LLMs
LLM capabilities, products and best practices
Across sections: 64 classics · 14 tutorials · 7 picks
Classics
2026-08-04 · 晚点 × Kimi K3 详解
Kimi K3 Explained: The Model That Shook Anthropic's Valuation
2026-08-04 · 盛颖 × 硅谷101
Sheng Ying on xAI Infra, SGLang, and Open Source
2026-08-01 · 姚顺雨 × 晚点
Yao Shunyu: 300 Days at Tencent
2026-07-31 · Patrick Collison × Y Combinator
Patrick Collison: Is AI Breaking the Lean Startup Playbook?
2026-07-30 · 陈冕（Liblib/Evoken 创始人） × 晚点
Liblib's Chen Mian: On Surviving and Near-Death Moments
2026-07-30 · Jeff Dean × Y Combinator
Jeff Dean: The 1% Rule for Building in AI
2026-07-29 · Alexandr Wang × Y Combinator
Alexandr Wang: A Once-in-a-Civilization Opportunity
2026-07-28 · 游凯超 × 张小珺
You Kaichao: Open-Source Infra, vLLM & Model Co-design
2026-07-28 · 叶奇意 × 硅谷101
Ye Qiyi on Yang Zhilin, Two Generations of Chinese AI & AGI Faith
2026-07-28 · Sam Altman × Patrick O'Shaughnessy
Sam Altman on AGI, Compute Race and Physical AI
2026-07-27 · Sam Altman × Y Combinator
Sam Altman: Never a Better Time to Do a Startup
2026-07-22 · Travis Kalanick × a16z
Travis Kalanick: Building a Company in Stealth
2026-07-07 · Steven Sinofsky × a16z
The New Rules of Enterprise Software with Steven Sinofsky
2026-07-03 · Nathan Lambert × 硅谷101
Nathan Lambert on China's AI Scene: Youth, Compute Anxiety & the AGI Showroom
2026-07-01 · Aravind Srinivas × Joe Rogan
Aravind Srinivas on AI search and the future of knowledge
2026-05-22 · Eric Schmidt × Alan Blinder
Eric Schmidt on the AI revolution: geopolitics, military & energy
2026-05-11 · 姚顺宇 × 张小珺
Yao Shunyu: Training Models at Anthropic & Gemini
2026-05-01 · 苏煜 × 张小珺
Su Yu: Agent Tech History & the OpenClaw Moment
2026-04-30 · 晚点 × DeepSeek V4 详解
DeepSeek V4 Explained: The Infra Whale & 1M Context
2026-04-29 · Andrej Karpathy × Stephanie Zhan
Karpathy: from vibe coding to agentic engineering
2026-04-29 · Demis Hassabis × Konstantine Buhler
Demis Hassabis: We're three quarters of the way to AGI
2026-04-24 · 罗福莉（小米大模型团队负责人） × 张小珺
Luo Fuli: The AI Paradigm Shift & the Agent Era
2026-04-06 · 晚点 LatePost（程曼祺）
DeepSeek before V4: Liang Wenfeng's talent war, org philosophy and AGI obsession
2026-03-23 · 黄仁勋 × Lex Fridman
Jensen Huang × Lex Fridman: NVIDIA, the $4T Company & the AI Revolution
2026-03-16 · 谢赛宁 × 张小珺
Xie Saining's 7-Hour Marathon: World Models & Twice Rejecting Ilya
2026-01-26 · 印奇（阶跃星辰董事长） × 张小珺
Yin Qi on Leading StepFun: Smart People's Temptations & Trade-offs
2026-01-08 · 张鹏（智谱 CEO）× 张小珺
Zhipu CEO Zhang Peng: The First Global LLM IPO
2025-12-30 · 季逸超（Manus 联合创始人） × 张小珺
Manus's Last Interview Before the Sale: Peak Ji on the Wild 2025
2025-11-25 · Demis Hassabis 等（纪录片）
The Thinking Game: DeepMind's Official Documentary
2025-11-25 · Ilya Sutskever × Dwarkesh Patel
Ilya Sutskever: From the Age of Scaling to Reconstruction
2025-11-10 · 张林峰/孙伟杰（深势科技）× 晚点
DP Technology: AI for Science, from Start to Now
2025-10-30 · 李想（理想汽车创始人/CEO） × 张小珺
Li Xiang Returns: CEO as LLM, MoE, and Human Wisdom
2025-10-09 · 吴明辉（明略科技）× 张小珺
Wu Minghui's 19-Year Story: Enterprise Agentic Models
2025-10-08 · Sam Altman × Ben Horowitz × Erik Torenberg
Sam Altman on Sora, energy, and building an AI empire
2025-09-18 · Mustafa Suleyman × Trevor Noah
Mustafa Suleyman on whether AI will save or end humanity
2025-09-11 · 姚顺雨（OpenAI）× 张小珺
Yao Shunyu (OpenAI): 6 Years of Agent Research
2025-08-27 · 杨植麟（月之暗面 CEO）× 张小珺
Yang Zhilin Returns: K2, Agentic LLMs & the Brain in a Vat
2025-07-22 · 戴雨森（真格基金）× 晚点
Dai Yusen's Mid-2025 AI Review: IMO Gold & Agent Spread
2025-07-22 · Geoffrey Hinton
Geoffrey Hinton: Will AI outsmart human intelligence?
2025-06-18 · Andrej Karpathy
Karpathy: Software Is Changing, Again (Software 3.0)
2025-06-02 · 张祥雨（阿里通义）× 张小珺
Zhang Xiangyu: Multimodal Struggles & Two GPT-4 Moments
2025-05-17 · 田渊栋（Meta）× 晚点
Tian Yuandong: An AI Researcher's Sci-Fi & 'Thought-to-Result'
2025-04-23 · Yann LeCun × Penn Engineering
Yann LeCun: Why LLMs Aren't the Path to AGI
2025-04-12 · Sam Altman × TED
Sam Altman at TED 2025: Agents, Superintelligence & ChatGPT
2025-03-18 · 马毅（香港大学）× 晚点
Ma Yi: DNA Is the First LLM; Intelligence Is Entropy Reduction
2025-03-14 · Geoffrey Hinton × Nobel Prize
Hinton's Nobel Interview: AI's Risks and Hopes
2025-02-25 · Robin Li（李彦宏）× Omar Sultan Al Olama
Robin Li on application-driven AI innovation
2025-02-11 · 王小川（百川智能创始人） × 晚点
Wang Xiaochuan: AI × Medicine and the Math of Life
2025-02-11 · 王小川 × 程曼祺
Wang Xiaochuan: Toward the mathematical principles of life sciences
2025-02-05 · Andrej Karpathy
Deep Dive into LLMs like ChatGPT
2025-01-29 · 张璐（Fusion Fund）× 晚点
Zhang Lu: How Silicon Valley Sees DeepSeek
2025-01-20 · 闫俊杰（MiniMax 创始人/CEO） × 晚点
MiniMax's Yan Junjie: Don't Apply Mobile-Internet Logic to LLMs
2025-01-20 · 闫俊杰 × 程曼祺
Yan Junjie: Don't apply mobile internet logic to LLMs
2025-01-14 · 李开复（零一万物创始人） × 晚点
Kai-Fu Lee: Only Big Tech Can Chase Frontier Models
2025-01-14 · 李开复 × 程曼祺
Kai-Fu Lee: Only big tech can chase super-large models
2025-01-02 · 李想（理想汽车创始人）× 张小珺
Li Xiang's First 3-Hour Interview (Full Podcast)
2024-12-22 · Yann LeCun × Kara Swisher
Yann LeCun: LLMs won't lead to AGI
2024-12-05 · Kai-Fu Lee（李开复）× Peter Diamandis
Kai-Fu Lee on how China is shaping the future of AI
2024-11-11 · Dario Amodei × Lex Fridman
Dario Amodei on Claude, AGI and the future of AI & humanity
2024-07-17 · 梁文锋 × 暗涌Waves（于丽丽）
Liang Wenfeng: Inside DeepSeek — China's most radical tech idealist
2024-03-18 · Sam Altman × Lex Fridman
Sam Altman on GPT-5, Sora and the board saga
2023-11-22 · Andrej Karpathy
Intro to Large Language Models
2023-08-14 · Ilya Sutskever
Ilya Sutskever: An Observation on Generalization
2023-01-17 · Andrej Karpathy
Let's build GPT from scratch, in code
Tutorials
2026-07-31 · Microsoft
Microsoft AI for Beginners: Complete 27-Lesson Course (MIT Licensed)
2026-07-30 · Google Gemini
Google Gemini API Quickstart: From AI Studio to Your First Request
2026-07-29 · OpenAI GPT
GPT API Quickstart: Build a Reliable Minimum Loop with OpenAI's Guide
2026-07-28 · OpenAI GPT
GPT Prompt Engineering: Turn Good Chat into an Evaluable Workflow
2026-07-27 · Anthropic Claude
Claude API Getting Started: From the First Message to Reliable Long-Context Work
2026-07-26 · Hugging Face
The Hugging Face LLM Course: From Model Calls to Your Own Evaluation Set
2026-07-25 · Microsoft Azure OpenAI
Azure OpenAI Quickstart: Put GPT Behind Enterprise Access and Monitoring
2025-11-05 · Anthropic
Anthropic's Prompt Engineering Docs: Claude in Context
2025-10-15 · Google Gemini
Google Gemini Agents Docs: Build Your First Agent
2025-09-01 · OpenAI GPT
OpenAI's Reasoning Models Guide: When & How
2025-08-20 · Google Gemini
Gemini API Docs Overview: Models, SDKs & Multimodality
2025-06-01 · Anthropic
Claude 3.5 Sonnet in Practice: From Chat to Agent Workflows
2025-05-10 · Microsoft
Microsoft's Generative AI Learning Path
2025-02-24 · Anthropic