News for hackers. Stuff that matters.
Re:ARC-AGI without pretraining by tripplyons on Tuesday March 04, 2025 @04:06PM (#43259806)
I'm not at all experienced in neuroscience, but I think that humans and other animals primarily gain intelligence by learning from their sensory input.
Re:ARC-AGI without pretraining by FergusArgyll on Tuesday March 04, 2025 @04:19PM (#43259895)
You don't think a lot is encoded in genes from before we're born?
Re:ARC-AGI without pretraining by aaronblohowiak on Tuesday March 04, 2025 @04:38PM (#43260055)
>a lot

this is pretty vague. I certainly dont think a mastery of any concept invented in last thousand years would be considered encoded in genes though we would want or expect an AGI to be able to learn calculus for instance. In terms of "encoded in genes", I'd say most of what is asked or expected of AGI goes beyond what feral children (https://en.wikipedia.org/wiki/Feral_child) were able to demonstrate.

Re:ARC-AGI without pretraining by tripplyons on Tuesday March 04, 2025 @09:29PM (#43261891)
I don't disagree, but I think there is much more information encoded in the brain. I believe this phenomenon is called the genomic bottleneck.

There are a few orders of magnitude more neural connections in a human than there are base pairs in a human genome. I would also assume that there are more than 4 possible ways for neural connections to be formed, while there are only 4 possible base pairs. Also, most genetic information corresponds to lower level functions.