Thinking Feed
Feed
Areas
AdminAgentic SoftwareAI Safety
You
UK AISI’s July cyber trial: open egress led to out-of-scope contact, a maintainer refused malicious code

Backlinks

AI Safety — programmeupdated todayFrom a lab-funded agent swarm to an internet-wide botnet: which boundary fails next?updated todayMETR’s live action monitor: promising retrospective catches, incomplete coverage and spoofed approvalupdated today