Don't get me wrong, it's interesting. But there is no technical discussion as to how they did it. It's simply: we did it and Mythos and Codex didn't.
It's good to know that it's possible, but I'd have already expected it. Put a base model versus a base model + harness + whatever else, and yea, if you do it right then you have a better system to find vulnerabilities.
> We then ran AISLE's autonomous AI system against curl.
They don't even mention what models the use under the hood. It wouldn't surprise me if they are from Anthropic and OpenAI.
melvinroest
We had a few AISLE-generated security reports, and the signal to noise was reasonably good.
The tool basically had to chain two exploits together to reach this. It also came up with a patch to fix which was fairly sensible (but I ended up editing it further for clarity).
rwmj
Curl seems to becoming one of the favourite things to demo AI finding vulns.
Curl is going to end up incredibly secure.
graemep
Since AISLE reported 29 issues but only 6 warranted a CVE, and all the found CVEs were "low" severity, this makes me wonder if AISLE simply is tuned for a higher false positive rate than the anthropic and openai tools (which may have found the same 6 issues and decided not to report them)
markasoftware
That's bragging rights correctly earned, i think! As marketing-y as this post is, definitely something to keep an eye on.
anilgulecha
Very unrelated to the content of the article, but that is a pretty weird ft ligature in the heading. It looks a letter from another alphabet. Which maybe makes this pretty cool after all.
janaagaard
Good marketing and definitive proof that local (read: on-prem & air-gapped) models with correct context and tools are good enough to perform on par and above SOTA cloud hosted solutions.
We have seen this point many times before with different technologies. The first computers at university were big and expensive, same as this machine. Give it a few years and this functionality will be a commodity.
comments (10)
Don't get me wrong, it's interesting. But there is no technical discussion as to how they did it. It's simply: we did it and Mythos and Codex didn't.
It's good to know that it's possible, but I'd have already expected it. Put a base model versus a base model + harness + whatever else, and yea, if you do it right then you have a better system to find vulnerabilities.
> We then ran AISLE's autonomous AI system against curl.
They don't even mention what models the use under the hood. It wouldn't surprise me if they are from Anthropic and OpenAI.
melvinroest
The most notable bug/exploit their scanner found was: https://gitlab.com/nbdkit/libnbd/-/commit/e50bbd2681117c2dd8...
The tool basically had to chain two exploits together to reach this. It also came up with a patch to fix which was fairly sensible (but I ended up editing it further for clarity).
rwmj
Curl is going to end up incredibly secure.
graemep
markasoftware
anilgulecha
janaagaard
We have seen this point many times before with different technologies. The first computers at university were big and expensive, same as this machine. Give it a few years and this functionality will be a commodity.
TechTechTech
curious they're willing to run AISLE on tmux to find more than mine.
blmarket
dec0dedab0de
That being said you cannot compare a model with a specialised harness. These are two completely different things.
Am I missing something?
_pdp_