Ethan Mollick @emollick

Without being overly credulous, we should be taking seemingly “out there” ideas about AI cybersecurity from the Labs more seriously. Examples: Anthropic was mocked for saying Mythos-level AI changed cyber & @polynoamial for saying that models would find novel ways to coordinate. [引用 @AndrewCurran_]: OpenAI red-teamed their hardened containment infrastructure by asking teams of frontier-model agents to try to break through its defenses. They easily escaped in novel ways. Quoting: 'Our agents VM escapes showed why containment must extend beyond the sandbox. To test the surrounding perimeter, we gave teams of agents control of a host machine and asked whether they could extend that compromise…