Re:ARC-AGI without pretraining
by exe34 on Tuesday March 04, 2025 @05:25PM
(#43260468)
"true generalisation" isn't really something a lot of humans can do.
[ Parent
| on HN ]
the thing is LLMs don't even do the kind of generalisations the dumbest human can do.
while simultaneously doing some stuff the smartest human probably can't
Re:ARC-AGI without pretraining
by kaptainkarl on Tuesday March 04, 2025 @06:59PM
(#43261058)
Describes computers in general pretty well
Moravec talked about this kind of thing in the '80s.
I’m interested to know more? Any specifics, or just look it up?
just check moravec paradox: https://en.wikipedia.org/wiki/Moravec's_paradox
Thank you.
> humans CAN do.
I think people often get confused with claims - Humans CAN generalize
- Humans CAN reason
- Humans CAN be intelligent
- Humans CAN be conscious
Generalization[0] is something MOST humans CAN do, but MOST humans DO NOT do. Do not confuse "can" and "are".One of my pet peeves is how often qualifying words are just ignored. They are critical parts of any communication.[1]
Another pet peeve is over anthropomorphization. Anthropomorphism is a useful tool, but.. well... we CAN over generalize ;)
[0] I don't know what you mean by "true generalization". I'm not going to address that because you can always raise the bar for what is "true" and let's try to be more concrete. Maybe I misunderstand. I definitely misunderstand.
[1] Classic example: someone says "most x are y" then there's a rebuttal of "but x_1 isn't y" or "I'm x and I'm not y" or some variation. Great! Most isn't all? This is not engaging in good faith and there's examples found with any qualifying word. It is quite common to see.
i feel like you're overgeneralizing here