Inside OpenAI's Codex comeback: from failed launch to swallowing ChatGPT
every · x · 2026-10-20
Every publishes Dan Shipper's long-form story "How Codex Happened" on OpenAI's comeback in coding. He recalls testing GPT-5 a month before launch — ten people holed up in upstate New York — and finding the in-Codex experience underwhelming: the earlier cloud version had missed product-market fit and the team was mid-pivot to a local terminal version. Today Codex is the centerpiece of OpenAI's comeback, having "swallowed ChatGPT from the inside." The piece also applies Shipper's test for good writing — specificity and honesty drawn from lived experience — to why AI writing often feels generic.
Related event: Every's Deep Dive: How OpenAI Codex Turned Failure Into Victory(4 posts)→
More from coding & agent
- Factory adds Linear delegations, letting Droid agents run issues automatically — matanSF · 2026-10-21
- Agent memory, goals and emotion should be designed as one system, argues dev — mimi10v3 · 2026-10-21
- Meta launches Muse Wonder coding models with 1M context, $4/$20 per million tokens — AIatMeta · 2026-10-21
- CastWorkshop: open-source studio ties Ollama and ComfyUI into persistent AI characters — CastWorkshop · 2026-10-21
- Agents break in production for boring backend reasons, not model reasons — DayKnown1050 · 2026-10-21
- REA turns any site, app, or game into an RL environment via open-source AgentEnv — henloitsjoyce · 2026-10-21