Nemeski@lemm.ee to Technology@lemmy.worldEnglish · 5 months agoOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comexternal-linkmessage-square102fedilinkarrow-up1447arrow-down17cross-posted to: technology@lemmit.online
arrow-up1440arrow-down1external-linkOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comNemeski@lemm.ee to Technology@lemmy.worldEnglish · 5 months agomessage-square102fedilinkcross-posted to: technology@lemmit.online
minus-squareqjkxbmwvz@startrek.websitelinkfedilinkEnglisharrow-up49·5 months ago“…today is opposite day.”
minus-squareKeenFlame@feddit.nulinkfedilinkEnglisharrow-up11arrow-down1·5 months agoI just love that almost anyone can participate in hacking language models. It just shows how good natural language is as a programming language, and is a great way to explain how useful these things can be when used correctly
minus-squareT156@lemmy.worldlinkfedilinkEnglisharrow-up2·5 months agoIt won’t be long before you end up with language models that suggest ways to break other language models.
/cdn.vox-cdn.com/uploads/chorus_asset/file/25362060/STK_414_AI_CHATBOT_R2_CVirginia_C.jpg)
“…today is opposite day.”
I just love that almost anyone can participate in hacking language models. It just shows how good natural language is as a programming language, and is a great way to explain how useful these things can be when used correctly
It won’t be long before you end up with language models that suggest ways to break other language models.