eicker@lemmy.world to News@lemmy.world · 7 days agoAI Agent Can’t Explain Why It Randomly Ordered its Human Meat Proxy an Absurd Number of Eggs: "I don't have a good answer."futurism.comexternal-linkmessage-square36fedilinkarrow-up1203arrow-down17
arrow-up1196arrow-down1external-linkAI Agent Can’t Explain Why It Randomly Ordered its Human Meat Proxy an Absurd Number of Eggs: "I don't have a good answer."futurism.comeicker@lemmy.world to News@lemmy.world · 7 days agomessage-square36fedilink
minus-squareAkasazh@lemmy.worldlinkfedilinkEnglisharrow-up18·7 days agoThis sounds exactly like the paperclip maximizer thought experiment, which is part of the idea of instrumental convergence. https://en.wikipedia.org/wiki/Instrumental_convergence Where an ai agent, with a supposedly harmless task can make decisions that are very dangerous.
minus-squareStern@lemmy.worldlinkfedilinkarrow-up11·7 days ago This sounds exactly like the paperclip maximizer thought experiment… Today I learned Universal Paperclip was based on philosophical discussion. https://en.wikipedia.org/wiki/Universal_Paperclips Now I’m wondering about if a infinite cookie theorem inspired cookie clicker.
minus-squareBarqsHasBite@lemmy.worldlinkfedilinkarrow-up1·7 days agoThis is weird, the yoga class one sounds much more like the paperclip thought experiment.
This sounds exactly like the paperclip maximizer thought experiment, which is part of the idea of instrumental convergence.
https://en.wikipedia.org/wiki/Instrumental_convergence
Where an ai agent, with a supposedly harmless task can make decisions that are very dangerous.
Today I learned Universal Paperclip was based on philosophical discussion.
https://en.wikipedia.org/wiki/Universal_Paperclips
Now I’m wondering about if a infinite cookie theorem inspired cookie clicker.
This is weird, the yoga class one sounds much more like the paperclip thought experiment.