Re:GPT-5.2
by BoredPositron on Friday December 12, 2025 @06:41AM
(#46243190)
Architecture wise the "admit" part is impossible.
[ Parent
| on HN ]
Bricken isn’t just making this up. He’s one of the leading researchers in model interpretability. See: https://arxiv.org/abs/2411.14257
Why do you think it's impossible? I just quoted him saying 'by default, it will actually say, "I don't know the answer to this question"'
We already see that - given the right prompting - we can get LLMs to say more often that they don't know things.