News for hackers. Stuff that matters.
Re:Frontier AI agents violate ethical constraints 30–50% of ... by hanneshdc on Tuesday February 10, 2026 @01:13AM (#46955981)
Yes - and this also gives me hope that the (very valid) issues raised by this paper can be mitigated by using models without KPIs to watch over the models that do.
Re:Frontier AI agents violate ethical constraints 30–50% of ... by ArcHound on Tuesday February 10, 2026 @01:48AM (#46956175)
But how would you evaluate performance of those watching models? It'd need an indicator, hopefully only one that's key to ensure maximal ethic compliance.