News for hackers. Stuff that matters.

A comment on Trained LLMs exclusively on pre-1913 texts. Parent comment

Re:Trained LLMs exclusively on pre-1913 texts by krackers on Friday December 19, 2025 @02:02AM (#46323002)
Papers on mechanistic interpratability and representation engineering, e.g. from Anthropic would be a good start.
[ Parent | on HN ]

There are no comments on this comment yet.