资讯

AI coding agents ace isolated tests but complete fewer than one in ten tasks in a simulated workplace

📅 2026-11-22 ⏱️ 约 2 分钟阅读 ✍️ AI导航编辑部 🔗 the-decoder.com
AI coding agents ace isolated tests but complete fewer than one in ten tasks in a simulated workplace
📝 内容摘要

AI coding agents ace isolated tests but complete fewer than one in ten tasks in a simulated workplace AI coding agents a

📌 核心要点

  • Continue reading with THE DECODER+
  • - Every Plus article and the full archive
  • - Frontier Radar: 6 deep dives a year

AI coding agents are nearing top scores on standard benchmarks. A new experiment puts them to work for the first time as digital employees inside a simulated software company with colleagues, project boards, and chat histories. Even Claude Opus 5.5 and GPT-6 Astra fully complete fewer than one in ten tasks.

Success stories about AI coding agents keep piling up. Anthropic says Claude writes more than 80 percent of the company's production code, and standard benchmarks like SWE-bench are nearly saturated.

THE DECODER+

Continue reading with THE DECODER+

- Every Plus article and the full archive

- No ad banners

- Frontier Radar: 6 deep dives a year

Already a subscriber? Sign in Back to the homepage

来源the-decoder.com· 本文为编辑整理,仅供参考