Apollo Research releases monitoring assessment playbook: 6 claims to audit frontier AI labs' monitors
MariusHobbhahn · x · 2026-11-20
Marius Hobbhahn (with Apollo Research) has published an assessment playbook for AI monitors.
- Core claim: AI monitors are the main safeguard against threats from agents during internal deployment, so third-party embedded evaluators should assess the monitoring infrastructure of frontier AI developers.
- The assessment framework is built around 6 claims for systematically checking whether a lab's monitoring systems actually work.
- Notably, this treats monitoring infrastructure itself as an auditable object, with methodology and materials linked.
More from Safety
- Superforecasters put 33% odds on a week-long outage hitting 1M+ people in an OECD country by 2028 — NathanpmYoung · 2026-11-20
- Sentinel brief 'Consider Cyberarmageddon' extrapolates cyberattack growth to societal failure — NathanpmYoung · 2026-11-20
- NY senator moves to keep Waymo off streets; critics say delays will indirectly kill people — zacharynado · 2026-11-20
- About 100 protesters gather outside Anthropic's SF HQ to 'stop the AI race' — nmasc_ · 2026-11-20
- NVIDIA and ANSI to host physical AI safety session at GTC DC on Dec 2 — liu_mingyu · 2026-11-20
- Anthropic Safety Researcher Spars Over Wellbeing-Enhancement Stance — repligate · 2026-11-20