[joe_the_user]

Any attention on Moravec's paradox is good imo because it is important.

That said, the article starts with several problems.

1) Claims that it isn't a paradox, which is just silly. A paradox is a counter-intuitive result. The result is generally counter-intuitive whatever explanation you give. Zeno's paradox remains a paradox despite calculus essentially explaining it, etc.

2) Calls the article "Understanding Moravec's Paradox" when it should be called "My Explanation of Moravec's Paradox".

3) The author's final explanation seems kind of simplistic; "Human activities just have a large search space". IDK. Human activity sometimes does still in things that aren't walking also. I mean, "not enough data" is an explanation why neural networks can't do a bunch of things. But not all programs are neural networks. One of the things humans are really good at is learning things from a few examples. A serious explanation of Moravec's Paradox would have to explain this as well imo.

[neerajsi]

> mean, "not enough data" is an explanation why neural networks can't do a bunch of things... One of the things humans are really good at is learning things from a few examples

I dispute the search space problem for something like folding clothes. Like a lot of human actions in space, folding clothes and other motor tasks are hierarchical sequences of smaller tasks that are strung together, similar to a sentence or paragraph of text.

We can probably learn things from each other from few examples because we are leaning on a large library of subtasks that all have learned or which are innate, and the actual novel learning of sequencing and ordering is relatively small to get to the new reward.

I expect soon we'll get AIs that have part of their training be unsupervised rl in a physics simulation, if it's not being done already.

[hexhowells]

> Like a lot of human actions in space, folding clothes and other motor tasks are hierarchical sequences of smaller tasks that are strung together

I disagree, you can model those tasks as hiearchical sequences of smaller tasks. But the terminal goal of folding clothes is to turn a pile of unfolded clothes into a neat pile of folded clothes.

The reason you would break down the task is because getting between those two states with the only reward signal being "the clothes are now folded" takes a lot of steps, and given the possible actions the robot can take, results in a large search space.

[hexhowells]

The human ability to learn from few examples can be explained with evolution (and thus search). We evolved to be fast learners as it was key to our survival. If you touched fire and felt pain, you better learn quickly not to keep touching it. This learning from reward signals (neurotransmitters) in our brain generalises to pretty much all learning tasks

[joe_the_user]

Everything can "be explained by evolution" but such an explanation doesn't tell you how a particular form serves a particular task.

[famouswaffles]

The point is that to be good at 'learning from a few examples', the architecture of the human brain had to be constructed from a enormous amount of trial and error data. This is not something you can just brush off or ignore. 'not enough data' is a perfectly valid for a 'serious' explanation.

[cwmoore]

Indeed, also ideally, the 2 second rule.