[silverlake]

I’m actually working on just this. What’s the smallest training data set required to learn tic-tac-toe? A 5yo doesn’t need much training to learn a new game, but a transformer needs millions of samples.

[rkomorn]

> A 5yo doesn’t need much training to learn a new game

A 5yo also has... 5 years of cumulative real world training. I'm a bit of an AI naysayer but I'd say the comparison doesn't seem quite accurate.

[silverlake]

It’s a glib analogy, but the goal remains the same. Today’s training sets are immense. Is there an architecture that can learn something with tiny training sets?

[Daltonagray]

This sounds super interesting. Will you be sharing your work anywhere? :)