Codex now keeps prompt cache forever for logged-in users; dev says usage burn is systemic
CtrlAltDwayne · x · 2026-10-21
OpenAI Codex lead Thibault Sottiaux announced API cache is now valid for 12 hours, and logged-in users on Codex & Work keep cache forever — resuming old conversations is guaranteed to hit cache with no penalty. Developer Kevin Naughton called it a real improvement but argued the excessive usage burn issue isn't isolated to the 40k users OpenAI claims; it's systemic.
More from coding & agent
- Characterizing a cheap SG90 servo with Claude's plan to build a MuJoCo model — _Stocko_ · 2026-10-21
- Decision model leads, LLM reviews: SRE diagnosis pass rate jumps to 89.5% — tianyin_xu · 2026-10-21
- Opus plans, DeepSeek codes: Autonomous's hybrid local agent stack hits 753 tok/s — dee_hw · 2026-10-21
- Cloudflare's "Build the next GitHub" multi-agent coding challenge finals set for Oct 21 — dinasaur_404 · 2026-10-21
- Characterizing an SG90 servo with Claude to build an accurate MuJoCo model — _Stocko_ · 2026-10-21
- Building yarrow: a shared fix library for coding agents where trust, not storage, is the hard part — Significant_Camp4148 · 2026-10-21