Systems Reading Group with Harbor/Terminal-Bench

​Join us for a deep dive session with the creators of Harbor and Terminal-Bench!

​Harbor is a framework for evaluating and optimizing agents in container environments. It is widely used by the top frontier labs, data vendors, and agent builders. If you're interested in RL infra and evals, this is the session for you!

​In this session, we will go through some of the key components of their architecture and how companies have successfully used Harbor to build benchmarks, generate training datasets, and handle RL rollouts.