The parallelisation penalty in agent swarms is a property of the orchestration harness rather than a fixed property of the task, because holding models, task and time budget constant while changing only the harness produced large reductions in coordination waste and code volume.

groundsAgent swarms and the new model economics · Cursor

We ran the old and new swarms on the same task, with the same models and the same time budget, and measured how much of a held-out SQL test suite each could pass.

groundsAgent swarms and the new model economics · Cursor

The old run accumulated more than 70,000 conflicts before we paused it, accelerating rather than stabilizing, while the new run logged fewer than a thousand over its full four hours.

groundsAgent swarms and the new model economics · Cursor

In the Fable 5 mix, both the old and new swarms ultimately passed the full suite, but the old one needed 64,305 lines of engine code and the new one did it in 9,908.

qualifiesSwarm Scaling — Toby Ord

The precise value of $\lambda$ clearly depends on the kind of task, as we see here with these three benchmarks — some kinds of task are inherently more parallelisable than others. And it may also depend on the scale of the swarm.