每月花费130万美元,OpenClaw创始人Peter Steinberger运行100个AI代理进行编码、审查PR和查找漏洞
阅读原文· the-decoder.comPeter Steinberger带领的三人团队为开源项目OpenClaw维持着约100个Codex实例的运行,每月驱动OpenAI API支出高达130万美元。他将这笔巨额开支定位为一项研究投资,旨在探索当令牌成本不再受限时,软件开发会呈现何种形态。该实验的核心是观察AI代理在编码、审查拉取请求和查找漏洞等任务上的规模化协作效能。
For $1.3 million a month, OpenClaw founder Peter Steinberger runs 100 AI agents that code, review PRs, and find bugs
Peter Steinberger, founder of the open-source project OpenClaw, shared how his team uses AI to build software. His team of about three people, working at OpenAI, keeps roughly 100 Codex instances running in the cloud. They review PRs, find security holes in commits, deduplicate issues, and write fixes. Some agents open PRs based on the project's vision; others monitor benchmarks and report regressions in Discord. Agents even listen in on meetings and start PRs for features the team discusses. The team also uses Clawpatch.ai, Vercel's Deepsec, and Codex Security for bug and security analysis.