We did train Codex models natively on Windows -
https://openai.com/index/introducing-gpt-5-2-codex/ (and even 5.1-codex-max)
10 karma · joined April 2, 2025
Prev: Built Arrakis - MicroVM Sandboxes for AI Agents (https://github.com/abshkbh/arrakis)
Prev: Systems and Infra at Replit, Google, Microsoft.
Feel free to get in touch at - Mail- abshkbh AT gmail.com LinkedIn- https://www.linkedin.com/in/abshkbh/ X- https://x.com/abshkbh
(Views my own)
Apple's equivalent is the Apple Virtualization Framework which exposes kvm like functionality at a higher level.
Will come with MacOS support very soon :) Does work on Linux
If you believe there is value in fuzzy tasks being done by LLMs then from that it follows that having separate "agent" services with a higher order orchestrator would be required. Each calling LLMs on their own inside.