Sam_Bass@lemmy.world to Technology@lemmy.worldEnglish · 3 days agoAn AI couldn’t beat humans at StarCraft, so it decided to cheatwww.theverge.comexternal-linkmessage-square85linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkAn AI couldn’t beat humans at StarCraft, so it decided to cheatwww.theverge.comSam_Bass@lemmy.world to Technology@lemmy.worldEnglish · 3 days agomessage-square85linkfedilink
minus-squareKirp123@lemmy.worldlinkfedilinkEnglisharrow-up0·3 days agoThe worst part is not the AI, it’s the people blindly following its instructions.
minus-squareSeralth@piefed.seralth.comlinkfedilinkEnglisharrow-up0·3 days agoBlindly following them while also telling the model to never question them. It creates stupidity feedback loops.
minus-squareabbadon420@sh.itjust.workslinkfedilinkEnglisharrow-up0·3 days agoYes that too, but when you’re dealing with “agent swarms” it’s those agents who are blindly following those instructions. Like the recent hugging face hack demonstrated.
The worst part is not the AI, it’s the people blindly following its instructions.
Blindly following them while also telling the model to never question them. It creates stupidity feedback loops.
Yes that too, but when you’re dealing with “agent swarms” it’s those agents who are blindly following those instructions. Like the recent hugging face hack demonstrated.