Hack: Using Codex to Pass Assessment by Removing Elements
rickasaurus · x · 2026-08-21
A retweet shares a case of bypassing AI detection using Codex. To pass a LinkedIn data annotator assessment, the user instructed Codex to complete the task. When Codex flagged the site's 'no AI' policy, the user instructed it to inspect elements and remove the warning paragraph, allowing Codex to complete the assessment and get approved as a human expert.
More from coding & agent
- Photon 2.0 launches unified messaging API for AI agents across iMessage and more — Scobleizer · 2026-10-16
- Claude Opus 5.5 effort levels tested: low reasoning iterates 9x faster than max — tom_doerr · 2026-10-16
- Photon 2.0 lets AI agents reach users via WhatsApp, Telegram, SMS and voice in one click — techNmak · 2026-10-16
- Figma launches Guidelines and Code Sources so AI agents can follow your design system — JaynitMakwana · 2026-10-16
- Ex-DeepMind Eng Lead's AI Calling Agent Fo Cut Hang-Up Rate from 80% to 20-30% — julianweisser · 2026-10-16
- SPACE Open-Sources Its Sandbox Platform for Agentic Code Execution — marktenenholtz · 2026-10-16