2026-05-05 05:24 UTC
Replies (7)
-
@madduci@mastodon.social 2026-05-05 05:30
@malwaretech impressive work, but isn't this kind of corner stone for a new crop of "script kiddies" that might replicate your work and use it fo r bad purposes?
-
@hsza@social.tudbut.de 2026-05-05 05:34
@NosirrahSec @malwaretech I assume that comment means to imply if you’re entering slopsychosis publicising that fact doesn’t do you any favors Unfortunate to find an unironic sloperator in my follows
-
@jab01701mid@mastodon.social 2026-05-05 05:34
@malwaretech The only thing more evil would be Elon Musk posting this here.
-
@themipper@mastodon.social 2026-05-05 06:23
@malwaretech this was an informative video. Thanks for being honest about the costs both in tokens and experience needed to get anywhere with the LLM. You mentioned "fuzzers?" in your video. I assume there are other automated tools that the vulnerability research community is using Today. How do they compare to the LLM pipeline in terms of outcomes, potential and costs? Disclaimer: I am no fan of LLMs but I am always a fan of understanding what is true and what is fiction/marketing.
-
@bobdobberson@kolektiva.social 2026-05-05 07:22
@malwaretech out of curiosity, wouldn't it have been efficient / effective to craft your prompt using a known and blacklisted vulnerable driver? That seems like that might have saved some tokens.
-
@disco3000@climatejustice.social 2026-05-05 10:41
@malwaretech and while doing this I found time hold my chin in an awkward way 😆
-
@technicaladept@techhub.social 2026-05-05 10:56
@malwaretech I was very interested in the part you described as "skipping a step" where the AI found a perfect vuln and you ran with it. But on reflection it found a shortlist and it was your skills in reviewing the shortlist that found the perfect vuln. Reminds me of how people reviewing a cold reading session recalled the accurate information the fake psychic had delivered but were then shown where in the transcript that information was first mentioned and realised that the techniques simply gave them a framework to supply information that the coldreader could then claim credit for knowing.