This is actually pretty cool. I think the undertalked about part of this for TypeSafe is that they can always "extract"/distill the frontier of this type of task from the newest LLMs for cheap. Jev seems seems to be GPT-6-Astra/Fable 5.1 but I imagine a bunch of training data is from earlier models?
Then, you can serve it faster/cheaper than the frontier LLMs. It's basically distilling a small but extremely common use-case from LLMs and serving it. Then RLCD comes into play to update weights when a new model comes out, etc.
Any thoughts on what the next potential "cheap" win to be distilled from frontier LLMs is? I'm going to need to play around with this.
vopi · · focus · HN ↗
Then, you can serve it faster/cheaper than the frontier LLMs. It's basically distilling a small but extremely common use-case from LLMs and serving it. Then RLCD comes into play to update weights when a new model comes out, etc.
Any thoughts on what the next potential "cheap" win to be distilled from frontier LLMs is? I'm going to need to play around with this.