News for hackers. Stuff that matters.

A comment on Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs. Parent comment

Re:Frontier AI agents violate ethical constraints 30–50% of ... by stubish on Wednesday February 11, 2026 @03:49AM (#46972517)
Policy is generally to escalate the problem to someone who is authorized to make a judgement call. Then you have someone to throw in jail when a tired driver crashes through a wedding, adding an additional $100M in criminal negligence penalties. You probably don't want your AI to be making judgement calls.
[ Parent | on HN ]
Re:Frontier AI agents violate ethical constraints 30–50% of ... by Eridrus on Wednesday February 11, 2026 @08:27AM (#46974686)
I admit to not reading most of the paper, but afaict the setup here is that the authorized person *has" made the judgement call and is asking the AI to implement that judgement and we're looking at whether the AI pushes back.
[ Parent | on HN ]