hello author here.

yes, it gives labs edge and leads to self-recursive improvement loops.

also i was myself able to finish 7th in a later competition with 2-3 other approaches which are variants of the method discussed in this blog.

in general, having a harness as thin as possible with some problem specific instructions while controlling for context rot is the key.

point i am trying to make is there are a lot of optimisation surface areas possible.

you may notice Kimi, GLM have also started telling how their model is able to optimise it's own inference pipeline

https://www.kimi.com/blog/kimi-k3