eicker@lemmy.world to Technology@lemmy.worldEnglish · 8 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-square16linkfedilinkarrow-up1125arrow-down14
arrow-up1121arrow-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 · 8 hours agomessage-square16linkfedilink
minus-squareStrider@lemmy.worldlinkfedilinkEnglisharrow-up5·6 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-up4·6 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-squareFiery@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up2·5 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.
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)