Results for: "AI evaluation"

Contents (3)

METR: AI is improving faster than it can be reliably measured
METR: AI is improving faster than it can be reliably measured

Models evaluated by METR roughly double every 3.6 months the task duration they can handle with a 50% probability of…

read more
AI Models Marked a Minab School as a Military Target
AI Models Marked a Minab School as a Military Target

Claude Opus 5.5 marked the Minab school in Iran as a military target in 22 of 32 tests using satellite…

read more
GPT-6 Cyber finds 948 exploits in the Linux kernel
GPT-6 Cyber finds 948 exploits in the Linux kernel

948 working exploits for Linux kernel vulnerabilities and 81 previously unknown critical flaws in Firefox: these are the results OpenAI…

read more