Benchtalks #1: Alex Shaw (Terminal-Bench, Harbor) - Building the benchmark factory

Snorkel AI co-founder Vincent Chen sits down with Alex Shaw, MTS at Laude Institute and co-creator of Terminal-Bench, to unpack what the rapid hill-climbing on TB2 reveals about the state of AI agent evaluation — and where the field needs to go. Watch the full episode: https://www.youtube.com/watch?v=UCn5gG0haCI