Noam Brown – Agent swarms, alignment, & recursive self-improvement
Episode publishedPodcast: Dwarkesh PodcastDwarkesh Podcast
Transcript preview
Preview only
Today, I'm chatting with Noam Brown, is a researcher at OpenAI. He was one of the foundational contributors to what became o one and the reasoning models, and now he's working on multi agent systems. Speaking of which, you guys announced last week that you solved one of the middle income price problems with a system of 10,000 different AI agents that spent 130,000,000,000 tokens over eighty eight hours. One of the reasons I was interested in talking to you is I think you were in the first people maybe two or three years ago who was thinking about how the reasoning models would allow us to see
So the way I think about it, when you plot the performance of these reasoning models with test time compute on the x axis and performance on basically any reasoning benchmark on the y axis. Yeah. You see a very clear pattern where the longer these models take to think about their answer, the better they do. And this is like a very natural thing. It's the thing with with people. If you're taking the SATs, you have five minutes to go through the entire exam, you're not gonna do very well. If you have five hours, you're probably gonna do a lot better. The AI models are pretty similar. And and the
Okay. I'm gonna ask a bunch of naive questions because these systems so this is an unreleased model. So we haven't publicly seen how these systems work. So I just have a bunch of ways in which I'm like confused about like what the qualitative properties of such systems are. I am shocked by the scale of cognitive effort that you can concentrate in such a short period of time. So if you think about what 130,000,000,000 tokens are, if it was a single human thinking as you know full time job stretched back to back, 130,000,000,000 tokens would be a human thinking for like four thousand years, you
Yeah. Let's talk about the paralyzation penalty and then we can talk about the qualitative stuff because the truth is that we don't have very good science on multi agent scaling up to this kind of scale.
Yeah.
So when we released 5.6, I think that was the first time that we had a proper multi agent system in in our models. And we actually did in the blog post show some plots of the scaling performance of multi agent systems because we we have it as an option. It's ultra mode. And the default is four agents, but you can set that to higher. And in the plot we show, okay, here's what the performance looks like on some benchmarks for one agent, for four agents working together, for 16 agents working together. And what you see, and it depends on the benchmark. But but for some of the benchmarks, basicall
Is it a linear serial time speed up or a sub linear speed up as you increase the number of parallel agents?
I would say it's slightly sub linear, though it does depend a lot on on on the problem. Yeah. Math for example is quite parallelizable. It's not the most parallelizable thing, but it is very parallelizable. I think web search, things like doing a deep research report where you have to like look through a bunch of sources, that's extremely paralyzable. I suspect that something like writing a novel would be very unparalyzable.
Yeah.
Keep exploring with a free account.
A free account preserves the short preview. Upgrade to Pro for the full transcript and episode chat.