Beep@lemmus.orgBanned to Technology@lemmy.worldEnglish · edit-25 个月前Hardening Firefox with Anthropic’s Red Teamblog.mozilla.orgexternal-linkmessage-square9linkfedilinkarrow-up172arrow-down113file-textcross-posted to: firefox@lemmy.ml
arrow-up159arrow-down1external-linkHardening Firefox with Anthropic’s Red Teamblog.mozilla.orgBeep@lemmus.orgBanned to Technology@lemmy.worldEnglish · edit-25 个月前message-square9linkfedilinkfile-textcross-posted to: firefox@lemmy.ml
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up3arrow-down1·5 个月前That’s…exactly my point though…
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up4arrow-down1·5 个月前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-up1arrow-down1·5 个月前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-up5arrow-down1·5 个月前Do you somehow not? Open source projects have been running out of resources because they’re overwhelmed with bogus bug reports filed by AI.
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.