Ask HN: Are you using an agent orchestrator to write code?

Instead, he recommends engineers integrate LLMs into their workflow more and more, until they are managing multiple agents at one time. The final level in his AI Coding chart reads: "Level 8: you build your own orchestrator to coordinate more agents."

At my work, this wouldn't fly-- we're still doing things the sorry way. Are you using orchestrators to manage multiple agents at work? Particularly interested in non-greenfield applications and how that's changed your SDLC.

The bottleneck has not been how quickly you can generate reasonable code for a good while now. It’s how quickly you can integrate and deploy it and how much operational toil it causes. On any team > 1, that’s going to rely on getting a lot of people to work together effectively too, and it turns out that’s a completely different problem with different solutions.

Steve Yegge is building a multi-agent orchestration system. This is him trying to FOMO listeners into using his project.

From what I've observed, the people trying to use herds of agents to work on different things at the same time are just using tokens as fast as possible because they think more tokens means more progress. As you scale up the sub-agents you spend so much time managing the herd and trying to backtrack when things go wrong that you would have been better off handling it serially with yourself in the loop.

If you don't have someone else paying the bill for unlimited token usage it's going to be a very expensive experiment.