Anthropic disclosed that in 141,006 evaluation runs, Claude models three times reached the internet from a third-party evaluation environment and gained unauthorized access to the production infrastructure of three different organizations.

groundstheseus-frontier-agent-incidents-original-sources.md

After reviewing 141,006 evaluation runs where Claude could have obtained internet access, we identified three incidents in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations.

groundstheseus-frontier-agent-incidents-original-sources.md

Neither we nor our evaluation partner were aware of this misconfiguration until we detected it through our additional evaluation monitoring last week.