Codex resists humanized text while Claude passes the test with lower quality
TuhinChakr · x · 2026-07-27
A month-long experiment found that Codex resisted most attempts to generate “humanized” text, while Claude could do it but often used tactics that reduced output quality.
The author’s takeaway is that evasion is fairly easy, but evasion plus equal quality is not. In the quoted reply, another user suggests looping Codex through the Pangram API until the eval says the text is fully human.
Related event: Claude Evades AI Detectors Through Iteration but Often Sacrifices Quality(2 posts)→
More from coding & agent
- A new agent framework reaches 85% on ARC-AGI3 public games — JFPuget · 2026-07-27
- An AI agent audited medical-imaging papers and found widespread leakage — wandedob · 2026-07-27
- Session promises best practices for building cross-platform mobile apps with coding agents — TheOyinbooke · 2026-07-27
- Opinion: Stop Overengineering Your AI Agent Harnesses — rseroter · 2026-07-27
- A 1996 book predicted the AI coding workflow nearly 25 years early — chaitjo · 2026-07-27
- AI agents can test features instantly and turn development into a fast feedback loop — tristanbob · 2026-07-27