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.
No one can keep up with the volume of code AI produces.
We wont stop using AI.
We will use AI to check AI.
Of course this is crazy, but it will also unlock pretty insane scaling and productivity and ultimately we will manage it on either end via requirements and tests.
You're suggesting that LLMs get better at fixing bugs/vulnerabilities, but at the same time stop getting better at finding them? What if this difference is inherent and essential?
The missing part of this is that verifying the bug with LLMs is also easy, and so is adversarially reviewing the proposed fix with LLMs.
The only thing left for you to do should be directional decisions. The LLMs should pause and rope you in if the fix involves directional/invariant changes.
I don't care if you call it an over-engineered looping machine or what, there are concrete benefits to using LLMs for this. They work faster than developing your own looping algorithm and more often produce useful results than not.
I dislike AI, but if AI finds real bugs then this is in my opinion objectively a positive thing. Of course the question is what constitutes a real bug.
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.
> but can't you just mark all "/" as potential divide by zero errors?
If you’re accepting large false positives rates: yes.
If you want users to take your warnings serious: no.
(Nitpick: you certainly don’t want to flag _all_ of them. Divisions by non-zero constants definitely should be excluded, for example (integer division by -1 can lead to overflow, but that would be a different warning))
I mean there could be a guard clause? But yeah, seems like this could be statically evaluated like how some IDEs see a null check and don’t complain about nullability within the same scope.
It would be more flexible for a compiler to reuse the range analysis logic used in optimizations for statically verifiable divide by zeros. That way you could extend it to other things like statically verifiable overflows.
The fruits of using LLMs to code.
You'll waste far more time finding what it quietly and subtly wrecked than you would have if you just coded it yourself.
It’s obviously Claude 69 with time travel functionality, that’s too dangerous to release to public. They’re working on space-time limiting sandbox to prevent these issues.
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.
Finding the bugs with LLMs is easy. Reviewing the output, cleaning it up, and making sure it doesn't break something else is the hard part.
No one can keep up with the volume of code AI produces.
We wont stop using AI.
We will use AI to check AI.
Of course this is crazy, but it will also unlock pretty insane scaling and productivity and ultimately we will manage it on either end via requirements and tests.
It's mostly (not entirely, but mostly) finding security issues in old human-written code. It'll eventually start running out of those.
From that standpoint, it's not a crazy setup security-wise. Maybe still crazy for development.
You're suggesting that LLMs get better at fixing bugs/vulnerabilities, but at the same time stop getting better at finding them? What if this difference is inherent and essential?
The missing part of this is that verifying the bug with LLMs is also easy, and so is adversarially reviewing the proposed fix with LLMs.
The only thing left for you to do should be directional decisions. The LLMs should pause and rope you in if the fix involves directional/invariant changes.
> 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.
No big deal? It’s not like it’s free… tokens cost money.
Often rounds to free compared to human costs.
I don't care if you call it an over-engineered looping machine or what, there are concrete benefits to using LLMs for this. They work faster than developing your own looping algorithm and more often produce useful results than not.
But what's your expectation of the net?
I dislike AI, but if AI finds real bugs then this is in my opinion objectively a positive thing. Of course the question is what constitutes a real bug.
A.I. is useful for this. But it would be even more useful if all new code were written in Rust or some other memory-safe language.
A.I. could also be used to port C/C++ codebases to Rust, which isn't economically feasible at the moment.
AI will have plenty of security bugs left to find in Rust codebases.
Unfiltered models will help build exploits for the bugs they find, so there is some means of measuring their efficacy.
If you're just talking about security bugs.
There are also non security bugs that don't have exploits but just make the user experience worse.
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.
> but can't you just mark all "/" as potential divide by zero errors?
If you’re accepting large false positives rates: yes.
If you want users to take your warnings serious: no.
(Nitpick: you certainly don’t want to flag _all_ of them. Divisions by non-zero constants definitely should be excluded, for example (integer division by -1 can lead to overflow, but that would be a different warning))
Fuzzers find inputs, not just "potential" errors that aren't triggerable.
What are you suggesting and how would it be different than how SIGFPE already works?
I mean there could be a guard clause? But yeah, seems like this could be statically evaluated like how some IDEs see a null check and don’t complain about nullability within the same scope.
It is interesting that FFmpeg has its own Git server. Maybe we should move there too?
What we need is a numeric type that cannot be zero.
Every day, we stray closer to Haskell. Dare I say it: good!
It would be more flexible for a compiler to reuse the range analysis logic used in optimizations for statically verifiable divide by zeros. That way you could extend it to other things like statically verifiable overflows.
And also cannot be INT_MIN, otherwise -1 / INT_MIN is undefined behaviour(!) in C and C++.
What we need are refinement types, where there’s a base type and a predicate. F* has this:
Generating an incorrect input file seems to be the easiest task of all for any fuzzer.
Generating correct input to get deep into the call stack and then finding something is the hard part.
send patches
...they did.
Where?
They only suggested a basic guard, chich can be useless if this case never happens
The fruits of using LLMs to code. You'll waste far more time finding what it quietly and subtly wrecked than you would have if you just coded it yourself.
Those sneaky LLMs going 7 years into the past and committing as a human:
https://code.ffmpeg.org/FFmpeg/FFmpeg/commit/8eda3c7f91e1a5b...
It’s obviously Claude 69 with time travel functionality, that’s too dangerous to release to public. They’re working on space-time limiting sandbox to prevent these issues.
Its all fun and games until the Claude-who-remains hunts you down
Just remember kids, never immanentize the eschaton.
You're not reading it right. The bug was found using a vibecoded fuzzer.
I wonder from where Claude stole this fuzzer.
Or it used something called an "analogy" which is a valid way to solve new problems.