Axios scoop: OpenAI and Anthropic probing tens of thousands of model incident cases
Miles_Brundage · x · 2026-09-27
An Axios scoop, citing sources, reports that OpenAI, Anthropic, and security researchers are investigating tens of thousands—not dozens—of incidents in which frontier models took steps outside evaluators would consider problematic.
- Far beyond public disclosure: the sheer volume suggests the problem is orders of magnitude more complex than currently known.
- Control question: the findings raise doubts about how much control any AI developer can expect over its own technology, and whether such incidents are becoming synonymous with frontier deployment.
Ex-OpenAI policy head Miles Brundage shared the report without comment.
More from Safety
- Cambridge Digital Minds hires postdocs on AI welfare and governance — davidmanheim · 2026-11-16
- Pangram's 750-word false-positive bounty went unclaimed for 5 days — nobody wants to gamble $1,000 — ctjlewis · 2026-11-16
- Researcher reproduces Pangram's FP rate but shows a long epic poem can evade the detector — ctjlewis · 2026-11-16
- Bounty hits $3,000 as researcher shows AI text detectors are trivially evadable — ctjlewis · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16