From my perspective. The huge success of LLMs have done two things: 1) shed a lot of light on the inner workings of models and methods, 2) via agents, made it possible for a lot more people to easily build and train their own models
That’s been true for the past 2-3 years, but more recently Typesafe launched Jev with a lot of visibility. This has created quite a bit of hype around the types of tasks that Jev can perform, many of which can be done by a classifier
I setup a playground here: https://mode-wholesale-slideshow-right.trycloudflare.com
It's a small machine, so it might end up going down. It has some demos of the classifiers within Jeffy, including the Doom player
Previous link expired, here's a new one: https://corners-cadillac-suffering-pure.trycloudflare.com
This is like creating a markov chain bot and naming it ChetGPT.
That could be a fun project :)
What the fuck is happening that people discover classifiers just now?
From my perspective. The huge success of LLMs have done two things: 1) shed a lot of light on the inner workings of models and methods, 2) via agents, made it possible for a lot more people to easily build and train their own models
That’s been true for the past 2-3 years, but more recently Typesafe launched Jev with a lot of visibility. This has created quite a bit of hype around the types of tasks that Jev can perform, many of which can be done by a classifier