Stanford CS329A Self-Improving AI Agents | Part 8 | Agentic Evaluations and Long Horizon Tasks
Source
youtube.com
Author
Stanford Online
Date
Why it matters
Explains why agentic evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → are harder than prior benchmarks and how task time horizon is used to measure long-task capability. Helpful for designing your own evals.
Terms in this piece · Glossary
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
videoAI & Cybersecurity: Dan Boneh Interviews Nicolas Carlini
videoStanford CS229 I Machine Learning I Building Agents That Do the Work of Human Software Engineers
videoStanford CS25: Transformers United V6 I From Next-Token Prediction to Next-Generation Intelligence
videoStanford CS329A Self-Improving AI Agents | Part 9 | Future Research Areas
