@[email protected] to [email protected]English • 6 months agoOutcry from big AI firms over California AI “kill switch” billarstechnica.commessage-square87fedilinkarrow-up1365
arrow-up1365external-linkOutcry from big AI firms over California AI “kill switch” billarstechnica.com@[email protected] to [email protected]English • 6 months agomessage-square87fedilink
minus-squareniftylinkfedilinkEnglish14•6 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