Evolutionary Algorithms for optimizing LLM weights Gradient descent and backpropagation have a lot of problems, alignment becomes a nightmare. Evolutionary algos fix this, but they don’t scale A recent paper, EGGROLL, makes it computationally feasible to do now www.alphaxiv.org/abs/2511.16652
Follow
@timkellogg.me is this Nano banana pro? Either it's a bit confused with greek vs latin alphabets, or it's making math / typographical puns
