eicker to News · 8 hours 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-square22linkfedilinkarrow-up1123arrow-down111
arrow-up1112arrow-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 to News · 8 hours agomessage-square22linkfedilink
minus-squareAkasazhlinkfedilinkEnglisharrow-up13·4 hours 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-squareSternlinkfedilinkarrow-up3·3 hours 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.
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.