Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Scientists Teach AI to Think About the Roman Empire

When progress doesn’t feel like home: Why many are hesitant to join the AI migration

‘Wizard of Oz’ blown up by AI for giant Sphere screen

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Andrej Karpathy

I started ‘vibe coding’ my own apps with AI and I’m loving it

By Advanced AI EditorApril 14, 2025No Comments3 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


My experience with vibe coding

I’ve always had an interest in programming, because I’ve always had an interest in computers. I put together websites in HTML as a teenager (which, yes, were hosted on GeoCities) and have been occasionally dabbling in Python since.

Yet none of my projects got very far and, apart from my early websites, I never made anything useful. My efforts all followed a familiar pattern: I’d fixate on a particular resource—like an O’Reilly book or an online course—and get started with great enthusiasm, but as I’d realize I was months or years away from creating anything remotely useful, I’d give up.

Anthropic Claude d20 dice roller example screenshot
I’ve used Claude AI to quickly generate a simple dice roller web app.

Matt Smith / Foundry

That changed in late 2024 when my general frustration with WordPress, which I was using for my personal website, got the better of me. In a fit, I threw my website’s content plus a screenshot of it into Claude 3.5 Sonnet and asked the AI to replicate my site with HTML, CSS, and JavaScript. To my amazement, Claude 3.5 generated a functional website. It wasn’t perfect, but after a couple hours of working with Claude, I wound up with a website I liked even better than its WordPress predecessor.

My approach was exactly what Karpathy described. I didn’t read the code, nor did I really try to understand it (though I did have to think a bit about how the featured articles carousel works). That aside, I just told Claude what to do, copy-and-pasted the results in VSCode, saved the file, and reloaded my browser to see what changed. And it worked.

AI vibe coding example Pico-8 puzzle game in progress screenshot
A work-in-progress screenshot of my Pico-8 puzzle game and the vibe-coded source.

Matt Smith / Foundry

But the most important part? It was fun! Fun enough that I’ve since tried my hand at several other coding projects. I made an online tool to track initiative and roll dice when DMing tabletop roleplaying games, I made another tool to simplify rolling dice in Battletech, and I’m currently making a puzzle game for the Pico-8 virtual game console. I also used AI to guide me through setting up tools that require a bit of fussing, like OpenAI’s Whisper speech-to-text model.

Notably, all three projects were in different programming languages—HTML/JavaScript, Python, and Lua—none of which I’m even remotely proficient with. I’ve also dabbled in some C#, as I started to make the puzzle game in Unity before deciding it was overbuilt for my needs and swapping to Pico-8. I also toyed with turning my tabletop RPG tool into a Windows app before deciding that wasn’t helpful.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleEfficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
Next Article Apple CEO ‘Hell Bent’ on Launching True AR Glasses Before Meta
Advanced AI Editor
  • Website

Related Posts

Elon Musk Wants Former Tesla AI Chief Back

July 23, 2025

LLM-Optimized Research Paper Formats: AI-Driven Research App Opportunities Explored | AI News Detail

July 11, 2025

How to Build a Thriving Open Source AI Community Using Modular Bacterial-Inspired Code Principles | AI News Detail

July 7, 2025
Leave A Reply

Latest Posts

David Geffen Sued By Estranged Husband for Breach of Contract

Auction House Will Sell Egyptian Artifact Despite Concern From Experts

Anish Kapoor Lists New York Apartment for $17.75 M.

Street Fighter 6 Community Rocked by AI Art Controversy

Latest Posts

Scientists Teach AI to Think About the Roman Empire

July 27, 2025

When progress doesn’t feel like home: Why many are hesitant to join the AI migration

July 27, 2025

‘Wizard of Oz’ blown up by AI for giant Sphere screen

July 27, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Scientists Teach AI to Think About the Roman Empire
  • When progress doesn’t feel like home: Why many are hesitant to join the AI migration
  • ‘Wizard of Oz’ blown up by AI for giant Sphere screen
  • 2 Artificial Intelligence (AI) Stocks With High Conviction
  • MIT’s bioinspired device mimics remora fish suction

Recent Comments

  1. GeraldDes on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. binance sign up on Inclusion Strategies in Workplace | Recruiting News Network
  3. Rejestracja on Online Education – How I Make My Videos
  4. Anonymous on AI, CEOs, and the Wild West of Streaming
  5. MichaelWinty on Local gov’t reps say they look forward to working with Thomas

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.