Comment by simondotau
20 hours ago
Once the dust has settled, it would be interesting to give LLMs the pre-patch source code and see whether any of them can identify this chain of vulnerabilities. Even if they can't identify the full chain, can they at least spot one of the constituent bugs and recognise its seriousness?
If they can't, why not?
If they can, why haven't they already?
If you tell them where the problem is (even rough code area) - I'm 99% sure they can, and have.
If you only tell them to find issues in PHP - the strongest models probably still can, although they might find different issues ;)
I’d hazard a guess that’s how the bug was found in the first place?
LLMs probably found this multiple times.
The original exploit, and then when the rumors of a big critical patch got out, the people who are leaking the details online probably used an LLM to find the exploit again.
Just revealing that an unpatched exploit exists in $XYZ these days basically guarantees that a bunch of people are going to target $XYZ with LLMs looking for that exploit.
I would have expected there to be a hundred entities running every single model over major code like PHP, and clang, and pretty much any behemoth open source project the world relies on. This is the sort of thing the model makers should be doing as a matter of course, as part of routine testing of their new models.
3 replies →
I would be astounded if labs were not already fine tuning on known vulnerabilities for their cyber models
Undoubtedly, but presumably not this specific set of vulnerabilities.
They can't, because the good guys get the LLM with restrictions.
The bad guys have invested the resources of the criminal enterprise into hardware running unrestricted models.