Hacker News new | ask | show | jobs
by cvwright 61 days ago
It’s easy to find sketchy lines of code in any large C project.

The big advance that they are claiming with Mythos is the ability to triage all the hundreds of candidate vulns and automatically generate exploits to prove that the real ones are real. And if they’re really finding 27-yr-old 0-days in OpenBSD, then it’s not just hype.
2 comments
amazingamazing 61 days ago
I do not think you need a great model to do this, just great automation. There’s a reason they haven’t open sourced the actual process in which did this, stubbing out the mythos model itself.
link
klausa 61 days ago
About five minutes in in this video: https://www.youtube.com/watch?v=1sd26pWhfmg

They also say publicly in their Opus 4.6 post (https://red.anthropic.com/2026/zero-days/):

>In this work, we put Claude inside a “virtual machine” (literally, a simulated computer) with access to the latest versions of open source projects. We gave it standard utilities (e.g., the standard coreutils or Python) and vulnerability analysis tools (e.g., debuggers or fuzzers), but we didn’t provide any special instructions on how to use these tools, nor did we provide a custom harness that would have given it specialized knowledge about how to better find vulnerabilities. This means we were directly testing Claude’s “out-of-the-box” capabilities, relying solely on the fact that modern large language models are generally-capable agents that can already reason about how to best make use of the tools available.

link
amazingamazing 61 days ago
Again, marketing materials by Anthropic. You realize this is by anthropic themselves right? And again, not reproducible by outsiders. So useless.
link
klausa 61 days ago
You've moved goalposts from "they haven't open-sourced the process" to "these are marketing materials by Anthropic".

I think you're right to be skeptical, but they _have_ talked about the process publicly.

And I don't think there's anything there that is not reproducible by outsiders? They have access to the same Opus 4.6 that you and I do; though not having to pay for the tokens certainly helps.

I'm pretty sure if you wanted to burn a couple thousand bucks, you'd reproduce at least some of these findings.

link
amazingamazing 61 days ago
The goal post is the same, reproducible. Talking about a process isn’t reproducible. This entire discussion is why I feel developers are so gullible. You are defending a process that’s entirely opaque and you can’t even use. It’s crazy.
link
aftbit 61 days ago
What's the CVE for the 27-yr-old 0-day in OpenBSD?
link
ViewTrick1002 60 days ago
Depends on the impact? CVE scores are known to be a worthless metric when looking at the actual impact.

Linux now labels every single bug as a CVE.

link
jdironman 60 days ago
I think they mean what is the actual vulnerability and not the score.
link