@null not as yet, but did a tiny bit of research before. If i understand it this would help mainly with batching (ie concurrent sessions/users/turns etc) to keep the pipeline more busy (vs a batch of a fixed size going together), which is interesting, but most work so far has been on latency hiding for straight line performance to start.
We did have a version of things which used expert islands for MoE parallel alternative (I think that has been mostly scrubbed from the code). It showed early promise by having trunk+hot experts together, but as models got larger, it made both that very large on its own but also didn't seem to work as well (or we just weren't good at grouping experts), the idea being to really side step latency and route sessions to those islands. It felt like as models scaled it didn't stay smart (as diverse experts activated more than I thought they would). Could be our mistake (was an exciting possibility though - if you don't mind accepting some loss).
tldr; yes this seems a very nice enhancement for smarter batching/keeping things busy and seems like most larger models we look at are MoE!
Have been using morph for a while (I am one of the authors of goose) and was surprised when introduced at the boost it gave me (much less iteration with the main expensive LLM, and I can even make the editing process simpler to take a load off the agent). Used it with claude 3.5, 3.7, 4 and currently with a o3/openai and anthropic/claude4 + morphllm combo today.
I built this using openAI codex, google cloudrun and streamlit (visualisations by graphviz - codex is not bad at translating pipelines to graphviz without really much prompting which somehow surprised me). Let me know what you think. No fine tuning required for this (as Codex already knows quite a lot).
I read somewhere (wish I could remember where, bizarrely I think it was on paper) that the very definition of a framework over a library is that inversion of control - ie your application runs inside the framework - you are beholden to its lifecycles and view of the world.
When on the JVM, I use scala - and I have found very little utility for frameworks. Libraries - oh yes, very much so.
Yes they have spun things that way - spinning it as good news for them. But it won't hold forever. People are not ignorant - well at least not all of them, not all the time ;)
You can lay for that in the gang of four book which recommended things like "abstract factory" - the odd thing was, I thought most of those authors were ex smalltalkers?