We found a division by zero bug in FFmpeg with a vibecoded fuzzer
dclavijo · 227 points · 171 comments · 14 ore fa · Open original
Comments
5 preview comments · loading full thread
Log in to use comments
Log in to h4cker, then connect Hacker News to publish comments.
AEaeyes10 ore fa
A patch for this was submitted in April: https://lists.ffmpeg.org/archives/list/ffmpeg-devel@ffmpeg.o...
Edit: And there was discussion about this back in 2024 as well
DAdabinat13 ore fa
It’s interesting how AI may both raise and lower the quality of software. It’s very easy to send an AI agent on an open-ended bug hunt, and if it wastes a bunch of time and effort and finds nothing, no big deal. Time is much more important for a human developer with a salary.
JUjustonenote10 ore fa
Whatever about the specifics of this bug and whether its a useful vector, this is not surprising even in the slightest?
My current opinion on LLMs is that they are superhuman in that they lack fatigue, they have close to full knowledge across all subjects which are known to humans at least publicly, and the fact that you can vibe code a harness to look for bugs in a famously complicated C codebase is intern level stuff and hardly news.
Smart aspiring blackhats will be targeting tmux next, both with light llm jailbreaks, light supply chain attacks (web search results) and LPEs within certain environments which weren't particularly useful before but with agents running on auto mode for hours become a very valuable springboard. I'm not sure on the quality of tmux code but I know its written in C and is very complex and was not at all designed to defend against this type of threat.
PEpeter_retief23 minuti fa
Bugs days are numbered with AI!
KSks204812 ore fa
No doubt fuzzers (vibecoded or otherwise) can be powerful, but can't you just mark all "/" as potential divide by zero errors?
I guess sometimes developers think they "know" some variable won't be zero, but unless it checked explicitly or by the compiler, that shouldn't be trusted.
Comments
5 preview comments · loading full threadLog in to h4cker, then connect Hacker News to publish comments.
A patch for this was submitted in April: https://lists.ffmpeg.org/archives/list/ffmpeg-devel@ffmpeg.o... Edit: And there was discussion about this back in 2024 as well
It’s interesting how AI may both raise and lower the quality of software. It’s very easy to send an AI agent on an open-ended bug hunt, and if it wastes a bunch of time and effort and finds nothing, no big deal. Time is much more important for a human developer with a salary.
Whatever about the specifics of this bug and whether its a useful vector, this is not surprising even in the slightest? My current opinion on LLMs is that they are superhuman in that they lack fatigue, they have close to full knowledge across all subjects which are known to humans at least publicly, and the fact that you can vibe code a harness to look for bugs in a famously complicated C codebase is intern level stuff and hardly news. Smart aspiring blackhats will be targeting tmux next, both with light llm jailbreaks, light supply chain attacks (web search results) and LPEs within certain environments which weren't particularly useful before but with agents running on auto mode for hours become a very valuable springboard. I'm not sure on the quality of tmux code but I know its written in C and is very complex and was not at all designed to defend against this type of threat.
Bugs days are numbered with AI!
No doubt fuzzers (vibecoded or otherwise) can be powerful, but can't you just mark all "/" as potential divide by zero errors? I guess sometimes developers think they "know" some variable won't be zero, but unless it checked explicitly or by the compiler, that shouldn't be trusted.