photonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 24 days agoOutcry from big AI firms over California AI “kill switch” billarstechnica.comexternal-linkmessage-square96fedilinkarrow-up1147arrow-down14cross-posted to: [email protected]
arrow-up1143arrow-down1external-linkOutcry from big AI firms over California AI “kill switch” billarstechnica.comphotonic_sorcerer@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 24 days agomessage-square96fedilinkcross-posted to: [email protected]
minus-squarenifty@lemmy.worldlinkfedilinkEnglisharrow-up11arrow-down1·23 days 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