OpenHands, every mention
6 scenes (2025) · ← back to OpenHands
tap a year for its mentions
every year 2025 anyone Graham Neubig 13Ivan Burazin 3Swyx (Marcos Swix) 2Shawn Wang 2Mike Merrill 2
Verbatim, from the transcripts: the passages where OpenHands comes up
Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
- ▶ 6:24 Mike Merrill Agents like Cloud Code or Open Hands don't appear on this leaderboard quite as often as our, ah, our minimal agent that we put together just for the purpose of understanding language models.
- ▶ 17:37 unnamed speaker You create an agent config, which defines your agent's, like, harness, the model name, and all that's taken care of underneath the hood, so you can use different agents, like OpenHands, or Terminus, or what have you to generate the data.
Terminal-Bench: Pushing Claude Code, OpenAI Codex, Factory Droid, et al to the limits
- ▶ 21:49 Mike Merrill The reason for this is that if you go and use an agent like Claude code or codec CLI or even open hands, it's not clear to the degree to which this agent has been optimized to make up for some of the weaknesses of a particular model, or…
smol agents are all you need
- ▶ 5:01 Swyx (Marcos Swix) We covered this with, um, uh, Graham Newbig, who also runs OpenHands and OpenDevin. 2 times in the scene
2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- ▶ 19:45 Shawn Wang He started, uh, open hand is currently still number one on SweetBench full, which is the hardest one.
- ▶ 1:08:31 Shawn Wang And so now we're about 50, um, open hands is around there.