On: Extracting training data from diffusion models

[lajamerr]

I wouldn't necessarily say it learns how a human would. But instead learns how an arbitrary brain would.

There's all kinds of brains in this world from all kinds of life. A dog can learn. A cat can learn. And they don't learn like a human would.

[toss1 → lajamerr]

>>A dog can learn. A cat can learn. And they don't learn like a human would.

Yes, but they learn a LOT MORE like a human would vs these machine models. Cats & dogs share the same underlying structure, from the neuron/synapse/neurotransmitter system, up to the brainstem/cerebellum/midbrain/cerebrum architecture, as well as being inextricably integrated into a living body and sensory system, and growth pattern.

And, as you say, there are big differences in how we all learn. But those differences are utterly trivial compared to the differences between humans and ML.