Positive experiences on other projects (curl) [LWN.net]

Positive experiences on other projects (curl)

Posted Oct 22, 2025 8:08 UTC (Wed) by taladar (subscriber, #68407)
In reply to: Positive experiences on other projects (curl) by lmb
Parent article: Large language models for patch review

On the other hand Daniel also mentions that the curl code base is several 100k lines of code and after decades of not applying a tool like that he only got a few hundred suggestions from the AI tool, most of them minor things or things they did not want to fix. Only a few were actual bugs and most of those were in implementations of protocols with decades old specs, so specs that were definitely part of the training data of the LLM.

Most code bases do not have that luxury so I would expect the useful results to be even lower in number.

to post comments

Positive experiences on other projects (curl)

Posted Oct 23, 2025 21:47 UTC (Thu) by Karellen (subscriber, #67644) [Link] (3 responses)

You expect most projects would get a lower rate of errors (per-kLOC?) than curl?

I'm not sure about that. From what I've read, the curl team (and Daniel Stenberg in particular) pays a lot of attention to code quality. Notably, they try to make a habit that when one bug is found, to search the codebase for similar bugs and eliminate them at the same time. More details at

https://daniel.haxx.se/blog/2025/04/07/writing-c-for-curl/

Daniel also did a presentation on the subject at FOSDEM 2025 - Tightening every bolt: https://www.youtube.com/watch?v=Yr5fPxZvhOw (25:44)

Positive experiences on other projects (curl)

Posted Oct 24, 2025 3:53 UTC (Fri) by edgewood (subscriber, #1123) [Link] (2 responses)

I believe that the luxury the OP was referring to is "most of those (bugs) were in implementations of protocols with decades old specs, so specs that were definitely part of the training data of the LLM".

In other words, curl might be a best-case scenario for LLM bug finding, due it being code that implements well known public specs. Other codebases, which are unlikely to implement well known public specs that are part of the LLM training data, may not benefit as much.

Positive experiences on other projects (curl)

Posted Oct 24, 2025 8:28 UTC (Fri) by taladar (subscriber, #68407) [Link] (1 responses)

That is exactly what I meant.

Positive experiences on other projects (curl)

Posted Oct 24, 2025 10:57 UTC (Fri) by Karellen (subscriber, #67644) [Link]

Ah, sorry for misreading your meaning, my mistake!