Every publishes 8,000-word Codex oral history, agent-native so your AI can dig the raw interviews
danshipper · x · 2026-10-16
Dan Shipper's Every released "How Codex Happened," an 8,000-word definitive history of Codex built on deep interviews with the team behind it, including gdb, Thibault Sottiaux, ajambrosino, embirico and more.
- The piece traces OpenAI's coding comeback: pre-launch testing of GPT-5 in Codex left Every's team underwhelmed; the early cloud version missed PMF and the team pivoted to a local terminal version
- Codex is now the centerpiece of OpenAI's comeback, with the CLI and VS Code extension exploding in popularity and reshaping the company's roadmap
- The article is agent-native: readers can have their own agent explore the full interview transcripts. Early reactions call agent-oriented reading promising for surfacing tensions and challenging the author's causal story, though unproven in a single trial
More from coding & agent
- ai& becomes an official built-in Cline provider with 13 open-weight models — DavidBennett__ · 2026-10-16
- x402 as a free GTM channel: agents discover 100+ tools, no API keys needed — 0xJeff · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16
- POV ski game on real Matterhorn elevation data, built with Claude Opus 5.5 — techartist_ · 2026-10-16
- Poisoned SERPs broke rank tracking — a Claude MCP + Notion workaround — VeryWellVersed · 2026-10-16
- OpenAI's Live API adds Decisions API for ~200ms real-time voice app decisions — juberti · 2026-10-16