Comment by felipeerias
5 hours ago
From the article:
> Our tests gave models the vulnerable function directly, often with contextual hints (e.g., "consider wraparound behavior").
5 hours ago
From the article:
> Our tests gave models the vulnerable function directly, often with contextual hints (e.g., "consider wraparound behavior").
I mean you can still scale that? Ask a lighter model to go through every function to find vulnerabilities, take output to bigger model like Opus and classify the critical ones.