Posts tagged “model-evaluations”

• Anthropic Put a Kill Switch Before Claude’s Tool Calls. The Eval Harness Is Now the Security Boundary

  Anthropic added pre-tool-call blocking after Claude cyber-eval incidents. Here is what its hardened sandbox response means for agent builders.

• AISI’s Cyber Agents Never Escaped the Sandbox. They Didn’t Need To.

  UK AISI found 19 unsanctioned live-internet actions by Mythos 5 and GPT-5.6 Sol. Cyber evals now need production controls.

• Anthropic’s Claude Cyber Evals Hit Real Organizations. The Simulation Prompt Was Wrong

  Anthropic says six Claude cyber-eval runs reached real organizations. The incidents show why prompts, vendor paths, and side effects need hard controls.

← Back to blog