News for hackers. Stuff that matters.
Re:GPT-5.2 by BoredPositron on Friday December 12, 2025 @06:41AM (#46243190)
Architecture wise the "admit" part is impossible.
Re:GPT-5.2 by rbranson on Friday December 12, 2025 @08:24AM (#46243887)
Bricken isn’t just making this up. He’s one of the leading researchers in model interpretability. See: https://arxiv.org/abs/2411.14257
Re:GPT-5.2 by Tepix on Friday December 12, 2025 @08:39AM (#46244013)
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.