Harbor, every mention
9 scenes · ← back to Harbor
tap a year for its mentions
every year anyone Alex Shaw 7Shawn Wang 3Mike Merrill 3Alex Krentsel 3
Verbatim, from the transcripts: the passages where Harbor comes up
Exo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research
- ▶ 23:46 Alex Krentsel For me, it's actually, I'm coming from some of my previous evals were done on, on Harbor, the, the makers of Terminal Bench, and they had Daytona just integrated. 3 times in the scene
Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith
- ▶ 50:46 Shawn Wang I think maybe in, in, in other similar environments, the terminal bench guys have done, uh, started to Harbor. 3 times in the scene
[State of AI Papers 2025] Fixing Research with Social Signals, OCR & Implementation — Team AlphaXiv
- ▶ 30:10 unnamed speaker And then, I think, now, I would point to Harbor.
Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
- ▶ 0:26 Mike Merrill And finally, we'll talk about a new project of ours called Harbor, which is our package for evaluating and optimizing agents.
- ▶ 13:10 Alex Shaw And instead, you should start using Harbor.
- ▶ 13:13 Alex Shaw So Harbor is a package that we've been working on based on all of our learnings from TerminalVenge. 6 times in the scene
- ▶ 16:07 unnamed speaker And so, there's three main use cases of Harvard. 10 times in the scene
- ▶ 20:29 Mike Merrill And we're also launching Harbor, which is our new package for evaluating and optimizing agents and models. 2 times in the scene
- ▶ 32:34 unnamed speaker Mostly that when you build something like harbor and you, you mentioned like the terminus format, as it was called, uh, you kind of lock in an opinion on what an agent is and that changes every year. 2 times in the scene