Noam Brown

Noam Brown

Person

Heard in 17 episodes across 11 shows since Aug 2026

Noam Brown is a research scientist at OpenAI focused on multi-step reasoning, self-play, and multi-agent artificial intelligence. He co-created Libratus and Pluribus, superhuman poker-playing AIs, and CICERO, a Diplomacy-playing AI.

Discussed inBusiness60%AI & Tech40%

Episodes

17
across 11 shows

This week

0
episodes on 0 shows

Guest appearances

1

Share of the conversation

Mentions of Noam Brown per 1,000 mentions of anything, 7-day rolling, across the podcasts PodLume Trends follows.

0.0‰0.05‰0.1‰0.15‰0.2‰Aug 25Sep 16Oct 9Oct 31Nov 22
Show the data
DayShare (7-day)Mentions
Aug 270.01‰1
Sep 90.01‰1
Sep 170.02‰2
Sep 210.04‰2
Sep 220.13‰11
Sep 260.16‰5
Sep 280.17‰3
Sep 290.08‰1
Oct 20.09‰1
Oct 30.05‰1
Nov 70.01‰1
Nov 130.02‰2
Nov 190.02‰1
Nov 210.02‰1

The full trend: rank, tone and why it is trending →

Email alert

Email me when Noam Brown comes up on a podcast

One email a week at most, with the new episodes that mention Noam Brown. Free, no account needed, unsubscribe in one click.

What Noam Brown has said on podcasts

52 statements

  1. on AI reasoning modelsPositiveSep 17, 2026· Dwarkesh Podcast

    More test-time compute improves reasoning-model benchmark performance.

    “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, you see a very clear pattern where the longer these models take to think about their answer, the better they do”

    Listen at 0:50

    Open the episode · Noam Brown – Agent swarms, alignment, & recursive self-improvement
  2. on Multi-agent AI systemsPositiveSep 17, 2026· Dwarkesh Podcast

    Multi-agent systems scale test-time compute through parallelization.

    “multi-agent is a way of scaling test-time compute in parallel instead of purely serial”

    Listen at 1:50

    Open the episode · Noam Brown – Agent swarms, alignment, & recursive self-improvement
  3. on Multi-agent AI systemsMixedSep 17, 2026· Dwarkesh Podcast

    Parallel multi-agent scaling is effective but less efficient than single-agent reasoning.

    “it is less efficient because it doesn't have— it's not like a single agent has all the context to itself, but it is a very effective way of scaling test-time compute if it's done well”

    Listen at 1:55

    Open the episode · Noam Brown – Agent swarms, alignment, & recursive self-improvement

Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.

Episodes

17 episodes featuring Noam Brown, newest first