Ilya Sutskever: evaluation

Transcript context

…What is your opinion of your former advisor’s new forward forward algorithm? I think that it's an attempt to train a neural network without backpropagation. And that this is especially interesting if you are motivated to try to understand how the brain might be learning its connections. The reason for that is that, as far as I know, neuroscientists are really convinced that the brain cannot implement backpropagation because the signals in the synapses only move in one direction. And so if you have a neuroscience motivation, and you want to say — okay, how can I come up with something that tries to approximate the good properties of backpropagation without doing backpropagation? That's what the forward forward algorithm is trying to do. But if you are trying to just engineer a good system there is no reason to not use backpropagation. It's the only algorithm. I guess I've heard you in different contexts talk about using humans as the existing example case that AGI exists. At what point do you take the metaphor less seriously and don't feel the need to pursue it in terms of the research? Because it is important to you as a sort of existence case.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.