Experiments in Using AI to Enhance the Linux Spanning Tree Protocol (STP)
summary
Experiments produce kernel patches, documentation and tests: JSON output for iproute2 is implemented with minor cleanup, working STP conformance test is generated in Python but only covers basic failover and needs deeper packet/conformance cases, while the attempt to add Rapid Spanning Tree yields an invalid, overly large patch that fails checkpatch and merge. AI helps boilerplate and docs, struggles with concurrency and large kernel changes, and requires significant human validation and iterative, narrowly scoped prompts.
AI-written summary · about
chapters (7)
- 0:00Introduction and motivation
- 3:32JSON support in IP route
- 6:22Spanning Tree Protocol basics
- 8:09AI-generated STP test
- 11:58Rapid Spanning Tree attempt
- 16:39AI limitations and lessons
- 19:48Future plans and Q&A
related talks
47mUsing AI To Bridge the Gap Between Safety Standards and Open Source Development
30mDesigning AI for Network Troubleshooting: A Langchain Proof of Concept
46mAI for Kernel Engineers
37mExploratory Load-Testing with AI Tooling - it's Time to Ramp Up!
15mA Study on Extending the TARA Methodology for Physical AI: A Case Study of ADS
43mExploratory Testing with AI
21mHow To Make AI-Assisted OSS Contributions Review-Ready
01h 06mEndnote: AI-Assisted Software Engineering