Codex throttled to 5 tok/s as dev argues local model deployment is the only fix
lxfater · x · 2026-10-09
A user shared a screenshot of OpenAI Codex running at just 5 tokens/s, apparently throttled. Developer lxfater quote-posted it arguing that locally deployed models are the real answer: no bans, no degraded intelligence, no throttling — implying cloud coding services carry uncontrollable usage and experience limits.
More from coding & agent
- Veteran dev: AI-coded it, I never read the code, but it's not vibe coding — judgment still matters — mjuric · 2026-10-09
- shadcn: the most important coding skill in the AI era is reading, not summarizing — shadcn · 2026-10-09
- Philosopher OKF: open-source LLM skill turns any topic into a structured study page — holyshitthatsucks · 2026-10-09
- Harrison Chase: trajectory labeling is several questions, not one pass/fail — Jev lands in LangSmith evals — hwchase17 · 2026-10-09
- Dev recreates seven Adobe apps in Rust with Claude, reigniting software copyright debate — technollama · 2026-10-09
- Hitting /compact Every Time Context Dips Below 60% Is Tech OCD — eigenron · 2026-10-09