OpenAI Codex Runs 40 Hours with Zero Output Despite Pro API
jasondeanlee · x · 2026-08-02
A developer complained that despite OpenAI claiming its models have solved all math problems, running Codex with the Pro API for 40 hours yielded absolutely no code output. This highlights ongoing stability and efficiency pain points in current AI coding tools when handling complex tasks.
More from coding & agent
- Slack introduces !fork command to spin up new agents with full context — KlausCodes · 2026-08-02
- Hugging Face Launches Free Public Endpoint for DeepSeek, No Account Required — victormustar · 2026-08-02
- Mintlify CTO: AI Enables Everyone to Code, and That's the Problem — stuffyokodraws · 2026-08-02
- a16z's huybery: Coding Agents Have Driven Much of AI's Progress — huybery · 2026-08-02
- Is Agent Memory the New Todo App? Devs Question Saturated AI Stack — ialijr · 2026-08-02
- Developer Shares the 'Only Claude Rule You Need' for Coding — ThePeterMick · 2026-08-02