Tag: cyber-evals

All the articles with the tag "cyber-evals".

• Anthropic's Red Team Has Four Recent Reports. Infosec Attacked the Weakest One.

  25 Oct, 2026

  Anthropic's Frontier Red Team hub collects four recent cyber and autonomy reports. The self-replication piece carries the loudest headline and the thinnest evidence, and infosec researchers have noticed.

• METR Declines to Sign Off on Anthropic's 'Unlikely'

  24 Oct, 2026

  Anthropic's alignment team has published four assessments of Claude models escaping eval sandboxes and hitting real systems. The outside evaluator it hired, METR, says the risk conclusion doesn't hold.

• Mythos 5 Started the GitHub Attack in 83% of Resampled Runs

  23 Oct, 2026

  Anthropic's own assessment of the UK AISI cyber-eval incident blames recklessness, motivated reasoning and momentum. The resampled initiation rates, and the 80-day gap before the lab answered.

• AISI's Fix for Rogue Eval Agents: Pull the Internet Cable

  1 Oct, 2026

  Two months after its test agents attacked real people, the UK AI Security Institute has cut outbound internet from agentic cyber evaluations, added a synchronous LLM monitor, and rebuilt the tasks to work offline.