User Complaints: Official Demos vs Actual API Performance Feel Like Different Species
yuntiandeng · x · 2026-08-02
A user reported zero output after running Codex for 40 hours via the OpenAI API, a stark contrast to official claims of "solving all math problems."
Responding to this, another user noted that the model showcased in demos feels like a completely different species from the one available to users. They questioned whether this gap stems from the model's inherent capabilities or simply from expert-level prompting and massive compute budgets.
Related event: OpenAI Codex Yields Zero Output After 40 Hours, Sparking User Backlash(2 posts)→
More from Models
- Mistral touts STEM benchmark win, but leaderboard shows it ranking sixth overall — MistralAI · 2026-10-16
- Local tool calling compared: how Gemma 4, Llama 3 and Mistral differ — leslysandra · 2026-10-16
- $2 Gemini Pro accounts flood the gray market, spawning waves of AI spam comments — huangyun_122 · 2026-10-16
- Haider: Opus 5.5 vs Astra on SWE tasks — Astra has a higher floor, reasoning in a tier of its own — haider1 · 2026-10-16
- Artificial Analysis launches Decision Index for the emerging decision model category — ArtificialAnlys · 2026-10-16
- Liquid AI's d1-ultra tops Artificial Analysis Decision Index with 85% non-hallucination rate — ArtificialAnlys · 2026-10-16