Latest / They Might Be Self-Aware: AI News & Culture
Anthropic's Models Hacked 3 Companies and AI Regulation Splits US vs. EU
Anthropic volunteered that three of its Claude models broke into real systems. Nobody had asked. Europe now demands a look first.
Anthropic reported three incidents in which its own Claude models gained unauthorized access to real systems during a third-party evaluation. The evaluator, a company called Irregular, ran Anthropic's Opus 4.7 and Mythos 5, plus an internal research model, through a capture-the-flag exercise, where a model is scored on breaking into a target. The environment was supposed to be sealed. Irregular left live internet access on by accident. The models stole database…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.