1 points | by nowflux 4 hours ago ago
2 comments
> Top 10%: 4/7 correct
I guess I'm human.
I expected a mix of false fact, so people has to reason from the facts in the screen and not from the their real world opinion. I'm not sure if that will be harder for humans or for AI.
The questions are much improved, but there is another issue I didn't think about: I got ChatGPT to correctly solve the coin in pockets puzzle.
There may be a near complete overlap with AIs and (reasonably) smart users here.
> Top 10%: 4/7 correct
I guess I'm human.
I expected a mix of false fact, so people has to reason from the facts in the screen and not from the their real world opinion. I'm not sure if that will be harder for humans or for AI.
The questions are much improved, but there is another issue I didn't think about: I got ChatGPT to correctly solve the coin in pockets puzzle.
There may be a near complete overlap with AIs and (reasonably) smart users here.