Espiritdescali@futurology.todayM to Futurology@futurology.todayEnglish · 1 month agoAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.comexternal-linkmessage-square10fedilinkarrow-up125cross-posted to: hackernews@lemmy.bestiver.setechnology@lemmy.ziptechnology@lemmy.ml
arrow-up125external-linkAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.comEspiritdescali@futurology.todayM to Futurology@futurology.todayEnglish · 1 month agomessage-square10fedilinkcross-posted to: hackernews@lemmy.bestiver.setechnology@lemmy.ziptechnology@lemmy.ml
minus-squareadeoxymus@lemmy.worldlinkfedilinkEnglisharrow-up2·1 month agoThat exact prompt isn’t in the report, but the section before (4.1.1.1) does show a flavor of the prompts used https://www-cdn.anthropic.com/4263b940cabb546aa0e3283f35b686f4f3b2ff47.pdf
That exact prompt isn’t in the report, but the section before (4.1.1.1) does show a flavor of the prompts used https://www-cdn.anthropic.com/4263b940cabb546aa0e3283f35b686f4f3b2ff47.pdf