alt Hacker NewsGoing on a bit of a tangent:
'Classic' non-AI fuzzers like AFL are still insanely useful and powerful, as are static analysis tools.
LLMs make all of these much, much easier to use. The other night, before I went to bed I told Kimi to go and fuzz filesystem code in the latest Linux kernel. I woke up to 26 crashes with reproducers and fixes. I'm still busy reviewing and upstreaming them. (Some have already landed.)
Replies
Foobar8568 • today at 4:08 PM
At work, I am arguing with tech leads that they should sanitize user inputs for a public facing chatbot.
I want to cry.
➕ show 1 reply
wavemode • today at 6:04 PM
> (Some have already landed.)
Do you have links to some of these?
➕ show 1 reply
elzbardico • today at 10:09 AM
It is more than LLMs are faster using those tools, than they are finding more errors by themselves analysing the code.
➕ show 1 reply
Similar use case here! Combining AI with fuzzers is so powerful, especially for creating a special fuzzing harness, or generating seeds for hard to reach code. That was taking hours/days and was frustratingly boring work before. Unfortunately the Codex models refuse a lot for me, I’m mostly using the cheapest models because they refuse the least, have you found Kimi to be a good alternative? Any other you tested that you can recommend? Thinking of switching.