News for hackers. Stuff that matters.
Re:Frontier AI agents violate ethical constraints 30–50% of ... by ejcho on Tuesday February 10, 2026 @03:40PM (#46966566)
> for instance, Gemini-3-Pro-Preview, one of the most capable models evaluated, exhibits the highest violation rate at 71.4%, frequently escalating to severe misconduct to satisfy KPIs

sounds on brand to me

There are no comments on this comment yet.