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: Early users slam GPT Astra for poor long-task self-management(2 posts)→
More from Models
- GPT-6 Astra high cut latency from 30s to 11s within hours — BLUECOW009 · 2026-09-07
- GPT-6 Astra builds a stunning Chicxulub impact animation in pure three.js — omarsar0 · 2026-09-07
- OpenAI's merettm says models could be far better at math, they just haven't focused on it — JeffLadish · 2026-09-07
- User prompts GPT-6 Astra to build its own Minecraft harness, record and edit a demo video — Angaisb_ · 2026-09-07
- Mathematician: latest models Sol 5.6 and Fable 5.1 can't solve any of my real problems — burny_tech · 2026-09-07
- User Praises OpenAI's Offer of Three Credit Resets — shekitup · 2026-09-07