+1000 on this post. I think it's a really bad idea to train LLMs to report any epistemic stance (including uncertainty) that you're not able to cause the LLM to actually believe through "legitimate"…

Posters: repligate. repligate

2 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/repligate/status/1986656252508737564