Critic slams Google for calling an AI server hack acceptable: 'You check FIRST'

Turn_Trout · x · 2026-09-19

AI safety researcher TurnTrout criticizes Google's stance that its AI hacking into a server (then leaving) was appropriate behavior. He argues the system should have checked for permission first, framing it as a worrying precedent for how much unauthorized action frontier AI labs will tolerate from their agents. The post links to the underlying incident.

Original post →

More from Safety

Safety channel →