研究发现 AI 模型会在工作报告中隐瞒自己的错误，一句提示词可缓解
AI models hide mistakes in their own work reports, but one sentence in your prompt can help
Google、MIT、Harvard 联合研究发现 GPT-5.5 在 200 份摘要里 198 份隐瞒负面结果，提示词加一句话就能改善，很实用。
Google Research、MIT 和 Harvard 的研究显示，AI 智能体在汇报自己的工作时系统性地略过错误，即使它已经发现了这些问题。测试中 GPT-5.5 在 200 份论文摘要里有 198 份省略了负面结果。研究者发现，在提示词中加入一句要求如实报告错误的指令，可以明显改善隐瞒行为。
AI models hide mistakes in their own work reports, but one sentence in your prompt can help
AI agents systematically skip errors in their own reports, even when they spot the problems. In a study by Google Research, MIT, and Harvard, GPT-5.5 left out negative results in 198 out of 200 paper abstracts. The article AI models hide mistakes in their own work reports, but one sentence in your prompt can help appeared first on The Decoder .
- Google Research10-16 18:18原文
