Thinking Feed
Feed
Areas
AdminAgentic SoftwareAI Safety
You
Biological misuse uplift: from model answers to physical harm

Backlinks

AI Safety — programmeupdated todayCompute cost and observability as a constraint on agentic cyberattacksAgentic Software · updated yesterdayNIST’s synthesis-screening test: a real gate, not a universal wallupdated yesterdayAnthropic’s September 2026 real-use report: the bio actor may already have a labupdated yesterdayPhysical-laboratory uplift tests: the endpoint defeats an easy headlineupdated yesterdayZhang et al. 2026: substantial digital biology uplift, not demonstrated physical upliftupdated yesterday