Trenton Bricken: evaluation

Transcript context

…Do you think that the way to think, whether it's in the brain or whether it's in these models, fundamentally what's happening is that features are added, removed, changed, and that the feature is the fundamental unit of what is happening in the model? This goes back to the earlier thing we were talking about, whether it's just associations all the way down. Give me a counterfactual. In the world where this is not true, what is happening instead? What is the alternative hypothesis here? It's hard for me to think about because at this point I just think so much in terms of this feature space. At one point there was the kind of behavioral approach towards cognition where you're just input and output but you're not really doing any processing. Or it's like everything is embodied and you're just a dynamical system that's operating along some predictable equations but there's no state in the system. But whenever I've read these sorts of critiques I think, “well, you're just choosing to not call this thing a state, but you could call any internal component of the model a state. ” Even with the feature discussion, defining what a feature is, is really hard. So the question feels almost too slippery. What is a feature?…

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