---
title: "OpenAI Codex developer says agent swarms mostly waste tokens"
url: https://www.parallelquant.com/posts/openai-codex-developer-says-agent-swarms-mostly-waste-tokens-c8d38d
source_name: "The Decoder"
source_url: https://the-decoder.com/ai-agent-swarms-are-a-massive-waste-of-tokens-with-zero-quality-gain-says-openai-codex-developer/
published: 2026-09-17T11:03:32.000Z
topics: ["llms", "products"]
publisher: "Parallel Quant"
---

# OpenAI Codex developer says agent swarms mostly waste tokens

*2026-09-17 · Source: [The Decoder](https://the-decoder.com/ai-agent-swarms-are-a-massive-waste-of-tokens-with-zero-quality-gain-says-openai-codex-developer/)*

Eric Provencher, a developer on OpenAI's Codex, says running more than two parallel AI sub-agents on a task rarely improves quality because the agents don't trust each other's work and end up redundantly re-checking it. He cites a case where 1,393 agents spent $20,000 in tokens on a Python refactor that one agent could have done far more cheaply.

**Why it matters:** This is direct pushback from inside a major AI lab against the popular multi-agent-swarm pattern being marketed as the next step in agentic coding tools. It's a useful data point for teams deciding how to architect AI coding workflows, and it tempers claims from agent-orchestration vendors.

**Topics:** llms, products

---
Read the original: https://the-decoder.com/ai-agent-swarms-are-a-massive-waste-of-tokens-with-zero-quality-gain-says-openai-codex-developer/
Canonical: https://www.parallelquant.com/posts/openai-codex-developer-says-agent-swarms-mostly-waste-tokens-c8d38d
Published by Parallel Quant — https://www.parallelquant.com