News for hackers. Stuff that matters.

A comment on Show HN: ARC Prize – a $1M+ competition towards open AGI progress. Parent comment

Re:Show HN: ARC Prize – a $1M+ competition towards open AGI ... by pants2 on Tuesday June 11, 2024 @07:38PM (#40652922)
Humans, I would bet, could distinguish between two animals they've never seen based only on a loose or tangential description. I.e. "A dog hunts animals by tracking and chasing them long enough to exhaust their energy, but a cat is opportunistic and strikes using stealth and agility."

A human that has never seen a dog or a cat could probably determine which is which based on looking at the two animals and their adaptations. This would be an interesting test for AIs, but I'm not quite sure how one would formulate a eval for this.

[ Parent | on HN ]
Re:Show HN: ARC Prize – a $1M+ competition towards open AGI ... by ryankrage77 on Tuesday June 11, 2024 @08:12PM (#40653134)
A possible way to this idea would be to draw two aliens with different hunting strategies and do a poll of which is which. I'd try it but my drawing skills are terrible and I'm averse to using generated images.
[ Parent | on HN ]
Re:Show HN: ARC Prize – a $1M+ competition towards open AGI ... by taneq on Tuesday June 11, 2024 @09:19PM (#40653504)
Only after being exposed to (at least pictures and descriptions of) dozens if not hundreds of different types of animal and their different attributes. Literal decades of training time and carefully curated curriculum learning are required for a human to perform at what we consider ‘human level’.
[ Parent | on HN ]
Re:Show HN: ARC Prize – a $1M+ competition towards open AGI ... by tigerlily on Wednesday June 12, 2024 @06:56AM (#40656640)
Seems analogous to bouba/kiki effect:

https://en.m.wikipedia.org/wiki/Bouba/kiki_effect

[ Parent | on HN ]