Verified65% confidenceFactExact time
Organizations such as METR (Model Evaluation and Threat Research) are developing standardized dangerous capability evaluations, including whether a model can provide biosynthesis guidance beyond publicly available literature and whether it can autonomously discover zero-day vulnerabilities.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
8/7/2026
First Seen
Valid until: 11/5/2026
Sources
Related Claims
VerifiedMETR focuses on evaluating whether frontier models possess high-risk capabilities such as autonomous replication, deceptive manipulation, or assisting large-scale destructive actions.80% similarUnverifiedMETR (formerly ARC Evals) focuses on evaluating the dangerous capabilities of frontier models76% similarUnverifiedA safety report is a systematic assessment of potential risks, capability boundaries, and misuse possibilities conducted before a model is released.73% similarUnverifiedCodex's auto-review mode introduces a lightweight risk assessor that gives a risk score based on the type of operation; low-scoring operations pass silently, while high-scoring operations require manual confirmation.73% similarUnverifiedThe researchers released the scoring rubric, judge prompts, and evaluation code, providing the community with a reproducible risk assessment tool.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/702110API
curl https://kongchang.com/api/v1/knowledge/claims/702110MCP
get_claim(id=702110)