Andrej Karpathy

is incredibly hard.

Those people are more likely to cheerlead you.

Yes.

Yeah, I think it's really hard to work on robotics in an academic setting.

Actually, I don't know that I recall the specific instance where I was unhappy or criticizing ImageNet.

I think ImageNet has been extremely valuable.

It was basically a benchmark that allowed the deep learning community to demonstrate that deep neural networks actually work.

It was...

there's a massive value in that.

So I think ImageNet was useful, but basically it's become a bit of an MNIST at this point.

So MNIST is like little 28 by 28 grayscale digits.

There's kind of a joke data set that everyone like just crushes.

Yeah, I could see that being helpful, but not in sort of like mainline computer vision research anymore, of course.

I mean, you know, the error rates are...

Yeah, we're getting like 90% accuracy in 1,000 classification way prediction.

And I've seen those images and it's like really high.

That's really good.

If I remember correctly, the top five error rate is now like 1% or something.

Unfortunately, I don't think academics currently have the next ImageNet.

We've obviously... I think we've crushed MNIST.