Post

I asked Claude 3.7 + GitHub MCP to do one thing. Very specifically, one thing. It did 3. I understand the line of thought, and it uses the chat context to make decisions autonomously. But that is not what I want it to do!

I want something else, and it would probably have been good if it had stopped by Step#1.

I guess the emergent behaviors with LLMs (ofc configured by LLM providers) are making and executing decisions. --- This is where we and AGI-ready LLMs probably diverge.