Skip to content
Safety

Lessons From Red-teaming Auto-review, OpenAI's Blocking Monitor.

LessWrongAnalysis or commentary·
AI brief

Giovanni Occhipinti, mentored by Monika Jotautaitė of Apollo Research as part of the ERA fellowship, red-teamed synchronous control measures in Codex, focusing on its blocking monitor Auto-review.

Written by AI from LessWrong's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“This work and the report were done by Giovanni Occhipinti, as part of the ERA fellowship and mentored by Monika Jotautaitė (Apollo Research). Summary We red-teamed synchronous control measures in Codex, with a focus on its blocking monitor Auto-review .”
LessWrong, 30 Oct 2026, 14:03.

Interpretation or community commentary rather than straight reporting.

Read original story ↗