iCreatAI News
Skip to content
Some English translations are not ready yet. The site is still in English. Untranslated news and event text is shown in its original language until background processing completes.
Trending storyUpdating

模拟职场评测:AI编码智能体完成率不足一成

1 reports1 sources32 min agoUpdated

Understand this story

AI overview

一项新实验把 Claude Opus 5.5、GPT-6 Astra 等 AI 编码智能体放进模拟软件公司,让它们以数字员工身份面对同事、项目看板和聊天记录。结果显示,这些智能体完整完成的任务都不足十分之一。 实验指出,这些智能体在 SWE-bench 等标准基准上接近饱和,但换到需要多任务协作的职场环境后表现明显下滑。

AI overview based on source reports · Updated 13 min ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 22
  1. The Decoder
    AI coding agents ace isolated tests but complete fewer than one in ten tasks in a simulated workplace

    AI coding agents are approaching top scores on standard benchmarks, but a new experiment placed them as digital employees in a simulated software company with colleagues, project boards, and chat histories. Even Claude Opus 5.5 and GPT-6 Astra fully completed fewer than one in ten tasks. The piece notes Anthropic's claim that Claude writes over 80 percent of its production code and that benchmarks like SWE-bench are nearly saturated.

Activity for this story

Not enough continuous observations to show a trend yet.