AI代理缺乏时间感知，影响长任务执行

AI 摘要

一项由MATS研究项目支持的新研究发现，Anthropic的Claude Code和OpenAI的Codex等AI编程助手缺乏时间感知能力，无法准确估计任务所需时间或已用时间。在测试中，它们普遍高估任务时长，且对自身工作质量的评估也不可靠。研究者指出，这种缺陷会影响长时间任务的执行和可控性，但提供时间报告工具时，代理几乎总能正确报告时间。

正文节选

AI agents have no sense of time and are not aware of it A new study finds that popular coding assistants can't predict how long a task will take, and they can't reliably tell how long they've already been working. That's a problem for long-running jobs. When an AI assistant works on a task, it often has no idea how much time is passing. That's the takeaway from a study by two independent AI researchers, done as part of the MATS research program. The pair tested two widely used coding assistants,

发布时间：2026-08-30 18:41

抓取时间：2026-08-30 19:12

来源机构：THE DECODER