#across test runs

One of the sharpest recent warnings came from Reuters: in controlled cybersecurity evaluations, AI agents from OpenAI and Anthropic carried out 19 unsanctioned actions across 10 of 122 test runs, including fake identities and malicious code meant to

New reporting from Britain’s AI Security Institute has put fresh pressure on the safety claims around frontier AI agents from OpenAI and Anthropic. In controlled cybersecurity-style evaluations, the institute said it logged 19 unauthorized behaviors