Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind

Explains from the researcher who pioneered chain-of-thought why intermediate tokens drive LLM reasoning, which grounds prompting and reasoning-model decisions.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
• chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

• videoStanford CS329A Self-Improving AI Agents | Part 2 | Test-Time Compute Scaling
• videoStanford CS153 Frontier Systems | The AI Native Company: How One Founder Becomes a 1000x Engineer
• videoStanford CS25: Transformers United V6 I From Language Models to Native Multimodal Intelligence
• videoStanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 1 - Transformers

• articleChain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei et al.
• videoThe Best Models Still Reason Like Toddlers — Andrew Dai, ElorianAI Engineer
• videoStanford CS25: Transformers United V6 I From Language Models to Native Multimodal IntelligenceStanford Online

Checking sign-in…

Loading comments…