Home

Talks & Presentations

Curated talks on LLMs, prompt engineering, agents, and AI systems from researchers and practitioners. Organized by topic for targeted learning.

Contents

Foundational Understanding

Essential background for understanding modern LLMs.

Talk Speaker Why Watch
Intro to Large Language Models Andrej Karpathy Best 1-hour introduction to how LLMs work
State of GPT Andrej Karpathy How ChatGPT was trained, from pre-training to RLHF
Let's Build GPT: From Scratch Andrej Karpathy Build a GPT from scratch in code — deep understanding
Neural Networks: Zero to Hero Andrej Karpathy Full course from basics to transformers
The Illustrated Transformer Jay Alammar Visual explanation of transformer architecture
Attention is All You Need Yannic Kilcher Paper walkthrough of the foundational transformer paper

Prompt & Context Engineering

Practical techniques for working with LLMs.

Talk Speaker Why Watch
Prompt Engineering Overview Elvis Saravia (DAIR.AI) Comprehensive overview of prompting techniques
Advanced Prompt Engineering Anthropic Official Anthropic guide to prompting Claude
Building Blocks of LLM Applications Chip Huyen Context engineering for production systems
Prompt Engineering for Developers Andrew Ng & Isa Fulford Free course on systematic prompting
The Art of Prompt Design Simon Willison Practical tips from an experienced practitioner

Agents & Autonomous Systems

Building AI systems that reason and act.

Talk Speaker Why Watch
Building Effective Agents Anthropic Official Anthropic guide to agent development
The Rise of AI Agents Harrison Chase (LangChain) Agent patterns and LangGraph architecture
AI Agents in LangGraph Harrison Chase Free course on building agents
Multi-Agent Systems with CrewAI João Moura Free course on multi-agent orchestration
Function Calling and Agents OpenAI Official OpenAI guide to function calling
The Agent Protocol Letta Standardizing agent interfaces

RAG & Knowledge Systems

Grounding LLMs with external knowledge.

Talk Speaker Why Watch
Building RAG Applications Jerry Liu (LlamaIndex) Advanced RAG techniques course
RAG From Scratch LangChain Complete RAG implementation series
Advanced Retrieval for AI Chroma Retrieval optimization techniques
Vector Databases Explained Pinecone Understanding vector search
When RAG Goes Wrong Jason Wei Common RAG failures and fixes

Building with LLMs

Engineering production LLM systems.

Talk Speaker Why Watch
Building LLM Applications Chip Huyen Production considerations for LLM apps
A Survey of Techniques for Maximizing LLM Performance OpenAI Official optimization techniques
Emerging Architectures for LLM Applications a16z Reference architectures for LLM apps
Productionizing LLM Applications Eugene Yan (Amazon) Lessons from production deployments
LLMOps: Production LLM Pipelines MLflow Operationalizing LLM applications

AI Safety & Alignment

Building safe and aligned AI systems.

Talk Speaker Why Watch
AI Safety Fundamentals Robert Miles Accessible introduction to AI safety
Constitutional AI Anthropic How Claude is trained to be helpful and harmless
Red Teaming Language Models Anthropic Finding and fixing model vulnerabilities
RLHF: Training Language Models from Human Feedback Hugging Face Understanding reinforcement learning from human feedback
Prompt Injection Attacks Simon Willison Security risks in LLM applications
Mechanistic Interpretability Neel Nanda (Anthropic) Understanding what's inside neural networks

Research Frontiers

Latest developments from leading researchers.

Talk Speaker Why Watch
Scaling Laws for Neural Language Models OpenAI Why scale matters
Chain-of-Thought Prompting Jason Wei (Google) Original CoT research
Emergent Abilities of Large Language Models Jason Wei What abilities appear at scale
The Future of Foundation Models Percy Liang (Stanford) Where foundation models are heading
Multimodal Learning Douwe Kiela Vision + language models
The Bitter Lesson Revisited Rich Sutton Fundamental insights about AI progress

Industry Perspectives

Insights from AI leaders and practitioners.

Talk Speaker Why Watch
Fireside Chat: The Future of AI Dario Amodei (Anthropic) CEO perspective on AI development
Building the Future of AI Sam Altman (OpenAI) OpenAI's vision and approach
AI Engineering Swyx The emerging AI engineering discipline
The AI Engineer Summit Keynotes Various AI Engineer World's Fair talks
Practical AI Podcast Various Ongoing discussions with practitioners
Latent Space Podcast Swyx & Alessio Deep dives with AI builders

Classic Talks (Pre-LLM Era)

Foundational thinking that shaped the field.

Talk Speaker Why Watch
Deep Learning Yann LeCun Pioneer's perspective on deep learning
The Future of Deep Learning Yoshua Bengio Insights from a Turing Award winner
AI and the Future of Work Kai-Fu Lee Impact of AI on employment
The Wonderful and Terrifying Implications of AI Jeremy Howard Early deep learning excitement and concerns
What Happens When Computers Get Smarter Than We Are Nick Bostrom Foundational AI safety thinking
How to Get Empowered, Not Overpowered, by AI Max Tegmark Long-term AI futures

Conference Channels

Where to find more talks:

Conference Focus Channel
NeurIPS ML research YouTube
ICML ML research YouTube
AI Engineer World's Fair AI engineering YouTube
Anthropic Claude, safety YouTube
OpenAI GPT, research YouTube
Google DeepMind Research YouTube
Hugging Face Open source ML YouTube

Notes

Links are verified as of January 2026 but may change. If you find a broken link, please open an issue.

Feedback and suggestions are welcome!

Last updated: January 2026