
Noam Brown
6
APPEARANCES
6
PODCASTS
012
DEC 30
JAN 6
JAN 13
JAN 20
JAN 27
FEB 3
FEB 10
FEB 17
FEB 24
MAR 3
MAR 10
MAR 17
MAR 24
MAR 31
APR 7
APR 14
APR 21
APR 28
MAY 5
MAY 12
MAY 19
MAY 26
JUN 2
JUN 9
JUN 16
JUN 23
JUN 30
JUL 7
JUL 14
JUL 21
JUL 28
AUG 4
AUG 11
AUG 18
AUG 25
SEP 1
SEP 8
SEP 15
SEP 22
SEP 29
OCT 6
OCT 13
OCT 20
OCT 27
NOV 3
NOV 10
NOV 17
NOV 24
DEC 1
DEC 8
DEC 15
DEC 22
DEC 29
JAN 5
JAN 12
JAN 19
JAN 26
FEB 2
FEB 9
FEB 16
FEB 23
MAR 2
MAR 9
MAR 16
MAR 23
MAR 30
APR 6
APR 13
APR 20
APR 27
MAY 4
MAY 11
MAY 18
MAY 25
JUN 1
JUN 8
JUN 15
JUN 22
JUN 29
JUL 6
JUL 13
JUL 20
JUL 27
AUG 3
AUG 10
AUG 17
AUG 24
AUG 31
SEP 7
SEP 14
SEP 21
SEP 28
OCT 5
OCT 12
OCT 19
OCT 26
NOV 2
NOV 9
NOV 16
Sep 17, 2026
Noam Brown – Agent swarms, alignment, & recursive self-improvement
9:09
9:20
9:29
9:51
9:55
46:43
Dwarkesh PatelHOST
So I, I, I wanna understand if in six months people will have access to multi-agent systems, how should one model what it is like to collaborate with or hire a multi-agent system?

Noam BrownGUEST
I should start by talking about how these multi-agent systems actually work, which is, I think, a very different way than a lot of multi-agent systems in, in other AIs.

Noam BrownGUEST
So a lot of people that have approached multi-agents for things like LLMs tend to take this like very scaffolded approach where, you know, for example, there might be a, uh, coordinator agent that delegates work to a bunch of children and gives them a task, and the children work on it and then return their answer.

Noam BrownGUEST
It definitely helps, but there are, are a bunch of limitations with these kinds of setups.

Noam BrownGUEST
So for example, if, if in this setup you have, um, a coordinator that's sending tasks to children, the children work on it and then return their answers, well, what happens if two children are given similar tasks? Can they talk to each other? And usually the answer is no.
37 MINS LATER
Dwarkesh PatelHOST
Uh, and then there's the question of will they be capable to do it? And I think that comes back to this question which a listener might disagree with on is just like, will there be billions of human-level or above intelligences, many of which are physically embodied in the world, within a matter of ten years or less, right? So if those two things are true, this Hugging Face thing is just, like, like, extremely analogous structurally, um, even if it's, like, quite boring or why it happened to how we totally lose control of the world.
What Happens When AI Starts Improving AI? | TITV’s AI Deep Dive
17:40
17:50
17:54
17:58

Noam BrownGUEST
So Deep Research came out, I think it was, like, probably early 2025 it came out.

Noam BrownGUEST
You know, you wanted to research the semiconductor industry, it would go around and do a ton of research.

Noam BrownGUEST
It would compile this, like, really comprehensive report with citations and deliver it to you.

Noam BrownGUEST
Now- Is that easily verifiable? I, I would think it's actually pretty hard to, to grade the quality of a detailed research report on an advanced topic.
23 MINS LATER
Why Traditional Benchmarks Fail Modern AI Models with OpenAI Research Scientist Noam Brown
1:37
1:47
1:53
1:58

Noam BrownGUEST
The motivation was we released 5.5, and the initial reaction was kind of skepticism that it was a substantially better model.

Noam BrownGUEST
To, to be fair, that only lasted for a few hours before people had some time to play around with it and, and try it out themselves, and they saw that it was actually substantially better.

Noam BrownGUEST
Um, but I think a lot of the skepticism came from the benchmark grid that was published.

Noam BrownGUEST
Basically, whenever a new model's released, there's this benchmark grid where they show all these different benchmarks on, on the X-axis and then the performance of different models on the Y-axis, and you can just, like, compare different models.
19 MINS LATER
Begin Proof — Noam Brown
12:50
13:01
13:12
13:28
13:37
13:43
36:32

Slater StichHOST
But I'm just curious about the play-by-play of, you know, we think that we have a solution to this problem, and what does it take to actually sort of, you know, believe that we've gotten all the way?

Noam BrownGUEST
Yeah, and basically what happened was we trained a new model, and it wasn't designed for math or anything, it wasn't, it's a general purpose reasoning model.

Noam BrownGUEST
And afterwards, we have people with, you know, math PhDs at OpenAI, some people that were formerly math professors that are interested in math and they just decided like kind of as a side thing, like, okay, well, let's see where the capabilities of this new model are.

Noam BrownGUEST
Let's run it on a bunch of unsolved problems and just see like if any of them, you know, if it thinks that any of them are correct.

Noam BrownGUEST
And of course, like one of the challenges is like actually verifying these things.

Noam BrownGUEST
And this is one of the problems where it came back and said like, actually it's solved.
23 MINS LATER

Slater StichHOST
But I was curious if you felt like any difference in kind on the AI research side between pointing the model at contest math versus pointing it at open research problems.
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
49:05
49:10
49:24
A
49:05AlessioHOST
Mm-hmm.

Noam BrownGUEST
... get a good profile of, like, who this player is, like, how they're playing, where their weaknesses are.

Noam BrownGUEST
Now, I think with more recent technology, that has come down, um, but still, the sample efficiency has been a big challenge.

Noam BrownGUEST
You know, it's a seven-player negotiation game, and-When we started working on it, I took a very game theory approach to the problem.
B
54:28BooksHOST
Do you think this will hold for multi-agents, like self-play to improve better than humans?
AI won't plateau — if we give it time to think | Noam Brown
3:17
3:25
3:42
3:55
4:06

Noam BrownGUEST
The incredible progress in AI over the past five years can be summarized in one word, scale.

Noam BrownGUEST
Yes, there have been algorithmic advances, but the frontier models of today are still based on the same transformer architecture that was introduced in twenty seventeen, and they are trained in a very similar way to the models that were trained in twenty nineteen.

Noam BrownGUEST
The main difference is the scale of the data and compute that goes into these models.

Noam BrownGUEST
Every year since then, for the past five years, the models have gotten bigger, trained for longer on more data, and every year they've gotten better.

Noam BrownGUEST
But today's frontier models can cost hundreds of millions of dollars to train, and there are reasonable concerns among some that AI will soon plateau or hit a wall.
13 MINS LATER
S
17:41speaker_4ADVERTISER
Yes.
