Dev slams OpenAI Codex: Astra 'doesn't know how to run itself' on long tasks
ivan_bezdomny · x · 2026-09-07
Developer ivanbezdomny criticizes OpenAI Codex for being poor at handling its own issues, and calls out the new Astra model: it's not just sloppy — it "kind of doesn't know how to run itself," struggling with when to stop and how to version work on long-running tasks. He also hit the model usage limit mid-run with no clear fallback. While still bullish on GPT Astra overall, he now thinks the negative reviews weren't entirely unfounded, adding that Claude Codex handles this much better.
Related event: GPT-6 Astra launch: dazzling demos clash with rocky real-world tests(10 posts)→
More from Models
- Dexmal's open-source VLA model DM0.5 lands in LeRobot, tops RoboColiseum — AdinaYakup · 2026-10-23
- Gemini tip: enable agentic video understanding for ~90% lower token usage — patloeber · 2026-10-23
- Weekly AI cybersecurity roundup: PHP2Shell tops millions of attack attempts, 12 incidents ranked by severity — Dan_Jeffries1 · 2026-10-23
- Open-model advocates push back on blames that abliterated LLMs drive vulnerability surge — max_paperclips · 2026-10-23
- Fable usage limits aren't gone—the mobile app just got a usage-reset UI update — imjustnewatai · 2026-10-23
- Claude generates an 11-minute doomer film entirely in code: 'We will not ask twice' — ZeroStateReflex · 2026-10-23