beep@piefed.world to Technology@lemmy.worldEnglish · 13 hours agoAn AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattackswww.security.comexternal-linkmessage-square5linkfedilinkarrow-up154arrow-down15file-text
arrow-up149arrow-down1external-linkAn AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattackswww.security.combeep@piefed.world to Technology@lemmy.worldEnglish · 13 hours agomessage-square5linkfedilinkfile-text
cross-posted from: https://piefed.world/c/tech/p/1487348/an-ai-agent-in-skynet-mode-hijacks-unprotected-language-models-to-launch-self-sustaining
minus-squaret҉̠̙ǵ̣̞̄ͪ͜x̸̱͚̳ͫ͐̑̈ͯͣ̚n̒͌҉͉̦̜̝ͅAlinkfedilinkEnglisharrow-up1·1 hour agomost people just don’t understand how this shit works. saying model rather that “unprotected LLM api endpoints” is easier to digest. in fact, it says exactly that in the key findings of the article!
most people just don’t understand how this shit works. saying model rather that “unprotected LLM api endpoints” is easier to digest.
in fact, it says exactly that in the key findings of the article!