I vibe-coded games over the last 72 hours using Claude's Fable 5. 10 things I learned: 1. You don't need to know how to code? See something broken? Just tell Fable to fix it. It finds the solution. That's how it's built. 2. Already a game dev? Even better! Upload your codebase. Use it to brainstorm, optimize, and explore ideas. 3. Stop sending tiny prompts: One long prompt. Multiple tasks. Tell it to tackle them 1 by 1. Burns fewer credits. 4. Got an error? Screenshot it. Paste it. Fable solves it. 5. The longer you push, the smarter it gets: Fable learns your code. At some point, every build just works on the first try. 6. Biggest beginner mistake: chasing graphics first: An ugly game that feels good beats a pretty game that plays badly. 7. The core rule: gameplay first, assets second: When the game feels good in your hands, that's when you build polished assets. 8. The asset stack is tiny: Higgsfield for 2D and video. Trippo for 3D models. That's it. 9. Stuck on 3D? @techhalla makes the best Trippo tutorials. He saved me hours. 10. If all of that still sounds like work, here's the shortcut: @higgsfield Games just dropped. You can use it in Claude with Higgsfield MCP, powered by Fable 5. Or just run it on the Supercomputer. It walks you through step by step, generates your assets, and deploys your game to a live URL, where your friends can join! The barrier to making games is... gone.

Current status:

I vibe-coded games over the last 72 hours using Claude's Fable 5. 10 things I learned: 1. You don't need to know how to code? See something broken? Just tell Fable to fix it. It finds the solution. That's how it's built. 2. Already a game dev? Even better! Upload your codebase. Use it to brainstorm, optimize, and explore ideas. 3. Stop sending tiny prompts: One long prompt. Multiple tasks. Tell it to tackle them 1 by 1. Burns fewer credits. 4. Got an error? Screenshot it. Paste it. Fable solves it. 5. The longer you push, the smarter it gets: Fable learns your code. At some point, every build just works on the first try. 6. Biggest beginner mistake: chasing graphics first: An ugly game that feels good beats a pretty game that plays badly. 7. The core rule: gameplay first, assets second: When the game feels good in your hands, that's when you build polished assets. 8. The asset stack is tiny: Higgsfield for 2D and video. Trippo for 3D models. That's it. 9. Stuck on 3D? @techhalla makes the best Trippo tutorials. He saved me hours. 10. If all of that still sounds like work, here's the shortcut: @higgsfield Games just dropped. You can use it in Claude with Higgsfield MCP, powered by Fable 5. Or just run it on the Supercomputer. It walks you through step by step, generates your assets, and deploys your game to a live URL, where your friends can join! The barrier to making games is... gone.

Biggest AI news of the year, unfortunately.

Fable 5 just turned me into an iOS developer. I spent 2 days building a full game with zero code written by hand. The last 10 builds succeeded on the first try. I needed a fun project to test it on, so I decided to make an iOS game. After a few experiments with other ideas, I settled on a runner starring Dario as the main character, called "Credit Runner". Hilarious, I know! In terms of credits spent, my Claude Max plan stands at 36% right now, and this isn't the only project I ran through Fable 5. A few quick notes: - This is just an early prototype, a long way from release, but it's really fun to play! - It's extremely fun to work with Fable 5! - Fable 5 wants to get things done, and it pushes you towards completion much faster than any other model. - Once we established the ground rules, how I wanted the game built, and the overall structure, the last 10 builds were flawless, succeeding on the first try. This is impressive! - All the assets were generated with AI (Magnific and Trippo for the visuals, ElevenLabs for the voices). The only thing that's not AI is the music. I just really liked this track. - There are many rules in the game designed to make it really fun to play, especially the randomness. - There are a lot of visual cues inspired by San Francisco, and I hope you catch them all. - At some point on the first day, I honestly thought I wasn't going to get where I wanted, but Fable pushed me towards the goal, and by the second day it started to deeply understand the project. - The prompts were really long, especially in the beginning, to make sure everything was covered. - Once the app was solid, I tried to pack as many changes as I could into a single prompt to maximize my Fable usage. This was just a fun project, but if anyone wants to play it, I might put the final, much more polished version on the App Store. What do you think? Should I?

I have to admit. In the past couple of days, I've been consumed by vibe coding. Fable 5 took over my life... and I'm having a blast!

I'm obsessed with Fable 5. I've been vibe coding today all day, in bed, working on: Credit Runner. Coming soon!

The good: Fable 5 is amazing! Everyone else has to do some hardcore catch-up. The bad: When June 23rd hits, y'all gonna pay a whole lotta $$$ to Anthropic, because you'll be hooked on it, and everything else will feel strange.

The only thing I see when people mention Fable 5

My co-founder @rezawrecktion is making waves at @Tribeca

Well, that escalated quickly...

Apple Intelligence will NOT be available in the EU. I'm really getting tired of this bullshit 🙄

Apple, powered by Google You know what, I actually like this. Gemini is a great model for everyday life tasks. PS: New Siri interface yet again, but this one's sick!

After over a month on the road I’m finally home, and I found this personalized gift from @Kling_ai waiting for me. What a thoughtful effort from the team. Thank you, guys!

It’s always the people that make everything special, even when they create with AI. These are some of the most forward thinking people today. Thanks @upscaleconf for the invitation and for organizing this wonderful event.

One of the first accounts I followed on Twitter was @Scobleizer Today, about 18 years later, I finally met him in real life, and we had a great conversation about the future of films: