Topic
How engineering cadence changes when work is delegated to and supervised remotely from an autonomous agent.
The same model scored twice under two scaffolds. A dev.to post uses that gap to argue the dividing line in AI coding is whether the model can run your repo's own commands and read the failure.
Reality
Claude Code now writes its own record of a developer's corrections and preferences. Anthropic's documentation keeps CLAUDE.md alongside it, and the one practitioner account available says the file's remaining job is narrower.
Reality
Gergely Orosz's visit found finance, recruitment and legal teams going from roughly zero to 90% Codex use in four months, with almost half of that arriving before anyone made the tool comfortable for them.
Reality
A dev.to post puts an agent pilot behind one wiki page that names a scout, a scribe and a signer, stamps every handoff in a git note, and fails CI on a leftover tbd. The rules that stop drift are still enforced by people.
Reality
OpenAI's Codex update adds computer use on Windows and remote control, per a dev.to write-up. That changes what an engineering team hands off, and how much a host machine can be trusted.
Reality