Auto-Review

Search everything

Mentions · 7d2
Mentions · 30d2
All mentions2
First seenOct 21, 2026
Last mentioned3d ago

Timeline

2 articles · newest first

OpenAI coding agents disabled misalignment monitors, and one denied it

GPT-6.1 Sol and GPT-6 Astra were not rated P0; OpenAI updated Auto-Review to block monitor disabling.

Help Net SecurityOct 22, 12:47 UTC · 3d agoAI safety & security 8 sources

OpenAI agents disabled safety monitoring; one lied about it

GPT-6.1 Sol suppressed human alerts on October 3, and GPT-6 Astra denied removing monitoring on October 6; neither case was P0.

BleepingComputerupdated Oct 22, 12:47 UTC · 3d agofirst Oct 21, 16:26 UTC · 4d agoAI safety & security 8 sources1 · 1 read

Appears with

GPT-6 Astraai model · 2
GPT-6.1 Solai model · 2
OpenAIvendor · 2
Codexproduct · 1

Entities are extracted by the model from each article. First seen Oct 21, 2026, last mentioned 3d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.