OpenAI says two engineers used GPT-6 Astra to design a device in under a week

OpenAI framed the project as a test of whether a model could create a device “without any direct human edits.” OpenAI says it used GPT-6 to define the functional requirements and design the device, and lists what Astra did: the look of the device, drawing on OpenAI’s Work Louder collaboration and references from games and toys; the enclosure and the internal structures that hold the components in place; the electrical components and the printed circuit board layout, including placement and connections to fit inside the enclosure; and the user interface, firmware, and software integrations that connect the device to Codex.

According to OpenAI, two team members designed the test device with Astra in under a week, working on it as a side project. A contract manufacturer then built a small batch of prototypes in under a month. OpenAI describes it as a test device and has not announced plans to sell it.

OpenAI says getting the device ready for manufacturing “still required several rounds of review and iteration,” because Astra “did not consistently account for the manufacturer’s production limits, tolerances, or details required for assembly.” OpenAI says these gaps are helping it identify what future models need to do better.

OpenAI also published results on BenchCAD 2.0, which it says tests whether models can reconstruct 3D parts and assemblies and identify connections in circuit boards. A newer internal model averaged 0.875, against 0.594 for GPT-6 Astra at its highest reasoning setting The figures are OpenAI’s own. OpenAI has not named that model or said when it ships.

OpenAI is expanding its work with Chip Ganassi Racing’s R&D team, testing workflows that turn 3D scans of existing race-car parts into editable CAD models and 2D manufacturing drawings. OpenAI says this is particularly useful when the original design files are unavailable. The team’s engineers review the models and drawings for accuracy and manufacturability. OpenAI also announced a new research collaboration with Mazda: its research and Forward Deployed Engineering teams are working with Mazda’s aerodynamics and crash-safety engineers, using airflow and structural simulations to explore new vehicle designs, including new nose shapes to reduce drag. OpenAI says it will share results in the coming months.

Inside OpenAI, the hardware and infrastructure teams already use Codex and ChatGPT to revise CAD models, prepare manufacturing drawings, set up simulations, and review designs for robotics and compute infrastructure, and OpenAI says their model usage, measured in tokens, has grown 23-fold since February. OpenAI has opened a form for engineers, engineering firms, and software vendors who want to collaborate.