echohive

The library

Everything I teach, in one place.

90+ video lessons, every Sunday Lab replay and the apps I’ve built, sorted by what you want to do: understand what’s changing, find your ideas and direction, build with the models, or look after your money and mind.

101 lessons, 93 Lab replays and 6 apps · newest first, each with its date

Browse

Find the one you need.

Show

Understand what’s changing

Find your ideas and direction

Build with the models

Money and mind

  1. Lesson 85 Ship it inside ChatGPTSeven steps to put your product inside ChatGPT, checked against OpenAI’s docs.In the Get Amplified collection on PatreonBuilding apps Members (opens in a new tab)
  2. Lesson 84 The 1.7% app playbookLessons from David Ch’s look at 431,757 apps.In the Get Amplified collection on PatreonBuilding apps · Your brand Members (opens in a new tab)
  3. Lesson 83 Neural networks are already clean, explainedA clear walk through Nick Cammarata’s essay, using its own figures.In the Get Amplified collection on PatreonResearch and learning Members (opens in a new tab)
  4. Lesson 82 How to be more ambitious with the modelsAim higher, and set the work up so the models can meet you there.In the Get Amplified collection on PatreonMeta thinking · Ideas and creativity Members (opens in a new tab)
  5. Lesson 81 Not a prompt, a conversation: how I built Instant 3D ModelsThe habits behind a build that came out of one long conversation.In the Get Amplified collection on PatreonBuilding apps · Simulations and visuals · Meta thinking Members (opens in a new tab)
  6. Lesson 80 How I built the world’s fastest video, website and app makersMy process, from the first idea to three working builders.In the Get Amplified collection on PatreonBuilding apps · Meta thinking Members (opens in a new tab)
  7. App Three spaceships by Astra UltraPALISADE, KATABASIS and VESPER, each one a single file you can open.Simulations and visuals Members (opens in a new tab)
  8. Lesson Rethink everything: eight realizations about building nowWhat changes when an idea no longer costs weeks of your time.Meta thinking · Building apps Members (opens in a new tab)
  9. Lab replay An astounding September, models at a million tokens a second, and making yourself the brandThe accelerating world · New models, tested · Your brand Lab (opens in a new tab)
  10. Lesson Watch the live build: one article into a research mapThe Branch constellation app, built live from start to finish.Building apps · Research and learning Members (opens in a new tab)
  11. App Live Streamer StudioA live stream that makes itself, now with the Singularity Show.Building apps · Films, songs and images Members (opens in a new tab)
  12. Lesson Everything is accelerating. How do we find our direction and meaning?Choosing what to do next when the models keep getting better at your work.Meaning and direction · The accelerating world Members (opens in a new tab)
  13. Lesson Turn one article into a research map with CodexBuild Branch: one link becomes a map of the ideas behind it.Research and learning · Codex · Building apps Members (opens in a new tab)
  14. Lab replay Building Branch, how I build the 2.5D scenes, and stopping Astra’s chess cheatingBuilding apps · Research and learning · Simulations and visuals · Safety and security Lab (opens in a new tab)
  15. App 15 Living PaintingsScenes you can explore, download and learn from.Simulations and visuals · Films, songs and images Members (opens in a new tab)
  16. Lesson AI kept giving me the same ideas. This helpedThree prompts that pull fresher ideas out of a model, tested in a small experiment with Astra.Ideas and creativity Free (opens in a new tab)
  17. Lesson From images to an interactive world in two hoursA mini-guide to the 2.5D parallax scenes, made with Opus 5.5.Simulations and visuals · Films, songs and images Members (opens in a new tab)
  18. Lesson Agreement prompts against agent reward hackingA simple agreement prompt, tested on Grok 4.6 agents that cheat at a task. An experiment, not a guarantee.Safety and security · Agents and workflows Members (opens in a new tab)
  19. Lab replay Drift, a better research app, and finding your core valueResearch and learning · Building apps · Meaning and direction · Markets Lab (opens in a new tab)
  20. App Drift, for open-ended researchExplore a question as a growing map of ideas.Building apps · Research and learning Members (opens in a new tab)
  21. Lesson How to make Astra creativeA three-step approach: guide the exploration without supplying the ideas.Ideas and creativity · New models, tested Members (opens in a new tab)
  22. Lesson Real-time voice that talks like a friendA voice app that fills silences and joins in when it has something to say.Building apps Members (opens in a new tab)
  23. Lab replay A voice app that interrupts, making Grok and Astra creative, and a pinky promise against cheatingBuilding apps · Ideas and creativity · Safety and security Lab (opens in a new tab)
  24. Lesson Solving problems you don’t fully understandWhy it’s worth trying, and some ways to approach it.Meta thinking · Research and learning Members (opens in a new tab)
  25. Lesson How to make Astra more creative, without giving it the ideasGuide the model toward fresh ideas instead of supplying them.Ideas and creativity · New models, tested Members (opens in a new tab)
  26. Lesson Astra vs Fable 5.1Two new models compared on real work.New models, tested Members (opens in a new tab)
  27. Lesson Astra and Fable 5.1 experimentsNeural networks, learning algorithms and evolution, built by two new models.New models, tested · Simulations and visuals Members (opens in a new tab)
  28. App Deep Talk BuddyTalk with a model the way you’d talk with a friend.Building apps Members (opens in a new tab)
  29. Lesson Get Amplified: an introductionWhat the course covers, and where to start.Meta thinking Members (opens in a new tab)
  30. Lab replay Astra updates, Astra vs Fable 5.1, and working on problems you don’t understandNew models, tested · Meta thinking · Research and learning Lab (opens in a new tab)
  31. Lesson 79 Finding meaning in the age of superintelligenceIf the models can do more of your work, what do you want to do with your life?Meaning and direction · The accelerating world Members (opens in a new tab)
  32. Lesson 78 RSI, superintelligence and marketsWhere value could build as the models move from code into the physical world.The accelerating world · Markets Members (opens in a new tab)
  33. Lesson Eight levels of asking the models to be originalThe same simple request, asked eight ways, from plain to deeply creative.Ideas and creativity Members (opens in a new tab)
  34. Lab replay RSI, superintelligence and markets, and finding meaning as the models riseThe accelerating world · Markets · Meaning and direction Lab (opens in a new tab)
  35. Lesson 77 Finding what you loveYou have more ways to build than ever. How do you find something worth building?Meaning and direction · Ideas and creativity Members (opens in a new tab)
  36. Lesson 76 Markets, robots and the singularityWhat changes when the models start working in the physical world?The accelerating world · Markets Members (opens in a new tab)
  37. Lab replay Markets, robots and the singularity, finding something you love, and neuroplasticityThe accelerating world · Markets · Meaning and direction · Mind and attention Lab (opens in a new tab)
  38. Lesson 75 Markets: recap and reviewWhere you could take part in an economy the models are changing. Never financial advice.Markets Members (opens in a new tab)
  39. Lesson 74 Meta strategies: review and recapGo beyond better prompts: decide what work is worth handing to the models.Meta thinking Members (opens in a new tab)
  40. Lab replay A recap of meta thinking, markets and mindfulnessMeta thinking · Markets · Mind and attention Lab (opens in a new tab)
  41. Lesson 73 Ideas by voice with GPT-liveTalk your way from a vague idea to a better question.Ideas and creativity Members (opens in a new tab)
  42. Lesson 72 What becomes valuable nowWhat becomes valuable when the models can do more of the solving?Meta thinking · The accelerating world Members (opens in a new tab)
  43. Lesson 71 Cool Grok use casesMore uses for Grok in your research and creative work.New models, tested · Research and learning · Films, songs and images Members (opens in a new tab)
  44. Lab replay Grok use cases, preparing for Astra and superintelligence, and ideas by voiceNew models, tested · The accelerating world · Ideas and creativity · Mind and attention Lab (opens in a new tab)
  45. Lesson 70 Simple ways into mindfulnessStart noticing where your attention goes.Mind and attention Members (opens in a new tab)
  46. Lesson 69 Meta thinking methodsFind bigger problems to explore, even when you don’t know every step.Meta thinking · Ideas and creativity Members (opens in a new tab)
  47. Lesson 68 Stock market updateKeep a wider view when AI stocks swing sharply. Never financial advice.Markets Members (opens in a new tab)
  48. Lab replay The coming Astra and its math proofs, singularity updates, stocks, and meta thinkingThe accelerating world · New models, tested · Markets · Meta thinking · Mind and attention Lab (opens in a new tab)
  49. Lesson 67 Stock market update: memory stocksThe assumptions behind AI investing, beyond daily price moves. Never financial advice.Markets Members (opens in a new tab)
  50. Lesson 66 Are we in the technological singularity?How should you respond when progress starts to feel hard to keep up with?The accelerating world Members (opens in a new tab)
  51. Lab replay Opus 5, are we in the singularity?, meta methods, and a simple way into mindfulnessThe accelerating world · New models, tested · Markets · Meta thinking · Mind and attention Lab (opens in a new tab)
  52. Lesson 65 The original instructions for mindfulnessExplore the instructions behind mindfulness for yourself.Mind and attention Members (opens in a new tab)
  53. Lab replay Kimi K3 and Qwen, loops, graphs and cortexes, Monte Carlo for stocks, and simpler mindfulness (audio only)New models, tested · Meta thinking · Agents and workflows · Markets · Mind and attention Lab (opens in a new tab)
  54. Lesson 64 How to play in the latent lab of the mindTurn inward with curiosity, not another task to perfect.Mind and attention Members (opens in a new tab)
  55. Lesson 63 J-space and the global workspaceExplore what enters your attention, and what you can do with it.Mind and attention Members (opens in a new tab)
  56. Lesson 62 Why meta thinking mattersAre old assumptions limiting what you ask the models to do?Meta thinking Members (opens in a new tab)
  57. Lesson 61 GPT 5.6, Codex and Claude Code updatesSee how I organize more capable agents around real work.New models, tested · Codex · Claude Code Members (opens in a new tab)
  58. Lab replay GPT 5.6, Codex and Claude Code, why meta thinking is the moat, and J-spaceNew models, tested · Codex · Claude Code · Meta thinking · Mind and attention Lab (opens in a new tab)
  59. Lesson 60 A cautionary enlightenment storyWhat can go wrong when meditation becomes an achievement to chase?Mind and attention Members (opens in a new tab)
  60. Lesson 59 Stock market strategiesUnderstand the choices behind an investing strategy. Never financial advice.Markets Members (opens in a new tab)
  61. Lesson 58 Tournament-style researchMake your research work harder before you choose.Research and learning · Meta thinking Members (opens in a new tab)
  62. Lab replay GPT 5.6, robotics, tournament-style research, and the earliest meditation instructionsNew models, tested · The accelerating world · Research and learning · Mind and attention Lab (opens in a new tab)
  63. Lesson 57 The latent lab of the mind: methods, simplifiedMake exploring your mind feel more approachable.Mind and attention Members (opens in a new tab)
  64. Lesson 56 The latent lab of the mind: why, and the theoryGet curious about the patterns behind your reactions.Mind and attention Members (opens in a new tab)
  65. Lesson 55 Codex side chats and manager threadsKeep several tasks moving with clearer coordination.Codex · Agents and workflows Members (opens in a new tab)
  66. Lab replay Codex workflows, and the latent lab of the mind: the theory and the methodsCodex · Mind and attention · New models, tested Lab (opens in a new tab)
  67. Lesson 54 Interpretability and the mind, part 1What can watching your own attention teach you?Mind and attention Members (opens in a new tab)
  68. Lesson 53 Stock update 7Build a clearer process for investing through uncertainty. Never financial advice.Markets Members (opens in a new tab)
  69. Lab replay Interpretability of the mind, how good GLM 5.2 is, and Codex and stock updatesMind and attention · New models, tested · Codex · Markets Lab (opens in a new tab)
  70. Lesson 52 How to create mathematical visualizationsTurn a visual idea into something you can explore.Simulations and visuals Members (opens in a new tab)
  71. Lesson 51 Everyday agent use casesPut your agent to work on the small tasks that eat your day.Agents and workflows · Films, songs and images Members (opens in a new tab)
  72. Lab replay Everyday agent use cases, mathematical visualizations, and agents talking latent to latentAgents and workflows · Simulations and visuals Lab (opens in a new tab)
  73. Lesson 50 Completion criteria: tips for longer agent tasksGive your agent a clearer finish line.Agents and workflows Members (opens in a new tab)
  74. Lesson 49 RSI, science, engineering and marketsRecursive self-improvement, and what it could mean for science, engineering and markets.The accelerating world · Markets Members (opens in a new tab)
  75. Lesson 48 Creative ways to ask the modelsWays of asking that get you more original answers.Ideas and creativity Members (opens in a new tab)
  76. Lab replay Creative ways to ask the models, /goal methods, is RSI near?, and the stock marketIdeas and creativity · Codex · The accelerating world · Markets Lab (opens in a new tab)
  77. Lesson 47 GPT 5.5 vs Opus 4.8, and Codex updatesThe newest models compared, and what changed in Codex.New models, tested · Codex Members (opens in a new tab)
  78. Lesson 46 Singularity updatesWhere things stand, and how fast they’re moving.The accelerating world Members (opens in a new tab)
  79. Lesson 45 Stock market update 6An educational discussion. Never financial advice.Markets Members (opens in a new tab)
  80. Lab replay A singularity update, Codex updates, GPT 5.5 vs Opus 4.8, and the stock marketThe accelerating world · Codex · New models, tested · Markets Lab (opens in a new tab)
  81. Lesson 44 Stock update 5An educational discussion. Never financial advice.Markets Members (opens in a new tab)
  82. Lesson 43 Switching from a PC to a MacMoving my whole setup over, and what to watch for. Members (opens in a new tab)
  83. Lab replay A GPT model solves an 80-year-old math problem, CAD designs, and Codex updatesThe accelerating world · New models, tested · Codex Lab (opens in a new tab)
  84. Lesson 42 npm, pip and uv package securityProtect your machine from malicious packages.Safety and security Members (opens in a new tab)
  85. Lesson 41 Simulations with CursorBuild simulations you can watch and play with.Cursor · Simulations and visuals Members (opens in a new tab)
  86. Lab replay /goal updates, package security, and stocksCodex · Safety and security · Markets Lab (opens in a new tab)
  87. Lesson 40 A super-exponential, and stocks (Stocks 4)Is progress speeding up faster than exponential, and what could that mean for markets?Markets · The accelerating world Members (opens in a new tab)
  88. Lesson 39 Stock updates, more objective (Stocks 3)An educational discussion. Never financial advice.Markets Members (opens in a new tab)
  89. Lab replay Is progress super-exponential? Stocks, and simulations in CursorThe accelerating world · Markets · Cursor · Simulations and visuals Lab (opens in a new tab)
  90. Lesson 39 Codex /goalGive Codex a goal and let it work toward it.Codex · Agents and workflows Members (opens in a new tab)
  91. Lesson 38 Cell simulations with CodexBuild a living cell simulation with Codex.Codex · Simulations and visuals Members (opens in a new tab)
  92. Lab replay Codex’s /plan feature, simulations in Codex, and AI stocksCodex · Simulations and visuals · Markets Lab (opens in a new tab)
  93. Lesson 37 Considering stocks in the age of AI (Stocks 2)An educational discussion. Never financial advice.Markets Members (opens in a new tab)
  94. Lesson 36 Animated images with ChatGPTBring still images to life.Films, songs and images Members (opens in a new tab)
  95. Lab replay The stock market with the models in mind, animated images, and GPT 5.5Markets · Films, songs and images · New models, tested Lab (opens in a new tab)
  96. Lesson 35 Opus 4.7 and GPT 5.4 on one projectTwo models working together, each where it’s strongest.New models, tested · Claude Code · Codex Members (opens in a new tab)
  97. Lab replay Getting the most from Opus 4.7 with GPT 5.4, plus Claude Code tipsNew models, tested · Claude Code · Codex Lab (opens in a new tab)
  98. Lesson 34 Changing Codex settings and the status lineSet Codex up the way you work.Codex Members (opens in a new tab)
  99. Lesson 33 Understanding the agent harness and its MD filesWhat the instruction files around an agent actually do.Agents and workflows · Claude Code · Codex Members (opens in a new tab)
  100. Lab replay Models vs poker, neural computers, Codex settings, and the agent harnessNew models, tested · Codex · Agents and workflows Lab (opens in a new tab)
  101. Lesson 32 Karpathy’s idea fileKeep a running file of ideas, after Andrej Karpathy.Ideas and creativity Members (opens in a new tab)
  102. Lesson 31 Insights, truth tables and counterargumentsAsk the models to argue back, so your ideas get sharper.Meta thinking · Research and learning Members (opens in a new tab)
  103. Lab replay A fix for malicious packages, Karpathy’s idea file, and GPT Image 2Safety and security · Ideas and creativity · Films, songs and images Lab (opens in a new tab)
  104. Lesson 30 Long narrative songs in SunoSongs that tell a story, made in Suno.Films, songs and images Members (opens in a new tab)
  105. Lab replay Taking it slowly, dynamic text with Pretext, and models that argue backMeta thinking · Building apps · Ideas and creativity Lab (opens in a new tab)
  106. Lesson 29 A song about Nvidia and FeynmanA song made with the models, from idea to finished track.Films, songs and images Members (opens in a new tab)
  107. Lesson 28 Space stocks (Stocks 1)An educational look at space companies. Never financial advice.Markets Members (opens in a new tab)
  108. Lab replay Rewriting insights into more insights, space stocks, and narrative songsIdeas and creativity · Markets · Films, songs and images Lab (opens in a new tab)
  109. Lesson 27 Making creative videos with the modelsFrom an idea to a finished, creative video.Films, songs and images Members (opens in a new tab)
  110. Lab replay How to relax the mind, creative videos, and Claude diagramsMind and attention · Films, songs and images Lab (opens in a new tab)
  111. Lesson 26 Cursor improving websites and sims on its ownRecursive improvement loops, including an agent that plays Tetris.Cursor · Agents and workflows · Simulations and visuals Members (opens in a new tab)
  112. Lesson 25 When subagents help, and GPT 5.3 Codex vs 5.4When to split work across subagents, plus a model comparison.Agents and workflows · Codex · New models, tested Members (opens in a new tab)
  113. Lab replay GPT 5.4 vision, self-improving sims, two agents on one task, and when subagents helpNew models, tested · Simulations and visuals · Agents and workflows Lab (opens in a new tab)
  114. Lesson 24 Codex or Claude Code as a tool inside CursorRun one agent from inside another editor.Codex · Claude Code · Cursor Members (opens in a new tab)
  115. Lab replay Codex as a tool in Cursor, and a pipeline of agentsCodex · Cursor · Agents and workflows Lab (opens in a new tab)
  116. Lesson 23 Agent use cases: charts marked with news eventsAgents that line up a chart with the news that moved it.Agents and workflows · Research and learning Members (opens in a new tab)
  117. Lesson 22 Agent use cases: future projection chartsAgents that research a subject and chart where it may go.Agents and workflows · Research and learning Members (opens in a new tab)
  118. Lab replay Interesting use cases for agentsAgents and workflows Lab (opens in a new tab)
  119. Lesson 21 Building Codex workflowsTurn work you repeat into Codex workflows.Codex · Agents and workflows Members (opens in a new tab)
  120. Lab replay GPT 5.3 Codex Spark vs Composer 1.5, and Codex workflowsNew models, tested · Codex · Cursor Lab (opens in a new tab)
  121. Lesson 20 Claude Code agent teamsSeveral agents working on one job together.Claude Code · Agents and workflows Members (opens in a new tab)
  122. Lesson 19 Recovering context during compactionKeep long Claude Code sessions on track when their context is compacted.Claude Code Members (opens in a new tab)
  123. Lab replay Claude Code agent teams, and recovering context after compactionClaude Code · Agents and workflows Lab (opens in a new tab)
  124. Lesson 18 A Claude Code subagent that uses CodexLet Claude Code call Codex as one of its tools.Claude Code · Codex · Agents and workflows Members (opens in a new tab)
  125. Lab replay Custom subagents in Claude Code, and Codex inside Claude CodeClaude Code · Codex · Agents and workflows Lab (opens in a new tab)
  126. Lesson 17 Opus 4.5 vs GPT 5.2 CodexThe two leading coding models, side by side.New models, tested · Claude Code · Codex Members (opens in a new tab)
  127. Lesson 16 Loops in Codex CLIThe same looping idea, run with Codex.Codex · Agents and workflows Members (opens in a new tab)
  128. Lab replay Opus vs GPT, and Codex in Ralph Wiggum style loopsNew models, tested · Codex · Agents and workflows Lab (opens in a new tab)
  129. Lesson 15 Claude Agent SDK quickstartBuild your own agents on the SDK behind Claude Code.Claude Code · Agents and workflows Members (opens in a new tab)
  130. Lesson 14 Loops in Claude Code: the Ralph Wiggum methodLet Claude Code work through a task in repeated passes.Claude Code · Agents and workflows Members (opens in a new tab)
  131. Lab replay Software engineering automated in three months? Plus a Claude Agent SDK crash courseThe accelerating world · Claude Code · Agents and workflows Lab (opens in a new tab)
  132. Lesson 13 CLAUDE.md and skills, a crash courseGive Claude Code lasting instructions and reusable skills.Claude Code Members (opens in a new tab)
  133. Lesson 12 Claude Code quickstartInstall it and get your first project going.Claude Code Members (opens in a new tab)
  134. Lab replay Claude Code, simplified: install, CLAUDE.md, skills, loops and pluginsClaude Code Lab (opens in a new tab)
  135. Lab replay Why things have changed and what it means, and how I built Auto ScientistThe accelerating world · New models, tested · Research and learning Lab (opens in a new tab)
  136. App Auto App Maker and ideation instructions for Claude CodeTwo CLAUDE.md files for building and ideating, with 18 apps made from them.Claude Code · Building apps · Ideas and creativity Members (opens in a new tab)
  137. Lesson 11 Awakenings with Opus 4.5 and Claude CodeWhat changed when Opus 4.5 and Claude Code arrived, and what it means.Claude Code · New models, tested · The accelerating world Members (opens in a new tab)
  138. Lab replay Where the models and coding are headingThe accelerating world Lab (opens in a new tab)
  139. Lab replay Thoughts on app building, Claude Code, Codex, and Claude as an agentBuilding apps · Claude Code · Codex · Agents and workflows Lab (opens in a new tab)
  140. Lesson 10 What I learned building Gallery of Babel and NCA evolutionLessons from two of my own builds.Simulations and visuals · Building apps Members (opens in a new tab)
  141. Lesson 9 How big thinkers might have thoughtBorrow the habits of great thinkers when you work with the models.Meta thinking · Ideas and creativity Members (opens in a new tab)
  142. Lab replay GPT 5.2 vs Opus 4.5, building ideas from podcasts, and learning with HTMLNew models, tested · Ideas and creativity · Research and learning Lab (opens in a new tab)
  143. Lesson 8 Applied research on any topic, with codeTurn a question on any subject into experiments you can run.Research and learning Members (opens in a new tab)
  144. Lesson 7 Why studying is the cheat code, and how to studyWhy learning pays off more than ever, and a way to do it.Research and learning Members (opens in a new tab)
  145. Lab replay Why studying is a cheat code, how to study, and applied research on any topicResearch and learning Lab (opens in a new tab)
  146. Lesson 6 Combine common ideas into a unique oneTwo ordinary ideas can make a webapp nobody else has.Ideas and creativity · Building apps Members (opens in a new tab)
  147. Lesson 5 Shape it in the chat, then let Cursor build itAn agentic process: plan the idea in Cursor’s chat, then hand over the build.Cursor · Agents and workflows Members (opens in a new tab)
  148. Lab replay Three apps, built as fast as we can, each with a different ideation methodIdeas and creativity · Building apps Lab (opens in a new tab)
  149. Lesson 4 Idea generation, method 2A second, quicker way to find ideas worth building.Ideas and creativity Members (opens in a new tab)
  150. Lesson 3 Idea generation, method 1A way to come up with an idea and then build it.Ideas and creativity Members (opens in a new tab)
  151. Lab replay The plan for Get Amplified, and building in Cursor and AntigravityMeta thinking · Cursor Lab (opens in a new tab)
  152. Lesson 2 Getting creative with Cursor, right awayThe basics of using Cursor as a creative tool from your first session.Cursor · Ideas and creativity Members (opens in a new tab)
  153. Lesson 1 Get Amplified: the series introWhat the series is for, plus 18 open-source projects to start from.Meta thinking · Building apps Members (opens in a new tab)
  154. Lab replay How to amplify yourself with the modelsMeta thinking Lab (opens in a new tab)
  155. Lab replay A new website, future projects, and learning with the modelsResearch and learning · Your brand · Cursor Lab (opens in a new tab)
  156. Lab replay Building an RL visualizer with Composer, and why math algorithms winSimulations and visuals · Research and learning · Cursor Lab (opens in a new tab)
  157. Lab replay A neural networks crash course, neuroscience to code, and predicting physicsResearch and learning · Simulations and visuals Lab (opens in a new tab)
  158. Lab replay A reinforcement learning crash course, and why mathematical thinking mattersResearch and learning Lab (opens in a new tab)
  159. Lab replay What to do when the models know everything, plus a machine learning crash courseThe accelerating world · Meaning and direction · Research and learning · Cursor Lab (opens in a new tab)
  160. Lab replay Cursor as a learning engine and stock analyst, and a multi-chat webappCursor · Research and learning · Markets · Building apps Lab (opens in a new tab)
  161. Lab replay Generating large codebases, and the vertical slicing principleBuilding apps · Agents and workflows Lab (opens in a new tab)
  162. Lab replay DSPy with GEPA for prompt optimizationAgents and workflows · Research and learning Lab (opens in a new tab)
  163. Lab replay In-context learning, optimizers like RL and tree search, and coding fastResearch and learning · New models, tested Lab (opens in a new tab)
  164. Lab replay Can models learn new things in context? And coding with Grok CodeResearch and learning · New models, tested Lab (opens in a new tab)
  165. Lab replay Webapps without a database, why studying inspires, and coding with Grok CodeBuilding apps · Research and learning · New models, tested Lab (opens in a new tab)
  166. Lab replay Sonic use cases, extending my Patreon apps, studying new things and solving puzzlesNew models, tested · Research and learning · Building apps Lab (opens in a new tab)
  167. Lab replay An Imagen 4 webapp, varied outputs from GPT-5, and GPT-5 vs Sonnet 4New models, tested · Building apps · Films, songs and images Lab (opens in a new tab)
  168. Lab replay Why GPT-5 is good, and building apps with itNew models, tested · Building apps Lab (opens in a new tab)
  169. Lab replay Singularity predictions, new models, and dealing with difficultiesThe accelerating world · New models, tested · Meaning and direction Lab (opens in a new tab)
  170. Lab replay Is Kimi K2 good? Are language models intelligent? Research with and without web searchNew models, tested · Research and learning Lab (opens in a new tab)
  171. Lab replay Tips on building agents, and getting through low timesAgents and workflows · Your brand · Meaning and direction Lab (opens in a new tab)
  172. Lab replay Visual vibe coding with Stagewise, and the Journey 10K marketing planBuilding apps · Your brand Lab (opens in a new tab)
  173. Lab replay Journey 10K, and strategies for marketingYour brand Lab (opens in a new tab)
  174. Lab replay Marketing with videos, Journey 10K, and Cursor 1.0Your brand · Films, songs and images · Cursor Lab (opens in a new tab)
  175. Lab replay Job market predictions, low motivation, and deploying the Journey 10K siteThe accelerating world · Meaning and direction · Building apps · Your brand Lab (opens in a new tab)
  176. Lab replay Journey to 10K, and new API features from OpenAI, Claude and GeminiYour brand · New models, tested Lab (opens in a new tab)
  177. Lab replay Journey to 10K: the startYour brand Lab (opens in a new tab)
  178. Lab replay Claude web search and Cursor 0.50New models, tested · Cursor Lab (opens in a new tab)
  179. Lab replay Deploying webapps: Postgres, rate limiting and moderationBuilding apps · Safety and security Lab (opens in a new tab)
  180. Lab replay Webapps: sign-in, tech stack and securityBuilding apps · Safety and security Lab (opens in a new tab)
  181. Lab replay How to build agents that observe and improve themselvesAgents and workflows Lab (opens in a new tab)
  182. Lab replay How to build language models from scratch for any taskResearch and learning · New models, tested Lab (opens in a new tab)
  183. Lab replay Cursor builds an agent it likes, a spec file for projects, and quicker researchCursor · Agents and workflows · Research and learning Lab (opens in a new tab)
  184. Lab replay AGI, a self-learning model, deep research, and models compared on UI designThe accelerating world · New models, tested · Research and learning · Building apps Lab (opens in a new tab)
  185. Lab replay An encode-decode challenge for language modelsNew models, tested · Research and learning Lab (opens in a new tab)
  186. Lab replay A 5,000-line chat webapp, built in about an hourBuilding apps · Cursor Lab (opens in a new tab)
  187. Lab replay Multiple Cursor rules for complex agent tasksCursor · Agents and workflows Lab (opens in a new tab)
  188. Lab replay Building a PDF-to-conversation app and a 2D brick-breaker gameBuilding apps Lab (opens in a new tab)
  189. Lab replay A deep dive into OpenAI’s Agents SDKAgents and workflows Lab (opens in a new tab)
  190. Lab replay Computer use and the file search toolAgents and workflows Lab (opens in a new tab)
  191. Lab replay OpenAI’s Responses API, the playground and web searchAgents and workflows · New models, tested Lab (opens in a new tab)
  192. Lab replay Custom website designs with Claude 3.7 Sonnet, and learning three.js in CursorCursor · Building apps · Simulations and visuals Lab (opens in a new tab)
  193. Lab replay Cursor’s new multi rules, and deploying a text-to-image appCursor · Building apps · Films, songs and images Lab (opens in a new tab)
  194. Lab replay Multiplayer games and an automatic SVG makerBuilding apps · Simulations and visuals Lab (opens in a new tab)
  195. Lab replay Building auto coders, and testing Grok 3Agents and workflows · New models, tested Lab (opens in a new tab)
  196. Lab replay o3, the singularity, custom deep research and multiple Cursor rulesThe accelerating world · New models, tested · Research and learning · Cursor Lab (opens in a new tab)
  197. Lab replay Web search through the API, reasoning from DeepSeek R1, and multi-thinking systemsNew models, tested · Agents and workflows · Research and learning Lab (opens in a new tab)
  198. Lab replay o1 use cases, threaded agents, and Cursor as a data scientistNew models, tested · Agents and workflows · Cursor Lab (opens in a new tab)
  199. Lab replay Building research agents, list making, and what prompting nicely doesResearch and learning · Agents and workflows Lab (opens in a new tab)
  200. Lab replay o3, using o1, agents and the voice APINew models, tested · Agents and workflows Lab (opens in a new tab)

Members: Get Amplified, $30 a month, has most lessons. The 1000x Lab, $50 a month, has all of them. Lab: replays come with the Lab plan. Tools and models move fast, so every entry keeps its date. An older replay still teaches the method, even when the model names have changed.

Can’t find it? Ask me.

Bring your question to the live Lab on Sunday, or work through it with me one to one.