This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads.
Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.
How difficult is it to make a RL env from scratch (not as great as @puffer_ai but a simple one.
Iam thinking of developing some env like Mars exploration with rover as agent
@rasbt blog is like a dictionary for LLM Architectures 🫡. He has a blog for everything.
I started with GLM 5.2 and then ended up reading his DSA, MLA, MTP, DeepSeekV3.2 blogs