Beep@lemmus.org to Technology@lemmy.worldEnglish · edit-28か月前Hardening Firefox with Anthropic’s Red Teamblog.mozilla.orgexternal-linkmessage-square9fedilinkarrow-up175file-textcross-posted to: firefox@fedia.iofirefox@fedia.iolobsters@lemmy.bestiver.se
arrow-up175external-linkHardening Firefox with Anthropic’s Red Teamblog.mozilla.orgBeep@lemmus.org to Technology@lemmy.worldEnglish · edit-28か月前message-square9fedilinkfile-textcross-posted to: firefox@fedia.iofirefox@fedia.iolobsters@lemmy.bestiver.se
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up10·8か月前Yeah 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.
minus-squarelIlIlIlIlIlIl@lemmy.worldlinkfedilinkEnglisharrow-up1·8か月前Hallucinated? From researched and documented code spelunking?
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up3·8か月前That’s…exactly my point though…
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up4·8か月前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.
minus-squarelIlIlIlIlIlIl@lemmy.worldlinkfedilinkEnglisharrow-up1·8か月前I guess I’m not sure how hallucinating and reading from source code are overlapping. Do you think these models are just barfing back garbage nonsense?
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up5·8か月前Do you somehow not? Open source projects have been running out of resources because they’re overwhelmed with bogus bug reports filed by AI.
Yeah 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.
Hallucinated? From researched and documented code spelunking?
That’s…exactly my point though…
What is?
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.
I guess I’m not sure how hallucinating and reading from source code are overlapping. Do you think these models are just barfing back garbage nonsense?
Do you somehow not? Open source projects have been running out of resources because they’re overwhelmed with bogus bug reports filed by AI.