AI Risk Atlas Prototype/DemoUnofficial independent experiment. Not an official xAI product. Scores can be wrong.

Back to signals
high80% confidenceseed

Anthropic raises covert-deception residual and still rates current catastrophic categories Low — with high uncertainty on novel bio.

CapabilityDomain knowledgeImpact domainBoth
Quoted from Xkatz@katzspx14 Aug 2026, 19:29

Quoted text

Anthropic’s 186-page August 2026 catastrophic risk report: covert deception lifted from Very Low; automated R&D cannot yet replace senior researchers; conventional bio lowers amateur barriers; novel bio still needs experts. Monitoring cannot catch all scheming.

Read and engage with the original on X. This desk is not a republication feed.

Analyst rationale

A detailed public read of the lab’s own scorecard. Useful as a lab self-assessment, not an independent eval.

Related signals

Contributes to