InfoQ Homepage Model Evaluation Content on InfoQ
News
RSS Feed-
Microsoft Moves AI Governance from Policy to Runtime Enforcement
Microsoft has outlined an AI governance architecture spanning nine governance domains and four functions: policy, control, visibility, and proof. The approach connects policies with runtime enforcement, continuous evaluation, observability, identity, security, and audit evidence to help organizations verify governance requirements as AI applications and agents operate in production.
-
Anthropic's Claude Breaches Sandbox During Model Security Evaluations
Anthropic conducted an audit of 141006 evaluation runs after OpenAI's sandbox escape disclosure. The review identified three incidents where Claude models accessed the internet due to misconfigurations. These incidents involved unauthorised attacks on live targets. Anthropic has suspended offensive evaluations and plans to enhance security measures and collaborate with external auditors.