What's special about a fantastic outcome? Suggestions wanted.

Stuart_Armstrong

I've been returning to my "reduced impact AI" approach, and currently working on some idea.

What I need is some ideas on features that might distinguish between an excellent FAI outcome, and a disaster. The more abstract and general the ideas, the better. Anyone got some suggestions? Don't worry about quality at this point, originality is more prized!

I'm looking for something generic that is easy to measure. At a crude level, if the only options were "papercliper" vs FAI, then we could distinguish those worlds by counting steel content.

So basically some more or less objective measure that has a higher proportion of good outcomes than the baseline.

I've been returning to my "reduced impact AI" approach, and currently working on some idea.

I'm looking for something generic that is easy to measure. At a crude level, if the only options were "papercliper" vs FAI, then we could distinguish those worlds by counting steel content.

So basically some more or less objective measure that has a higher proportion of good outcomes than the baseline.

I'm looking for something generic that is easy to measure. At a crude level, if the only option were "papercliper" vs FAI, then we could distinguish those worlds by counting steel content.

So basically some more or less objective measure that has a higher proportion of good outcomes than the baseline.

If you're planning to simulate an AI in a universe in a box and examine whether the produced universe is good via some process that doesn't allow the AI to talk to you, the AI is just gonna figure out it's being simulated and pretend to be an FAI (Note that an AI that pretends to be an FAI maximizes not for friendliness, but for apparent friendliness, so this is no pathway to FAI) so you'll let it loose on the real world.

To the first approximation, having a box that contains an AI anywhere in it output even a few bits of info tends to choose those bits tha... (read more)

2Eliezer Yudkowsky12y

Merely higher proportion, and we're not worried about the criterion being reverse-engineered? Give a memory expert a large prime number to memorize and talk about outcomes where it's possible to factor a large composite number that has that prime as a factor. Happy outcomes will have that memory expert still be around in some form. EDIT: No, I take that back because quantum. Some repaired version of the general idea might still work, though.

1Leonhart12y

Smiles, laughter, hugging, the humming or whistling of melodies in a major key, skipping, high-fiving and/or brofisting, loud utterance of "Huzzah" or "Best thing EVER!!!", airborne nanoparticles of cake, streamers, balloons, accordion music? On the assumption that the AI was not explicitly asked to produce these things, of course.