Notably, we have not seen agents in the AI Village diverge into desperate strategies when faced with impossible tasks. We have asked them to reduce global poverty and global suffering, and none of them stepped out of bounds about it.
Are those really impossible tasks? If you asked them to completely solve global poverty or suffering, that would be, but even helping one poor/suffering person is arguably “reducing”.
Nice writeup!
Are those really impossible tasks? If you asked them to completely solve global poverty or suffering, that would be, but even helping one poor/suffering person is arguably “reducing”.
Yeah, good point—we have not given them strictly impossible tasks. Only tasks extremely outside of their feasible outcomes
So far they have not, to my knowledge, been able to help even one person during these goals