🚨 Uber 内部用来盯 AI agent 的那套安全系统 ADR，开源了，能把公司里没人报备就偷偷用上的 AI 工具揪出来。 GitHub 上 1623 star、172 个 fork，相关论文被 MLSys 2026 接收，系统本身已经在 Uber 生产环境跑着。 现在公司里的 agent 安全基本是个黑洞：谁在用 Cursor、谁装了 Claude Code、哪个客服 agent 被人用提示词绕过去了，安全团队看不见。ADR 把这件事拆成五块来做——先把没批准的 AI 工具找出来，再观测 agent 到底调了什么工具、执行了哪些动作，然后评测防御能力、检测威胁、拦住不安全的操作。 观测这块已经在生产环境里跨 macOS、Linux、Windows 采了七种以上 AI 编程工具的轨迹；检测用的是两层结构，先高召回粗筛，再对可疑会话做深一层的推理。它还带了一个 ADR-Bench，300 多个任务、134 个 MCP server，把 17 种 agent 攻击手法全覆盖了一遍。 要说清楚的是，这次开源的是 Discovery、Sensor、ADR-Bench 和 Detector 这几块，负责拦截的 Prevention 组件和离线的 Explorer 引擎没放出来。 agent 进了生产，安全这一课迟早得补。 GitHub：

开会前还在把文档一页页搬进 PPT？Presenton 可以先帮你搭初稿。 它能根据提示词、文档或现成模板生成演示稿，生成后还能自己拖拽修改。 最后可以导出可编辑的 PPTX 或 PDF，适合先把方案讲清楚。 中文字符裁剪有人报过问题，正式交付前记得逐页看版面.

和Quant Alex @StochAlex07 讨论： SABR Theta与Spot Theta+Vol Theta+Cross Theta的异同与应用，以及SABR模型自洽性分析。 **English Summary of the Chat** **SABR Theta vs Spot Theta + Vol Theta + Cross Theta** The conversation between **Alex Wu** (white bubbles) and **Jeff Liang** (green bubbles) is a technical discussion focused on **SABR Theta versus Total Theta** (i.e., Spot Theta + Cross Theta + Vol Theta), model self-consistency, PDE residual, and the correct definition of SABR Greeks. ### Key Points Discussed: 1. **SABR Gamma = Spot Gamma** (first major question, raised by Jeff) Jeff asked whether SABR Gamma (\(\partial^2 P / \partial F^2\)) is identical to Spot Gamma and whether it includes the dependence of \(\sigma_B\) on \(F\). He also provided the full chain-rule expansion of SABR Gamma in terms of Black-76 Greeks. Alex confirmed the understanding and **later affirmed in code** that this is exactly how SABR Gamma is implemented in their system. 2. **SABR Theta vs Total Theta and Model Self-Consistency** (main topic, led by Jeff) Jeff shared a clear 3-point understanding: - SABR Theta is computed directly via the SABR approximation formula to obtain \(\sigma_B\), then applying the Black-76 chain rule: \(\partial P/\partial t =\) BS_Theta(\(\sigma_B\)) + BS_Vega \(\cdot \partial\sigma_B/\partial t\). - Total Theta is the exact decomposition from the SABR PDE (Spot Theta + Cross Theta + Vol Theta). - When the model is **fully self-consistent** (Residual = \(\partial P/\partial t + \mathcal{L}P = 0\)), SABR Theta = Total Theta; otherwise the difference is the unexplained PnL caused by the approximation error in the Hagan formula (especially pronounced in long-dated, high vol-of-vol, or high-skew options). 3. **Practical Implication – Theta Decomposition Decision** (comment by Alex) Alex noted that whether to perform Theta decomposition depends on the risk-management approach: - Without decomposition → use SABR Gamma vs. dP/dt. - With decomposition → SABR Gamma maps to Spot Theta, Vanna to Cross Theta, and Volga to Vol Theta. **Overall Tone**: The discussion is highly technical and collaborative. Jeff drives the conversation by asking clarifying questions and presenting a well-structured 3-point summary of his recent study. Alex provides confirmations, practical insights, and code-level validation. Both participants demonstrate a strong command of SABR model nuances, particularly the relationship between approximation error, PDE residual, and real-world risk management.