Some interesting analysis here: https://www.lesswrong.com/posts/6cb7qd3RSkgnviCpf/swarm-scal...
I think the advantage is strongest in highly parallelizable problems (e.g. trying 1,000 different approaches to solving a math problem).
Some interesting analysis here: https://www.lesswrong.com/posts/6cb7qd3RSkgnviCpf/swarm-scal...
I think the advantage is strongest in highly parallelizable problems (e.g. trying 1,000 different approaches to solving a math problem).