---
title: "While a great feature, I never needed such a thing in Codex after GPT 5.2. It just one shots..."
date: 2025-12-28
canonical: https://solmaz.io/x/2005327138615120368/
x_url: https://x.com/onusoz/status/2005327138615120368
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

While a great feature, I never needed such a thing in Codex after GPT 5.2. It just one shots tasks without stopping

So we have proof by existence that this problem can be solved without any such mechanism. Wish to see the same relentlessness in Anthropic models

*Quotes a post by another author (https://x.com/i/status/2004916410687050167); its text is omitted here because it is not covered by this site's license.*