A clear, practical explanation of how LLM agents work: treating the LLM as the agent's “brain,” tool calls as actions, and executed tools as the environment. The talk walks through the mechanics of function calling, prompts, schemas, and iterative tool-use loops. It covers strategies for reliable tool calling and the engineering needed for long tool-call chains, including caching, finite-state control, external memory, and techniques to prevent goal drift. Overall, it bridges classic RL concepts with modern LLM agent design to show how to build robust, long-horizon AI agents.
Register for the hackathon: https://www.wemakedevs.org/hackathons/assemblehack25
Advantages and disadvantages
Advantages
Free, one long video that covers a topic end to end.
Use the chapters to jump to what you need.
Completely free.
Self-paced: start any time.
Start watching right away, no sign-up.
Disadvantages
No exercises or certificate: code along to make it stick.
No certificate.
Short (45 minutes): an overview, not deep coverage.
No graded assignments or feedback.
Some points apply to every course of this kind; see how we rank.
Free
Free: Watch on YouTube, no account needed.
Certificate: None. Code or take notes along to make it stick.
Explore the cutting-edge realm of Large Language Models (LLMs) with this expertly curated YouTube playlist. Featuring insights from industry leaders, educational content, and in-depth discussions, this selection highlights the latest advancements in LLM technology.
This course explores the world of Transformers and Large Language Models (LLMs). You will learn the evolution of NLP methods, the core components of the Transformer architecture, along with how they relate to LLMs as well as techniques to enhance model performance for real-world applications. Throu…
Dive into the intriguing world of AI Transformers with this curated YouTube playlist. Featuring expert insights, educational content from leading organizations, and engaging discussions, this playlist keeps you informed about the latest breakthroughs in Transformer technology.
Stanford CS25: Transformers United Since their introduction in 2017, transformers have revolutionized Natural Language Processing (NLP). Now, transformers are finding applications all over Deep Learning, be it computer vision (CV), reinforcement learning (RL), Generative Adversarial Networks (GANs)…
Instructors: David Sontag, Peter Szolovits View the complete course: https://ocw.mit.edu/6-S897S19 Introduces students to machine learning in healthcare, the nature of clinical data, and the use of machine learning for risk stratification, disease progression modeling, precision medicine, diagnosis…