Terminal-Bench: Evaluating AI Agents | Stanford CS329Z Guest Lecture with Alex Shaw & Ryan Marten

Browse Stanford's online courses in Agentic AI: https://stanford.io/4AIRb2z

Lecture Overview:
How do frontier AI labs measure whether agents can do real work? In this Stanford CS329Z: Engineering AI Agents guest lecture, Alex Shaw and Ryan Marten of the Laude Institute, co-creators of Terminal-Bench, explain why evals have become the source of truth for agent software, how Terminal-Bench measures how well agents accomplish hard, real-world tasks in a terminal environment, and how to write tasks, design verifiers, prevent reward hacking, and maintain a benchmark with their open-source framework, Harbor.

Speakers: Alex Shaw and Ryan Marten

Alex Shaw is a founding Member of Technical Staff at the Laude Institute building the infrastructure for evaluating and training AI agents. He is the co-creator of Terminal-Bench, a benchmark of hard, realistic command-line tasks that frontier labs now report in their model cards, and the creator of Harbor, the open-source framework for building agent evaluations and RL environments.

Ryan Marten is a Member of Technical Staff at the Laude Institute building the training data, benchmarks, and infrastructure behind more capable reasoning models and autonomous agents. He helped lead OpenThoughts, the fully open data recipe behind the OpenThinker reasoning models, and Terminal-Bench, which virtually every frontier lab now uses to measure how well agents complete real tasks in a terminal, and contributes to Harbor, the open-source framework for building agent evaluations and RL environments.

Course website: https://cs329z.stanford.edu/

Watch the full CS329Z playlist: https://youtube.com/playlist?list=PLPRcF5HR02_U&si=3Z4OYphngcmQ0GIy

Recorded 10/26/2026 in CS329Z: Engineering AI Agents, a graduate course at Stanford University taught by Diyi Yang, Michael Ryan, and John Yang.

#AIAgents #AgenticAI #Stanford Receive SMS online on sms24.me

TubeReader video aggregator is a website that collects and organizes online videos from the YouTube source. Video aggregation is done for different purposes, and TubeReader take different approaches to achieve their purpose.

Our try to collect videos of high quality or interest for visitors to view; the collection may be made by editors or may be based on community votes.

Another method is to base the collection on those videos most viewed, either at the aggregator site or at various popular video hosting sites.

TubeReader site exists to allow users to collect their own sets of videos, for personal use as well as for browsing and viewing by others; TubeReader can develop online communities around video sharing.

Our site allow users to create a personalized video playlist, for personal use as well as for browsing and viewing by others.

@YouTubeReaderBot allows you to subscribe to Youtube channels.

By using @YouTubeReaderBot Bot you agree with YouTube Terms of Service.

Use the @YouTubeReaderBot telegram bot to be the first to be notified when new videos are released on your favorite channels.

Look for new videos or channels and share them with your friends.

You can start using our bot from this video, subscribe now to Terminal-Bench: Evaluating AI Agents | Stanford CS329Z Guest Lecture with Alex Shaw & Ryan Marten

What is YouTube?

YouTube is a free video sharing website that makes it easy to watch online videos. You can even create and upload your own videos to share with others. Originally created in 2005, YouTube is now one of the most popular sites on the Web, with visitors watching around 6 billion hours of video every month.