I heard about the ShinkaEvolve on a podcast where the guest had used it to evolve an agent harness for a less capable model.

I ended up borrowing the ideas from it for one of my own personal projects.

Do you actually understand why evolution methods are beneficial?

SGD generates a stronger learning signal,is more efficient, and scales better. Using it end-to-end makes it stronger yet.

Yet somehow mixing in a weaker blunt evolution stage improves the result?