One of the amazing details of GPT-5 is the router that sits in front of the different models. It’s been a rocky start so far, but over time, this is one of the ideas that will last and become crucial going forward.
A routing model in front of other models is ~isomorphic with a single large model, no? In both cases, it’s an attempt to find the optimal path through a space. One starts with an entry point and navigates. “Multiple models” are separate spaces. Are they superior to a single larger space?