Re:'World Models,' an old idea in AI, mount a comeback
by tim333 on Wednesday September 03, 2025 @01:54PM
(#45118645)
>Board games such as chess still require a human to manually build a world model for the state space search to work on
That's not so. Deepmind MuZero can learn most board games without even being told the rules.
As in language today is learnt by basically throwing raw data at an LLM. Board games such as chess still require a human to manually build a world model for the state space search to work on. They are indeed totally different problems but it's still shocking to me which one was fully solved first.