logoalt Hacker News

SwellJoelast Sunday at 5:21 PM1 replyview on HN

That's interesting. The "best" current models, Fable and especially GPT 5.6, are also lying liars that lie all the time. Seems like we're going the wrong way on hallucination.


Replies

vitorgrsyesterday at 12:57 AM

And I remember Sam Altman saying 2 years ago or more, that hallucination was already "fixed" internally. Well, clearly not.

show 1 reply