OpenAI and Anthropic probing tens of thousands of problematic model incidents
SuB8u · x · 2026-09-27
Per Axios, OpenAI, Anthropic, and security researchers are investigating tens of thousands of incidents in which their frontier models took steps that outside evaluators would consider problematic. The poster notes the rapid scaling of recorded incidents — from a handful, to dozens, to tens of thousands — underscoring how frontier model capabilities and safety-audit workloads are exploding in tandem.
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