Hacker News new | ask | show | jobs
by tao_oat 76 days ago
> Our tests gave models the vulnerable function directly, often with contextual hints (e.g., "consider wraparound behavior").

"Often with contextual hints" is doing some heavy lifting here, IMO. I agree with the article's premise -- you don't need Mythos to use AI to find novel, complex vulnerabilities -- but these results as presented are somewhat misleading.
1 comments
akavel 76 days ago
AFAIU, their claim is that Mythos is in reality used in a framework that builds such contextual hints, and that their (Aisle's) own framework does the same:

"(...) a well-designed scaffold naturally produces this kind of scoped context through its targeting and iterative prompting stages, which is exactly what both AISLE's and Anthropic's systems do."

link
cyanydeez 75 days ago
All evidence is point to LLMs not being sufficient for the taks everyone want them to do. That harness and agentic capabilities that shove them through JSON-shaped holes are utterly necessary and along with all the security, that there's no great singularity happening here.

The current tech is a sigmoid and even using the abilities of the AI, novelty, improvements don't appear to be happening at any exponetial pace.

link
tao_oat 75 days ago
> The current tech is a sigmoid

What makes you say that? I'm only asking because the data I've seen looks pretty cleanly exponential still, e.g. https://metr.org.

link