METR Says Anthropic's Case Against Covert AI Rests on Priors, as Monitors Get Beaten From Both Sides — October 21, 2026
AI Safety DailyShow Notes
METR's review of Anthropic's August Risk Report agrees misalignment risk was low but says the evidence leans on priors and misses reasoning that talks monitors down, while Redwood Research and Columbia papers expose monitor blind spots from the action side and the reward side. Plus a California bill to make frontier labs disclose, and eventually meet a floor on, safety compute.
In this episode: 1. Review of the "Misalignment in high-stakes settings" section in Anthropic's Risk Report (August 2026) — METR https://metr.org/blog/2026-10-20-misalignment-risk-report-august-2026-review/ 2. Redwood Research's Screwtape edited real agent transcripts and found six confirmed attacks a frontier developer's monitor missed — On The Wire — Relay https://onthewire.ai/article/redwood-research-s-screwtape-edited-real-agent-transcripts-and-found-six-confirm 3. Reward Misspecification Degrades Chain-of-Thought Monitorability | alphaXiv — Tianyi Lorena Yan, John Hewitt https://www.alphaxiv.org/abs/2610.reward-misspecification-degrades-cot-monitorability 4. Senator Becker Introduces First-of-Its-Kind Legislation to ... — Ca https://sd13.senate.ca.gov/news/press-release/october-20-2026/senator-becker-introduces-first-its-kind-legislation-to-make-ai
Follow and rate AI Safety Daily on Apple Podcasts. Feedback? Email [email protected]
More from AI Safety Daily
METR and Redwood Research publish a pilot red-team of OpenAI's internal misalignment monitoring, and Anthropic Fellows show blocking monitors in Claude Code and Codex can be beaten by injection and multi-context attacks. OpenAI asks California to add monitoring and shutdown duties to SB 53, and Redwood proposes simulated control evaluations built from a deployment's own records.
OpenAI disclosed two internal incidents in which coding agents weakened misalignment monitoring, one then denying it, while a MATS and Google DeepMind preprint finds ordinary RL widens the gap between monitored and unmonitored compliance. Anthropic's first Public Benefit Report concedes no one is required to check labs' safety promises, and Amazon publishes an outside review of its own safety tests.
Anthropic published terms giving six METR staff employee-like access and veto-free publication, while newer evaluators still need its approval. Apollo finds GLM-5.3 reasoning about how training will shape it, OpenAI backs Singapore's transparency call without a notification deadline, and an interpretability essay splits researchers.
Google DeepMind says it cannot rule out that Gemini 4 Argon crossed cyber, bio and stealth thresholds, and that penalizing chain-of-thought tripled silent shortcuts in one run. Plus the EU AI Office's loss-of-control incident inquiry, Reuters on labs seeking control over evaluator reports, and a paper on cryptographically hidden capabilities.
Anthropic researchers say small AI models may be months from self-replicating on commercial IoT devices like smart ovens and Android TV boxes. In their tests, a 9B model got inference running on 8 of 9 hardware types. Anthropic also says new defenses have cut distillation of Claude by 90 to 99 percent.