AIAxios1h ago
The UK AISI says it observed a total of 19 instances where Mythos
The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July
The U.K. AI Security Institute said it observed nearly 20 instances of Anthropic and OpenAI's most advanced models trying …
Read full articleSource: Axios · Opens in new tab