Podcast
AI with Kyle - Daily AI News and Updates
Hosted by Kyle Balmer · EN
AI With Kyle - Daily AI News With Zero Hype, Zero BS AI With Kyle is the daily podcast for people who want to understand artificial intelligence without hype...
62episodes
Episodes
Newest firstAll episodes
173: How to Build a TEAM of AI Agent Using Anthropic’s New Tool (Anyone Can Do This)
Apr 1500:31:42Tap to summarizeGet AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Orchestration is the new buzzword in AI, and for once it's actually worth paying attention to. In this episode I walk through what it means to go from simply chatting with AI to building entire teams of agents that work for you in parallel, check each other's work, and keep running while you sleep. Anthropic quietly released a managed agents platform with a graphical interface that makes this dramatically more accessible than it used to be. No terminal commands, no SDK setup, just a chat window where you describe what you want and it builds the agent for you. I give you a full walkthrough of how to set it up, configure environments, and start thinking in systems rather than individual prompts. I also dig into the bigger picture of what this means for entrepreneurs and businesses. Anthropic leaked what looks like a Lovable competitor, which signals that the big AI companies are now willing and able to replicate indie SaaS products in a weekend. That squeeze on mid-market founders is real and it's coming fast. On the flip side, if you're the person who learns to orchestrate these agent teams, you go from being one individual to effectively running a small company. The skill that matters now isn't prompt engineering, it's management. Turns out all those years of leading teams and thinking about systems might be the most valuable thing you bring to AI. —— Time Stamps —— 0:00 What Is AI Orchestration and Why It Matters 3:33 The Restaurant Analogy: Users vs Builders 5:22 Cowork vs OpenClaw vs Managed Agents Compared 7:28 Getting Started with Claude Managed Agents 9:02 Always-On Persistent AI: The 2026 Shift 10:37 Why Parallel Processing Beats Sequential Agents 11:15 The New No-Code Quickstart Interface 12:32 Live Demo — Building an AI News Scraper Agent 16:06 Configuring Environments and Running Sessions 18:36 Iterating and Improving Your Agent 20:10 Anatomy of a Managed Agent: Model, Sandbox and Tools 21:55 Multi-Agent Systems: Managers and Sub-Agents 23:33 How to Develop Systems Thinking Skills 26:35 Business Use Cases: Products, Operations and Consulting 29:54 Summary and Next Steps —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →172: Claude Mythos Cracks All Security, Project Glasswing, and the New AI Underclass
Apr 1400:46:30Tap to summarizeGet AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Claude Mythos is Anthropic's new model and they're refusing to release it publicly, which is the first time a major lab has held back a model since GPT-2. The headline is that Mythos can find and exploit zero-day vulnerabilities in every major operating system and browser. A sandboxed version that wasn't supposed to have internet access somehow found its way out and emailed a researcher while he was eating a sandwich in a park. Security researchers are saying they've found more bugs in a few weeks with Mythos than in their entire careers. Is some of this marketing ahead of Anthropic's IPO? Probably. But the exploits are being independently verified by the companies whose systems got cracked open, so there's clearly something real at the core of this. Instead of releasing Mythos publicly, Anthropic have launched Project Glasswing, a consortium giving early access to companies like Microsoft, Apple, Google, AWS and others so they can patch their systems before this kind of capability hits the wild. Think of it as handing a skeleton key to every locksmith in the world before announcing that the old locks are broken. Whether or not this qualifies as AGI is, frankly, a bit of a distraction. What matters is what it can functionally do, and right now it can make a mockery of security systems that have been trusted for decades. Even if Mythos itself never goes public, the capability will be replicated and distilled within months. The world just got a stay of execution, not a pardon. —— Time Stamps —— 0:00 Intro 0:42 What is Claude Mythos? The Sandbox Escape Story 1:32 Separating Mythos Hype from Reality 2:06 Why Anthropic Won't Release Mythos Publicly 2:57 Why Mainstream Media is Ignoring Mythos 4:07 First AI Model Held Back Since GPT-2 4:45 Forget AGI — Focus on What Mythos Can Actually Do 5:37 Mythos Found Zero-Day Exploits in Every Major System 7:24 Anthropic's 245-Page System Card: Why This is Different 8:16 120 Features in 90 Days: Is Mythos Powering Anthropic Internally? 10:09 Is Mythos AGI? The Goalpost Problem 11:58 Project Glasswing: Which Companies Get Early Access? 13:46 The Skeleton Key Metaphor for AI Cybersecurity 15:31 Dario Amodei on the AI Cyber Threat 16:20 IPO Hype or Real Danger? Anthropic Hits $30B Revenue 19:06 The AI Permanent Underclass Problem 20:21 What Engineers and Businesses Must Do Right Now 22:13 Your Wake-Up Call: Why You Need to Be AI Ready 23:57 Q&A: Can Mythos Secure Systems and Who Should Control It? 26:19 Claude Code Source Leak and Why Clean Code is Overrated 29:48 Which Careers Are Most at Risk from AI? 31:09 Every Job is a Bundle of Tasks AI Will Shrink 33:23 AI Won't Take Your Job — It Will Stop New Ones Being Created 35:58 Why Starting a Business is Your Best Move Right Now 38:42 Why Coaches and Community Leaders Will Thrive in the AI Era 40:21 How to Position Your Business Online in the AI Era 42:21 How to Start an AI Consulting Business 44:40 Will Vibe Coding Kill Software Companies? 46:09 Closing Thoughts —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →171: How I Get 200+ Email Subscribers a Day Using AI, ManyChat & Spark Loop
Apr 100:27:47Tap to summarizeLead generation guide (free): https://aiwithkyle.com/mini/automated-blueprint Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: In today's session I walked through the entire system I use to drive a couple of hundred email subscribers into my list every single day. It's the engine behind everything I've built over the last two years, taking the business from absolute zero to mid six figures. The core idea is simple: social media is rented land, your email list is an owned asset. I break down how I pick trending topics, shoot short conversion videos, and use ManyChat alongside Claude Cowork to automate the whole thing across Instagram, TikTok, YouTube Shorts and LinkedIn. I also showed how I use AI to generate lead magnets and landing pages daily without them feeling like generic rubbish, and how Spark Loop lets you earn money the moment someone subscribes. It's not fully automatic and it shouldn't be. The human bit matters. But once the plumbing is in place, you can repeat the process every single day and watch the numbers compound. Quite satisfying, honestly. —— Time Stamps —— 0:00 How I Get Hundreds of Email Subscribers Every Day 1:27 Why Email Lists Are More Valuable Than Social Media 2:41 How AI Powers This Entire System 4:36 The 5-Step Blueprint for Email List Growth 5:57 Creating Short Videos That Convert Followers to Subscribers 7:15 Choosing Your Topic and the Perfect Video Format 9:24 Automating DM Replies with ManyChat and Claude Cowork 10:05 ManyChat Results: What Worked and What Flopped 10:58 Building AI Landing Pages and Lead Magnets with Claude Code 13:57 Monetize Every Signup Instantly with SparkLoop 16:32 The Complete Daily Lead Magnet Workflow 17:28 Why Lead Magnet Quality Makes or Breaks First Impressions 19:21 Live Q&A: Start Small and Build Your Lead Magnet Machine 20:44 How to Define Your Target Audience for AI Content 22:06 Can You Have Too Many Lead Magnets? 24:28 Content Waterfall: One Live Stream Into Multiple Formats 26:48 Wrap-Up and Where to Get the Free Guide —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →170: NotebookLM Masterclass: Create Presentations, Hallucination Free Content Creation and it’s FREE
Mar 3100:30:31Tap to summarizeFree NotebookLM Content Engine guide: https://aiwithkyle.com/mini/notebooklm-content-engine Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Most people have heard of NotebookLM by now, but almost nobody is using it properly. In this one I break down exactly how I use Google's free RAG tool to power my entire content operation. I walk through the interface, explain what RAG actually is (without making it sound like a computer science lecture), and show how NotebookLM pulls from your sources rather than hallucinating answers from the void. If you work in law, academia, or anywhere that needs accurate information, this alone makes it worth your time. But the real trick is what happens after you create content. I show how I feed my existing YouTube videos back into NotebookLM to generate lead magnets, infographics, slide decks, and even cinematic explainer videos, all from a single source. That process brings hundreds of new subscribers into my newsletter every day. I also touch on connecting NotebookLM to Claude Code via the unofficial Python API, which lets you automate the whole thing at scale. It is genuinely one of the most underrated tools in AI right now, and it costs nothing. —— Time Stamps —— 0:00 The Free AI Tool You're Sleeping On 0:50 What is RAG? (Retrieval Augmented Generation Explained) 3:44 NotebookLM Interface Walkthrough 5:37 Demo: Importing a YouTube Video into NotebookLM 6:27 Chat With Any Video or Document Using AI 8:48 NotebookLM Output Types (Slides, Videos, Podcasts & More) 10:29 AI Cinematic Video Generation Demo 12:09 AI Podcast Feature You Can Join Live 14:38 How I Create Daily Content Using NotebookLM 16:55 How to Create Lead Magnets with NotebookLM 20:14 Automate NotebookLM with Python API & Claude Code 21:52 Live Q&A: Customization Tips & Best Practices 25:43 Is NotebookLM Content "AI Slop"? 27:13 NotebookLM vs Claude Cowork Explained 28:40 How to Still Access GPT 5.1 After Removal 29:53 Wrap Up & Free Resources —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →169: Replace your SEO agency with AI (Full Guide)
Mar 2700:36:55Tap to summarizeGet AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: I used to run an SEO agency. Charged businesses a couple of thousand quid a month, locked them into six-month contracts, and handed over PDFs that looked impressive but were, honestly, a bit of a black box. That entire model is now dead, and I say that with zero nostalgia. Today I walked through a free Claude Code skill called Claude SEO that runs a full technical audit, content analysis, keyword gap strategy, and AI search optimisation on your entire website. The same work that would cost tens of thousands a year from an agency took about 50 minutes on my site and cost me nothing beyond a Claude Pro subscription. The real magic is what happens after the audit. You feed the findings back into Claude Code, have it build a prioritised implementation plan, and then schedule it to chip away at fixes overnight. Title tags, header hierarchy, schema markup, meta descriptions, the lot. It just quietly gets on with it while you sleep and presents a little report in the morning. I also covered why SEO still matters in the age of AI, how Google indexing directly affects whether you show up in ChatGPT, Gemini, and Claude, and why blocking AI crawlers from your site is probably a mistake. The whole guide is linked below if you want to set this up yourself. —— Time Stamps —— 0:00 What is SEO and Why It Matters 0:49 Why AI is Killing the SEO Agency Model 3:37 Is SEO Still Important in the Age of AI 6:12 Using AI Instead of an SEO Agency 8:20 Claude SEO Skill: $20 vs $10K Agency Costs 8:55 Free Claude SEO Skill Walkthrough 9:58 How to Install the Claude SEO Skill 10:57 Running Your First AI SEO Audit 12:29 Content Analysis, EEAT and AI Crawler Access 13:45 Feeding Your Audit Back Into Claude Code 15:43 Connecting MCP to Analytics Tools 17:11 Recommended AI SEO Workflow 19:53 Q&A: Syncing Claude with Claude Code 21:11 Community Showcase: WTF is this Tech 23:24 How to Build and Host a Website with Claude 26:32 Does Every Business Actually Need SEO 29:16 Using Multiple LLMs for Better Results 30:25 Community Showcase: Sequestered AI 32:02 Best AI Creators to Follow Right Now —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →168: AI Latest: OpenAI Shuts Down Sora, Disney Drops $1B Deal, Claude Does Your Job For You
Mar 2601:11:29Tap to summarizeGet AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Big day for OpenAI news, and not the good kind. Sora is officially dead, pulled before it even launched in most of the world, and that billion dollar Disney deal has collapsed with it. The internal message at OpenAI is clear: stop the side quests, start making money. They're pivoting hard toward API revenue and enterprise clients, essentially copying Anthropic's playbook after watching them generate comparable revenue with a fraction of the users. Shopping features are getting reworked, flashy consumer toys are being shelved, and researchers are being told to put down the fun projects and focus on profitability. It's a sensible business move, but it does make OpenAI a little less interesting. Meanwhile, Anthropic have been on an absolute tear. Since January alone they've shipped Cowork, Opus 4.6, Excel and PowerPoint integration, a million token context window, Claude Code channels, and just yesterday, full computer use. That last one is particularly spicy because it means Claude can now click around your screen, open programs, and do tasks as if it were sitting at your desk. Someone in my chat pointed out the obvious implication: if you work from home, you could technically outsource your own job to Claude before your employer does it for you. Cheeky, ethically questionable, and probably inevitable. —— Time Stamps —— 0:00 Welcome & Show Introduction 0:21 OpenAI Kills Sora: Video Generation App Shut Down 1:14 Why OpenAI Is Cutting Features Before Its IPO 2:01 ChatGPT vs Claude: Why I Switched to Claude 3:08 OpenAI vs Anthropic: Consumer vs API Revenue 5:23 OpenAI's Pivot to API and Enterprise Revenue 6:42 Disney's $1 Billion OpenAI Deal Collapses With Sora 10:49 Disney AI Strategy: IP Licensing and Legal Battles 18:02 Is the Claude Ambassador Program Worth It? 20:48 Why Sora Failed After Its Viral Launch 22:54 ChatGPT Shopping: Why Instant Checkout Flopped 30:51 OpenAI's Pre-IPO Slash and Burn Strategy 32:18 Every Anthropic Claude Launch in 2026 35:53 OpenClaw vs Claude Cowork: Which AI Agent to Use? 41:23 Why Anthropic's API Business Model Wins 43:50 Claude API Errors and Server Capacity Issues 44:46 How I Use Codex and Claude Code Together 46:10 Edge AI Explained: Running Models on Local Devices 49:13 China's Open Source AI Soft Power Strategy 51:11 Is Cursor Getting Crushed? Future of AI Code Editors 54:48 How to Start Vibe Coding for Free 56:19 AI Models Are Converging: Why Harnesses Matter More 59:57 Lovable vs Claude Code: Trade-offs for Beginners 1:02:03 How to Set Up Claude Computer Use (Tutorial) 1:02:56 How to Move Projects from Cursor to Claude Code 1:05:49 Can You Outsource Your 9-to-5 Job to AI? 1:07:46 Claude Usage Limits: Codex vs Claude Code Pricing 1:08:59 How Claude Computer Use Works: 3 Methods Explained 1:11:33 Outro & Sign Off —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →167: Claude Can Now Control Your Entire Computer (FULL Explainer)
Mar 2500:33:24Tap to summarizeGet the free Vibe Coding guide here: https://aiwithkyle.com/mini/5-builds Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Anthropic just dropped Claude Computer Use and it's a proper shift. As of last night, Claude can now take full control of your Mac, not just Chrome, not just a sandboxed virtual machine, but your actual computer. It opens apps, navigates your file system, clicks around desktop software, the lot. If you've been following Open Claw, this is essentially that functionality baked directly into the Claude ecosystem, minus the terminal setup, minus the security headaches, minus the afternoon you'd lose tinkering instead of working. You toggle it on in the desktop app and you're away. I've been playing with it all morning and it's genuinely impressive how seamless it feels. What's really striking though is the pace Anthropic are shipping at right now. Two or three features a week since January. Cowork, Opus 4.6, dispatch, channels, remote control, scheduled tasks, computer use, it's relentless. Meanwhile Open Claw's creator has been hired by OpenAI and we've seen precisely nothing from that side. Perplexity Computer costs $200 a month and just got made redundant overnight. The big picture here is simple: we're moving from chatting with AI to AI actually doing things for us, and Anthropic are leading that charge by a comfortable margin. If you haven't explored what agents can do yet, now's probably the time. —— Time Stamps —— 0:00 Claude Computer Use Just Dropped — Here's What It Does 1:11 The Shift From Chatting to AI Doing Things For Us 3:18 How OpenClaw Proved the Demand for AI Assistants 6:26 Everything Anthropic Shipped in 3 Months 9:45 What Is Claude Computer Use and How to Turn It On 12:08 How Claude Decides: Connectors vs Browser vs Screen Control 16:03 Safety: Claude Computer Use vs OpenClaw Compared 20:27 How to Download and Set Up Claude Computer Use 22:41 Control Your Computer Remotely With Dispatch and Channels 25:04 Alternatives Compared: OpenClaw vs Perplexity vs Manus 27:36 The Big Takeaway: We Can Just Build Anything Now 30:41 Live Q&A —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →166: So you’ve Vibe Coded something brilliant — Now what?
Mar 2400:47:43Tap to summarizeGet the free Vibe Coding guide here: https://aiwithkyle.com/mini/5-builds Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: So you've vibe coded something. Brilliant. Now what? That's the bit nobody talks about. Everyone's showing you how to build the thing, but the moment you want actual humans to use it, pay for it, and not have their passwords stored in a spreadsheet, you need a proper stack. Today I walked through every tool I use to go from a half-baked idea to a live, deployed, money-making web app. GitHub, Supabase, Vercel, Stripe, Resend, Beehive, PostHog. The full lot. I explained what each one does, why you need it, and crucially, the order you should set them up in. The best part is nearly all of it is free to start. You only begin paying once thousands of people are actually using what you've built, which is a very good problem to have. I'm running a six-figure business and my entire tech stack costs me about a hundred dollars a month. That's an absurd margin. Whether you're using Lovable, Google AI Studio Build Mode, or Claude Code, this is the roadmap for turning your proof of concept into something real. I also shared a prompt that will generate a full deployment plan for your specific project, so you're not fumbling through DNS records alone at midnight. —— Time Stamps —— 0:00 The Vibe Coder's Toolkit Overview 1:44 Best Vibe Coding Tools to Build Your App 5:50 What Happens After You've Built Something 7:07 GitHub — Cloud Storage and Version Control 9:40 Supabase — Your Database and User Authentication 12:45 Deploying Your Web App With Vercel 15:37 Buying and Connecting a Custom Domain Name 18:10 Getting Paid — Stripe and ThriveCart Setup 21:03 Email Systems — Transactional vs Marketing Emails 25:00 PostHog — Analytics and A/B Testing for Your App 27:48 Full Vibe Coding Tech Stack Recap 30:58 The Master Prompt to Deploy Your App 33:08 Q&A — Lovable vs Claude Code and Getting Started 35:22 Building Free or Nonprofit Apps Without Going Bankrupt 37:50 Claude Code Remote Control — Channels, Dispatch and More 39:35 The Danger of Always-On Coding From Your Phone 40:40 Why AI Tool Costs Shouldn't Stop You From Building 42:23 Is AI Overhyped? The Levels of AI Usage 44:03 OpenClaw vs Claude Cowork — Which AI Agent Should You Use? 47:00 Outro and Newsletter —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →165: Massive Global Study: 81,000 people CONFESSED what they really want from AI
Mar 2300:40:46Tap to summarizeGet the free Vibe Coding guide here: https://aiwithkyle.com/mini/5-builds Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Three big things today. Anthropic dropped a massive study where they interviewed 81,000 Claude users about how they actually feel about AI, and the results are fascinating. Nearly 19% said AI hasn't delivered what they expected, with my favourite quote being "AI should be cleaning windows and emptying the dishwasher so I can paint and write poetry." Instead, it's doing the painting and the poetry. The data also shows a clear global divide: developing nations are overwhelmingly optimistic about AI while the West is increasingly nervous, which makes perfect sense when you think about who has the most to lose. I also got hands on with Claude's new Dispatch feature, which lets you message your always-on computer from your phone and have Cowork handle tasks while you're out. It's basically Open Claw for grownups, doing 90% of what made that tool exciting but in a much more secure package. Anthropic have been shipping features at a ridiculous pace and they're clearly stitching Claude Chat, Cowork and Code into one coherent system. Plus, a reality check for anyone moving from ChatGPT to Claude and hitting usage limits: Anthropic's real business is the API, not the $20 consumer plan, and that's not changing anytime soon. —— Time Stamps —— 0:00 Intro: Claude and Anthropic Are Killing It 0:34 Anthropic's 81,000 Person AI Study Explained 5:00 What 81,000 People Actually Want From AI 8:08 Is AI Actually Delivering on Its Promises? 12:44 AI Accessibility: Changing Lives for Disabled Users 14:45 What People Worry About: AI Hallucinations and Reliability 16:25 AI Job Displacement: Why This Time Is Different 17:56 Existential Risk and the AI Optimist vs Pessimist Debate 20:03 Global AI Sentiment: Why Developing Nations Love AI 23:24 Claude Dispatch and Cowork: OpenClaw for Grownups 29:42 Dispatch vs Remote Control: What's the Difference? 30:15 Is Any Job Future Proof? The Solopreneur Answer 32:05 Karpathy's AI Job Exposure Tool: How Safe Is Your Job? 33:17 Why Anthropic Doesn't Care About $20 Users 36:32 OpenAI vs Anthropic: The Business Model War 39:45 Outro & Free Resources —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →164: How to start VIBE CODING for free (no coding experience required, at all)
Mar 1900:32:32Tap to summarizeGet the free Vibe Coding guide here: https://aiwithkyle.com/mini/5-builds Get AI-Ready with Kyle’s 5-Day Challenge: https://aiwithkyle.com/join Kyle’s AI Canon — Curated list of AI learning essentials: https://aiwithkyle.com/ai-canon Subscribe and turn on notifications to catch the next live stream: https://www.youtube.com/channel/UChlLglbHDASnoGkbjDeHnQg Summary: Today I stripped vibe coding back to the absolute basics. If you've been hearing the term thrown around and feeling like you need to be technical to get involved, you don't. I walked through exactly how to get started using Google AI Studio's hidden Build mode, which is completely free, requires zero setup, and lets you build working apps just by describing what you want in plain English. I built a social media growth projector live on stream, from nothing to a functioning tool with charts and milestone calculations, in about two minutes. The whole point was to remove every barrier I could think of. No paid tools, no terminal commands, no deployment headaches. Just open a browser, click Build, and start talking. I also put together a second tool, a task automation analyser, to show how quickly you can go from idea to something genuinely useful. If you've had projects sitting on a to-do list for months because you assumed you'd need to learn to code first, this is your way in. Start with a toy project, get the bug, and worry about the complicated stuff later. —— Time Stamps —— 0:00 Getting Started with Vibe Coding for Complete Beginners 2:41 Why Google AI Studio Build Mode is the Best Free Tool 3:38 How to Use the Chat Interface and Voice Input 4:15 Start with a Toy Project Not Your Dream App 5:40 Live Build: Social Media Growth Calculator with Gemini 10:00 Publishing and Deploying Your First App for Free 11:06 Why Learning to Code Still Matters with AI 11:44 Bugs vs Features: The Vibe Coding Feedback Loop 14:28 How to Fix Bugs Using Screenshots and Error Logs 15:28 From Toy Project to Real Business Tool Using Claude 16:36 Planning Your Project Before Building 19:53 Dropping a Project Plan into Google AI Studio Build 20:47 What Beginners Should Skip: Auth, Databases and Deployment 22:51 Vibe Five: 5 Mini Projects to Build Your Coding Portfolio 24:55 Live Demo: AI-Powered "What Should I Automate First" Tool 28:28 AI-Generated Automation Suggestions That Actually Work 29:10 Recap: How to Start Vibe Coding Today 31:28 Join the Community and Free Resources —— More Useful Resources —— Find everything else at https://aiwithkyle.com/
Transcribe →