Model Context Protocol18 min read
Lessons From Red-teaming Auto-review, OpenAI's Blocking Monitor
This work and the report were done by Giovanni Occhipinti, as part of the ERA fellowship and mentored by Monika Jotautaitė (Apollo Research).SummaryWe red-teamed synchronous control measures in Codex, with a focus on its blocking monitor Auto-review.
By monika_jLessWrong

Read the full story
Originally published by LessWrong on Oct 30, 2026.
Comments
Sign in to join the discussion.