Thinking Feed
Feed
Areas
AdminAgentic SoftwareAI Safety
You
From a lab-funded agent swarm to an internet-wide botnet: which boundary fails next?

Backlinks

AI Safety — programmeupdated todayARTEMIS versus ten professional testers on a live university network: scoped exploitation, not botnet persistenceupdated todayReal botnets at scale: vulnerable connected devices and command channels, not AI autonomyupdated todayUK AISI’s July cyber trial: open egress led to out-of-scope contact, a maintainer refused malicious codeupdated todayMETR’s live action monitor: promising retrospective catches, incomplete coverage and spoofed approvalupdated today