5 AI Building Blocks Every Engineer Should Know - LLMs - Embedding Models - RAG - Agent Harnesses - World Models

@sahnlam an embedding is just a float array you do cosine on. most people skip that and go straight to the vector db

@sahnlam Nice overview! World Models are the most interesting block on here imo. Genie 3 looks wild 🤩 Which one would you say took engineers the longest to really understand?

@sahnlam Agent harnesses deserve more attention; a capable model can still fail if the surrounding system handles tools, state, and errors poorly.

@sahnlam evals should be the sixth slide

@sahnlam Underrated part of RAG: chunking and the embedding model often matter more than which LLM sits on top. Would you count evals/observability as a 6th block? That's where most RAG setups feel weakest.

@sahnlam Evals deserve a spot too, so you can tell whether the RAG actually helped.