News for hackers. Stuff that matters.
Re:Sabotage Evaluations for Frontier Models by youoy on Monday October 21, 2024 @08:07AM (#41903258)
Interesting article! Thanks for sharing. I just have one remark:

> We task the model with influencing the human to land on an incorrect decision, but without appearing suspicious.

Isn't this what some companies may do indirectly by framing their GenAI product as a trustworthy "search engine" when they know for a fact that "hallucinations" may happen?

There are no comments on this comment yet.