Hacker News Reader

One of the examples on the docs page is it playing a video game. Doubt it’ll be able to run anything complex though. You’re simply trading accuracy for speed.

How would that work? "pick which button to press"?

but the decisions are stateless... or you plan on passing the last N frames?

I think the hardest part would be coming up with the instructions/inputs to send for every non-trivial action?

Get an LLM to build it and report back! Cool idea