Andrej Karpathy
Andrej Karpathy
0
Andrej Karpathy, a founding member of OpenAI and former director of AI at Tesla, hosts in-depth lectures on neural networks and large language models, frequently building them from scratch. The show walks through the technical foundations of modern AI in a hands-on, educational style. Episodes are aimed at learners and practitioners who want to understand how these systems work at a deep level. Links to Karpathy's X account, personal website, Discord community and Eureka Labs are included with the show.
Episodes
-
Stable diffusion dreams of steam punk neural networks 21.11.2026 5m -
Building makemore Part 4: Becoming a Backprop Ninja 21.11.2026 2h 3m -
Building makemore Part 2: MLP 21.11.2026 1h 23m -
Building makemore Part 5: Building a WaveNet 21.11.2026 1h 4m -
The spelled-out intro to language modeling: building makemore 21.11.2026 2h 5m -
Let's build GPT: from scratch, in code, spelled out. 20.11.2026 2h 4m -
Stable diffusion dreams of psychedelic faces 20.11.2026 6m -
[1hr Talk] Intro to Large Language Models 20.11.2026 1h 7m -
Stable diffusion dreams of steampunk brains 20.11.2026 26m -
Stable diffusion dreams of "blueberry spaghetti" for one night 20.11.2026 7m -
Building makemore Part 3: Activations and Gradients, BatchNorm 20.11.2026 2h 3m
Popular in
The podcast also appears in the podcast charts of these countries.