Stanford CS329X HW3 has students simulate human-agent interaction and build auto-evaluators
EchoShao8899 · x · 2026-11-04
In Stanford's CS329X (Human-Centered LLMs, taught by Diyi Yang), HW3 gives students hands-on experience collecting multi-turn human-agent interaction data via simulation and deriving high-fidelity metrics for unverifiable tasks. The assignment builds on Coco (an open-source collaborative desktop agent, forked into a minimal readable version) and AutoMetrics, with Persimmon provided free by humansand as a user simulator. The repo is MIT-licensed on GitHub.
课程官网: https://web.stanford.edu
Related event: Stanford CS329X HW3: Collecting Human-AI Interaction Data with Coco(2 posts)→
More from Companies & People
- Daily AI brief: Tencent launches Hy4 with computer use, Apple opens Siri AI to all devs — testingcatalog · 2026-11-04
- Cambridge's van der Schaar Lab opens PhD applications for 2027 entry — MihaelaVDS · 2026-11-04
- Nvidia struggles to hire RL talent from Anthropic, highlighting chipmakers' reinforcement learning gap — teortaxesTex · 2026-11-04
- Replit's User Ops lead built an AI app to prioritize and route support tickets — amasad · 2026-11-04
- John Lewis's worst-reviewed Christmas ad: why it wants to stop cash gift cards — aakashgupta · 2026-11-04
- Datasite CTO on ditching in-house parsing: better parsing lifted recall 22% — AI Engineer · 2026-11-04