Stanford CS329Z Lecture 9 Released: Optimizing AI Agents via Prompts vs. Weights
stanfordnlp · x · 2026-11-21
Stanford's CS329Z: Engineering AI Agents course has released Lecture 9, Optimizing AI Agents: Prompts vs. Weights, with slides and video publicly available (taught by Michael Ryan).
The lecture lays out a full framework for agent optimization:
- Context optimization: iteratively evolving prompts (e.g., GEPA)
- Weight optimization: training weights with RL methods like GRPO
- Self-optimization with agents
Slides cover conditions for optimization, when to use each strategy, and decision criteria (per the lecture overview: 25 min each on context and weight optimization, plus strategy selection).
Earlier lectures' slides are already public and videos are rolling out; course page, slides, and the YouTube playlist are all freely accessible.
More from coding & agent
- Solo dev runs agent swarm in Antigravity to automate SEO analysis — gaganghotra_ · 2026-11-21
- 3500-word guide: building agent evals from real LangGraph traces — strickvl · 2026-11-21
- Stanford CS329Z Lecture 6: AI Agent Design Patterns — ReAct, CodeAct & More — stanfordnlp · 2026-11-21
- 'Fix the Prompt Before You Fine-Tune': Stanford CS329Z's Agent Optimization Roadmap — stanfordnlp · 2026-11-21
- OpenAI agents now finish 46% of 2-4 hour tasks autonomously, up from 23% — AIFlow_ML · 2026-11-21
- Connecting SoduWork to an OpenAI-Compatible Gateway: Config and the 180-Second Stall — JeremyCMorgan · 2026-11-21