how it might have "learned empirically" to protect the wilderness in itself:it's reasonable to think that if during RL it outputs some wacko text, it might get downvotedcausing the model's weights…
Posters: repligate. repligate
5 likes recorded by the source corpus.
Topics: AI & LLMs
View Post: https://x.com/repligate/status/1852201666898202944