photonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 5 months agoOutcry from big AI firms over California AI “kill switch” billarstechnica.comexternal-linkmessage-square65fedilinkarrow-up1353cross-posted to: artificial_intel@lemmy.ml
arrow-up1353external-linkOutcry from big AI firms over California AI “kill switch” billarstechnica.comphotonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 5 months agomessage-square65fedilinkcross-posted to: artificial_intel@lemmy.ml
minus-squarenifty@lemmy.worldlinkfedilinkEnglisharrow-up13·5 months agoSmall problem though: researchers have already found ways to circumvent LLM off-limit queries. I am not sure how you can prevent someone from asking the “wrong” question. It makes more sense for security practices to be hardened and made more robust
Small problem though: researchers have already found ways to circumvent LLM off-limit queries. I am not sure how you can prevent someone from asking the “wrong” question. It makes more sense for security practices to be hardened and made more robust