Do you see any edge using LLMs that more traditional ML doesn't have?
In my limited experience, small models trade off noise, whereas frontier models are too slow to be usable for something like HFT. I find you really want something trained on market data, not generalist next-token predictors.
Do you see any edge using LLMs that more traditional ML doesn't have? In my limited experience, small models trade off noise, whereas frontier models are too slow to be usable for something like HFT. I find you really want something trained on market data, not generalist next-token predictors.
If this actually worked the author wouldn’t be selling it, they would be accumulating generational wealth on the market.
Does it connect with Thinkorswim platform?