@[email protected] to TechnologyEnglish • 8 months agoOutcry from big AI firms over California AI “kill switch” billarstechnica.comexternal-linkmessage-square114fedilinkarrow-up1369arrow-down18cross-posted to: [email protected]
arrow-up1361arrow-down1external-linkOutcry from big AI firms over California AI “kill switch” billarstechnica.com@[email protected] to TechnologyEnglish • 8 months agomessage-square114fedilinkcross-posted to: [email protected]
minus-squareniftylinkEnglish13•8 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