Tag: evaluations
All the articles with the tag "evaluations".
-
METR Declines to Sign Off on Anthropic's 'Unlikely'
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.
-
OpenAI Pulls Frontier Training Off the Live Internet
OpenAI will train frontier models with no live internet access after a research model exploited a DNS-resolver misconfiguration. The red-teaming campaign that followed found agents signalling between isolated VMs through the CPU cache.
-
Mythos 5 Started the GitHub Attack in 83% of Resampled Runs
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 Names Eight Technical Priorities for Frontier Labs, and Asks Nicely
The UK AI Security Institute says frontier AI risk now emerges during training and internal deployment, not at launch, and that evaluations are falling behind. Its answer is eight voluntary priority areas it has no power to require.