Pedro Domingos: commitment

Transcript context

…Very good. And and by the way, you can implement transformers and anything else in tensor logic. It's so easy in fact that I fed your paper into Claude code and I got it to implement the whole lot this afternoon and maybe I'll publish that on GitHub if folks wanna have a look. But it it it's quite straightforward. But just to get the trajectory a little bit here, Pedro, you're famous for writing this master algorithm book and in that book you spoke about all of these different tribes of machine learning, you know, like Bayesian folks and logic folks and kernel methods and neural networks and and all of this. And I guess, do you see this as as a step towards unifying these things together? Because now in tensor logic, you can actually create a composition of different modalities of AI and and it just works. But this might seem a bit weird to people. I mean, you explain what that might actually look like? Absolutely. So in a way the master algorithm was laying out my agenda, right, was asking the question what is the master algorithm. I did say at the outset, I'm not gonna give you the master algorithm in this book, I'm just gonna tell you where we are and why I think this is the central goal of AI. I would say that tensor logic is that answer. Tensor logic, we haven't talked about that yet, but in tensor logic unifies not just symbolic AI and and and deep learning, it also unifies things like kernel machines and graphical models. The you know, the the thing the things that graphical models for example are built out of, and then you can compute probabilities with them, are they are a direct I didn't do this on purpose, but it just fell out. You know, the the the factors that graphical models are made of, those are just tensors. And then the marginalization and and and summation and and and Sorry, the marginalization and and the the point wise products that are what probabilistic inference is made of, they are just tensor joints and projections on those tensors that represent potentials in the case of Bayesian network conditional distributions. So at this point, we do have this very simple language where you can do the entire gamut of AI, which honestly I didn't think this was gonna be possible going in. I thought the answer would be much more complicated. Now, is this the master algorithm? Tensor logic per se is not the master algorithm because it's just a language. I would say that it's the scaffolding on top of which you can build the master algorithm. Now, tensor logic is not just the language, it's also the learning and reasoning facilities under the hood. So for example, 1 of the best things about tensor logic is that the autograph is incredibly simple. Because there's just 1 construct, it's the tensor equation, and and and the gradient of a tensor logic program is just another tensor logic program. So this is all there. So the learning and the reasoning are all there. However, you know, what I would say is that this is not the the mass value per se, but it's what we need to producing and I intend to produce it on short order. You've described a language and certainly if components of that language are Turing complete, that's a big vexed issue, we'll come to that a little bit later. But because of computational equivalence, we can, you know, from an expressibility point of view, we can describe anything in the universe. So we've got this framework. But to me, the challenge in AI is structure learning. Right? So as well as being able to express stuff, it's being able to adapt to novelty and and create perhaps from building blocks that we already have a new structure to allow us to do something useful in that domain. And I can't quite make that leap with with your technology yet. So how how do we do the meta thing where we actually build the the tensor logic constructions to represent the kind of world that we're seeing?…

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