# More agents can buy speed. The savings still need measuring.

[Canonical reading](https://escapemeridian.com/readings/brown-coordination-cost)

Brown argues that parallel agents can reduce waiting time while increasing total compute. He expects better models to organize themselves more effectively and credits the underlying model with most of the mathematical result, while saying very large teams remain poorly compared with smaller ones.

Headline and sourced paraphrase by Escape Meridian. Inclusion is not endorsement.

## Original source

Dwarkesh Podcast · Interview transcript

Original source date: Sep 17, 2026 (2026-09-17).

Date basis: Publication date displayed on the official episode page.

Publisher transcript read on 23 September 2026, New York time. Timestamp marks a chapter, not an exact quote. Audio/video not independently listened to.

The date this reading was added to Escape Meridian is not recorded.

- [Noam Brown – Agent swarms, alignment, & recursive self-improvement](https://www.dwarkesh.com/p/noam-brown)
- [00:00 — Parallel work and its cost](https://www.youtube.com/watch?v=6AgOfiZOWiY&t=0)

## Limits

The interview's large mathematical example lacks a single-agent comparison. It cannot establish a general advantage for adding agents or coordination software.


## Editorial test, not a stated concession

Compare one agent with a team on the same task and sources. Count quality, elapsed time, total cost and human checking. Repeat with newer models.


## qualifies

Brown says the large mathematics example lacks a single-agent comparison, and gives most of the credit to the underlying model rather than the agent team.

- [Supporting source](https://www.dwarkesh.com/p/noam-brown)

## Source and contributor context

Noam Brown · OpenAI researcher interviewed by Dwarkesh Patel

Researcher working on reasoning models and multi-agent systems, as introduced in the episode.

Provider experience informs the account; it does not establish the return on a business's agent deployment.

Declared interests are limited to the records linked here; absence of a record does not establish absence of an interest.

- [Episode introduction](https://www.dwarkesh.com/p/noam-brown)
- [Works at OpenAI and discusses its systems.](https://www.dwarkesh.com/p/noam-brown)

## Assumptions

Editorial reconstruction: time saved is valuable enough to justify the extra compute and review.


## Source media

Media retrieval status: found.

- [Watch the conversation · Dwarkesh Podcast](https://www.youtube.com/watch?v=6AgOfiZOWiY)

## Questions between perspectives

Editorial comparison; no direct exchange established: As delegation becomes easier, which organizational costs remain?

- [Related reading](/readings/amodei-fast-diffusion)

## Terms and references

Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.


## Noam Brown

Noam Brown is an OpenAI researcher discussing reasoning models, agent teams and results from his employer on the Dwarkesh Podcast.

- [Explore this context](/entities/noam-brown)
- [Reference](https://www.dwarkesh.com/p/noam-brown)

## Dwarkesh Podcast

Dwarkesh Podcast features long conversations with researchers, builders and thinkers about technology, history and the future.

- [Explore this context](/entities/dwarkesh-podcast)
- [Reference](https://www.dwarkesh.com/)

## Corrections and challenges

[Send a correction or an opposing source](https://escapemeridian.com/corrections/)

[JSON record](https://escapemeridian.com/readings/brown-coordination-cost.json)