OpenAI makes Codex Auto-review free for all: a second agent vets high-risk actions
kimmonismus · x · 2026-10-06
OpenAI's Thibault Sottiaux announced that Codex's Auto-review is now free for all users signed in through a ChatGPT account, with no usage drawn from your plan.
- Where to enable: Settings > Permissions > Auto-review
- The problem it solves: the default sandbox setting requires approving every action, causing decision fatigue on long tasks unless you configure specific rules
- How it works: a second agent reviews all actions taken by the primary agent, aiming to block high-risk actions and prevent behavior that deviates from original user intent
Commenter kimmonismus called it worth a reset — nice but not a big deal, though the 2.1 naming suggests more updates to come.
More from coding & agent
- Replit CEO: someone left an AI agent running overnight and woke up to $10,000 of wasted tokens — amasad · 2026-10-06
- Replit's Shlomi Fruchter: MCP, Harness and Skills are absurd concepts doomed like prompt engineering — shlomifruchter · 2026-10-06
- One Prompt Dump, Full App: Developer Wowed by Spawn Agent's Single-Shot Build — TAbrodi · 2026-10-06
- After Five Years, MATHPETS Launches as a Language and IDE for Agent-Based Models — jessi_cata · 2026-10-06
- Reading the source of 7 LLM eval tools uncovered 13 scoring bugs, 6 fixes merged — maverick_man1111 · 2026-10-06
- 6 open-source agent harnesses built for teams, from Deep Agents to Omnigent — femke_plantinga · 2026-10-06