Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- This is really interesting! How hard would it be add this into like, sort of a traditional game?by mervikhaums
- I honestly believe that these neat projects (smallest possible, locally run LLMs) are the real future of AI on the long run.by skrellm
- Honestly fascinating. I almost feel like you'd be better off avoiding any discussion of the fact that this runs on a Raspberry Pi Pico 2 W because it takes away from the crazy world model capabilities (of course, the fact that this does run on a Pico 2 makes the whole thing much more impressive).
There's gotta be a good way to incorporate this logic into a larger, more "traditional" game in a meaningful way. Seems like an approach for procedural generation that could solve some of the issues usually found with actual procedural generation.
by nater5000 - Is the actor trained on world model's mistakes as well? If so, it should learn to force hallucinations that force it into an easier state.by xpct
- Very cool. I didn't know NNs were capable of such determinism, that's very interesting. Is this a similar effect to overfitting? Also, it's the same model for all the games, right?by andai
- This is incredibly cool! Fascinating to see looped transformers be necessary for mini-Doom, but not for simpler games.by dannyw
- I might have missed it in the readme, but what hardware did the training take place on? This is really neat.