OpenAI Codex 开发者称多代理集群是代币浪费，无质量提升
AI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer
OpenAI 的 Codex 开发者说，多代理集群是代币浪费，不如用单个 Astra 代理，很实用。
OpenAI Codex 开发者 Eric Provencher 指出，运行超过两个并行子代理时，由于代理间缺乏信任会互相复核工作，导致代币消耗增加但质量无提升。他提到一个项目用 1,393 个代理花费 2 万美元代币完成 Python 重构，而单个 Astra 代理即可以极低成本完成。
AI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer
OpenAI Codex developer Eric Provencher warns that running more than two parallel sub-agents almost always burns tokens without improving quality because agents don't trust each other and end up double-checking everyone's work. He calls this the "coordination tax" and points to a project where 1,393 agents spent $20,000 in tokens on a single Python refactoring that one Astra agent could have handled for a fraction of the cost. The article AI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer appeared first on The Decoder .
