‹ BackHN Continuity

Thread

Security auditing in the age of (good enough) AI

96 points · 16 comments · aray07

  1. Segv77 · · focus · HN ↗
    Good enough AI for security auditing feels like asking for "good enough" brakes. There's just no room for complacency.
    1. fovc · · focus · HN ↗
      Not sure I follow the analogy, so apologies if I'm reading it backwards, but we do in fact have standards for "good enough" brakes without being brake-maxxers.

      Similarly here, I'd argue that a verified implementation with correctness proofs, mechanical translation, and easily auditable theorems seems close to good enough? A lot rides on the Claude-built translator, I suppose, but the trusted code for that project seems to be tiny in comparison to what it would have been 2 years ago!

      1. jessebldr · · focus · HN ↗

        [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.