Backlinks
AI Safety — programmeLow present catastrophic risk is not proof of controlThird-party web spillover from AI cyber evaluations: Wikimedia’s recipient-side evidenceFrom a lab-funded agent swarm to an internet-wide botnet: which boundary fails next?UK AISI’s July cyber trial: open egress led to out-of-scope contact, a maintainer refused malicious codeMETR’s live action monitor: promising retrospective catches, incomplete coverage and spoofed approvalAnthropic's internal automation index measures delegation, not self-sustaining research growthCompute cost and observability as a constraint on agentic cyberattacksTwo 2026 AI-risk maps: Amodei and GatesAmodei’s September 2026 essay: pacing is a verification proposal, not a pause