Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB
by danenania on Saturday December 21, 2024 @07:16AM
(#42479241)
I’d say that while a full basketball game is a lot more complex, it’s made up of a lot of component tasks that still have objective success criteria: dribbling, passing, setting picks, doing your part in a play, etc. Ultimately your team either scores or it doesn’t.
Not to say it isn’t difficult, but I don’t think humans are doing anything particularly magical when they learn to play basketball—something I did myself when I was a kid. You learn each skill from a coach’s demonstration, practice them all a lot (practice = trial and error) and develop an intuition (reasoning) about what do to in various situations.
You just said what there is to judge in one specific scenario, a general AI has to make the decision to judge itself that way which is not objective, it is extremely hard to decide what to judge yourself by in a generic situation.
For example, lets say you are in a basketball court, with a basketball. What is a good outcome? Is it shooting the ball in the hoop? But maybe it isn't your turn, someone else is shooting now, then shooting at the hoop is a bad outcome, how do you make the AI recognize that instead of mindlessly trying to make the ball go in the hoop without considering the context?