In agent teams, layering different kinds of review pays off, because checking work costs far less than producing it.

groundsAgent swarms and the new model economics, Cursor

No single lens catches everything, but decorrelated lenses stack, the way self-driving systems reach above-human reliability without any single perfect component. The compute spent on review is high return, since review is much cheaper than the work it audits.

groundsAgent swarms and the new model economics, Cursor

We also tried reviewers running on different models, with different training and a different personality.

groundsOf Swarms and Sand Gods, Séb Krier

The other objection will be something like scalable oversight: "*monitors would need to be as capable as the thing being monitored.*" This would possibly be true if you had to have a single weak model simply verify the entire output of a larger, better model; but (a) checking work is generally easier than producing it; - (b) with the scaffolding in place, the smaller model would only need to verify certain narrow components (though this isn't a panacea); - (c) in fact you would need a multitude of *different* models, to avoid correlated errors, meaning that they could catch a lot more, while remaining cheaper than using an equivalent large model.