News for hackers. Stuff that matters.
Re:Small models also found the vulnerabilities that Mythos f... by woeirua on Saturday April 11, 2026 @06:23PM (#47734541)
There is absolutely zero reason to believe you could use this same approach to find and exploit vulns without Mythos finding them first. We already know that older LLMs can’t do what Mythos has done. Anthropic and others have been trying for years.
Re:Small models also found the vulnerabilities that Mythos f... by nozzlegear on Saturday April 11, 2026 @07:08PM (#47734774)
> There is absolutely zero reason to believe you could use this same approach to find and exploit vulns without Mythos finding them first.

There's one huge reason to believe it: we can actually use small models, but we cant use Anthropic's special marketing model that's too dangerous for mere mortals.

Re:Small models also found the vulnerabilities that Mythos f... by Filligree on Saturday April 11, 2026 @09:36PM (#47735455)
If all you have is a spade, that is _not_ evidence that spades are good for excavating an entire hill.
Re:Small models also found the vulnerabilities that Mythos f... by apgwoz on Sunday April 12, 2026 @12:04AM (#47736060)
It takes longer, but a spade is better than bare hands. The goal is to speed up finding valid vulnerabilities, and be faster than humans can do it.
Re:Small models also found the vulnerabilities that Mythos f... by naasking on Sunday April 12, 2026 @09:29AM (#47739404)
> If all you have is a spade, that is _not_ evidence that spades are good for excavating an entire hill.

If you have an automated spade, that's still often better for excavating that hill than you using a shovel by hand.

Re:Small models also found the vulnerabilities that Mythos f... by nardons on Friday April 24, 2026 @05:20AM (#47887709)
A perfect analogy given a spade and a for loop can definitely excavate a hill.
Re:Small models also found the vulnerabilities that Mythos f... by apgwoz on Saturday April 11, 2026 @09:32PM (#47735437)
Why? They claim this small model found a bug given some context. I assume the context wasn’t “hey! There’s a very specific type of bug sitting in this function when certain conditions are met.”

We keep assuming that the models need to get bigger and better, and the reality is we’ve not exhausted the ways in which to use the smaller models. It’s like the Playstation 2 games that came out 10 years later. Well now all the tricks were found, and everything improved.

Re:Small models also found the vulnerabilities that Mythos f... by usef- on Saturday April 11, 2026 @10:03PM (#47735565)
If this were true, we're essentially saying that no one tried to scan vulnerabilities using existing models, despite vulnerabilities being extremely lucrative and a large professional industry. Vulnerability research has been one of the single most talked about risks of powerful AI so it wasn't exactly a novel concept, either.

If it is true that existing models can do this, it would imply that LLMs are being under marketed, not over marketed, since industry didn't think this was worth trying previously(?). Which I suspect is not the opinion of HN upvoters here.

Re:Small models also found the vulnerabilities that Mythos f... by apgwoz on Saturday April 11, 2026 @11:00PM (#47735798)
I use the models to look for vulnerabilities all the time. I find stuff often. Have I tried to do build a new harness, or develop more sophisticated techniques? No. I suspect there are some spending lots of tokens developing more sophisticated strategies, in the same way software engineers are seeking magical one-shot harnesses.
Re:Small models also found the vulnerabilities that Mythos f... by salawat on Sunday April 12, 2026 @04:37AM (#47737367)
...The absolute last thing I'd want to do is feed AI companies my proprietary codebase. Which is exactly what using these things to scan for vulns requires. You want to hand me the weights, and let me set up the hardware to run and serve the thing in my network boundary with no calling home to you? That'd be one thing. Literally handing you the family jewels? Hell no. Not with the non-existence of professional discretion demonstrated by the tech industry. No way, no how.

To be honest, this just sounds like a ploy to get their hands on more training data through fear. Not buying it, and they clearly ain't interested in selling in good faith either. So DoA from my point-of-view anyways.

Re:Small models also found the vulnerabilities that Mythos f... by kenjackson on Sunday April 12, 2026 @11:46AM (#47741093)
I don’t think these companies are hurting for access to code.
Re:Small models also found the vulnerabilities that Mythos f... by cycomanic on Sunday April 12, 2026 @02:55AM (#47736822)
From the article:

>At AISLE, we've been running a discovery and remediation system against live targets since mid-2025: 15 CVEs in OpenSSL (including 12 out of 12 in a single security release, with bugs dating back 25+ years and a CVSS 9.8 Critical), 5 CVEs in curl, over 180 externally validated CVEs across 30+ projects spanning deep infrastructure, cryptography, middleware, and the application layer.

So there is pretty good evidence that yes you can use this approach. In fact I would wager that running a more systematic approach will yield better results than just bruteforcing, by running the biggest model across everything. It definitely will be cheaper.