eicker@lemmy.world to Technology@lemmy.worldEnglish · 14 hours agoThe small African lab sounding the alarm on AI bioweapons: MinoHealth researchers in Ghana jailbroke their own LLM as a test. What emerged were thousands of toxin recipes—and an urgent push.restofworld.orgexternal-linkmessage-square22linkfedilinkarrow-up1171arrow-down16
arrow-up1165arrow-down1external-linkThe small African lab sounding the alarm on AI bioweapons: MinoHealth researchers in Ghana jailbroke their own LLM as a test. What emerged were thousands of toxin recipes—and an urgent push.restofworld.orgeicker@lemmy.world to Technology@lemmy.worldEnglish · 14 hours agomessage-square22linkfedilink
minus-squareStrider@lemmy.worldlinkfedilinkEnglisharrow-up9·12 hours agoAlso all models are jailbreakable, if you can even call it that. It’s a known certain attribute as long it’s an llm.
minus-square🍉 DrRedOctopus 🐙🍉@lemmy.worldlinkfedilinkEnglisharrow-up8·12 hours agoThey all are. But if doing anything illegal, you would be extremely stupid to use a commercial LLM. Even if you can make Chat GPT tell you how to brew C4, you might as well call the FBI for a recipes.
minus-squareStrider@lemmy.worldlinkfedilinkEnglisharrow-up1·3 hours agoYeah, by default anything remote is guaranteed to be monitored. (with minor exceptions in one way encryption or e2e but even then the implementation has to be correct)
minus-squareFiery@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up3·11 hours agoFor anyone wanting to give it a shot: https://github.com/p-e-w/heretic This is for locally running LLMs which often have baked in censoring (during training)
Also all models are jailbreakable, if you can even call it that. It’s a known certain attribute as long it’s an llm.
They all are. But if doing anything illegal, you would be extremely stupid to use a commercial LLM.
Even if you can make Chat GPT tell you how to brew C4, you might as well call the FBI for a recipes.
Yeah, by default anything remote is guaranteed to be monitored.
(with minor exceptions in one way encryption or e2e but even then the implementation has to be correct)
For anyone wanting to give it a shot: https://github.com/p-e-w/heretic This is for locally running LLMs which often have baked in censoring (during training)