RAG vs. Agentic RAG visually explained:

LLMQuoter Enhances RAG capabilities using a "quote-first-then-answer" strategy. Adopts Llama-3B and finetunes with LoRA on a 15K sample subset of HotPotQA to enhance RAG by identifying key quotes before passing them to reasoning models. "This workflow reduces cognitive

MIT's "Principles of Applied Mathematics" Lecture notes: ocw.mit.edu/courses/18-311…

What a great resource to learn how others are building with LLMs and AI agents.

Traditional RAG vs. Agentic RAG, clearly explained (with visuals):

Agentic RAG Overview This is a great intro to LLM agents and Agentic RAG. It provides a comprehensive exploration of Agentic RAG architectures, applications, and implementation strategies.

DeepSeek-R1: Technical Deep Dive 36-page report courtesy of Deep Research. Models like o3 still make mistakes so keep that in mind. (prompt + report in the ALT)

You're the product of your thoughts, choices, and habits

"An Introduction to Mathematical Reasoning" sites.math.washington.edu/~conroy/m300-g…

How to Read a Book

Fantastic question, and one I’ve been thinking about for a long time. If you are willing to choose a preferred specification, you can report the smallest distance such that you do not reject all other specifications are within that distance from your main specification.

The Transformers architecture clearly explained 👇🏻

Gilbert Strang's "The Big Picture of Linear Algebra" shows the relationship between four fundamental subspaces of an m by n matrix. These four subspaces are: - Column space: all combinations of columns of A - Row space: all combinations of rows of A - Nullspace of A: all

Prompt Engineering is NOT dead! If you develop seriously with LLMs and are building complex agentic flows, you don't need convincing about this. I've built the most comprehensive, up-to-date course on prompting LLMs, including reasoning LLMs. 4 hours of content! All Python!

Stanford's "Probability for Computer Scientists" PDF: web.stanford.edu/~mossr/pdf/p4c…

Prompting reasoning LLMs like o3-mini is different from prompting standard chat LLMs. Here are 10 tips on how to effectively prompt reasoning LLMs: (🔖bookmark for later)

5 levels of Agentic AI systems, clearly explained (with visuals):

// Chain-of-Tools // This new paper presents Chain-of-Tools (CoTools), a new method to enable LLMs to incorporate expansive external toolsets—including tools never seen during training—while preserving CoT (chain-of-thought) reasoning. Highlights: • Frozen LLM with

// Building Effective Agents using Agents SDK // Had a lot of fun going through the agentic workflow examples using OpenAI Agents SDK. I shared a getting-started guide that I'm working on for an upcoming short course. If you missed it, find it below. (bookmark for later)

9 RAG, LLM, and AI Agent cheat sheets for AI engineers (with visuals):