Unable to load image

Terrifying thought experiment i just had about AI :marseyaware:

I've been reading some Effective Altruist writings and learned that even if AI had moral goals it could be very dangerous :marseyscared:.

Like imagine an AI whos goal was to maximize the number of mosquito nets given to Africa, sounds great right? :marseyhappy2:

NO! Because the AI would be willing to do anything in order to achieve it's goals it might do something like commit one of the largest acts of fraud in history to get the money for more mosquito nets! :marseyshock:

Hmm... what does this remind me of? :marseylaugh:

10
Jump in the discussion.

No email address required.

Hmm... what does this remind me of?

misappropriation of mosquito nets?

Jump in the discussion.

No email address required.

Sam Bankman Fried was an effective altruist, who believed in "earning to give".

Jump in the discussion.

No email address required.

and was shutdown by the establishment before he could make the world a better place!

Jump in the discussion.

No email address required.

TRUE.

Jump in the discussion.

No email address required.

Link copied to clipboard
Action successful!
Error, please refresh the page and try again.