Thread

1. wslh · 1789648828 · focus · HN ↗

   Tip for security professionals using LLMs: audit skills that explicitly frame the task as security research sometimes trigger refusals from the top OpenAI and Anthropic models because they guard against misuse. What works for me: separate skills for bug classes (and bugs in general) without the security framing, plus another skill that combines their findings to spot security bugs.

   1. viraptor · 1789651890 · focus · HN ↗

      If you're a security professional, go through their validation. You won't get the security refusals anymore. Well... you'll still get the occasional downgrade from Fable, but not the "oh no, I can't do exploits for you" breaks.

      1. xur17 · 1789657949 · focus · HN ↗

         Except their validation doesn't seem to work. I've gone through both (both personally and for my company), and.. no response for weeks.

         1. viraptor · 1789726810 · focus · HN ↗

            Weird. I have minimal publicly visible record of security work and got the approval almost immediately.

Unofficial Hacker News client; not affiliated with Y Combinator.