New Age Tooling BoF · Netdev 0x1A

The Cost Asymmetry of AI-Generated Code: a Case Study in the SRv6 Subsystem

Public analysis of an AI-generated patchset submitted to the Linux kernel SRv6 subsystem: what went wrong, why, and lessons learned for using AI in kernel development.

Stefano Salsano
University of Rome Tor Vergata · CNIT, Italy
New Age Tooling BoF @ Netdev 0x1A · 13–16 July 2026 · Rome, Italy

The slides

Presentation — 9 slides

Self-contained Reveal.js deck that runs in any browser, also offline. Navigate with the arrow keys or a presenter remote; press S for speaker notes, F for fullscreen.

Open the slides Download PDF

The talk

A 5,155-line AI-generated patchset (six SRv6 Mobile User Plane behaviors, RFC 9433) reached the netdev list with green CI, textbook commit messages and 2,400 lines of passing selftests. One month of expert review later, nothing was mergeable. We analyzed the full thread — and re-verified, against kernel source, every finding of the AI reviewer that looked at the same series.

Materials & references

Notes

We are not here to blame anyone. We are here to learn and to improve the kernel development process, taking into account both the opportunities and the risks of AI.

Special thanks to Andrea Mayer, SRv6 maintainer, who performed the manual review at the heart of this case study.

Contact: stefano.salsano@uniroma2.it