Stanford CS193T Thinking with AI | Autumn 2026 | Managing Sources

Stanford CS193T Thinking with AI | Autumn 2026 | Managing Sources

Title history
  • Stanford CS193T Thinking with AI | Autumn 2026 | Managing Sources — observed on 20261111-1900 UTC (YouTube)
🎙 Cynthia Bailey 👥 1.3M 📅 November 11, 2026 ⏱ 63 min 👁 174 📄 tutorial 🧭 2026-11-11
Available in: English (current) Français

Keywords

RAGcontext windowprompt injectionsycophancymemory

Summary

This lecture from Stanford’s CS193T course focuses on managing sources and persistent context in AI tools. Cynthia Bailey begins by explaining how to set user preferences in ChatGPT, Claude, and Gemini, including custom instructions to reduce sycophancy and adjust formatting. She then discusses automatic memory features that glean information across chats and how to inspect or export them. The lecture elaborates on the contents of the context window, including system prompts, settings, memories, uploaded documents, and web search results. The core topic is Retrieval-Augmented Generation (RAG) as a solution for grounding AI with external documents, highlighting failure modes like the ‘adaptable chameleon’ (over-reliance on RAG content) and the ‘stubborn sloth’ (resistance to override training knowledge). The speaker also covers saving complex instructions as Claude Skills or Gemini Gems, and concludes with a caution about prompt injection and the importance of treating unknown sources carefully. The session includes interactive discussions and emphasizes practical management of AI memory and context.

158 words

Critical Evaluation

Value of the Information & Strength of the Argument

The lecture provides solid practical value by offering concrete steps for managing AI preferences and understanding the components of the context window. The argumentation is clear and well-supported with examples, such as the Gemini memory import script and the Stanford Claude skill. The discussion of RAG failure modes is particularly insightful, referencing a specific research paper to illustrate both over-reliance and resistance. The speaker presents balanced viewpoints, acknowledging trade-offs, and encourages critical thinking about who controls knowledge and correctness. The arguments are coherent and logically structured, building from basic concepts to advanced applications.

Scientific Rigor, Source Quality, Title Accuracy

The scientific rigor is generally high: the speaker is an expert, and the content aligns with current AI practices. The video explicitly mentions the research paper ‘Adaptive Chameleon or Stubborn Sloth’ to support claims about RAG trust issues, which adds credibility. However, not all claims are substantiated with citations, and the lecture leans on anecdotal examples. The title ‘Managing Sources’ accurately captures the focus, and the video adequately covers the advertised topics without significant deviation. The description provides a link to the course homepage, and other external references are implied but not explicitly cited.

202 words

Title / Content Match

The title accurately reflects the video's focus on managing sources within AI context windows, covering RAG, memory, and related techniques.

Quality & Reliability

8/10

Lecture by Cynthia Bailey, a Stanford senior lecturer with extensive AI education and policy background. The content is accurate, well-structured, and grounded in both practical examples and research literature, though some claims about model behavior lack explicit citations.

Key Moments

Cited Sources

Contribution & Novelties

This lecture provides a comprehensive, accessible overview of managing context and sources in modern AI tools, emphasizing practical strategies for reducing sycophancy and optimizing RAG usage. Its original contribution lies in clearly explaining the conceptual separation between model weights and context window contents, and in presenting failure modes of RAG with real-world relevance.

Pour aller plus loin :

97 words

Radar Profile

The radar profile shows strong scores in information quality and reliability, with slightly lower technical depth and quantity. This indicates a well-balanced introductory-to-intermediate lecture that prioritizes practical guidance and credible content over exhaustive technical detail.

Reliability 8/10