Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures

**Dwarkesh Patel** (0:01)
Okay, today, I have the pleasure of interviewing Shane Legg, who is a founder and the chief AGI scientist of Google Deepmind. Shane, welcome to the podcast. Thank you.
So first question, how do we measure progress towards AGI concretely? So we have these loss numbers, and we can see how the loss improves from one model to another. But it's just a number. How do we interpret this? How do we see how much progress we're actually making?

**Shane Legg** (0:28)
That's a hard question, actually.
AGI by its definition is about generality. So it's not about doing a specific thing. It's much easier to measure performance when you have a very specific thing in mind because you can construct a test around that. Well, maybe I should first explain, what do I mean by AGI because there are a few different notions around. When I say AGI, I mean a machine that can do the sorts of cognitive things that people can typically do. Possibly more, but to be an AGI, that's the bar you need to meet. So if we want to test whether we're meeting this threshold, or we're getting close to this threshold, what we actually need then is a lot of different kinds of measurements and tests that spans the breadth of all the sorts of cognitive tasks that people can do. And then to have a sense of what is human performance on these sorts of tasks, and that then allows us to sort of judge whether or not we're there.
It's difficult because you'll never have a complete set of everything that people can do, because it's such a large set. But I think that if you ever get to the point where you have a pretty good range of tests of all sorts of different things that people do, cognitive things people can do, and you have an AI system which can meet human performance and all those things, and with some effort, you can't actually come up with new examples of cognitive tasks where the machine is below human performance, then at that point, it's conceptually possible that there is something that the machine can't do, that people can do. But if you can't find it with some effort, I think it will be practical purposes. You now have an AGI.

**Dwarkesh Patel** (2:11)
So let's get more concrete.
You know, we measure the performance of these large language models on MMLU or something. And maybe you can explain what all these different benchmarks are. But the ones we use right now that you might see in a paper, what are they missing? What aspect of human cognition do they not measure adequately?

**Shane Legg** (2:30)
Oh, yeah, now that's hard to agree. These are quite big areas. So they don't measure things like understanding streaming video, for example, because these are language models and people can do things like understand streaming video.
They don't do things like humans have what we call episodic memory, right? So we have a working memory, which are things that have happened quite recently, and then we had sort of cortical memory. So these are things that have sort of been in our cortex. There's also a system in between, which is episodic memory, which is the hippocampus. And so this is about learning specific things very, very rapidly. So some of the things I say to you today, if you remember them tomorrow, that will be your hippocampus. Our models don't really have that kind of thing, and we don't really test for that kind of thing. We just sort of try to make the context windows, which is, I think, more like a working memory, longer and longer to sort of compensate for this. But yeah, we don't really test for that kind of a thing.
So there is all sorts of bits and pieces, but it is a difficult question because you really need to, as I said, intelligence, the generality of human intelligence is very, very broad. So you really have to start going into the weeds of trying to find out if there's specific types of things that are missing from existing benchmarks or different categories of benchmarks that don't currently exist or something.

**Dwarkesh Patel** (3:54)
The thing you're referring to with episodic memory, would it be fair to call that sample efficiency or is that a different?

**Shane Legg** (4:01)
It's very much related to sample efficiency. It's one of the things that enables humans to be very sample efficient.
Large language models have a certain kind of sample efficiency because when something's in their context window, they can then that biases the distribution to behave in a different way. And so that's a very rapid kind of learning. So there are multiple kinds of learning and the existing systems have some of them, but not others. So it's a little bit complicated.