Cosine's 'swarm' feature — a hierarchical orchestration of up to 253 sub-agents, with an orchestrator delegating to subplanners who delegate to workers — let a model with no horology knowledge build a complete, physically-accurate mechanical-watch design SDK with a 3D viewer in one shot, something no single frontier model could do out of the box.
Pullen describes Cosine's "swarm" — an orchestrator that breaks a task into subplanner-owned verticals which delegate further to worker agents (253 in one case) — successfully building a full mechanical-watch design SDK with a physics-accurate 3D viewer in one shot, a task no single model, including Opus or Gemini, could do alone. ✦ AI generated
Alistair Pullen · Machine Learning Street Talk · 2026-07-13 · original ↗
starts at this moment · 40:53
“I mean how do you see that evolving over time because now it's quite a manual process but do you think well I mean you've got this swarm thing maybe.”
A swarm is genuinely like a real a lot of a lot of sub agents running at the same time in a hierarchical way... for that problem we use 253 sub agents which I think is more than you tend to see in a claude code session and so on... when you do that it is possible and you can do that entire project in one shot.
verbatim transcript · starts at 40:53
40:33you've got this swarm thing maybe. >> Oh thank thank you for bringing that up because that was exactly what I was going to answer. Swarm to me is sub aent orchestration taken to the logical extreme. Um, we're kind of lucky to be able to do it because I think that obviously Claude Code has, I believe, workflows. Um, and Codeex has sub agents as well. Um, a swarm is what it sounds
40:53like on the tin. A swarm is genuinely like a a real a lot of a lot of sub aents running at the same time in a hierarchical way. Um, and because cosign isn't trying to serve hundreds of millions of people a day, we are able to serve a swarm-like feature. Um whereas I think if Anthropic had a swarm for like Opus I think they would even Colossus
41:10Swan would run out of run out of tokens. Um swarm does exactly what you've just outlined automatically basically. So that there is um there is a video on my on my Twitter and also my LinkedIn um of me taking our Lumen outpost model which is post train Kimmy K2.6. So definitely not an opus or a mythos or anything like that. Um, and I asked it, okay, um, I
41:33want you to build me a mechanical watch compiler was the use case that I came up with. I am Swiss by birth, so I have a reason to do this. Um, and I basically asked and and actually someone did this exact same task with Fable. I don't know if you saw it on Twitter when Fable was out. Um, but essentially like I want you to build me a SDK in Python for me to be
41:52able to like specify mechanical watches in code because I don't know herology, but I want to be able to do it anyway. Um, I want it to be physically congruent. I want you to use some kind of physics engine. Um, and then I also want like a 3D viewer to be able to like see the thing running. Um, and it all needs to be possible in real life. You
42:10can't have things like intersecting each other wouldn't be possible and so on. Um, and that is something that out of the box Kimmy cannot do. There's no way, not even close. Like it would be terrible. Um, in fact, even Gemini 3.5 and Opus and 5.5 can't really do it. But as soon as you put them in a swarm and for what swarm looks like for cosign is
42:29you have one orchestrator at the very top it breaks down a problem into um sub problems for uh basically product managers or or or whatever you want to call them. We call them subplanners but they own verticals of this. So like within that task you would have had um a subplanner to do the SDK. You would have had a subplanner to do the 3D viewer. had a subplanner to write the
42:53documentation and so on. Um, and then those subplanners could then delegate to workers and then they have like a flat layer of of as many workers as they like. Um, and for that problem we use 253 sub aents which I think is more than you tend to see in a claude code session and so on. I think I think you you'd probably hit your usage limit pretty