> AI is helping patch previously unrealized holes.
AI is also making plenty of holes.
I have not seen a single case of anything that an AI has found that could not have been automatically found without AI.
> AI is helping patch previously unrealized holes.
AI is also making plenty of holes.
I have not seen a single case of anything that an AI has found that could not have been automatically found without AI.
Mozilla had 400 Firefox CVEs found by Mythos; if those were so easy to find, why didn’t humans do it before?
Humans did do it before.
------------------------
It's also worth pointing out that the developers at Mozilla literally decided to make a brand new programming language (Rust) that eliminated an entire categories of bugs and started working on a new browser (Servo) where its components could be switched into firefox.
Then Mozilla fired the team working on it.
Lesson 1: Better tools and processes eliminate bugs.
Lesson 2: If you don't have the tools, make them.
Lesson 3: Mismanagement leads to security vulnerabilities.
> It's also worth pointing out that the developers at Mozilla literally decided to make a brand new programming language (Rust)
In my memory, that does not seem 100% right. And indeed https://en.wikipedia.org/wiki/Rust_(programming_language)#20... says a single developer who happened to work at Mozilla started it as a personal project.
After a few years Mozilla became interested in it and then sponsored its development, transforming it into the language it is today.
Good point about the whole new language as a tool for eliminating many thousands(?) as a whole category
Yes, and even after introducing and using Rust, there were still vulns in the remaining code.
FWIW, Rust is my main language, so I am grateful to the humans that created it, and it is indeed a monumental effort. But vuln finding is a different kind of creative endeavour, and one that is heavily weighted against defenders.
Yes, which is why you don't stop at rust.
You would choose rust (from a security standpoint) because it massively reduces memory safety issues (which from a Microsoft study was responsible for around 70% of bugs).
Then you look at things like linting, fuzzing, design by contract, proofing, deterministic test runs, etc...
As I said above: use better tools and processes.
LLMs don't fit that criteria.