Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Cursor wants to KILL programming 0:00 - skip this part 0:55 - Why Fable is stuck 2:42 - SpaceX acquires Cursor 5:16 - Cursor wants to kill code 7:53 - Chinese open-source model beats out Fable 11:19 - AI is killing Tim Ferris

Mo

72,072 subscribers

57,346 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The fastest way to clone a multi million dollar mobile app with Cursor (And Add Multiple AI Features) Here's what I did: 1. Prototype on phone 2. Add Whisper for Voice Recording + GPT4o Image 3. Export to Cursor 4. Make Changes on Cursor while testing on phone 5. Add Perplexity API for research Timestamps 00:00 Intro 00:23 ChatGPT for Design Description 00:43 Prototype in vibecode.dev 01:16 Uh oh, we got an error, let's fix 02:55 Note Details Page Works! Let's go 04:16 Adding AI Generated Thumbnails with gpt4o Image model 06:15 Moving Prototype to Cursor 08:15 Making Changes to app with Cursor 11:21 Adding Perplexity Research to the App

The fastest way to clone a multi million dollar mobile app with Cursor (And Add Multiple AI Features) Here's what I did: 1. Prototype on phone 2. Add Whisper for Voice Recording + GPT4o Image 3. Export to Cursor 4. Make Changes on Cursor while testing on phone 5. Add Perplexity API for research Timestamps 00:00 Intro 00:23 ChatGPT for Design Description 00:43 Prototype in vibecode.dev 01:16 Uh oh, we got an error, let's fix 02:55 Note Details Page Works! Let's go 04:16 Adding AI Generated Thumbnails with gpt4o Image model 06:15 Moving Prototype to Cursor 08:15 Making Changes to app with Cursor 11:21 Adding Perplexity Research to the App

Riley Brown

95,984 views • 1 year ago

Fable 5 is GREAT at design... Especially when its connected to a Figma-Like Canvas. Here's a complete guide for using Claude Code with Fable 5, connected to the Agent Native version of Figma, called Paper. This workflow works with Cursor, Codex, Devin, or any other agent platform. 00:00 - Intro 01:41 - Set up Claude Code x Paper Connection 04:14 - Creating YouTube Thumbnails 10:21 - Instagram Graphics with text and overlays 16:33 - Creating Presentations with Fable 5 21:22 - Converting Designs into a site on the internet

Fable 5 is GREAT at design... Especially when its connected to a Figma-Like Canvas. Here's a complete guide for using Claude Code with Fable 5, connected to the Agent Native version of Figma, called Paper. This workflow works with Cursor, Codex, Devin, or any other agent platform. 00:00 - Intro 01:41 - Set up Claude Code x Paper Connection 04:14 - Creating YouTube Thumbnails 10:21 - Instagram Graphics with text and overlays 16:33 - Creating Presentations with Fable 5 21:22 - Converting Designs into a site on the internet

Riley Brown

73,064 views • 1 month ago

Here's my conversation with the founding team of Cursor, a popular code editor (based on VSCode) that specializes in AI-assisted programming. This is a super technical conversation that is bigger than just about one code editor. It's about the future of programming and, in general, the future of human-AI collaboration. It's here on X in full, and is up on everywhere else. Timestamps: 0:00 - Introduction 0:59 - Code editor basics 3:09 - GitHub Copilot 10:27 - Cursor 16:54 - Cursor Tab 23:08 - Code diff 31:20 - ML details 36:54 - GPT vs Claude 43:28 - Prompt engineering 50:54 - AI agents 1:04:51 - Running code in background 1:09:31 - Debugging 1:14:58 - Dangerous code 1:26:09 - Branching file systems 1:29:20 - Scaling challenges 1:43:32 - Context 1:48:39 - OpenAI o1 2:00:01 - Synthetic data 2:03:48 - RLHF vs RLAIF 2:05:34 - Fields Medal for AI 2:08:17 - Scaling laws 2:17:06 - The future of programming

Here's my conversation with the founding team of Cursor, a popular code editor (based on VSCode) that specializes in AI-assisted programming. This is a super technical conversation that is bigger than just about one code editor. It's about the future of programming and, in general, the future of human-AI collaboration. It's here on X in full, and is up on everywhere else. Timestamps: 0:00 - Introduction 0:59 - Code editor basics 3:09 - GitHub Copilot 10:27 - Cursor 16:54 - Cursor Tab 23:08 - Code diff 31:20 - ML details 36:54 - GPT vs Claude 43:28 - Prompt engineering 50:54 - AI agents 1:04:51 - Running code in background 1:09:31 - Debugging 1:14:58 - Dangerous code 1:26:09 - Branching file systems 1:29:20 - Scaling challenges 1:43:32 - Context 1:48:39 - OpenAI o1 2:00:01 - Synthetic data 2:03:48 - RLHF vs RLAIF 2:05:34 - Fields Medal for AI 2:08:17 - Scaling laws 2:17:06 - The future of programming

Lex Fridman

1,261,340 views • 1 year ago

Is Claude Code Better Than Cursor? This video is a crystal clear explanation on what makes Claude Code different than Cursor, Codex and Windsurf. A classic whiteboard conversation! Next time he's on the pod (soon) he's going to build an app from scratch that will blow your mind. TIMESTAMPS: 00:00 Intro to Claude Code 00:28 Why Claude Code Is Best 02:38 Comparing Cursor, Windsurf & Claude Code 07:41 Using Claude Code with Other IDEs 12:41 Future of AI Coding Tools & Claude’s SDK 19:58 Integrating Codex with Chat GPT 21:14 Best AI Code Review Tools (Devon, CodeRabbit 26:49 Building an App with Claude Code (Step-by-Step) 35:32 Future Plans

Is Claude Code Better Than Cursor? This video is a crystal clear explanation on what makes Claude Code different than Cursor, Codex and Windsurf. A classic whiteboard conversation! Next time he's on the pod (soon) he's going to build an app from scratch that will blow your mind. TIMESTAMPS: 00:00 Intro to Claude Code 00:28 Why Claude Code Is Best 02:38 Comparing Cursor, Windsurf & Claude Code 07:41 Using Claude Code with Other IDEs 12:41 Future of AI Coding Tools & Claude’s SDK 19:58 Integrating Codex with Chat GPT 21:14 Best AI Code Review Tools (Devon, CodeRabbit 26:49 Building an App with Claude Code (Step-by-Step) 35:32 Future Plans

Riley Brown

115,665 views • 1 year ago

Cursor Complete Guide for AI Coding... 1. The Basics, Composer, Cursor 2.0, Why use Cursor? 2. Multiple Agent Testing, Adding Database, Deploying to Vercel 3. Comparing the big 4: v0, Replit, Lovable, Cursor And more... with Senior Software Engineer Kehan Zhang TIME STAMPS --------------- 1. BASICS: 00:00 Introduction 01:01 Overview of Cursor and Its Features 01:47 Getting Started with Cursor 02:39 Understanding IDE and Vibe Coding 06:00 Cursor For Mobile Apps 10:26 Downloading and Installing Cursor 11:17 Creating and Managing Projects in Cursor 15:14 Building a Simple Game with Cursor 19:10 Advanced Features and Customization 40:28 Fixing Styling Rules 40:53 Redesigning the App 42:17 Exploring Cursor 2.0 Features 43:22 Setting Up the Project Structure 44:17 Adding and Testing Meme Templates 46:08 Debugging Text Issues 2. ADVANCED 49:46 Using Multiple Agents 01:10:40 Creating Custom Commands 01:14:15 Creating Commands in Settings Tab 01:15:11 Introduction to Instant DB 01:16:04 Setting Up Instant DB in Your Project 01:18:24 Building a Full Stack Application 01:19:04 Using the Agent to Plan and Build 01:26:06 Testing and Debugging the Application 01:53:02 Deploying the Application with Vercel 01:55:35 Setting Up the CLI 01:56:15 Understanding Command Line Interfaces (CLI) 01:57:32 Deploying Code to Vercel 01:58:07 Handling Environment Variables 01:58:44 Interacting with the Vercel Deployment 02:00:34 Exploring Cursor's Capabilities 3. COMPARING VIBE CODING TOOLS 02:09:48 Comparing Vibe Coding Tools 02:31:04 Final Thoughts and Recommendations

Cursor Complete Guide for AI Coding... 1. The Basics, Composer, Cursor 2.0, Why use Cursor? 2. Multiple Agent Testing, Adding Database, Deploying to Vercel 3. Comparing the big 4: v0, Replit, Lovable, Cursor And more... with Senior Software Engineer Kehan Zhang TIME STAMPS --------------- 1. BASICS: 00:00 Introduction 01:01 Overview of Cursor and Its Features 01:47 Getting Started with Cursor 02:39 Understanding IDE and Vibe Coding 06:00 Cursor For Mobile Apps 10:26 Downloading and Installing Cursor 11:17 Creating and Managing Projects in Cursor 15:14 Building a Simple Game with Cursor 19:10 Advanced Features and Customization 40:28 Fixing Styling Rules 40:53 Redesigning the App 42:17 Exploring Cursor 2.0 Features 43:22 Setting Up the Project Structure 44:17 Adding and Testing Meme Templates 46:08 Debugging Text Issues 2. ADVANCED 49:46 Using Multiple Agents 01:10:40 Creating Custom Commands 01:14:15 Creating Commands in Settings Tab 01:15:11 Introduction to Instant DB 01:16:04 Setting Up Instant DB in Your Project 01:18:24 Building a Full Stack Application 01:19:04 Using the Agent to Plan and Build 01:26:06 Testing and Debugging the Application 01:53:02 Deploying the Application with Vercel 01:55:35 Setting Up the CLI 01:56:15 Understanding Command Line Interfaces (CLI) 01:57:32 Deploying Code to Vercel 01:58:07 Handling Environment Variables 01:58:44 Interacting with the Vercel Deployment 02:00:34 Exploring Cursor's Capabilities 3. COMPARING VIBE CODING TOOLS 02:09:48 Comparing Vibe Coding Tools 02:31:04 Final Thoughts and Recommendations

Riley Brown

65,392 views • 9 months ago

CLAUDE + CURSOR + REPLIT = MAGIC (FULL VIDEO TUTORIAL) You can now write create complex web apps with just english (No copy - paste) using the BEST AI Code generation tool on the market - Cursor. The only problem with cursor for a coding beginner like me, is that its not that easy to deploy web apps. Well, Replit ⠕ makes deploying web apps and creating templates incredibly easy. In this video goes over how to sync Cursor and Replit. And then using our new template we made an AI version of Trello by Atlassian in like 6 or 7 cursor composer prompts. --------------------- In this video: 00:00 - Intro 04:08 - Syncing Cursor and Replit 07:40 - setting up Firebase 10:27 - Using Cursor and Replit to Create Trello Front End 19:41 - Setting up Backend API endpoint (we will make dedicated video on this soon w/template) 21:09 - Adding AI features to Trello!

CLAUDE + CURSOR + REPLIT = MAGIC (FULL VIDEO TUTORIAL) You can now write create complex web apps with just english (No copy - paste) using the BEST AI Code generation tool on the market - Cursor. The only problem with cursor for a coding beginner like me, is that its not that easy to deploy web apps. Well, Replit ⠕ makes deploying web apps and creating templates incredibly easy. In this video goes over how to sync Cursor and Replit. And then using our new template we made an AI version of Trello by Atlassian in like 6 or 7 cursor composer prompts. --------------------- In this video: 00:00 - Intro 04:08 - Syncing Cursor and Replit 07:40 - setting up Firebase 10:27 - Using Cursor and Replit to Create Trello Front End 19:41 - Setting up Backend API endpoint (we will make dedicated video on this soon w/template) 21:09 - Adding AI features to Trello!

Riley Brown

309,237 views • 2 years ago

Full Cursor Getting Started Beginners Guide You can build an AI wrapper in 30 minutes that uses @ChatGPTapp and API, even if you've never written a line of code, ever. This was 7 total Cursor Composer Prompts. Many people got stuck while following along my recent videos so I wanted to slow it down make one for beginners. From Downloading Cursor to Deploying on Vercel Template link is pinned to this profile @senior_swc Time Stamps 00:00 No-Code App Building 01:00 Getting Started and Downloading Cursor 01:50 Downloading the Template 03:13 Intro to Cursor Composer 04:06 First Prompt Getting Template Set Up 05:05 First Prompt For Real adding ChatGPT api 08:46 Setting up ChatGPT API 10:46 Testing Chat Feature 13:40 Cursor Feature Overview 17:40 Now Lets Add Voice 21:27 Asking Composer to Deploy the app on Vercel

Riley Brown

177,177 views • 1 year ago

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?

Max Blade

19,431 views • 1 month ago

$60 Billion SpaceX Cursor Deal? This week on The Brainstorm ⬇️ 0:00 — SpaceX buying Cursor for $60 B? We think this is the reason why 6:05 — SpaceX has reportedly committed ~$310B in 12 months acquiring its way toward the AI frontier 9:55 — "If you're not getting rate-limited by Claude, you might just be bad at using AI" 12:24 — The compute crunch that could hit in 2 years, and why we think few are pricing it in 15:10 — Tim Cook is out. Could Apple finally be about to start cooking? 18:05 — The AI gap at Apple that, if Microsoft is any guide, could prove costly 20:14 — Why AirPods, not the iPhone, may be Apple's most underrated AI weapon 33:49 — OpenAI is building hardware with Qualcomm. Why we don't think it'll really be a "phone" 40:12 — Why Google could go from paying Apple ~$20B/yr to Apple paying Google

$60 Billion SpaceX Cursor Deal? This week on The Brainstorm ⬇️ 0:00 — SpaceX buying Cursor for $60 B? We think this is the reason why 6:05 — SpaceX has reportedly committed ~$310B in 12 months acquiring its way toward the AI frontier 9:55 — "If you're not getting rate-limited by Claude, you might just be bad at using AI" 12:24 — The compute crunch that could hit in 2 years, and why we think few are pricing it in 15:10 — Tim Cook is out. Could Apple finally be about to start cooking? 18:05 — The AI gap at Apple that, if Microsoft is any guide, could prove costly 20:14 — Why AirPods, not the iPhone, may be Apple's most underrated AI weapon 33:49 — OpenAI is building hardware with Qualcomm. Why we don't think it'll really be a "phone" 40:12 — Why Google could go from paying Apple ~$20B/yr to Apple paying Google

ARK Invest

64,826 views • 3 months ago

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

Ali Romman

119,837 views • 2 months ago

How to 10x your Cursor workflow? Many people struggle to get Cursor produce error free projects Here is my workflow to rebuild a $1 million micros Sass with ease: 1. O1 to prep doc with file tree & dependencies 2. Use Cursor for functionality & v0 for UI touch up 3. Use templates for modular functions like auth, payment, etc. 4. Use Helicone to monitor LLM usage 5. ... 0:00 Intro & Setup 2:25 Step 1 - Plan & Prep PRD 16:57 Step 2 - Build frontend 22:34 Step 3 - Connect LLM monitoring platform 25:44 Step 4 - Build backend - Supabase 37:26 Step 5 - UI Touch up Join my community where I share AI building tips weekly:

How to 10x your Cursor workflow? Many people struggle to get Cursor produce error free projects Here is my workflow to rebuild a $1 million micros Sass with ease: 1. O1 to prep doc with file tree & dependencies 2. Use Cursor for functionality & v0 for UI touch up 3. Use templates for modular functions like auth, payment, etc. 4. Use Helicone to monitor LLM usage 5. ... 0:00 Intro & Setup 2:25 Step 1 - Plan & Prep PRD 16:57 Step 2 - Build frontend 22:34 Step 3 - Connect LLM monitoring platform 25:44 Step 4 - Build backend - Supabase 37:26 Step 5 - UI Touch up Join my community where I share AI building tips weekly:

Jason Zhou

157,152 views • 1 year ago

Everyone is talking about GPT-5.6 versus Fable 5. I put both models head-to-head with the exact same prompts to determine which is actually best (it's not even close). 0:00 Intro 0:32 Benchmarks analysis 3:09 Building a game (Test 1) 5:15 Data processing (Test 2) 8:20 Content creation & creatives (Test 3) 11:53 Design (Test 4) 13:50 Peter Gostev's view 17:11 My new AI stack

Everyone is talking about GPT-5.6 versus Fable 5. I put both models head-to-head with the exact same prompts to determine which is actually best (it's not even close). 0:00 Intro 0:32 Benchmarks analysis 3:09 Building a game (Test 1) 5:15 Data processing (Test 2) 8:20 Content creation & creatives (Test 3) 11:53 Design (Test 4) 13:50 Peter Gostev's view 17:11 My new AI stack

Miles Deutscher

38,970 views • 1 month ago

My biggest fear for AI is concentration of power. Open-source is a solution. Watch this video to understand what's going on: 0:00 Intro 0:52 NVIDIA's letter 1:36 What is open-source? 3:53 How open-source works 5:48 Kimi K3 6:38 Closed vs Open 8:39 Open-source in the U.S. 12:10 The AI stack 13:05 What if open source wins? 14:08 Jevon's Paradox 14:56 How the AI stack is affected 18:04 User experience 19:38 AI safety 30:30 China 35:50 Distillation 41:40 Banning Chinese models? 43:38 Anthropic's response

My biggest fear for AI is concentration of power. Open-source is a solution. Watch this video to understand what's going on: 0:00 Intro 0:52 NVIDIA's letter 1:36 What is open-source? 3:53 How open-source works 5:48 Kimi K3 6:38 Closed vs Open 8:39 Open-source in the U.S. 12:10 The AI stack 13:05 What if open source wins? 14:08 Jevon's Paradox 14:56 How the AI stack is affected 18:04 User experience 19:38 AI safety 30:30 China 35:50 Distillation 41:40 Banning Chinese models? 43:38 Anthropic's response

Matthew Berman

13,685 views • 20 days ago

POD UP! Core four is back 🚨 Big show: -- SpaceX-Cursor deal, using compute as leverage -- SaaS debt bomb coming to PE?, venture debt risk -- Software bloodbath, buy low potential? -- New Apple CEO: future of the company -- SPLC indictment, major allegations, out of control NGOs -- Science Corner returns! Colon cancer cause discovered? (0:00) Bestie intros! (4:55) SpaceX-Cursor deal, compute as leverage (18:33) SaaS bloodbath, debt bomb incoming, buy the dip? (46:20) New Apple CEO: John Ternus succeeds Tim Cook, what's next for Apple? (1:00:32) SPLC indictment, out of control NGOs (1:19:03) Science Corner: Potential cause discovered for colon cancer spike in young people

POD UP! Core four is back 🚨 Big show: -- SpaceX-Cursor deal, using compute as leverage -- SaaS debt bomb coming to PE?, venture debt risk -- Software bloodbath, buy low potential? -- New Apple CEO: future of the company -- SPLC indictment, major allegations, out of control NGOs -- Science Corner returns! Colon cancer cause discovered? (0:00) Bestie intros! (4:55) SpaceX-Cursor deal, compute as leverage (18:33) SaaS bloodbath, debt bomb incoming, buy the dip? (46:20) New Apple CEO: John Ternus succeeds Tim Cook, what's next for Apple? (1:00:32) SPLC indictment, out of control NGOs (1:19:03) Science Corner: Potential cause discovered for colon cancer spike in young people

The All-In Podcast

235,856 views • 3 months ago

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

Max Blade

128,812 views • 1 month ago

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

painn

253,746 views • 1 month ago

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has *all* the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring Federico Cassano (Composer Lead at Cursor) and Dmytro Dzhulgakov (Co-Founder at Fireworks). The Cursor team trained Composer 2 on Fireworks by starting with a strong base model (Kimi 2.5) and performing large-scale mid-training on code tokens and web data to learn common patterns and libraries, followed by a large-scale Reinforcement Learning run to learn how to navigate the Cursor harness, call tools, and write correct code. Today's episode dives into the systems and infrastructure challenges of making that large RL run happening, and there were many (!!), from numerical mismatch to global distribution to synchronizing rollouts across asynchronous pipelines to keeping track of expert activation across runs and more. Extremely nerdy in-the-weeds challenges that Federico and Dima were delighted to nerd out on together :) Beyond RL infra, we also discussed Online vs Simulated rollouts, self-summarization for long-horizon agents, environment design ("the most powerful RL environment is the product itself"), and other technical nuggets. PS: We filmed this episode before the SpaceX news, while the Cursor team was still compute-constrained. While Cursor now has all the flops, the takeaways and hurdles crossed ring true for any serious application-level company that is racing to post-train their own models. I believe that more serious application companies will go the way of Cursor and post-train their own models. 00:00 Introduction 00:53 Why Cursor Trained Composer 2 04:55 Specialization vs Bitter Lesson 06:16 Composer 2 Training Recipe 16:32 Scaling RL Infrastructure Globally 23:32 Floating Point Drift 25:11 MoE Sensitivity Explained 26:25 Router Replay Fix 27:19 Real Time RL Loop 31:49 Long Horizon Agents 34:29 Why RL Everywhere 37:34 LLM as Judge Rewards 39:14 RL in Hard Domains 40:13 Build Your Own Environments 44:34 Closing Thoughts

Sonya Huang 🐥

79,834 views • 2 months ago

Everyone is talking about Vibe Coding (Using AI to Create Apps Only using AI) This is the most Comprehensive Guide for Vibe Coding with Cursor (By Far) 250 Minutes, All the vibe code basics of cursor, plus 4 Projects in one video! This is how I, as someone who has never written a line of code, approach building apps (every day). Part 1A Intro to Cursor, Composer, and some basics --------------------- 00:00 Intro 03:41 Downloading Cursor 06:09 What the hell is Composer? 10:47 A Note on Context and Keeping Composer Threads Small 11:38 Simple Desings with Cursor Composer From Blank Project 14:04 Editing a Simple Animation With Cursor Composer 16:35 Setting Up The Voice to Talk to Cursor Composer Whispr Flow 17:54 Lets an Early 2000's Landing Page Part 1B AI Image Generator --------------------- 23:59 Using the GitHub Template to Create a NextJS App 26:43 Template is Open, Let's Edit it 28:55 Drawing Out My Idea With Whimsical 30:11 First Prompt Using Place Holders For Image Generation 32:10 Accept All Vs Save All and Restoring in Composer (Saving your work) 33:54 Adding AI Feature (Brief Teaser, Deep Dive Later) 35:15 What is an API 37:22 Perplexity the best place to learn about API's 40:21 Api keys and running prompt for first AI Feature 42:48 Debugging, Woohoo! Learn to love this :) 43:20 Inspect - Console, In Browser Debugging Hack 48:02 AI Image Generation Works! Lets add more Part 2: Landing Page ---------------------- 51:03 Pause and Reflect, What have we done so far? 53:41 Plan for rest of video 54:34 Ok Let's Talk about (1) Designs 56:19 GitHub is like --sref for those who do image gen 58:20 Starting Cursor project from a GitHub Repo we found on Perplexity 01:00:48 Yolo Mode... Wtf is that? 01:02:38 Inspecting GitHub Repo's Examples, to use in our landing page 01:02:58 The Project We're making - A landing page 01:03:56 Landing Page from Screenshot 01:06:17 Making Changes to Landing Page 01:11:42 Making a more epic section 01:13:42 The Essence of Vibe Coding 01:15:17 Creating Cool Testimonials Section From Screenshot 01:18:18 Deploy to Vercel! But First New Repo on GitHub 01:20:45 Ok it's on GitHub... Now lets do vercel 01:21:17 Untechnical Explanation of what Vercel is Lol 01:24:18 Connecting Custom Domain (Bought on Name Cheap) To Vercel Deployment Part 3: App With Database and Authentication ---------------------- 01:27:59 Recap and Prep For The Bigger Project! 01:35:13 Getting Started from Template (Again) 01:38:52 Setting Up Database and Authentication (Firebase) 01:44:01 Back To Cursor, Let's Set up The Auth in the app 01:48:35 Switching to mermaid because compatibility issues 01:51:13 Using AI (Claude) to Generate Mermaid Diagrams 01:52:19 Adding Docs to Cursor to use AI Features over and over again 01:54:38 Let's Troubleshoot 01:56:10 Adding View Button and EDIT WITH AI 02:01:45 AI Diagram Edit Feature is DOPE 02:03:17 Using Search Feature on Cursor to find text in Codebase 02:05:55 Lets add ability to save these to Database 02:09:33 What does saved to Google Firebase even mean? 02:13:00 We can Export as PDF! 02:15:48 GitHub and Vercel Again! 02:17:27 Vercel with CLI From Cursor 02:20:52 Setting Vercel Domain as an Authorized Domain 02:27:34 How To Learn More

Everyone is talking about Vibe Coding (Using AI to Create Apps Only using AI) This is the most Comprehensive Guide for Vibe Coding with Cursor (By Far) 250 Minutes, All the vibe code basics of cursor, plus 4 Projects in one video! This is how I, as someone who has never written a line of code, approach building apps (every day). Part 1A Intro to Cursor, Composer, and some basics --------------------- 00:00 Intro 03:41 Downloading Cursor 06:09 What the hell is Composer? 10:47 A Note on Context and Keeping Composer Threads Small 11:38 Simple Desings with Cursor Composer From Blank Project 14:04 Editing a Simple Animation With Cursor Composer 16:35 Setting Up The Voice to Talk to Cursor Composer Whispr Flow 17:54 Lets an Early 2000's Landing Page Part 1B AI Image Generator --------------------- 23:59 Using the GitHub Template to Create a NextJS App 26:43 Template is Open, Let's Edit it 28:55 Drawing Out My Idea With Whimsical 30:11 First Prompt Using Place Holders For Image Generation 32:10 Accept All Vs Save All and Restoring in Composer (Saving your work) 33:54 Adding AI Feature (Brief Teaser, Deep Dive Later) 35:15 What is an API 37:22 Perplexity the best place to learn about API's 40:21 Api keys and running prompt for first AI Feature 42:48 Debugging, Woohoo! Learn to love this :) 43:20 Inspect - Console, In Browser Debugging Hack 48:02 AI Image Generation Works! Lets add more Part 2: Landing Page ---------------------- 51:03 Pause and Reflect, What have we done so far? 53:41 Plan for rest of video 54:34 Ok Let's Talk about (1) Designs 56:19 GitHub is like --sref for those who do image gen 58:20 Starting Cursor project from a GitHub Repo we found on Perplexity 01:00:48 Yolo Mode... Wtf is that? 01:02:38 Inspecting GitHub Repo's Examples, to use in our landing page 01:02:58 The Project We're making - A landing page 01:03:56 Landing Page from Screenshot 01:06:17 Making Changes to Landing Page 01:11:42 Making a more epic section 01:13:42 The Essence of Vibe Coding 01:15:17 Creating Cool Testimonials Section From Screenshot 01:18:18 Deploy to Vercel! But First New Repo on GitHub 01:20:45 Ok it's on GitHub... Now lets do vercel 01:21:17 Untechnical Explanation of what Vercel is Lol 01:24:18 Connecting Custom Domain (Bought on Name Cheap) To Vercel Deployment Part 3: App With Database and Authentication ---------------------- 01:27:59 Recap and Prep For The Bigger Project! 01:35:13 Getting Started from Template (Again) 01:38:52 Setting Up Database and Authentication (Firebase) 01:44:01 Back To Cursor, Let's Set up The Auth in the app 01:48:35 Switching to mermaid because compatibility issues 01:51:13 Using AI (Claude) to Generate Mermaid Diagrams 01:52:19 Adding Docs to Cursor to use AI Features over and over again 01:54:38 Let's Troubleshoot 01:56:10 Adding View Button and EDIT WITH AI 02:01:45 AI Diagram Edit Feature is DOPE 02:03:17 Using Search Feature on Cursor to find text in Codebase 02:05:55 Lets add ability to save these to Database 02:09:33 What does saved to Google Firebase even mean? 02:13:00 We can Export as PDF! 02:15:48 GitHub and Vercel Again! 02:17:27 Vercel with CLI From Cursor 02:20:52 Setting Vercel Domain as an Authorized Domain 02:27:34 How To Learn More

Riley Brown

368,431 views • 1 year ago

I gave the keynote at UC Berkeley's ProductCon - "How to Become an Elite AI-Powered Product Manager" This is the full talk + behind-the-scenes footage: 0:00 - Why This Matters 4:11 - Layer 1: Prompting Fundamentals 10:46 - Layer 2: AI Co-pilots 19:45 - Layer 3: AI Agents 27:00 - Layer 4: AI Prototyping 31:45 - Layer 5: AI Discovery 39:37 - Layer 6: Evals & Observability 42:53 - Layer 7: Vibe Experimentation 50:56 - Behind the Scenes

I gave the keynote at UC Berkeley's ProductCon - "How to Become an Elite AI-Powered Product Manager" This is the full talk + behind-the-scenes footage: 0:00 - Why This Matters 4:11 - Layer 1: Prompting Fundamentals 10:46 - Layer 2: AI Co-pilots 19:45 - Layer 3: AI Agents 27:00 - Layer 4: AI Prototyping 31:45 - Layer 5: AI Discovery 39:37 - Layer 6: Evals & Observability 42:53 - Layer 7: Vibe Experimentation 50:56 - Behind the Scenes

Aakash Gupta

410,928 views • 6 months ago

Anthropic just released a 3-hour masterclass on how the best companies in the world, from Cursor to Spotify, build with Claude: 00:06 – how Cursor built its cloud agents 14:30 – how Lovable vibecodes at scale 45:22 – Spotify: why coding is no longer the constraint 1:42:56 – building AI-native, from Cognition to Harvey 2:09:18 – enterprise scale: mondaycom, Doctolib, Delivery Hero 2:38:11 – how one team went from 1 person to 80 This 3-hour watch will replace 10 paid AI engineering courses on the internet. Watch it today, then go build your own agents in part 2, below.

Anthropic just released a 3-hour masterclass on how the best companies in the world, from Cursor to Spotify, build with Claude: 00:06 – how Cursor built its cloud agents 14:30 – how Lovable vibecodes at scale 45:22 – Spotify: why coding is no longer the constraint 1:42:56 – building AI-native, from Cognition to Harvey 2:09:18 – enterprise scale: mondaycom, Doctolib, Delivery Hero 2:38:11 – how one team went from 1 person to 80 This 3-hour watch will replace 10 paid AI engineering courses on the internet. Watch it today, then go build your own agents in part 2, below.

Phosphen

23,457 views • 1 month ago