The 2026 LLM stack: models, inference, tooling, and trade-offs — companion videos

Andrej Karpathy

This is the clearest end-to-end explanation on YouTube of what an LLM actually is — pretraining, tokenization, SFT, RLHF, reasoning RL, tool use, hallucinations — at the level of detail an engineer needs to reason about model trade-offs. Watch it once and the "GPT-class vs. open-weights vs. reasoning model" decisions in the article stop feeling like brand choices and start feeling like training-recipe choices.

What you should get from this: Understand the modern LLM stack well enough to reason about tokens, training, tools and failures.

Watch or know first: Engineering background helps; no ML prerequisites, but budget for the three-and-a-half-hour runtime.

Y Combinator

Karpathy's AI Startup School keynote frames LLMs as a new kind of computer — utility, fab, and OS rolled together — and argues for "partial autonomy" products with a human-controlled leash. It is the cleanest articulation of the stack-level mental model the article assumes: that you are picking inference vendors and tooling for a programmable substrate, not a chatbot.

What you should get from this: Evaluate partial-autonomy product ideas where humans keep control over high-risk decisions.

Watch or know first: None — watchable cold; it pairs well after the deep dive's training-recipe grounding.