Karunjith M

AI made knowldge cheap and accessible. Now everyone is trying to learn everything. But I dont believe its going to cut it in the future. There is so much out there that one lifetime is not enough to learn everything. Find what you like first and then find the right recipe. ...

TLDR; Instead of throwing everything into the LLM at once, break the work into multiple steps, summarize each outcome, and save checkpoints along the way. So at first there was LLM Then there was prompt engineering, evals, traces, etc Then there was a tool/ function calling. Then the Model Context Protocol (MCP) Now we have Context Engineering. What is context? All the inputs that you give to the LLM are called context. The words you type in, the pictures you upload, are all part of the contex...