Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by dwedge on Thursday October 02, 2025 @11:19AM
(#45450895)
Yeah this is really fair play to Daniel Stenberg that he still approached these AI generated bug reports with an open mind after all the problems he's had.
[ Parent
| on HN ]
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by athorax on Thursday October 02, 2025 @11:33AM
(#45451074)
I think the big difference is that these aren't AI generated bug reports. They are bugs found with the assistance of AI tools that were then properly vetted and reported in a responsible way by a real person.
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by Legion on Thursday October 02, 2025 @01:01PM
(#45452301)
Basically using AI the way we have used linters and other static analysis tools, rather than thinking it's magic and blindly accepting its output.
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by stocksinsmocks on Thursday October 02, 2025 @11:24PM
(#45458619)
In the defense of the language models, the bugs were written by humans in the first place. Human vetting is not much of a defense.
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by NegativeK on Friday October 03, 2025 @10:01AM
(#45463135)
> Human vetting is not much of a defense.
The issue I keep seeing with curl and other projects is that people are using AI tools to generate bug reports and submitting them without understanding (that's the vetting) the report. Because it's so easy to do this and it takes time to filter out bug report slop from analyzed and verified reports, it's pissing people off. There's a significant asymmetry involved.
Until all AI used to generate security reports on other peoples' projects is able to do it with vanishingly small wasted time, it's pretty assholeish to do it without vetting.
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by josefx on Friday October 03, 2025 @11:00AM
(#45463743)
From what I understand some of the bugs where in code the AI made up on the spot, other bug reports had example code that didn't even interact with curl. These things should be relatively easy to verify by a human, just do a text search in the curl source to see if the AI output matches anything.
Hard to compute, easy to verify things should be the case where AI excel at. So why do so many AI users insist on skipping the verify step?
Re:Daniel Stenberg on 22 curl bugs found by AI and fixed
by abrookewood on Thursday October 02, 2025 @08:49PM
(#45457448)
Yep, I feel for the guy. He's had to deal with a hell of a lot of frustrating crap from AI slop to crazy end-users. Kudos for staying on top of it.