Re:Gödel's theorem debunks the most important AI myth – Roge...
by unparagoned on Sunday March 09, 2025 @08:19AM
(#43308459)
There was a study where they trained a model to lie. When they looked at what was happening internally they could see it knew the truth but just switched things at the outer nodes to lie.
[ Parent
| on HN ]
There are no comments on this comment yet.