Stanford AI 课程地图 EN GitHub ↗
← 返回课程地图
Stanford · 2026—27 CS 521 LLM 与 Agent —

延伸课程 · LLM 与 Agent

AI 安全 seminar

Seminar on AI Safety

AI 安全前沿论文与研究方向讨论。

1 学分 2026–27 未排课 Satisfactory/No Credit —
AI 安全 seminar

课程定位

AI 安全前沿论文与研究方向讨论。 本页保留官方档案与入口,具体内容与考核以当季官网为准。

主要内容

本页为延伸课程速览,主要内容见下方官方描述。

先修

见官方描述(延伸课程暂未单独整理先修)。

考核与工作量

以当季官网为准(延伸课程暂未单独整理考核)。

适合谁

对「AI 安全 seminar」方向感兴趣的人。

学习建议

先读官方描述和课程官网,再判断是否适合自己。

相关课程

官方课程描述(英文原文)

In this seminar, we will focus on the challenges in the design of safe and verified AI-based systems. We will explore some of the major problems in this area from the viewpoint of industry and academia. We plan to have a weekly seminar speaker to discuss issues such as verification of AI systems, reward misalignment and hacking, secure and attack-resilient AI systems, diagnosis and repair, issues regarding policy and ethics, as well as the implications of AI safety in automotive industry. Prerequisites: There are no official prerequisites but an introductory course in artificial intelligence is recommended.