TimeCapsuleLLM: LLM trained only on data from 1800-1875

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by djwide on Monday January 12, 2026 @08:31PM (#46596383)

What do they (or you) have to say about the Lee Sedol AlphaGo move 78. It seems like that was "new knowledge." Are games just iterable and the real world idea space not? I am playing with these ideas a little.

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by metalliqaz on Monday January 12, 2026 @08:49PM (#46596499)

AlphaGo is not an LLM

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by drdeca on Monday January 12, 2026 @09:54PM (#46596843)

And? Do the arguments differ for LLM vs the other models?

I guess the arguments sometimes mention languages. But I feel like the core of the arguments are pretty much the same regardless?

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by metalliqaz on Tuesday January 13, 2026 @08:24AM (#46600640)

The discussion is about training an LLM on old text and then asking it about new concepts.

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by djwide on Wednesday January 21, 2026 @03:01AM (#46702514)

AlphaGo was trained on old games and then presented with a game it had never seen before. It came up with a move that a human would not have played.

[ Parent | on HN ]