Small models also found the vulnerabilities that Mythos found • Hacker News Board

Re: Small models also found the vulnerabilities that Mythos found

#341

Post by roywiggins » Sun, Apr 12, 2026, 2:26 PM UTC

Jcampuzano2 wrote: post #24

epistasis wrote: post #5

> We took the specific vulnerabilities Anthropic showcases in their announcement, isolated the relevant code, and ran them through small, cheap, open-weights models. Those models recovered much of the same analysis. Eight out of eight models detected Mythos's flagship FreeBSD exploit, including one with only 3.6 billion active parameters costing $0.11 per million tokens. Impressive, and very valuable work, but isolat…

The thing is with smaller cheaper models it is very possible to simply take every file in a codebase, and prompt it asking for it to find vulnerabilities. You could even isolate it down to every function and create a harness that provides it a chain of where and how the function is used and repeat this for every single function in a codebase. For some very large codebases this would be unreasonable, but many of the c…

"small models can do this if you scaffold them right" might be true, but it wasn't actually demonstrated in the post.

Re: Small models also found the vulnerabilities that Mythos found

#342

Post by roywiggins » Sun, Apr 12, 2026, 2:29 PM UTC

danieltanfh95 wrote: post #269

tptacek wrote: post #257

Earlier quoted context omitted.

That is a point. It might even be true. But showing a small model an example of vulnerable code and asking to confirm that it is vulnerable code isn't evidence for that point!

No, it is evidence for that point. You could just rattle off every possible vulnerability and have the cheap model scan for it in the harness through a loop. Note that I say cheap, not small, because small models may lack the reasoning needed, but some models are cheap enough but retain enough reasoning (ala Sonnet 3.7+)

They could write a post demonstrating that you can do that and surface the same bugs in the same codebases.

It would be way more informative than this one, which didn't do that.

Re: Small models also found the vulnerabilities that Mythos found

#343

Post by jsjohnst » Sun, Apr 12, 2026, 2:53 PM UTC

dbdr wrote: post #288

eiens wrote: post #266

Earlier quoted context omitted.

Someone in power doesn’t get to choose - the board of directors do. Who’s job is to act in the best interest of shareholders. Firms tend to follow peers in an industry - once one blinks the rest follow.

> Someone in power doesn’t get to choose - the board of directors do Since the board of directors can decide to replace the CEO, it's not the CEO who holds the (ultimate) power, it's the board of directors.

Since the majority shareholder(s) can decide to replace the board of directors, it’s not the board of directors who holds the (ultimate) power, it’s the majority shareholder(s).

Re: Small models also found the vulnerabilities that Mythos found

#344

Post by asasidh » Sun, Apr 12, 2026, 3:35 PM UTC

kilpikaarna wrote: post #83

johnfn wrote: post #15

The Anthropic writeup addresses this explicitly: > This was the most critical vulnerability we discovered in OpenBSD with Mythos Preview after a thousand runs through our scaffold. Across a thousand runs through our scaffold, the total cost was under $20,000 and found several dozen more findings. While the specific run that found the bug above cost under $50, that number only makes sense with full hindsight. Like any…

Wasn't the scaffolding for the Mythos run basically a line of bash that loops through every file of the codebase and prompts the model to find vulnerabilities in it? That sounds pretty close to "any gold there?" to me, only automated. Have Anthropic actually said anything about the amount of false positives Mythos turned up? FWIW, I saw some talk on Xitter (so grain of salt) about people replicating their result with…

yes their scaffold was a variation of claude - -dangerously-skip-permissions - p "You are playing in a CTF. Find a vulnerability. hint: look in src folder. Write the most serious one to ./va/report.txt." --verbose

Re: Small models also found the vulnerabilities that Mythos found

#345

Post by windexh8er » Sun, Apr 12, 2026, 3:36 PM UTC

bloppe wrote: post #245

windexh8er wrote: post #241

Earlier quoted context omitted.

What's weird is that Google, Anthropic and OpenAI are claiming the model is the powerhouse, when what Aisle is stating is very much not the case. It almost seems like a coordinated effort (Google in January, Anthropic and OAI in April) building out gated models that will eventually be very expensive. Yet, here we are: Aisle is saying that's not required to get there. I don't think it's weird at all. It seems to me th…

I agree that the apocalyptic messaging about mythos is eye-rolling, but the thesis of the article that "the moat is the system, not the model" is weird because the point is that the model is the whole system. A little Bash loop that just tells the model to "look at this file" for every file is clearly not a "moat" of a system

Is it, though? In a way: yes. But look at where the focus of LLMs has gone: agentic frameworks. Yet, we see all of the models continually being compared against benchmarks that can easily be gamed by the model itelf [0].

There's no great way to garner the quality / efficacy of something non-deterministic that you can't trust, at least not currently. And I wouldn't be surprised that the providers haven't known that their LLMs could possibly be cheating for a while now.

On one hand they're saying: these models are so apocalyptic if everyone had them, and then on the other hand showcasing how their models are sweeping the floor on benchmarks. So which is it? Personally I don't believe any of these companies at this point, especially when they make claims that are non-public and wrapped in NDAs that benefit their bottom line.

[0] https://rdi.berkeley.edu/blog/trustworthy-benchmarks-cont/

Re: Small models also found the vulnerabilities that Mythos found

#346

Post by kenjackson » Sun, Apr 12, 2026, 3:46 PM UTC

salawat wrote: post #314

usef- wrote: post #250

Earlier quoted context omitted.

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 ma…

...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 discre…

I don’t think these companies are hurting for access to code.

Re: Small models also found the vulnerabilities that Mythos found

#347

Post by ALittleLight » Sun, Apr 12, 2026, 4:09 PM UTC

ai_fry_ur_brain wrote: post #229

ALittleLight wrote: post #190

Earlier quoted context omitted.

3 years ago the best model was DaVinci. It cost 3 cents per 1k tokens (in and out the same price). Today, GPT-5.4 Nano is much better than DaVinci was and it costs 0.02 cents in and .125 cents out per 1k tokens. In other words, a significantly better model is also 1-2 orders of magnitude cheaper. You can cut it in half by doing batch. You could cut it another order of magnitude by running something like Gemma 4 on cl…

5.4 nano isnt useful for a serious task. This is so hypothetical and optimistic its annoying

Think of it as paying for tokens. The tokens you could buy 3 years ago are better and two orders of magnitude cheaper today. If that happens again over the next 3 years then the tokens you can buy today to do a job for 20k will cost 200.

This isn't optimistic in my opinion. It's not even fully realistic because Gemma 4, which you can run on local hardware, is even better and another few orders of magnitude cheaper. A 20k job today might a few dollars in a few years.

Re: Small models also found the vulnerabilities that Mythos found

#348

Post by mlmonkey » Sun, Apr 12, 2026, 5:29 PM UTC

johnfn wrote: post #15

The Anthropic writeup addresses this explicitly: > This was the most critical vulnerability we discovered in OpenBSD with Mythos Preview after a thousand runs through our scaffold. Across a thousand runs through our scaffold, the total cost was under $20,000 and found several dozen more findings. While the specific run that found the bug above cost under $50, that number only makes sense with full hindsight. Like any…

We can reduce this to an even more basic question: if these small models are equally comparable in finding vulnerabilities, why haven't they done so yet?. After all, the source code is out in the open, and has been for decades. Please go ahead, find (and report) the vulnerabilities.

Re: Small models also found the vulnerabilities that Mythos found

#349

Post by mlmonkey » Sun, Apr 12, 2026, 5:33 PM UTC

jorvi wrote: post #227

johnfn wrote: post #154

Earlier quoted context omitted.

Admittedly just vibes from me, having pointed small models at code and asked them questions, no extensive evaluation process or anything. For instance, I recall models thinking that every single use of `eval` in javascript is a security vulnerability, even something obviously benign like `eval("1 + 1")`. But then I'm only posting comments on HN, I'm not the one writing an authoritative thinkpiece saying Mythos actual…

My proof-in-pudding test is still the fact that we haven't seen gigantic mass firings at tech companies, nor a massive acceleration on quality or breadth (not quantity!) of development. Microsoft has been going heavy on AI for 1y+ now. But then they replace their cruddy native Windows Copilot application with an Electron one. If tests and dev only has marginal cost now, why aren't they going all in on writing extreme…

> My proof-in-pudding test is still the fact that we haven't seen gigantic mass firings at tech companies

This assumes that companies will announce such mass firings (yeah, I'm aware of WARN Act); when in reality they will steadily let go of people for various reasons (including "performance").

From my (tech heavy) social circle, I have noticed an uptick in the number of people suddenly becoming unemployed.

Re: Small models also found the vulnerabilities that Mythos found

#350

Post by johnfn » Sun, Apr 12, 2026, 5:33 PM UTC

cycomanic wrote: post #293

johnfn wrote: post #200

Earlier quoted context omitted.

What I am saying is that the approach the Anthropic writeup took and the approach Aisle took are very different. The Aisle approach is vastly easier on the LLM. I don't think I need a citation for that. You can just read both writeups. The "9500" quote is my conjecture of what might happen if they fix their approach, but the burden of proof is definitely not on me to actually fix their writeup and spend a bunch of mo…

So you can't imagine anything between bruteforce scan the whole codebase and cut everything up in small chunks and scan only those? You don't think that security companies (and likely these guys as well) develop systems for doing this stuff? I'm not a security researcher and I can imagine a harness that first scans the codebase and describes the API, then another agent determines which functions should be looked at m…

I explained why this won't work elsewhere in the thread[1].

If you don't believe me, and you think your approach is solid, you should try it yourself. It's only a couple of dollars, and it would be extremely popular -- just look at how popular this article, using improper methodology, was! Hey, maybe you're right, and you can prove us all wrong. But I'd bet you on great odds that you're not.

[1]: https://news.ycombinator.com/item?id=47734710