用文本特征生成专家可理解的解释，提升AI决策透明度。
arXiv:2511.04070v3 Announce Type: replace Abstract: As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users ar…
用AI写了大量代码后，该如何诚实地向他人介绍自己的工作是开发者们的新难题。
Hi! I was working on a couple of personal projects, and I've been using Claude Code for a while. Recently, I've been wanting to talk about my work pub…
OpenAI秘密武器：让大模型学会“认错”，诚实度飙升的秘密在这篇研究里！
OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI hone…
OpenAI官宣：引入独立专家第三方测试，强化前沿AI安全评估与透明度。
OpenAI works with independent experts to evaluate frontier AI systems. Third-party testing strengthens safety, validates safeguards, and increases tra…
OpenAI首次公开心理健康相关诉讼处理原则，强调关怀、透明与尊重，并加强ChatGPT安全支持。
We’re sharing our approach to mental health-related litigation. O handle sensitive cases with care, transparency, and respect while continuing to stre…
代理式AI的透明性设计：在“黑箱”与“数据倾倒”之间找到平衡，让用户信任AI决策。
Designing for agentic AI requires attention to both the system’s behavior and the transparency of its actions. Between the black box and the data dump…