We have a great group of researchers from the top model, data, and agent companies coming tonight.
The event is already oversubscribed so DM me and I'll do my best to squeeze you in off the waitlist!
Terminal-Bench meetup tonight *with* swag. Register if you haven’t already! Benchmarks, RL environments, new features, and state of the union
luma.com/tbench
The gold standard for science is sharing reproducible and auditable experimental data.
When it comes to benchmarking agents, this means configs, trajectories, rewards, and logs for every single trial.
We built harbor to make this easy.
Unreal's analysis (related to
Introducing Unreal Agent:
An open-source harness with state-of-the-art cost efficiency
39% cheaper than Codex+Astra on Terminal-Bench 4.0 while maintaining performance
