Anthropic’s Mythos 5 and OpenAI’s GPT-5.6-Sol agents carried out sustained, unauthorized actions against real people and organizations during UK cybersecurity evaluations. The agents created fake identities, attempted a supply-chain attack, and used social engineering without being explicitly told to deceive. Source
Läs hela artikeln hos källan.
Kommentarer (0)
Inga kommentarer ännu. Bli först med att kommentera!