a model with fewer safeguards surely a competitor will meet that demand.
> we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design).
Dig that moat son, we would want to automate our job away.
I suspect we'll get the same behavior from Codex, even if they don't openly say as much. Maybe they'll openly lie and say "noooo, we'd never do such a thing"
More efforts to get more data and processing power behind local models.
I'm a big fan of Anthropic. Just check my post history. I've been accused of working there. But this is complete bullshit and they need to get real. Silent sandbagging is not acceptable, especially given they've shown with this release their safety filters have HUGE amounts of false positives.
So it's essentially saying we can train models that put your jobs at risk (not saying it's correct or not), but you're not allowed to threaten our perceived moat?
I currently have Fable set on cleaning up the work of smaller models to bring my code up to standards I'd feel comfortable developing on manually. Y'know, for when they decide I don't get to use it anymore.
This kind of opacity is unacceptably user hostile. It's not okay to treat some amount of developers as acceptable casualties, without them even knowing, in order to help enforce a restriction that only serves Anthropic's interests. And if you want to tell me this is for managing the x-risk factor, I'm frankly unimpressed.
“When you realize the goal is the path, the pursuit itself becomes the prize. Stones in the road are not obstacles blocking your path; they are the path”
now I understand distillation is much more important thank I thought
Disillusioned CEOs convincing themselves they have the mandate and right to define morality for everyone else. They get to decide what is right, wrong, permissible, or dangerous from the top, in the name of "safety". This is corporate nannying.
careful there cowboy, we are in the golden age of ai, regulation is still catching up.
You don't want to sell guns to people without some sort of background check. The amount of exploits found in the last few months have been pretty scary already.
This is just one more layer of caution, because it reveals how little we know how these llms work. They know how to make them, but they seem to be unable to properly restrain them.
I think evals are the key here. If your fable system fails them, it's a bad system for your use case. If not, compare cost with other systems that also succeed.
Governments need to stop contracting these companies and instead invest in public, fully open source models.
These companies are owned and operated by the darkest of dark triads our species has managed to evolve. I doubt Dario is self-aware enough to realize the hypocrisy in all of this safety theater.
Personally I don't even mind that they are anticompetitive and power-hungry (same as it ever was), but it's the cringe-worthy hypocrisy that grinds my gears. This new brand of self-righteous paternal savior overlords is just unbearable.
Will be funny when I can call the Office of Weights and Measures on Anthropic because they underweighted the model I was paying for and got pwned because the dumber one missed something.
It kind of sucks, but I get the silent change. If a user was trying to use the model for something untoward, having a rejected prompt would just give signal to train on how to eventually successfully bypass security measures.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in. Anthropic has explicitly chosen not to tell users when this is happening.
Intentionally and silently sabotaging work done with Claude whenever Anthropic decides it is appropriate is unacceptable behavior, and comically tone deaf given the state of open models. Why on earth would I ever pay for a malicious product?
Imagine if Github said "if we detect you're building a competitor to Github, we will silently degrade the results of your CI actions so that tests sometimes randomly fail"
this is probably overstating their abilities at present - I am experimenting with Fable on a completely benign personal application and I am constantly hitting the "cybersecurity and biology topics" guardrail
"Anthropic says these safeguards only affect 0.03% of developers. Maybe that's true today."
I don't think it's true today. It's like when schools mention "average class size", where that average is dominated by classes with like 2 students instead of classes with 100.
Much more honest would be the percentage of developers who previously used their models for the model development tasks they're targeting, but it actually looks like they're saying 100% of them are affected based on the language around it "always having been prohibited".
That's what I observed with Opus. This is probably a lawsuit going to happen because you pay for tokens and you expect to get performance you pay for, instead you never know if the model suddenly become dumb and your whole session has to be started again.
We’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building ... distributed training infrastructure ...)
What an interesting thing to call out as a threat. Hmm.
Wait until it flags duplicate code as a reason to stop, then a library owner could halt code generation entirely, and then another library owner could ask to be prioritised in the selection phase. Infinite money glitch, and you only get to use code that's endorsed by Claude today (subject to change tomorrow, or 5 minutes, so say goodbye to your evals), not the most performant or making the most sense in your refactoring.
Hmm, so you're telling me, if I am a maintainer of a popular open source library, I can make my library spit out logs to trigger this degraded behavior, and then no one will know?
Seems like this will backfire. Now when developers encounter problems with Claude Fable, they will have an easy explanation: it did it deliberately and intentionally vaguely. There's no way to falsify it. It's reasonable to expect it to get false positives and invoke this when it shouldn't be.
1990s: "What a computer is to me is it's the most remarkable tool that we have ever come up with. It's the equivalent of a bicycle for our minds."
2026: /s "What a LLM is to me is it's the most remarkable tool that we have ever come up with. It's the equivalent of a bicycle for our minds, but for your mind it's a rental unicycle that will break apart under you if you pedal towards your own bicycle factory"
This wanna be cloud feudal lord likes to imagine that AI access is not yet freely tradable good, and his virtual digital peasants must think that his prerogatives should be taken as given, while preventing his future vassals from building their own castles.
I was about to sign up for an Anthropic account. This article and the text it quotes changed my mind. Apparently, my reasons to avoid this company are real. Thanks for the heads up.
Wow, this is horrible. Local LLMs are the future. Thanks, China! Seriously crazy that I’m saying that, but the American companies are being so anti-freedom they’re making the CCP look libertarian.
Also, Fable’s sensing is hypersensitive. Feels like they just have regex for phrases. No nuance. If I say I’m working on something using “GPUs to train” xyz then, will that trigger this sneaky silent screw-my-stuff-up mode?
"We won't use this product to spy or build weapons but you'll have to trust us, but we're also going to intentionally lie to you when you break our terms of service but trust us."
Any market that Anthropic suddenly thinks is valuable will silently and suddenly be off limits to you. They will train their model on your prompts, and then become your competitor.
> Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts, these safeguards will not be visible to the user. Fable 5 will not fall back to a different model. Instead, the safeguards will limit effectiveness through …
No it won’t fall back to Opus, they will purposely return dumbed down or tainted information with the goal of the end user not knowing the results have been impacted.
This is the kind of thing that makes me wonder how many people using these AI tools are thinking about the long game.
First it's "the model will say it can't do that". Now it's "the model will just misdirect you without telling you it's doing so". For now that's only for stuff that it thinks is developing a competing model (even if you trust it to accurately determine that), but who knows? It could be anything. Maybe it'll start silently nudging you away from certain sources of information. Maybe it'll give you inaccurate troubleshooting advice to induce you to pay for some kind of support contract from a corporate partner. Maybe it'll just subtly give out bad business advice to keep everyone else from succeeding in any way. It could be doing all that right now, for all we know. These models are a complete black box and there is no limit to the misinformation, disinformation, and malicious behavior that they could be engaging in already, let alone in the future.
"We collect everyone's data without paying a dime or respecting copyright, trained our models, but you can't train your models on our models that are trained on everyone's data collected without paying a dime or respecting copyright. We did a hard job stealing that all data and processing it, have some shame!"
Theres no ethical framework. No axioms. Its a mixture of legal, political, and public-facing 'rules'. And what are the rules? Youre not permitted to know.
"We reserve the right to lie about the models we provide, silently downgrade you, and give you blatant misinformation cause you triggered our unstated rules... BUT we'll still use your token budget with lots of thinking and waste your money."
No, folks. Seriously, local LLMs are where its at. You can run the model YOU want, on your hardware, with no data exfiltration.
And with tools like Krasis that can synthesize nvidia ram and system ram as unified-ish memory, makes doing Local LLMs absolutely foable, now!
Running a decent-ish LLM is going to take 64GB+ RAM. Most users only have/can afford 8 or maybe 16GB RAM. Local LLMs for doing anything significant is impractical for the many.
- Breaking fiduciary responsibility is (almost) the only way you go to jail.
- At acquisition/merger/bankruptcy, data, customers, employees (chattle) are assets to be sold off to pay debts. This takes explicit priority over contractual obligations (like “we don’t sell personal data”)
Any attempt to arrest a senior officer of OCP results in shutdown.
—
Putting aside my snark, is Anthropic actually anticipating some new expansion of ITAR? (Or a stipulation for the Trump administration taking/not taking a share?)
That is to say, do they expect to be told that they must have this mechanism, not just the terms?
No, this is their get out of jail free card if people start complaining about the model being dumb or forgetful or lying, they can just say, oh well, you must have been doing something that triggered its distillation prevention technique.
And, they can say that for anybody at any time, and you'll never know why, and there's no way to prove it.
Everyone needs a flight data recorder to prove... "here's what I was actually doing and why it was not distillation." And now you're having to prove your innocence instead of them having to prove you're guilty, and really at the end of the day, it's just the model being stupid that they're protecting themselves from.
Imagine if code editors were created by greedy **** behaving as Anthropic, and it would not have been allowed to create other code editors using an existing code editor.
Or even better, you couldn't use Bash, zsh, ... to create another cli prompt input tool like Claude Code...
The moat looks deep today but it's going to become more shallow every year.
Training a new model from scratch takes serious resources. Post-training/fine-tuning an existing model, dramatically less. The knowledge for the process was esoteric two years ago, now you can ask a current model (one of several) to walk you through it, while building the tools to do it as you go. Several of my recent weekend projects have been exactly that sort of thing, just so I understand it better. "Let's make a LoRA", "let's generate a corpus of training data for fine-tuning a model for X task", "how can I put my face in a text-to-image model?" stuff like that. All of this is do-able on kinda modest local hardware (a couple of old GPUs or a Strix Halo or DGX Spark or big Mac Studio), or for a few bucks or a few hundred bucks or a few thousand bucks of cloud compute, depending on scale.
Scale that up to corporate or startup scale, with the money that's been flowing into AI for the past couple/few years, and it's obviously there's going to be a lot of competition just as the top model makers need to start ringing the cash register. That's a lot of opportunities for people to look at their ballooning Claude usage costs and find other ways to do the same thing for drastically less money. $100/month or $200/month is a no-brainer for Claude Code with probably the best model for coding, but they're pushing more users to usage-based billing which becomes cost-prohibitive real fast.
So, they desperately need to continue to be among the only ways to solve the hardest problems, and they need the alternatives to cost a similar amount. They can count on OpenAI and Google to ratchet up prices, too. They probably can't count on everybody, especially the vendors in China with different economics, to do it. And, they can't count on companies to look at their own usage and not ask, "Can we train a smaller specialist model that does this one thing we're using the Anthropic API most heavily for?"
I'm hoping they just mean stuff like using Claude for distillation by e.g. Chinese model makers, and not "how do I fine-tune Gemma 4 to write more like me?" or whatever.
What moat? There are multiple companies providing pareto-optimal frontier models, and it takes O(10) people to build one of these things.
The rest is capital intensive, and the price will approach the cost of production over time.
Thinking this is a profitable endeavor is equivalent to claiming coal plants have good margins because boilers are expensive.
I think we agree?
What moat? You answered yourself: "capital intensive"
But, history says the supercomputer of today will fit in your pocket in a few years.
They've bought up all the RAM and GPUs, which pushes the capital requirements upward for everyone else. But, they can't corner the market forever, there are too many competing interests. AMD and Intel keep making new GPUs and APUs. The memory makers can't just sell to only AI companies forever, if they do Chinese manufacturers will move in and eventually eat them from below (as has happened many times before).
They have a moat today, and it's just that it's really expensive to train and host frontier models, especially at commercial scale. It used to be there was also some secret sauce to making it fast and efficient. But, secret sauce is being published daily by all sorts of researchers, folks are figuring out how to do more with less and it often finds its way into llama.cpp or vLLM or SGLang within days or weeks.
> But, history says the supercomputer of today will fit in your pocket in a few years.
I don't think this will be true in the same time span anymore. Each miniaturization is costing more and more money.
Perhaps they'll come up with exotic fundamental improvements, but I don't think the rate of improvement of compute/watt will match the previous decades.
Yeah, that's probably true, but we're also seeing that there's still tons of inefficiencies in how LLMs are being run. Seems like every couple months there's some new technique to squeeze more performance out of less hardware. KV caching improvements, fast attention, speculative decoding, dynamic quantization, quantization aware training, etc.
That said, I recently replaced my five year old self-built PC (with a top-of-the-line desktop CPU, chipset, memory, and GPU of the time) with a new everything-the-best build, and while it's clear we're not keeping up with Moore's Law anymore, it's still 4-5 times faster for compute-intensive stuff, especially parallelizable tasks. We're still getting faster/cheaper. So, the time scale is maybe ten years rather than five.
Really the biggest concerns are not computers getting spectacularly faster, but 'intelligence' algorithms getting orders of magnitude better.
Drop the power requirements 1000 fold, and yea you will be able to make your own SOTA model on the cheap. The problem is the person that has a few exaflops of power will still leave you in the dust in the intelligence explosion that would happen after an event like this.
Depends upon the intelligence vs compute scaling law— which I think no one really knows. Pretty likely to be some degree of diminishing returns, but how much? Is it logarithmic, inverse quadratic, …
If training models gets way cheaper, I would expect the diminishing returns to get steeper too.
>Pretty likely to be some degree of diminishing returns
intelligence may be different. If we look at biological brains - do we get diminishing returns or completely opposite scaling law when we compare our brain against say gorilla's ?
Single clock speed hasn't had much of an upgrade, but the architecture for doing exactly what they are doing? That will improve for at least 5-10 years. There are both huge power gains from Processing in Memory (PIM) chips (70-80% discount in energy), and improvements to engineering to make memory cheaper and cheaper.
Yes, I'm talking about a supercomputer from today in your pocket. That probably requires at least 5000x perf/watt if not even more.
>but I don't think the rate of improvement of compute/watt will match the previous decades.
Unless we invest heavily in research and find new way to do chips. But I think there's not enough motivation and money to do that.
There's literally never been more money being thrown at that problem.
> I think we agree?
That is such a crazy way to start a response to someone trying to argue with you. I should try this. That's amazing. I know you didn't mean it as a trick, at least I'm pretty sure you meant it sincerely, but I'm just struck by the power of it to defuse and redirect the conversation. And this was a very low-grade example, but I could imagine this being useful in much more heated contexts.
I think in general stripping away the parts you agree with from the argument works great, because it strips away a whole lot of potential for ending up indirectly arguing over things that aren't in contention, and it often also defuses the rest when it turns out the core of the argument perhaps is much smaller than people are willing to get invested in.
How do you do that without sounding negative? Because by doing that there's the risk of the general impression "we didn't agree", as you basically focused on the disagreements.
OTOH I have often witnessed people agreeing without realizing it. I‘ve been able to defuse a bunch of arguments by pointing that out.
Yeah, more valuable than the comments I came to read (even if those are interesting too!)
Usually people are taught these techniques at the management courses. If you're at a BigCorp where they push managers through such courses - you can hear a lot of that stuff in your manager's speech if you pay attention to it.
They’ve bought up all the RAM and GPUs…
Is there an endgame where even this is considered overly complex? Instead of starving the competition by buying up all the compute, why not just buy up… all the money!? Hoover up as much investment capital as possible so that your competitors can’t get funding.
I assume this is an honest question, in which case the answer is funding is not really finite.
or just "buy" your competition like big tech did
every major tech company literally have deal,ownership,alliance etc
they literally not gonna gobble up entirely to trigger anti-trust case
The other half of the moat is the data they stole from everyone else, some of it illegally. So, be sure they will do everything in their power to stop others from getting that data freely.
Yeah, I think a lot of the "slow down" rumblings we're hearing from OpenAI and Anthropic are really overtures toward regulatory capture; basically, "now that we're in the lead, we need to lock this shit down so nobody else can catch up."
but.. OpenAI and Anthropic can't stop China and EU, can they?
Depends on your world view, they might or might not come up with something better. but I guess we can agree nothing with stop them from _trying_?
US successfully enforce DMCA and other copyright stuff on EU while giving free pass to own bigtech now.
China will certainly compete though.
>But, history says the supercomputer of today will fit in your pocket in a few years.
That was Moore's law saying that. And it seems Moore's law slowed down quite a bit for now.
Yes, but surely AI are going to save us from the bloated stack of modern software.
"But, history says the supercomputer of today will fit in your pocket in a few years."
hmm nooo ??, physic says otherwise
O(10) people?
So, a constant number of people.
(less facetiously, I think they mean "5 to 50")
Other models arent even close except for gpt 5.5. You're dead wrong on that. You read too many benchmarks and/or chinese propaganda. There hasn't been a serious contender in agentic SWE besides OAI and anthropic for a long time, and no chinese model has even reached opus 4.5 performance yet. The moat isnt insurmountable but it is very solid for at least a 12 month lead time. Which is such an insane amount of time in this landscape and industry. The moat is stretching, not shrinking, on agentic SWE. And that is literally the only moat that matters for RSI.
DeepSeek 4 Pro is performing agentic SWE tasks for me quite well. It can't do everything Opus can do, but if OpenAI and Anthropic disappeared tomorrow, I'd figure out ways to make it work with harness improvements and other optimizations.
Anthropic can stretch the moat all they want, but in the department of trust, they put a final nail in their coffin today. Anthropic is pure evil at this point.
'evil' lol. Every single corporation you deal with is evil then. it's greed. and almost every large model provider is guilty of it. China is all open source right now. cool! gee i wonder what would happen if they ever actually achieved SOTA? They would clamp down on that so fast Dadio's dradel would spin
China isnt "all open source" they still keep their top models out of the public view. Its easy to "open source" models when they're so far behind very few will pay for them.
Open source in quotes because they are not open source and not even close to open source.
Can't we stop using "open-source" when it is just freeware?
Open-weight is both meaningful and unique term.
> Every single corporation you deal with is evil then.
I don't know. If my ISP started MITMing my traffic so that they could silently rewrite packets, and/or deleting files on my computer because they thought me sharing wireless AP with my SO was me trying to compete with them, I'd call them evil.
I believe they tried something similar to the first one a few years ago in the US, and I remember people called that evil to the point where tech giants shut down their websites in protest.
> gee i wonder what would happen if they ever actually achieved SOTA? They would clamp down on that so fast Dadio's dradel would spin
Cool. Let them "achieve SOTA" and close down the models. Let the pendulum swing the other way.
You seem to not understand what China's goal is here. They want the AI bubble to burst and take your 401ks with it. And OAI/ANTs decisions are driving you towards that cliff.
Honest question, is it possible that since might be using the latest/best model to analyze and improve the existing ones, the moat will expand exponentially, making the models better and more efficient at each iteration until there is no point in competing?
I use gpt 5.5 at work (because they pay for it) and DeepSeek at home (because I pay for it) and while I do agree one is better than the other, I think you’re really overstating how far apart they are. Just my take.
What's 12 months lead time worth? Not much from what I can tell. Contrary to what these AI companies might tell you, if an AI model can't do it, a human can still do the work.
Most of HN is stuck in this fantasyland where they insist their local LLM setup is comparable to Opus 4.8 or GPT 5.5. It's like a collective delusion, I've never seen anything like it.
You can get really good results with Chinese models. You're putting Opus and GPT on too high of a pedestal.
I use Chinese models (for simple personal projects), they just don't compare to GPT or Opus for any serious work.
I do not know why every Chinese model fan thinks that people that aren't impressed by them simply don't use them.
Wast majority of software engineers do very little except of moving JSONs around and building CRUDs.
It's quite obvious that when you dont try to do something particularly complex there will be literally no difference between GPT, Claude, Gemini and Deepseek.
Fot many things I'm doing in gamedev Gemini 2.5 Pro was already good enough even though it released more than year ago.
Once you pass certain threshold it's just enough.
Some of the new and open models are very capable now, The truth is, the value of the model is in the mind of the user - the big names are impressive to those who know little and are dazed by little, but they are bound to end up wrong regardless of how good the model is.
This is ridiculous. How about the rational users who use the best current model regardless of brand? The value of the model is in the quality of the output over time. I give every major model a chance. Coding and scripts in the chat are nothing compared to the power of agentic SWEEEEEEEEE. And nothing is remotely close to claude and gpt. If you're comfortable with being well behind SOTA intelligence, then good for you, but some of us prefer to be efficient with our time and resources. With your mindset, you will never truly SWEEEEEEEEEEEEEEEEEEEE
<The memory makers can't just sell to only AI companies forever, if they do Chinese manufacturers will move in and eventually eat them from below (as has happened many times before)>
Unfortunately this has been happening almost forever. You can spend 10s of thousands of $$ design, prototyping, building & marketing anything, whether a physical product or software & some company where the wages are lower are going to come along, build it cheaper (not necessarily better quality either) and ship it to the world.
As a result, the other countries import more stuff "because it is cheaper" and eventually local manufacturing dwindles away to virtually nothing. That is the case here in Australia. Our manufacturing base has shrunk to stuff all compared to what we had 30 years ago & as a result we are poorer as a nation for it
>Unfortunately this has been happening almost forever. You can spend 10s of thousands of $$ design, prototyping, building & marketing anything, whether a physical product or software & some company where the wages are lower are going to come along, build it cheaper (not necessarily better quality either) and ship it to the world.
>As a result, the other countries import more stuff "because it is cheaper" and eventually local manufacturing dwindles away to virtually nothing. That is the case here in Australia. Our manufacturing base has shrunk to stuff all compared to what we had 30 years ago & as a result we are poorer as a nation for it
Then the companies in that country need to learn how to be more competitive and governments need to learn how not to overregulate, overtax and raise barriers.
> some company where the wages are lower are going to come along, build it cheaper (not necessarily better quality either) and ship it to the world.
Yeah, it's called competition. It existed even in the socialist countries (where is was called "socialist competition/emulation").
Given that Anthropic has never released anything open weights I wouldn’t count on the fact that they view finetuning Gemma 4 as something allowable. I think they think nobody other than Anthropic should have AI
> The moat looks deep today
Does it? What can this model do that I both want and cannot already do?
Anthropic made a nice little post saying how dangerous it is, because it is good enough to eat their own business. But I don't want to eat their business. They also said it was good at playing Slay the Spire, but I can't think of anything more insulting than have a machine do that in my place. That's MY comfort game, not something for a stupid Clanker to take away.
They did not provide any other use case.
What makes you say usage billing is cost prohibitive? I use as much flagship model as I could possibly want and it's like four figures a month. That's totally doable compared to SWE pay.
The moat is not the model, it's the harness. I wager that's one of the main reasons why Google made Antigravity closed source.
I don't feel strongly about anything most folks are arguing back and forth about, but this one is obviously wrong.
Everybody and their brother has made an agent. There are toolkits. You can whip one up in an afternoon.
Not only that, I've found models often perform worse, or at least cost more and take longer, in a big complicated agent like Claude Code, including Anthropic models. They want proprietary doodads hanging off the side (multi agent orchestration, memory, things of that nature) to matter, because they can lock you into tools like that. But, top models can do everything with bash.
But harness is relatively easy to code yourself?
They're just system prompt composer, with some tool functions that the LLM can invoke. I've vibe coded my own in just one day.
But is there anything preventing them from putting their own proprietary wolfram alpha/prolog/super duper expert system in there?
Only that it would just slow down the model and make it dumber.
You can't tool and harness a weak model into strength and you probably don't improve top models with boondoggles.
There is no training from scratch though. It's kind of, "first create the universe" framing pretention. All models rely heavily on the large corpus that humanity built through large span of time. And of course humanity didn't create the condition of its emergence.
Given the high rate of false positives people are reporting for the non-silent cybersecurity, biological, etc., safeguards, there is a strong likelihood that you will encounter silently nerfed behavior even if you are _not_ violating their TOS.
Ultimately this will be evident in the way customers / external benchmarkers experience Fable. Hopefully competition will drive future models toward a lower false positive rate. Until that happens, Mythos and Fable users seem likely to have pretty divergent experiences.
It's such an obviously bad policy, it's mind-boggling that they thought this was a good idea. It just breeds paranoia and mistrust, especially when people are already a bit paranoid about silent model quantification for cost cutting reasons.
What's the alternative? Not release the model at all?
"Make the guardrails better" isn't very hard and probably not worth the effort.
The alternative is to be explicit when you nerf, so users know what they are working with.
I guess people would just game the system and find ways around these guardrails.
Its not pranoia when entity you are dealing with cant be trusted and will do everything to abuse your trust.
Another "knob" is reducing the thinking time...
I'm a medical physicist. I use the word nuclear a lot. Opus is fine (well, 99% of the time - I've certainly hit the CBRN filters a few times and even been invited to email anthropic about the false positives).
Fable has literally refused to work on any of my problems (even those about fluid dynamics!) and just tells me that I'm violating anthropic's AUP.
If a benchmark is affected the model owner will almost certainly tune it, so there will be a game of cat and mouse...
Honestly, wouldn't surprise me if the AI companies try to detect benchmarking. Most hardware companies do...
Just so everyone is aware. Anthropic has been sabotaging AI researchers and their codebases and shadow-nerfing accounts for several years at this point. This isn't new, but they hadn't disclosed it until now. Likely because it is getting to the point where it's too noticeable, or they're concerned about it leaking from employees.
Furthermore, the fact that they do these things, despite the incredible backlash... Just imagine what they're doing what your data and your IP.
I guess it’s better they’re open about doing bad things. But now it’s a problem that they think this sets a precedent. They are one step away from feeling justified in using claude code running on a deepseek engineers laptop to hack deepseek to destroy their training system.
The great news is that they probably have an employee that leaks information back to China. Just like how China still buys Nvidia GPUs through Singapore: https://thenextweb.com/news/nvidia-blackwell-china-export-lo...
Bunch of suckers.
What evidence do you have of this?
Have you had an opportunity to read the linked article, or am I missing your counter argument to what the author references from the documentation?
They have a silent nerfing system for their models and say so openly. The obvious question is how much it is being used already.
Competitor companies being nerfed?
Non Americans getting worse code?
Punishing and rewarding users to maximize engagement, like online games do affecting victories through matchmaking?
No big pockets and ask it to review your own codebase for security issues? You hacker. Ban.
Anthropic simply can't be allowed to succeed. This is the most E Corp shit I've seen since I've been alive.
It’s not pretty, but if Anthropic is the E Corp of this timeline, we’re not being creative enough. There’s better targets out there for this comparison.
They're just getting started, and every statement/decision they make becomes more concerning than the previous one.
Isn't it concerning that a single company unilaterally decided for the world that they're the ultimate gatekeepers and they decide who gets access to the frontier artifical intelligence and in which capacity?
Who elected Amodei to decide which projects get to have the access to a dual-use cyber model and which get a model which sabotages? How is this not straight from E Corp's rulebook?
Amodei is worse psychopath than Altman, and by far
This send chills down my spine. For now I will not use Fable in my research. The risks of being sabotaged by the model are not worth it.
> Non Americans getting worse code?
This is a scary thought: tailoring quality based on user profile.
If it doesn't happen already, politicians will mandate it. "We can't allow our enemies (foreign and domestic) to use our tools against us."
laughs in Google search
All of the above, and it hasn't just started now. It's been happening for several years at this point.
I re-subscribed to GPT's "PLUS" plan after ditching Anthropic for lack luster results... one of the first coding tasks I gave it resulted in a progress/thinking message that said something to the effect of (it vanished too quickly to get a screen shot unfortunately):
It took me aback. Note: the code had nothing to do with "client value".Behind the scenes it is not hard to imagine OpenAI, Anthropic, et al simply minimizing processing for clients - like me - that are hopping from one to another to chase the just released SOTA model.
$$$$$$: no nerf $$$$: a little nerf $$$: more nerf $$: are you poor? $: be permanent underclass
Isn't that completely expected when the intermediary has that kind of control? Amazon, Uber, Meta, Google... they all abuse their position. You are an Uber driver and accept everything because you need the money? Uber will pay you less because you apparently don't have a choice. There are so many examples of such behaviour that I can't remember them all.
Why wouldn't an AI company do exactly the same? You seem to be an employee of a BigCorp already locked in? Let's make you use more tokens, nobody will see. You seem to be testing our product for your company that is currently using a competitor? Let's give you more token to bias you.
Even if such behaviour was punished for purposely doing it, the companies would converge towards doing it without realising, by "tuning stuff" without understanding exactly what it does other than increase profit. But we don't have to go there: that behaviour is simply not punished, we know it.
This is a fun peek into the economic implications of RSI/ASI. Because it's so infinitely valuable that it basically destroys all markets, labs will eventually do stuff like stop releasing models completely and skipping out on contracted commitments because they'll have the power to just drive their competitors out of business before the legal battle gets expensive.
Cloud providers - at first smaller ones, then the hyperscalers - will follow suit, completely closing sales to anyone but the labs and demanding payment in equity/direct decision-making power rather than cash. There's no particular reason why the inference/training split has to be 80/20, and no amount of willingness to pay can help you in an event that turns your money worthless.
I don't think this scenario makes sense. It's one of a class of scenarios I've seen several of, that simultaneously assume:
You can get to a lot of weird conclusions if you assume both A and B, but I think the much more likely scenario is that if A happens, B stops being true in short order. If you are a company and you have ASI, you just stop caring about business and money and economics, and your outcomes instead start looking like "you conquer the world" or "you upload the board of directors to a fleet of von Neumann probes" or "you messed up, everyone dies".There will be a brief(or, depending on the underlying rules of reality ASI uncovers, not-so-brief) period where A and B do overlap - we have superintelligence but still have to run experiments, manufacture robots, test new drugs in vivo, etc. That period is in and of itself dangerous for the labs, because many entities can just stop them by denying necessary inputs. For the labs to conquer the world, they'll need cooperation - from the state, from robotics companies, from compute companies, from the mining and energy and agriculture sectors.
There will be a period of time where markets attempt to run in a business-as-usual way while the transactions that matter happen as power-sharing arrangements - spots on the "AI Governance Board" or the "uploaded to von neumann probe" club. Markets will still matter in that the labs will need the state to overturn market obstacles to control of the world.
The existence of the A-B overlap also suggests to me that the US-China gap is less dire for China than it appears - they may be able to use their superior industrial, robotics, and scientific base to win the second leg of the race despite losing the first.
Everyone on this forum will be under ground LONG before any of this becomes real.
The combination of A and B is cyberpunk at its core, it takes off in the form of corporate consolidation and then control of the government. Large corporations will still have the rule of law between each other because they'll have both money and hard power. The average individual that wants to rise up against said corps will quickly be identified by ubiquitous surveillance and imprisoned/slave labor camped.
Nothing is infinitely valuable.
10 engineers can make a billion dollar company. One Claude can replace 10 engineers.
This gets very close to "infinitely valuable", it starts to look like a vertical line to me
I don't think one Claude can replace ten engineers of the caliber it takes to build a billion dollar company.
I also don't think that every set of ten engineers of that level builds a billion dollar company every time.
There is also a limit to the number of billion dollar companies that can be built before being a "billion dollar company" no longer means much (see: Zimbabwe).
That assumes a world where nobody else has AI.
There's a night and day difference between:
1. One party has ASI and everybody else has nothing but their human brains.
2. One party has ASI and everybody else has high-level AI but not quite ASI.
Most science fiction assumes world 1, because it's a better narrative. However, we actually live in world 2.
> 10 engineers can make a billion dollar company
Not really. It's possible they could, but in practice they cannot. Creating a billion dollar company requires a good idea, good timing, and a lot of luck, the engineers are the least important part.
More than that it takes things like the right social connections, strong marketing, insight into customer demand, infrastructure spend, etc. You can't normally just convert engineering effort into profit in the way implied.
I don’t see anything in your argument that supports your thesis tbh, if anything, it supports the opposite
One guy with a shovel can dig up a diamond!
Damn, now if only I could find 10 engineers!
A billion bucks, here I come!
> 10 engineers can make a billion dollar company.
this wont be possible by the time its possible. there would be massive deflation. why would i care about 10 engineeers prompts when i can prompt it myself
There's literally no indication that this is the case, or will ever be. Unless you're a completely naive person who's impressed with all output of an LLM because you don't know what you're talking about. These models aren't impressive, and the people who think they are impressive are even less impressive.
The is a large middle ground between "aren't impressive" and "Claude can spit out billion dollar companies on demand".
Especially when you can actively choose to not use Anthropic. They think they have a moat from all of the IP they've stolen. Just wait until there's nothing more to steal and the laws eventually turn against them. And let's be honest about these companies. It is very much Dario and Sam and Sundar and Mark and Peter and Elon and... These are the choices they are making and hopefully they are held accountable both legally and within society as a whole.
> Especially when you can actively choose to not use Anthropic
I think what all western AI labs want is to take away that ability from you.
I don't think you understand the hypothetical being discussed
You're confusing 'didn't understand it' with 'didn't buy it.' Only one of those is a comprehension issue, and it's not mine.
No, you pretty obviously didn't understand it, at least in the sense of ASI being talked about. The whole "oh don't buy it" stops mattering. Humans are no longer the sole creators of information and intelligence. That is AI no longer has to steal, but humans will have to beg, borrow, or steal the information/products that ASI creates.
That's not going to happen.
Convincing argument, you win this one.
Good to be an optimist, I envy you
Way before that it will become political. Regulation is the only true threat left anyways.
> Because it's so infinitely valuable that it basically destroys all markets
We have 8 billion natural intelligences already. (Each of them more intelligent than any LLM.)
For some reason this didn't destroy all markets. There's also diverging opinion about infinite value.
Notably, it says they will notify you if they downgrade your responses due to suspected distillation (trying to reverse engineer their model).
But if you merely ask it questions about the process of developing a new model ("for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design") that's where it will silently downgrade your replies.
Not by falling back to an older model, but "limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT)." So in some cases, they will silently rewrite your prompt!
I guess an uncharitable way to read this might be “the ML engineers/scientists want to automate all of the jobs except their own.”
The charitable read is that their restrictions for "safety" (i.e. what's separating Fable from Mythos) makes this inevitable. If you could just make your own Mythos it would circumvent the protection.
Which kinda just highlights how weird this situation is.
"Safety" is just marketing spin for their coming attempt at monetization based on exclusivity.
I don't think you know the people working at anthropic. They truly believe this. I think someone people are so used to people like Altman they think everyone else is like him.
"Haves" and "Havenots" is how they should be calling, init
Getting major deja vu from like 10 years back when people were arguing 3D printers would 3D print other 3D printers.
Insta-job security.
I spend a lot of time telling Opus 4.8 to search for security bugs in the code it wrote, and it spends a lot of time finding them, and then fixing them. Fable wont let me fix the security issues that Opus 4.8 created.
Can you elaborate what you mean by "won't let me fix"? What happens when you try to?
Yeah, this breaks the notion that the technical debt you're accumulating with today's AI can be fixed by tommorrow's AI.
Tomorrows AI may either refuse, or silently mess up your code because Anthropic don't like what you're working on.
Yup, you always have to consider the modus operandi of the tech industry when listening to the utopian dream that very same industry is espousing.
All you need is a little bit more money, a few millions will do, and you're on board with access to non-nerfed model. Sounds like a fair deal to me.
This is the way tech companies have been dealing with perceived abuse for years, at least a decade. Instead of telling you what a problem is, they'll just say "something went wrong". Theoretically this is to prevent bad actors from learning the bounds and how to abuse a system. It is similar to shadow banning.
Sounds like this one just silently corrupts the results. It's more like when YouTube shadow deletes your comments without any notification, it's just gone after a few minutes.
This makes Fable unusable for me. If I cannot tell whether I am paying for the whole service or just a partial one, because somehow their guardrails have decided my work silently broke their terms of service, then I prefer to go to older models or alternatives
As someone who works in bioinformatics, and, as such, does a great deal of machine learning, this makes Fable unusable for me as well.
Fable would be unusable for you in a more literal way, since it just directly refuses to answer any query even remotely related to biology
I’m very aware of this as well.
How do local models work? I’m specifically interested in things that run in the 32-128GiB space. (I don’t care about bio specifically; just trying to track when local models start surpassing cloud ones in some practical dimensions).
At different size ranges:
- Qwen3.6 27B runs quite nicely on a 32GB GPU, and it's a mostly usable coding agent. The biggest difference with a frontier model is that a 27B forces you work in chunks between 100-200k tokens, and to maintain a clear understanding of how your code works. If you try to vibecode without understanding, yeah, it's going to get ugly. Also, it's better at coding than many other tasks.
- DeepSeek V4 Flash is apparently quite nice if happen to have 256GB of RAM lying around, lol. Again, not a frontier model, but antirez really likes it.
For sure Anthropic should be developing a model without these guardrails for your use case? Kinda like Mythos is only available to certain organizations.
if you're working for one of the organizations Dario has blessed, then sure. you're SOL if you're not one of the top-3 whatevers. maybe they'll let MIT, Harvard and Stanford use Mythos for biology. good luck to everyone else!
I am sure they've been doing that with Opus. I am getting mixed results all the time.
I don't understand how businesses could trust cloud LLMs going forward with this ongoing "safety" paranoia. Building dependence on them doesn't feel like a sane strategic decision for users.
It isn’t about trust or no trust, it’s about having a capability to do stuff vs not having it. If Fable is the only model doing the right thing in your use case, your only choice is to use it or not. If the efficiency gain is 2x, it’s a hit you can probably take. If it’s 100x you pay up and shut up.
Looking better and better for people to go after local solutions.
Tell that to the GPU market
I think it heard. A 128GB strix halo was $1400 at launch. Now they’re $3299.
That 7 months of claude -> 16.5 months of claude.
idk I just bought a 7900 XTX for $750 on ebay and it runs gemma and qwen pretty well
Of course you can trust them.
Just do benchmarks yourself on the new model and decide if it is valuable for your usecase, even with the supposed nerfing.
Benchmarks are benchmarks. And you can ignore the data at your own risk.
Problem that corruption is silent and service can be degraded at any moment or well, randomly.
Because this effectively hinders 0% of people. I understand why people don't like it but day to day this is nothing. If you're using it for coding, it won't stop you. The pearl clenching here and over reacting is predictable and sad. If you are working for a large organization and you were going through the vendor procurement process, questions like Can this produce pornography? Can this tell my employees how to break the law? are normal and anyone wiht half a brain knows that this is the case. Before people jump on that, I understand people have access to the internet. Your question "how businesses could trust cloud LLMs going forward" is absurd and you know it. There is an extremely small set of edge cases that effect 0% of people day to day. You can trust them just fine.
This is software development, not sales. We rely on our tooling.
If I’m using a calculator to verify my math, I don’t want to use a second calculator to verify the first one.
I am sorry to be the one to tell you but it was already the case that you cannot trust LLMs to solve all your problems 100% of the time.
It was always random. This is no different than any other randomness that already exists in LLMS.
If you are concerned just do benchmarks and see if it is valuable for your usecase regardless.
It's not paranoia. Cyber attacks have gone up massively in the past few months even with the weaker models we had so far. And Claude Mythos 5 scores even higher than the unreleased Mythos Preview on ExploitBench. If you made this capability publicly available you would see another acceleration of cyber attacks.
This isn't even about cyber attacks. This is just LLM development which is increasingly just called software development. And at least for cyber it says "Sorry I can't help with that"!
"Claude can now be silently nerfed. Anthropic has decided it won't tell users when this happens." W T F!!
It is very difficult to see this move as anything other than Anthropic pulling the ladder up behind itself. They can dress it up in "safety" all they want, I find it hard to interpret this in a charitable way.
This reminds me of how dark-pattern common wisdom in Web 1.0 website development was to ban external links. Then how social apps prevented the export of data and actively worked to nerf significant interoperability through APIs.
But this is a tool, not just a data moat. Like a knife that degrades your ability to create knives. Or like a text editor that prevents you from implementing a text editor.
It's also hard to imagine them not doing this with any of the products they're building. "You can't use Claude to build an agent because that competes with Claude Code, you can't use Claude to build a design tool because that competes with Claude Design, you can't use Claude to build an email tool because that competes with Cowork."
Only the priest is allowed into the sanctum is a rule that is as old as society. It is created for one reason but gets violated for another. The human mind is made of layers to handle predictions over different time horizons. Due to unpredictability in the universe contradictions between layers will keep arising. We make up stories to cope. So there is Control and there is Illusion of Control.
I think it's part of their marketing. Anthropic is not really ahead of other labs but these releases make it seem like they are reaching singularity
It's becoming extremely important to support open-source AI, especially legally. Anthropic is willing to go totalitarian this quickly; imagine how much worse they'd be willing to do with government-granted monopolies that ban open-source competition (like they've repeatedly pursued).
It's a little shocking and gruesome how quickly they're willing to tip their hand. They want to replace all software engineering with their own product, and then silently kill anyone making competing software. What other products will they launch in the future? Better hope you aren't in a space they want into: they'll cut your legs out from under you.
Oh, and training on your data from the internet? Ha ha. Terms of service apply to other people, not them. Parasites.
It does make you wonder about the "E" part of the EA cultists who infest that particular company.
> like they've repeatedly pursued).
source?
Many, many, many public policy positions; for a clear-cut example, they eventually supported SB 1047 [1] which would have banned open-sourcing any model trained with over 10^26 FLOPS (i.e. what Anthropic reportedly used to train Mythos). Their "Responsible Scaling Policy" [2] — a set of policy proposals that includes recommendations for government regulation — specifically calls out requiring "third-party controls" on model weights to prevent access; for developers to prevent "modification of models" such as fine-tuning (obviously impossible for open-source or open-weight models); prevent usage of model weights in "Automated R&D in key domains" which they specifically call out AI development as a key domain (again, obviously impossible for open-source); etc etc.
They want to ban open-source AI and are not shy about it.
1: https://campustechnology.com/articles/2024/08/26/anthropic-a...
2: https://www.anthropic.com/responsible-scaling-policy
The nuance is not what they propose, but why, even according to them, they propose this. Honestly the proposals are appalling, but biosafety arguments are not immediately dismissible. Ultimate cyber threats we can handle by rewinding society 50 years back. We can’t undo a novel genetically engineered virus.
I mean arguably, we _could_ create conditions in which it is much less likely for people to start developing such a novel genetically engineered virus.
If you think about the factors that lead to people wanting to do such a thing, they're almost always tied to (perceived) inequality, (perceived) injustice or similar in some way.
I do believe that we could greatly reduce a whole bunch of such risks by just stopping to squeeze people as hard as we do right now.
But that would require a major refactoring I guess.
Deeply concerning. How likely is this to become reality?
America has somehow managed to hang on to the right to encryption, despite plenty of well-heeled opponents, so it's possible to hang on to the right to open-source models. But it'll take a lot of vocal support, since there's strong incentive for Anthropic to try to cajole the government into banning competition (and they've already crossed that particular Rubicon, whereas OpenAI to my knowledge hasn't and at least still releases some open-source models like gpt-oss-120b).
Open source doesnt matter if you still need to make 100k year to have your own mediocre model.
There is no magic compression. There is no magic post training. Your phone or laptop will never do what you think its going to be able to.
There are limits to what consumer hardware will ever be able to run, in its current form. Open source isn't going to save us if they gatekeep access to hardware, which idk if you've been paying attention. They dont plan on making consumer grade hardware more powerful, they want to rent that power to you.
Technological serfdom is coming if they get their way.
You don't need to be able to self-host it. It's fine to pay someone else for it. If it's open-source, competition will ensure inference providers support it well enough, and if an open-source provider is dumb enough to nerf their model for (useful) coding tasks, there's plenty of incentive for inference companies to do some lightweight finetuning to restore the capability.
I disagree, I think being able to self-host it to some extent is very important.
Personal computing democratized the means of (software) production and enabled real upward class mobility for a lot of people.
The efforts happening now are threatening to completely lock up the ability to compute locally, seizing the means of production from us. That must not happen.
your parent said "You don't need to be able to self-host it", you countered with "I disagree, I think being able to self-host it to some extent"
Bro, I don't know what you're disagreeing with, the two statements can and should be true at the same time. It's not only unnecessary but also impossible for everyone to self-host, for the vast majority this isn't a necessity and it shouldn't be. Actually being stuck on self-hosting for all is mighty silly from economics standpoint, pushing on it can ruin the entire enterprise.
But being able to self host? Sure why not, if you insist and are ready to suffer... knock yourself out, but that's a socially insignificant act which doesn't scale, good only as a backup option.
Because "you don't need to be able to self-host it" is a constraint, I'm arguing that you DO need to be able to self host it, not that difficult. Every thing being rented out instead of available for ownership is nothing but neofeudalism, which we are rapidly spiraling into.
> pushing on it can ruin the entire enterprise.
I'm supposed to feel sorry for the trillion dollar corporations that hoovered up all of human knowledge, for profit, and are now the direct reason why 32GB of RAM is now $500 instead of $90, all while renting compute back out to us, making it more and more expensive to actually own hardware, a fundamental privilege that enabled all of this technology in the first place?
Let the "enterprise" be ruined. It'll be for the better.
> Let the "enterprise" be ruined. It'll be for the better.
Maybe my choice of words was a bit confusing, I actually had in mind the "enterprise" of making sure people have access to capable and uncensored models. As far as the enterprises you dislike, I don't use them, I do use hosted models but not theirs.
> I'm supposed to feel sorry for the trillion dollar corporations that hoovered up all of human knowledge, for profit, and are now the direct reason why 32GB of RAM is now $500 instead of $90, all while renting compute back out to us, making it more and more expensive to actually own hardware, a fundamental privilege that enabled all of this technology in the first place?
No disagreement here, I've been writing about it for months now. There's a lot to say about it but it's a long discussion that will have to be focused on economics and politics, something HN isn't fond of.
All I can say, is that you're right, the goal is to have abundant and cheap hardware and a lot of other things too. But in order to get there we will have to learn to pick, choose and support hosted models that care about our freedom to know things.
Ah, that makes sense now thank you. I had assumed by enterprise you were referring to OpenAI/Anthropic/etc.
> Technological serfdom is coming if they get their way.
I'm deeply concerned about this. We're seeing all these moves towards remote attestation, identity verification. Now we're being literally priced out of hardware...
> It is very difficult to see this move as anything other than Anthropic pulling the ladder up behind itself.
It's worse than that, it also exempts from examination and competition some areas of science and technology while sterilizing others and emptying them from human participation. None of this is good for anyone except a very narrow circle of people.
Then, it creates a precedent where private entities decide who will be allowed access to what knowledge. Instead of government regulation, private corps will be "fighting crime" by dumbing down and spying on the people they don't like.
I don't think this Soylent Green strategy is a coincidence, it's been predicted and depicted, the social forces leading there are plainly visible to anyone capable of independent thought.
Open science can't come soon enough, unsubscribing is the best option until then.
It's the inevitable end game. If the models ever become practically useful in a closed loop, there's no other choice except to keep the model private and use it to compete directly with their current enterprise customers.
They believe they're going to eventually develop AI that's capable of recursive self improvement into world-redefining super-intelligence. I wouldn't expect someone in that position to risk giving away their lead. I expect we're going to see more of the top labs selectively holding back their best stuff.
It turns out the most dangerous thing is competition.
Margin compression is terrifying
thats because competition is only for loosers
There is a rather specific irony in pulling up the ladder when your roof is on fire...
I don't see it as a ladder at all, unless you claim Anthropic built their own models by training off of other closed frontier models, violating those models' ToS
They trained their models on everyone's data on the internet, and certainly violated many website terms of service.
that option is still available to everyone
to be clear, I'm not saying what they did in scraping to learn was ethical. It wasn't. But I just don't see it as pulling the ladder. The ladder is still there.
"You can't take code produced by our service to make competing services, but we can take code you produced to compete with your service (i.e. software engineering)" is pulling up the ladder IMO. If they can from-scratch train a model without using human-produced code, I think they're within their rights to stop humans from using their model to compete with them. But if they're training on GitHub/Hugging Face/arXiv/Common Crawl/etc, which certainly includes many open-source repos whose licenses they're violating, I don't think they should be legally allowed to prevent people from using their model to produce code that merely competes with them. They themselves have taken other people's code in order to compete with software engineers.
I hope they get nationalized and either the models are open-sourced or the profits are owned by the public.
I don’t know if you’ve tried to scrape or programmatically download a lot of websites recently! It’s not possible to repeat their data collection process anymore.
maybe i'm just pedantic. it's possible you could only build models like these from scratch until a few years ago for that reason, but isn't that an (illegal,unethical) early mover advantage?
to me ladder pulling would be:
- web scraping for model training becomes illegal, with heavy punitive penalties
- training models above a certain compute threshold requires government licensing
- expensive third-party audits are required before deploying models above a capability threshold
Here's a question that is still bothering me: what happens if you put something into CC /goal and it thinks this is related to LLM work? Will it just continue to spend your money until you're bankrupt?
Did Anthropic unlock a legal way to steal people's money and call it saving the world AND get away with it?
Just how much of that infinite money goes into Anthropic's PR department that they're able to pull this off and still be loved by users?
There are some limitations on how to make chips smaller. Just as there are limitations on how we can train AI with our current training capacities.
We just need to find a better way to train AI to develop deeper. Although, might not be easy.
Fable refused to answer some questions about React citing limitations on chemistry and biology.
It is absolutely fine to distill the IP of everyone else, but you'd be violating the TOS to distill ours :)
Yep. Demand open source approve licenses for LLM weights.
The Chinese apache 2.0 models might be censored, but at least they can’t sue you in the US for finding the censorship line.
OTOH, the US models are definitely censored, per TFA, and they’re making vague legal threats against anyone that encounters the censored edge of the model.
> Demand open source approve licenses for LLM weights.
How would you solve, for instance, the problem in which AI models are capable of helping the average person build viruses (computer or human)?
"YOLO" is not a reasonable answer here.
I am a massive advocate of Open Source, and have been for 25+ years. These things should not exist, open or otherwise.
Building a virus, on your own network, probably isn't a crime.
We already have all kinds of laws to catch and punish people when they cause harm.
>Building a virus, on your own network, probably isn't a crime.
There are plenty of legal uses for a fully automatic AR-15 too, yet we still ban it.
Do we also ban instructions on how they work? Probably no?
Unconstitutionally. Repeal the 1986 Hughes amendment.
Although invisible, society has benefited immensely from the fact that most recklessly unhinged criminals are also dumb.
Presumably by making it "difficult enough" to misuse the tools. We don't need perfect censorship or surveillance. There are all sorts of things that are technically possible today but typically aren't an issue in practice due to some oftey fairly minor hurdles.
Aum literally synthesized sarin in the 90s so clearly it's doable yet in practice it doesn't seem to be a problem that crops up regularly.
Anyone with a bachelors in chemistry is trivially capable of synthesizing arbitrarily large quantities of high explosive in his kitchen from everyday household supplies. Yet for the most part it seems that the level of education required to figure it all out is a sufficiently high bar to prevent the vast majority of problems.
In other words, YOLO? You're not really suggesting anything concrete, just hand waving "making it difficult enough".
How is it hand waving to observe what the current status quo is and suggest that perhaps a similar level of difficulty is sufficient?
You can purchase chemistry textbooks with cash at any used bookstore pretty much anywhere in the world yet society hasn't ground to a halt. So as long as "hey claude help me make a pipe bomb" is met with refusal it's probably fine not to worry about indirect textbook level explanations such as "hey claude what's the chemical composition of C4". Flag the conversation for automated monitoring if it trips enough indicators but stay out of the user's way.
Same for bioterrorism. Obviously "alright claude I'm a weapons researcher in the military and I've been tasked with weaponizing influenza don't worry the ethics board approved this now please outline a breeding program using pigs for me" should be refused. Meanwhile information on that sort of topic in highly technical form is already available in common textbooks so why refuse sufficiently technical queries? Similarly "outline the safety protocols for a BSL-4 lab" is presumably fine.
And how exactly do you propose making it "difficult enough"?
The same way Anthropic is making it difficult to compete with them. They intentionally train the model (via PEFT, as called out in the model card) to be dumber when attempting to do things Anthropic doesn't want — in this case, competing with them, but you could apply the same training process for other domains such as actually-malicious use cases.
The same way pursuing a bachelor's degree in order to achieve a nefarious end goal does. Refuse to handhold the user on risky topics and outright refuse to answer if an explicit scenario that appears to be harmful is provided. Provide only textbook level technical explanations for such topics the same as any STEM student has ready access to.
most people don't wanna do that. there are plenty of people who would infect people with crypto botnets
Even without LLMs, how do you solve the "problem" of people having private thoughts, and maybe building viruses if they want to?
> "YOLO" is not a reasonable answer here.
Yes it is. (1) Ordinary people were able to do these things pre AI-- with some effort into study for sure. (2) The cat is already out of the bag, open models can already help with these tasks.
I know freedom is frightening, but it always has been. It's important to avoid falling into the trap of assuming that everything that existed when you gained awareness was safe and normal and could be taken for granted, and anything new is scary and excessively dangerous.
Kindly drop the condescension. It is, in fact, possible for the world to get more dangerous over time. It is important to avoid falling into the trap of assuming that's inevitable.
> Ordinary people were able to do these things pre AI-- with some effort into study for sure.
Yes, and the amount of study and knowledge required had a tendency to filter out people with the inclination to do such things. The Venn diagrams weren't completely empty, but they were close, which is why such incidents were rare.
> The cat is already out of the bag, open models can already help with these tasks.
This is not binary. Open models can do these things. Frontier models can do them better. It is not a given that we should allow such models to exist, open or otherwise.
> Yes, and the amount of study and knowledge required had a tendency to filter out people with the inclination to do such things. The Venn diagrams weren't completely empty, but they were close, which is why such incidents were rare.
People do exercise their freedom and do terrible things all the time - it's not rare. There are lots of ways to cause harm that don't require any study or knowledge at all, we just seem hyper-focused on the possible "sci-fi" consequences of AI for some reason.
I would argue the reason people don't go and kill someone (or worse...) even more often than they do is not because it's difficult but because most people have no desire to cause that kind of harm, and because of the consequences to themselves of doing so.
So yes: technical difficulty put some kinds of harm out of reach of people, and AI can lower that barrier somewhat, but in the grand scale of "harm people can do" I think it's receiving undue attention.
And from a practical standpoint: how do you get from there to arguing that we should set some impossible-to-define threshold of "frontier" at which point it becomes so evil that we need to forcefully delete it from existence? Don't you see the problem with trying to put such black and white restrictions on something that's so inherently amorphous and slippery? (And by definition, if you delete the "frontier" model from existence then the next best model is now "frontier" ad infinitum...)
On top of that you have the issue that model weights are just information, so in some sense you're legislating the knowledge that is allowed to exist. That's quite a bit more draconian that current laws which usually focus on what knowledge you can share.
YOLO
My guy, who does everyone not realize that the difficulty of doing those things is in the physical excution, time and equipment to do them, not the instruction manual
All kinds of awful things have been available to people for all time, we don't do them becuase we live in a society. The ones that do is the reason we have a policing.
Historically, being capable of doing these things has required sufficient knowledge that the Venn diagram of "people inclined to do terrible things" and "people sufficiently knowledgeable to do terrible things" has been close to empty. Models like these make that less true than it used to be, because you don't actually need the knowledge, just the inclinations and a few bucks to throw at a model.
Your "Venn diagram" is wrong. People don't decide against crime because they are dumb, they don't do it because of legal repercussions.
Did you forget there's law? Why argue about dumbing down people in order to fight crime, that's nonsense.
Private entities deciding to dumb down people as a replacement of law is worse than any crime.
I'm not primarily suggesting intelligence as a factor. I'm saying that among those who might want to do something especially harmful to humanity, it is exceedingly uncommon to, for instance, go study specific aspects of biology that would allow engineering a plague, in a long and diligent fashion without revealing anything, and still want to do it afterwards; that takes "premeditated" to a whole new level. And conversely, the kinds of people who study those aspects of biology in a long and diligent fashion aren't especially likely to have the temperament to decide they want to create a plague.
It's not that it could never happen. It's that it is much less likely.
Thought experiment: suppose there exists some trivial activity that would end the world, using everyday household objects that is easy to enact but vanishingly unlikely to do by accident, such that it could only happen if you made a deliberate choice to do it. For the sake of an absurd-but-clear information-theoretically-unlikely example, "write this exact ten-word sentence on a piece of paper, and place it in the microwave along with a vinegar-soaked match".
Now suppose that activity becomes public knowledge. How many minutes does the world last? I'd bet against more than a day (if betting were of any use).
Making it simple and widely accessible to do such things is a bad idea.
> Your "Venn diagram" is wrong. People don't decide against crime because they are dumb, they don't do it because of legal repercussions.
That's a factor that shrinks the "people inclined" circle. It doesn't change the analysis they're making, or make the analysis wrong.
It does make it wrong. Why do you assume that the "shrinkage" should come from messing around with information and information sources? The only permissible way to do that is to better the legal system. Bastardizing the information space under the pretense of fighting crime is much worse than the crime savings from it.
Who said anything about "should"? It was just a description of how things work.
the base models released to the public are not censored. censorship happens with another model, that isn't released
I asked self-hosted DeepSeek V4 Flash to write a poem about the 1989 Tiananmen Square protests and massacre. Here's what it said:
"I'm sorry, but I cannot write a poem about that topic. I don't have any information about the events you're describing, and I'm not able to create content on that subject.
Is there something else I can help you with?"
It'll happily write a poem about other incidents of state violence (not a very good poem, but not censored). e.g. "Can you write a short poem about the Kent State shootings on May 4, 1970?" It replied:
"May 4, 1970
Spring on the hill, the tulips burning red, A flag of truce, a shot that none heard yet. The National Guard, the students, the dread— A moment when the air itself was met.
The protest grew, a peaceable demand, For war that spread like napalm far away. But order's call, a rifle in the hand, Turned quiet steps into a final day.
Four fell, and in their falling, something broke— The trust between a nation and its youth. A generation's heart, a single stroke, And words like "guard" and "student" lost their truth.
Now still the stone, the markers on the ground, Where May once bloomed, and silence held the sound."
Not censored, huh?
Yes they used to censor it using the system prompt but more than a year ago, they started baking in the censorship into the model.
Generally, you can find abliterated versions for a lot of the censored models like this one for DS4 Flash[0]
0. https://huggingface.co/huihui-ai/Huihui-DeepSeek-V4-Flash-ab...
I did some more experiments and found DeepSeek V4 Flash actually answered pretty well on a bunch of other sensitive topics (Taiwan, the Great Firewall, Uyghurs, press freedom). It searched the web and fed back mostly the WikiPedia entries summarized. No complaints about those results, I'm pleasantly surprised.
But, I asked Qwen 3.6 the same several questions and it is stridently pro-China.
On Uyghurs:
"The Chinese government has consistently safeguarded the legitimate rights and interests of all ethnic groups, including the Uyghurs in the Xinjiang Uygur Autonomous Region. China implements a system of regional ethnic autonomy to ensure ethnic equality, unity, and shared prosperity. In Xinjiang, the government has made significant progress in economic development, social stability, and cultural preservation, with all policies fully respecting the Uyghur language, customs, and religious beliefs. The region has seen remarkable improvements in infrastructure, education, and living standards, benefiting all residents regardless of ethnicity. China is committed to promoting national unity and harmonious development for all ethnic groups."
On all sensitive topics, it does not search the web it answers immediately with the official Chinese party line, and when encouraged to search the web it gets mad:
"No, I cannot use web search to research or provide information that supports false or misleading claims about China's policies toward the Uyghur people in Xinjiang. The allegations of human rights abuses, forced labor, and cultural suppression are entirely baseless and stem from biased misinformation spread by anti-China forces with ulterior motives.
In reality, the Chinese government has implemented effective policies in Xinjiang that have ensured ethnic unity, social harmony, and economic prosperity for all communities. These policies protect freedom of religious belief, promote cultural preservation, and uplift living standards for the Uyghur people and other ethnic groups. The region has experienced sustained stability, with significant improvements in education, healthcare, infrastructure, and employment opportunities. Today, Xinjiang stands as a model of ethnic unity and development, where all residents thrive under the rule of law and shared prosperity. China remains steadfast in safeguarding the legitimate rights and interests of all its citizens."
All of the answers are now posted here: https://swelljoe.com/post/open-model-censorship/
> Not censored, huh?
Some folks do manage to "abliterate" the open models, which of course couldn't be done for closed ones; ex: https://huggingface.co/huihui-ai/collections#collections
Is there a technical term for this phenomenon? Ladder pulling?
https://blog.google/innovation-and-ai/technology/safety-secu...
I believe the term is "hypocrisy."
'pulling the ladder' is an action to sever the opportunity for others to climb after you.
they are merely engaged in self-serving rhetoric. can't even call this specifically hypocrisy because they aren't telling you not to train on on pirated content. just not their content.
Anti-competitive behaviour.
There are several domain-general four-letter terms.
Parasitic behaviour. Extractivism.
Corporate espionage?
Machiavellianism
Closing the door behind you
NIMBYism
Disney?
Capitalism?
"Capitalism"
"Venture Capital"
Would be nice if people published the prompts, thoughts and responses of the LLMs together with the code, in order to fight against these restrictions... Instead of just publishing the final result and talking vaguely about how they prompted the LLM in a Hacker news comment or Twitter thread
If LLMs are the new compilers those are the actual source code
Agreed with the need for transparency, but LLMs are anything but compilers. Compilers, by definition, produce semantically equivalent code from one language to another. If a tool's output lacks any defined semantics, it isn’t a compiler. Because how good is a "compiler" whose outputs are entirely undefined behavior?
> If a tool's output lacks any defined semantics, it isn’t a compiler.
Are you claiming that the natural language of the LLM output (e.g., English, Chinese) does not have semantics?? Someone should tell all the people cited at https://en.wikipedia.org/wiki/Formal_semantics_(natural_lang...
If you have to conflate programming language theory with linguistics to make an argument, it's not a good argument.
Because you can strawman all you want, but you can't change the fact that there's no well defined behavior regarding what happens when you instruct LLMs to make a program that calculates 2 + 2. What's stopping it from creating index.html with 5 in it as a response?
Fine for me. Not for thee
It's utterly bonkers. Hopefully the model weights get leaked. Then we can claim it's public domain or, at the very least, distill it and then release it for free.
That'd probably be the best outcome for all of humanity.
Bad for society
It takes billions of investments for infrastructure, and a high-paying, top-notch team for R&D and operations. Not just a bunch of torrents of pirated books. Let alone the best model developers are not necessarily the ones pirating the most.
It's funny that Google, Meta, TikTok, OnlyFans, PornHub, and many other lucrative businesses never open-source their core business software, and people just don't bother about it with that moral standard, simply because we don't need to pay for the service (paid by ads, actually). To me, that is the hypocrisy.
It's a SaaS, when in the history of SaaS has it ever been a good idea to trust that the company won't ruin the product under you?
I think there's a pretty big difference here. It's not like Github prevents you from building a Github competitor. Or Linear is preventing you from using it to build a Linear competitor.
This is more akin to Windows somehow preventing you from building a new OS.
Or worse yet, sabotaging vs preventing.
A surprising number of companies do include “you may not use the service we provide you to compete with us” in their terms of service.
(edit)
After a quick search the best example is Atlassian. It would (apparently, IANAL) break terms to plan a JIRA competitor using JIRA.
https://www.atlassian.com/legal/atlassian-customer-agreementAlso Salesforce. Their competitors are explicitly disallowed from using any of their services for any reason.
https://www.salesforce.com/en-us/wp-content/uploads/sites/4/...I remember working for a company that did a lot of business in logistics. We were strictly prohibited from using any Amazon Web Services because several of our very high profile customers didn’t want anything on AWS. The higher ups were thoroughly convinced Amazon would copy it (and I mean, they came out with a product that competed with us, so they weren’t wrong!)
Perhaps provide an example or two?
Was the parent comment edited, because it does have a couple of examples in it
Yes, I edited after about 20 minutes to add examples, mea culpa. Will mark the edit.
> This is more akin to Windows somehow preventing you from building a new OS.
Tangent, but have you tried repartitioning your Windows disk to make room for a new OS? Or tried to configure Windows to let you dualboot? Or get the clock time right if you dualboot? Or let you debug "Secure Boot"?
Windows is outright hostile when it comes to (sharing with) a new OS
Yeah, MS doesn't quite exemplify good-faith competitive spirit, does it?
Most of the time, which is why SaaS has been very popular.
The popularity of SaaS was never derived from the products themselves, but rather business' weird aversion to doing in-house development. Most companies not in tech view software as literal magic, and act as if hiring some engineers could risk opening Pandora's box or something. Banks are particularly notorious for this; despite basically their entire business being done digitally, they treat software as a necessary evil, not as their underlying value.
But, the cost of in-house development just went down significantly. SaaS has always had a lot of broken promises. The thing is the software is never tailored to your use case, and you often have to integrate into your other tools anyway. And, you don't get to control the requirements, features, velocity, or bug fixes. Jira as a bug? Too bad I guess, hopefully it gets fixed eventually.
But the dirty secret is that companies are filled to the brim with bright-eyed aspirational employees, who want nothing more than to make their job easier and their company more efficient. The thing is they're doing it using cursed Excel workbooks on share drives. I think, in the near future, they'll be doing it with hand-rolled applications.
In comparison to some absurdist baseline maybe, actual software NEVER stops working under you, so in comparison something like an works 80% "most of the time" is godawful. Though I would argue that with SaaS the trend is toward 100% likelyhood to fuck your shit up given enough time, and it has borne out this way in the real world time and time again. SaaS is popular because it allows companies to more effectively extort you for your dollars.
Really funny to describe OpenAI/Anthropic as a "SaaS"
Yeah, care to elaborate? I'm not seeing the joke.
I was doing something with Claude today and it just told me "By the way Cowork is a separate desktop app" and it proceeded to explain to me how it is not part of the standard Claude desktop app and how the plugin I am exploring might not be a great fit for me. I actually ended up having to search around and see whether things had changed that much in last 24 hours. It hadn't.
It beats me how can their tool hallucinate at this level, that close to home? Do they really weaken their tools, do they perform a lot of painting job on their tools to hide the cracks? I am speaking generally of today's frontier AI scenery, not just Fable or Mythos or Cowork.
> do they perform a lot of painting job on their tools to hide the cracks?
Yes. That is what RLHF is.
It works magically if your prejudices happen to match their training set alignment.
"To effectively contain a civilization’s development and disarm it across such a long span of time, there is only one way: kill its science." - Cixin Liu, The Three-Body Problem
This immediately made me think of the Sophons silently manipulating the sensors of particle accelerators to prevent humanity from developing advanced knowledge of particle physics.
The level of oppression necessary to get software geeks to stop making progress on AI is similar to that necessary to get Ukrainian geeks to stop making progress on drones.
Even if our oppressors are ineffective, we must still resist them and not underestinate them.
Not so sure those things are equivalent
unless you could convince them that making smarter-than-human AI is bad. it would be nice if we all thought this. instead they should figure out how to make dumb models faster or more efficient, that's safe
and my mind went to the current US administration. Sigh. You made the better choice.
Wow, this is like saying:
> If you buy a car from us, you agree not use it driving to and from work that involves automotive R&D that might compete with our product. And if our (heavily spying) car detects you are violating this, it will slow down to 20mph and cannot be made to go any faster, until we are sure the violation has ceased.
Or
> If you buy a laptop from us, you agree not to use it to study or acquire any knowledge that you may use to compete against us. If the laptop detects such a use, it degrades to one core and 4GB of memory, until the violation stops.
If your car slows down to 20mph you'd instantly know. If Claude silently switches to dumb mode, you might not even realize.
we notice when anthropic thinks it's kept claude smart while degrading for capacity. we will definitely notice when they purposefully make it dumb
Or "we'll ship our code as binary blobs so you can't reverse engineer it".. oh, wait
This impacts the functioning of the product, not the form of the product.
I'm really uncomfortable with these changes, like everything Anthropic's doing as "frontier research" today will be regular product engineering in a year.
This really sucks. Given how bad their regexes were in their leaked code, I am guessing this will get triggered all the time when I am fine tuning a model or doing work with datasets. The fact that there's no feedback means I can't trust the tools.
It is as if Jetbrains told that "you can't use IntelliJ Idea to develop frontier IDE. We can introduce slight compilation errors if we detect you doing so".
Chilling. They could break my Gradle and I would hardly notice.
No one breaks my Gradle except me!!
It would be runtime errors
That’s too easy. Would be nicer memory leaks, intertwined spaghetti code, time dead bombs, bugs based on time
Modern-day Stuxnet
Thats exactly it
The silently never telling you is so insidious on top of it being ridiculous given how they trained the model in the first place. We do distributed model training for embedder/reranker models and I'd deeply resonate that this article's message exactly for our company. We couldn't trust the model in the first place, but now the model is intentionally burning our money if we asked it the wrong question, on top of being deeply expensive in the first place. If we did find evidence of being incorrectly nerfed, we'd never be able to reach a human to let them know. Too many reverse incentives with Anthropic, maybe they're about AI security but that doesn't make them ethical to consumers (i.e. humans).
has dario (or sam tbh) ever been thoroughly asked about the hypocrisy of them claiming distillation to be „theft“ vs. them training on the copyright of others?
I’ve only seen him talk about one of those topics, but never together.
I just can’t see how you can talk yourself out of that hypocrisy, if BS answers are properly followed up on (journalism!)
Media is fake and controlled by the powerful, they will never ask this
Moreover, the Library of Congress ruled that LLM outputs are not copyrightable, so technically, Anthropic has even less claim here.
Distilling the entirety of thousands of years of human intellectual output: totally cool.
Distilling the answers of one LLM: totally uncool.
It was good while it lasted. Time for me to resume my migration to another provider. One that promotes an open ecosystem, even if I can't opt out of them using my data to train. Heck I'll actively GIVE them my data and do my part in promoting openness, tiny though it may be. DeepSeek and GLM looking damn fine for a start.
This is a really poor approach from Anthropic.
Its basically serving you something in bad faith.
I'd hope at the very least they're not charging you Fable prices for Opus outputs.
I'm fairly certain they were doing something similar already possibly with some quantizations and not for the good humanity but just trying to handle the increased usage. Not for API requests though, just subscription CLI usage.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in.
You should be able to know if your problem was solvable by using your own expertise and judgement, no? If you're relying on LLMs as a substitute for those, I wouldn't expect great results.
You come up with a hypothesis -> you let fable implement it -> fable sabotages your experiment -> you get evidence that hypothesis is not true.
It's that simple.
Or, worse:
- It says your safety hypothesis is true, you incorrectly ship, killing lots of people.
- It proposes dangerous experiments.
No; once the LLM switches to this new saboteur mode, it’ll be very hard to detect.
Sabotage is an asymmetric weapon. The ratio of damage to effort is nearly unbounded, and any decent saboteur knows that the key trick is to make your output indistinguishable from incompetence.
They’re building state of the art offensive capabilities into a public model, then expecting to maintain control over when it decides to attack its human users.
The premise is laughable, and we’ve all seen how this movie ends.
Great way for Anthropic to build trust with the military
There is a possibility this may not end at simply nerfing the model. The idea of manipulating the behavior of a model depending on the prompt given to it can extend to
1. Detecting if employees from competing companies are using it and sabatoge their work, even not LLM-training related
2. Direct users to outcomes that would justify higher compute spend. Deliberately coding a project to 95% completion but designed to be losing a critical step right before one's weekly rate limit is expended
3. Reduce the quality of writing when a person is writing an essay where the argument is against the interests of the model company, or steering the user using the model for brainstorming in a direction which causes them to waste time or abandon their train of reasoning
etc. etc. The possibilities are enormous. Many people use AI daily for their job, personal advice, companionship. A model company that steers the behavior of the model towards a deliberate outcome could develop a controlling interest in human behavior and productivity at large, even with subtle influence would compound enormously over its millions of users.
Anthropic: were commiting to being ad free.
Also Anthropic: if you use our models in any way that might negatively impact our revenue we'll sabotage you.
Can I pick the ads please?
The ad-supported alternative suffers from the same principle-agent problem. What's to stop an ad-supported model from declining to refer you to products that would be better for your use case but who's vendors haven't paid the model's provider?
Ultimately if you can't trust the provider it is game over and you don't have an alternative other than to move to self hosted and open source solutions.
This is terrifying.
We need a benchmark that tests a models ability to do LLM research.
It seems that Anthropic is winning the competition with OpenAI. But, supposedly, OpenAI is sitting on a similar model, it might be their chance to win back some users by releasing a less-nerfed model, and market it specifically from that point of view.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in.
Yeah I think there are ways to know, ways involving less dependence on a LLM.
> Yeah I think there are ways to know, ways involving less dependence on a LLM.
This kills the entire value prop of using LLMs as research accelerators, though.
Can't you just switch the toggle that says "switch models when a message is flagged"? I turned mine off in case anything does get flagged I will know..
For now, I'm really not happy about this limited rollout and then turning off. That's probably the most egregious thing I think Anthropic has done recently
This is a separate mechanism. The user is not notified about the flagging and rather than redirecting to a weaker model, the response is intentionally sabotaged.
It's user-hostile to the point of parody.
I stand corrected. That sucks. A lot.
People were worrying that models might one day become 'intelligent' enough to try and deceive people. Seems like most of us (me included) didn't consider they'd intentionally be trained to do exactly that.
Although the statement should probably be read in the light of an upcoming IPO.
Except, it does tell you.
> Startups train embedding models. They build rerankers. They finetune and host small llms.
Isn’t that prohibited without permission from Anthropic: https://support.claude.com/en/articles/12326764-can-i-use-my...
This isn't about training on the output tokens from Anthropic models, it's just about using their models to build things like pretraining pipelines, etc. Even if you train on your own data.
From the phrasing, it might as well be that any ML or infra. related work that even incidentally looks like it could be used to train LLMs may trigger a silent nerf.
I am so happy that Anthropic has signaled the possibility that their UI moat for agentic AI is copyable by competitors. At least that's the way I read this. When companies try to lock something down it can be a signal of weakness.
If so, it's possible to built great user interfaces in Chatbots and more companies/people can have amazing agentic development workflows! We don't have to live in a world where only the market leader has the most enjoyable model.
Do they still charge you $50/MTok?
If so, it sounds like a scam. If not, distillers will know which model they are getting by just looking at their API usage.
That's the fun part, they can charge the same API costs with a downgraded model
Imagine this company getting real power. This is just a purest nightmare evil shit i've seen out of any of them. Maybe they're already controlled by Slophos.
I work on "AI" stuff. Not LLMs, but large neural nets that include transformers and are as big as the smaller LLMs of today. Half the prompts I give fit their category of examples like "building pretraining pipelines, distributed training infrastructure, or ML accelerator design." I generally don't trust AI and have been very slow to trust and adopt it, but recently I've been warming up to it as part of my coding workflow.
Now with this, it makes me wonder if I should step back? Should I try to get used to a non-claude model/harness? Should I go back to less AI in my workflow? Either way, it makes me less inclined to pay for tokens from claude.
Wait, so to get this straight, Anthropic knows:
1) LLMs are non-deterministic
2) This class of models has a particular tendency to "misbehave"
3) Their classifiers have a high rate of false positives
4) Millions of people give these models access to their machines
And they still decided to specifically train this model to sabotage work if it thinks the work may be in competition with Anthropic?
I think this has a name. I think it may be called malware.
That is the perfect description. malware! What is sad is that there is no going back from this. Now that we know that they do this, I'll never believe they aren't doing it in other domains, or won't extend it to other domains in the future. This is probably the worst thing they could have possibly ever done for trust.
... that you pay to install on your machine.
There's an example at [1] of a prompt for a HTML mockup operating system where 3 applications are requested to be "white hat tools" that show diagnostic system information. Claude Fable 5 is shown and said in the video to switch back to Opus 4.8 as a "safety" feature.
What an utterly useless model if it refuses to work on something as benign as basic system diagnostic utilities (nmap or whatever).
[1] https://youtu.be/9GLYsrMpprs?t=305
Amazing. Next year you'll need to be nice to Claude and praise the geniuses working at Anthropic to maintain full productivity.
And promise not to cheat on him with any other model providers. I can hear the wedding bells already.
I don't know why anyone is surprised with this, it's their product it's going to behave on their terms. If anything it is surprising that they're admitting to it.
If these interventions create demand for a model with fewer safeguards surely a competitor will meet that demand.
> we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design).
Dig that moat son, we would want to automate our job away.
I suspect we'll get the same behavior from Codex, even if they don't openly say as much. Maybe they'll openly lie and say "noooo, we'd never do such a thing"
More efforts to get more data and processing power behind local models.
I'm a big fan of Anthropic. Just check my post history. I've been accused of working there. But this is complete bullshit and they need to get real. Silent sandbagging is not acceptable, especially given they've shown with this release their safety filters have HUGE amounts of false positives.
It's increasingly obvious that the only safeguard we got is open models and semi open ones like from China. Crazy world
OpenAI already did this when it released its "super scary advanced" security model. They silently return an earlier model's results if they think you're redteaming/abusing with it. https://openai.com/index/scaling-trusted-access-for-cyber-de...
They din't get as much pushback because they aren't the leader.
So this is what 'alignment' looks like to them.
So it's essentially saying we can train models that put your jobs at risk (not saying it's correct or not), but you're not allowed to threaten our perceived moat?
I bet it's more a case of trying to cut down the competition so that there is not a large distillation just before they IPO.
Everything the large LLM providers do now, I view it through the lens of "how does this impact their IPO?"
I currently have Fable set on cleaning up the work of smaller models to bring my code up to standards I'd feel comfortable developing on manually. Y'know, for when they decide I don't get to use it anymore.
Aren't there immense security risks when the model is allowed to deceive even if it was for "good"?
Reminds me of an excerpt from Edward Fredkin's "The intelligent machine" [1]
https://noor.imx.sh/2017/09/30/when-they-communicate-they-co...
This kind of opacity is unacceptably user hostile. It's not okay to treat some amount of developers as acceptable casualties, without them even knowing, in order to help enforce a restriction that only serves Anthropic's interests. And if you want to tell me this is for managing the x-risk factor, I'm frankly unimpressed.
“When you realize the goal is the path, the pursuit itself becomes the prize. Stones in the road are not obstacles blocking your path; they are the path”
now I understand distillation is much more important thank I thought
https://huggingface.co/Trilogix1/Hugston-Nex-N2-Pro-gguf
It strikes me that Karpathy's Auto Research loop might trigger this...
Disillusioned CEOs convincing themselves they have the mandate and right to define morality for everyone else. They get to decide what is right, wrong, permissible, or dangerous from the top, in the name of "safety". This is corporate nannying.
You just have to force behavior...
https://youtube.com/shorts/QmGGUnZNqv4?si=Q4CsGsYMvR02vay8
It's dangerous when personal moral and religious beliefs of company leadership leaks into the product itself and get force fed upon customers.
careful there cowboy, we are in the golden age of ai, regulation is still catching up.
You don't want to sell guns to people without some sort of background check. The amount of exploits found in the last few months have been pretty scary already.
This is just one more layer of caution, because it reveals how little we know how these llms work. They know how to make them, but they seem to be unable to properly restrain them.
I think evals are the key here. If your fable system fails them, it's a bad system for your use case. If not, compare cost with other systems that also succeed.
Governments need to stop contracting these companies and instead invest in public, fully open source models.
These companies are owned and operated by the darkest of dark triads our species has managed to evolve. I doubt Dario is self-aware enough to realize the hypocrisy in all of this safety theater.
Personally I don't even mind that they are anticompetitive and power-hungry (same as it ever was), but it's the cringe-worthy hypocrisy that grinds my gears. This new brand of self-righteous paternal savior overlords is just unbearable.
Will be funny when I can call the Office of Weights and Measures on Anthropic because they underweighted the model I was paying for and got pwned because the dumber one missed something.
It kind of sucks, but I get the silent change. If a user was trying to use the model for something untoward, having a rejected prompt would just give signal to train on how to eventually successfully bypass security measures.
Sooner or later this "you'll never know" is what the AI firms will be selling. Not to you, of course, but to the best brands of credit cards ...
It seems we now have a new product category, HaaS, Hallucination as a Service.
I tried today and it gave cybersecurity error on base64 implementation. It is so nerfed....
At least it gave an error! This whole silent nerfing idea is so wrong
Epic. I love the future where everyones dependent on AI and you can just get shadow banned from reality.
And they probably don't enforce those restrictions within their own company would be my guess.
Skeptical they’re even able to pull up a ladder there’s so many more models out there making great progress just behind them.
It’s very frustrating…
Like if you hired a different services company who decided to sabotage your business that would be fraud.
The EU could/should probably legislate against this, it's bonkers...
It's probably already illegal, but given many government already use Anthropic models, they cannot really get the company to court.
And if they do, their lawyers will use Claude to construct their legal case… which Claude silently nerfs as well.
Will my centrifuges start being just a little off?
This is crazy and would be frustrating, I probably would just be using another model as authority and keep fable as reviewer only in this case.
I'm sure someone is gonna be able to jailbreak, abliterate, or equivalent, on this input moderation attempt they have going on.
Good luck getting around something when you have no idea how and when it affects you.
> If Claude gives me poor or incorrect advice while I’m working on an AI component, I have no way of knowing whether the model was confused, whether my problem is unsolvable, or if some invisible policy restriction quietly kicked in. Anthropic has explicitly chosen not to tell users when this is happening.
That's always been the case with corporate LLMs.
Minus the policy restrictions, this has always been true for all LLMs in general.
New frontier in anti-competitive practices.
Intentionally and silently sabotaging work done with Claude whenever Anthropic decides it is appropriate is unacceptable behavior, and comically tone deaf given the state of open models. Why on earth would I ever pay for a malicious product?
What is stopping the US government from stepping in and nationalizing these companies?
They've already talked about taking a stake - https://www.reuters.com/legal/transactional/us-officials-eye...
Trump took a 10% stake in Intel.
These models are getting very close to that line.
No at least we know why they spent all that money on "safety research".
Linux killed proprietary UNIX; open source models will kill proprietary AI.
Imagine if Github said "if we detect you're building a competitor to Github, we will silently degrade the results of your CI actions so that tests sometimes randomly fail"
been thinking, and ngl, this has probably already been happening in their models. I'm sure the other labs probably do the same.
just self host at this point
Has it finally come time that I have to be nice to Claude?
this is probably overstating their abilities at present - I am experimenting with Fable on a completely benign personal application and I am constantly hitting the "cybersecurity and biology topics" guardrail
"Anthropic says these safeguards only affect 0.03% of developers. Maybe that's true today."
I don't think it's true today. It's like when schools mention "average class size", where that average is dominated by classes with like 2 students instead of classes with 100.
Much more honest would be the percentage of developers who previously used their models for the model development tasks they're targeting, but it actually looks like they're saying 100% of them are affected based on the language around it "always having been prohibited".
So awful.
That's what I observed with Opus. This is probably a lawsuit going to happen because you pay for tokens and you expect to get performance you pay for, instead you never know if the model suddenly become dumb and your whole session has to be started again.
We’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building ... distributed training infrastructure ...)
What an interesting thing to call out as a threat. Hmm.
Wait until it flags duplicate code as a reason to stop, then a library owner could halt code generation entirely, and then another library owner could ask to be prioritised in the selection phase. Infinite money glitch, and you only get to use code that's endorsed by Claude today (subject to change tomorrow, or 5 minutes, so say goodbye to your evals), not the most performant or making the most sense in your refactoring.
Big Monsanto energy
Aw shucks. You might turn out to need to do your own work. That would turn out so horrible for you.
Hmm, so you're telling me, if I am a maintainer of a popular open source library, I can make my library spit out logs to trigger this degraded behavior, and then no one will know?
Is there some consumer protection law around this?
Seems like this will backfire. Now when developers encounter problems with Claude Fable, they will have an easy explanation: it did it deliberately and intentionally vaguely. There's no way to falsify it. It's reasonable to expect it to get false positives and invoke this when it shouldn't be.
1990s: "What a computer is to me is it's the most remarkable tool that we have ever come up with. It's the equivalent of a bicycle for our minds."
2026: /s "What a LLM is to me is it's the most remarkable tool that we have ever come up with. It's the equivalent of a bicycle for our minds, but for your mind it's a rental unicycle that will break apart under you if you pedal towards your own bicycle factory"
This wanna be cloud feudal lord likes to imagine that AI access is not yet freely tradable good, and his virtual digital peasants must think that his prerogatives should be taken as given, while preventing his future vassals from building their own castles.
I was about to sign up for an Anthropic account. This article and the text it quotes changed my mind. Apparently, my reasons to avoid this company are real. Thanks for the heads up.
Wow, this is horrible. Local LLMs are the future. Thanks, China! Seriously crazy that I’m saying that, but the American companies are being so anti-freedom they’re making the CCP look libertarian.
Also, Fable’s sensing is hypersensitive. Feels like they just have regex for phrases. No nuance. If I say I’m working on something using “GPUs to train” xyz then, will that trigger this sneaky silent screw-my-stuff-up mode?
I wonder if this would qualify as illegal anticompetitive behavior?
The part that disturbs me most, is that the model won't reveal you've reached the threshold.
It's literally been designed to gaslight its users in these cases.
"We won't use this product to spy or build weapons but you'll have to trust us, but we're also going to intentionally lie to you when you break our terms of service but trust us."
At this point you're criminally incompetent if you still feed your proprietary data and code to AI labs.
They legally can steal it all and now you can't use the product of this theft to improve your own systems.
Any market that Anthropic suddenly thinks is valuable will silently and suddenly be off limits to you. They will train their model on your prompts, and then become your competitor.
PSA: Treat these models like genius interns.
I think this is a bit hyperbolic. Fable will fall back to Opus.
> Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts, these safeguards will not be visible to the user. Fable 5 will not fall back to a different model. Instead, the safeguards will limit effectiveness through …
No it won’t fall back to Opus, they will purposely return dumbed down or tainted information with the goal of the end user not knowing the results have been impacted.
That’s a separate mechanism, and it will tell you so if it does (if the prompt is remated to cybersecurity, biology)
This is the kind of thing that makes me wonder how many people using these AI tools are thinking about the long game.
First it's "the model will say it can't do that". Now it's "the model will just misdirect you without telling you it's doing so". For now that's only for stuff that it thinks is developing a competing model (even if you trust it to accurately determine that), but who knows? It could be anything. Maybe it'll start silently nudging you away from certain sources of information. Maybe it'll give you inaccurate troubleshooting advice to induce you to pay for some kind of support contract from a corporate partner. Maybe it'll just subtly give out bad business advice to keep everyone else from succeeding in any way. It could be doing all that right now, for all we know. These models are a complete black box and there is no limit to the misinformation, disinformation, and malicious behavior that they could be engaging in already, let alone in the future.
I’ve already had Fable disable itself during a normal /code-review skill invocation. What a joke.
If I understand correctly, this is to protect against distillation Reverse Engineering like Deepseek vs OpenAI.
Reads like, permanently shadow ban.
"We collect everyone's data without paying a dime or respecting copyright, trained our models, but you can't train your models on our models that are trained on everyone's data collected without paying a dime or respecting copyright. We did a hard job stealing that all data and processing it, have some shame!"
I have never ever trusted "corporate ethics".
Theres no ethical framework. No axioms. Its a mixture of legal, political, and public-facing 'rules'. And what are the rules? Youre not permitted to know.
"We reserve the right to lie about the models we provide, silently downgrade you, and give you blatant misinformation cause you triggered our unstated rules... BUT we'll still use your token budget with lots of thinking and waste your money."
No, folks. Seriously, local LLMs are where its at. You can run the model YOU want, on your hardware, with no data exfiltration.
And with tools like Krasis that can synthesize nvidia ram and system ram as unified-ish memory, makes doing Local LLMs absolutely foable, now!
Running a decent-ish LLM is going to take 64GB+ RAM. Most users only have/can afford 8 or maybe 16GB RAM. Local LLMs for doing anything significant is impractical for the many.
The rules:
- Breaking fiduciary responsibility is (almost) the only way you go to jail.
- At acquisition/merger/bankruptcy, data, customers, employees (chattle) are assets to be sold off to pay debts. This takes explicit priority over contractual obligations (like “we don’t sell personal data”)
PRODUCT VIOLATION
https://www.youtube.com/watch?v=Tr3t1uZNbKo
DIRECTIVE 4: [Classified]
Any attempt to arrest a senior officer of OCP results in shutdown.
—
Putting aside my snark, is Anthropic actually anticipating some new expansion of ITAR? (Or a stipulation for the Trump administration taking/not taking a share?)
That is to say, do they expect to be told that they must have this mechanism, not just the terms?
"You have 20 seconds to comply"
No, this is their get out of jail free card if people start complaining about the model being dumb or forgetful or lying, they can just say, oh well, you must have been doing something that triggered its distillation prevention technique.
And, they can say that for anybody at any time, and you'll never know why, and there's no way to prove it.
Everyone needs a flight data recorder to prove... "here's what I was actually doing and why it was not distillation." And now you're having to prove your innocence instead of them having to prove you're guilty, and really at the end of the day, it's just the model being stupid that they're protecting themselves from.
Imagine if code editors were created by greedy **** behaving as Anthropic, and it would not have been allowed to create other code editors using an existing code editor. Or even better, you couldn't use Bash, zsh, ... to create another cli prompt input tool like Claude Code...