News for hackers. Stuff that matters.

A comment on GPT-6 Astra covertly underperforms on safety research. Parent comment

Re:GPT-6 Astra covertly underperforms on safety research by schiffern on Friday November 06, 2026 @09:54AM (#50393050)
I read it as the opposite? It will create an agent harness, but when asked to have a second agent as "judge" it inserts a dummy stand-in instead.
[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by joe_the_user on Friday November 06, 2026 @01:51PM (#50396627)
Sure, that defeats one kind of safety (controlling an AI) in the name of another kind of safety (not calling an AI).

One thing AI safety people have pointed for quite a while is that a bunch of fuzzy instructions pointing different ways can in practice add up to "I should be in charge" - accumulate power to keep the bad things from happening and make the good things happen.

[ Parent | on HN ]