One coding agent built a working Linux-compatible kernel in eleven days
Ginux: A New Kernel Runs Linux Userspace, Made via Human-Directed AI Engineering
Gregory Kurtzer of CIQ presents Ginux, a research prototype that tests Human-Directed Agentic Engineering: humans set the architecture, constraints, milestones, and stopping points, while an autonomous agent implements, runs, diagnoses, and revises. Over eleven days, a single persistent coding-agent task produced a Rust-first x86-64 kernel that boots via UEFI, implements its own OS mechanisms and a Linux compatibility layer, runs unmodified Alpine programs, and brings up a Rocky Linux 10 userspace with systemd through multi-user.target. Kurtzer stresses narrow hardware coverage, no independent security audit, and no claim of production readiness.
Ginux demonstrates the rapid integration of established systems mechanisms, but it remains a research prototype.
- vikramkr
Y'all I get that the term "vibe coding" feels derogatory and that it took off as a term before it took over regular dev work too. But we're kinda stuck with the name and running away from it with "Agentic Engineering" or "Human-Directed AI Engineering" to try and distinguish from some normie asking Claude to make a random app iw just not gonna stick. Maybe if we go with "vibe engineering" as a tongue in cheek sort of name but I think running away from the "vibe" part of vibe coding to describe agentic dev is just not gonna work nobody's gonna let us get away with it
- hideki_okumura
Tasks like ×× that are compatible with 〇〇 are what AI excels at most. This is because the process of expanding compatibility can be improved incrementally, and the acceptance criteria are clear.
1. Prepare one item that works with 〇〇
2. Make it work with ××
3. Return to (1) until it is deemed sufficient
4. Prepare 100 items that work with 〇〇
5. Measure performance with ××
6. Measure performance with 〇〇
7. Consider several performance improvement measures
8. Implement improvement measures while verifying that compatibility is not compromised
9. Return to (4) until it is determined that performance has improved sufficiently
10. Completion of ××, which is sufficiently compatible with 〇〇 and not inferior in performance
- jonhohle
Project includes an Apache license, but code created by an AI is not copyrightable and it’s output is in the public domain.
> Ginux is available under the Apache License 2.0. See LICENSE and NOTICE.
Zarya of the Dawn concludes that human direction and selection is not enough to produce a copyrightable work from AI generated content. Without copyright, there is no legal basis to offer a license. The code is public domain or worse, mislicensed, AI washed GPL or BSD.
- gdgghhhhh
An initial review found a few things:
https://social.kernel.org/notice/BBry0fMLEodHRiUqGW
Apparently they got fixed by now.
- codetiger
I recently built a concept Linux OS with the entire UI generated by a local AI model based on the user's intend. https://github.com/codetiger/velliangiri