@freddy@social.security.plumbing
Post #1671863
2026-04-13 19:55 UTC
@gabrielesvelto @hsivonen not really. Some bugs are truly hard to find with fuzzing and are more easily identified by seeing codesmell and trying to trace it back to user. Reading and remembering code is limited by brain power / will power. As sad as it is: LLMs scale better here.
Replies (1)
-
@hsivonen@mastodon.social 2026-04-13 20:08
@freddy @gabrielesvelto Also, it looks to me that fuzzing requires more human setup of what part of code to fuzz and how to deal with stuff like checksums whereas reportedly LLMs can deal with less specific harnesses and figure out how to fill in checksums.