Comment on Hardening Firefox with Anthropic’s Red Team
PabloSexcrowbar@piefed.social 1 month agoYeah I’m actually kinda into this. Even if the AI vomits up a bunch of hallucinated vulnerabilities, there’s a team of (presumably) capable people there to figure that out. Seems like a pretty valid use for the technology.
lIlIlIlIlIlIl@lemmy.world 1 month ago
Hallucinated? From researched and documented code spelunking?
PabloSexcrowbar@piefed.social 1 month ago
That’s…exactly my point though…
lIlIlIlIlIlIl@lemmy.world 1 month ago
What is?
PabloSexcrowbar@piefed.social 1 month ago
That even though the team is using AI to check for vulnerabilities, they’re trained and know when their AI is hallucinating and when it’s not.