Forget boring cursor highlighters 😁
Pokey turns your cursor into an interactive pointer that taps every click you make.
Keep it subtle – “Shy Finger” mode. Or make it impossible to miss – “In Your Face” mode 🤟🏼
Say goodbye to boring demos and screen shares!
submitting an iOS app soon?
this might save you from losing two weeks to one stupid App Store rejection
I went through the most common reasons Apple rejects apps and put them all into one article
it’s a long article, so don’t just scroll past and forget it
save it now and read it when you have time
This is one of the wildest things I have built with AI so far 😱
Asked Claude Fable 5 to create a fully interactive 3D crime investigation board using @threejs and it did it in ONE Prompt.
It took one more prompt to give it a polished UI inspired by a reference design that I created with GPT Image.
What surprised me most was not how it looked. It was how it worked.
Fable built a complete Verlet rope physics system with 46 particles in every thread. It handled gravity, damping, distance constraints and all other features of file upload, text and everything.
The threads/ropes even lift naturally with pinned evidence instead of clipping through it.
I never asked it to implement any of that. I only described the experience I wanted.
Maybe that's how we should work with AI. Instead of writing long long specs, we should explain what we want as an experience and let AI do its thing.
Anyway, every day Fable 5 raises the bar for what I think AI can build. More to this
Live: https://t.co/VChXb0GFaY
Code: https://t.co/6LSCbmL8tI
Spent the last couple of days trading a bit more privacy for better AI context.
Built a CLI skill that lets my AI read my WeChat chat history. Having it behind my own CLI means I get to decide exactly what the agent can access, so I still have control over which conversations ever leave my machine.
Next up: WhatsApp and Telegram. That should cover most of my day-to-day context.
@zarazhangrui Project-based learning is still the best way to learn imo. Once you're trying to solve a real problem, you naturally figure out what you need to learn. Building something tangible is a much stronger long-term motivator than just studying.
What if a newspaper app had real paper? 🗞️
Just built this React Native app where the pages behave like real paper:
- Scroll too far: it stretches and crumples
- Swipe: the paper warps and crumples under your finger
- Bad article? Tear the corner, crumple it into a ball… and yeet it 🗑️
All at 60fps on the UI thread. Pure real-time Skia shaders + hand-rolled 3D mesh with Reanimated.
This was stupidly fun to build.
Repo in the replies!
Been running my entire life context in Obsidian for my AI agents.
Accumulated tons of notes, decisions, and data from every angle.
So I fed the whole vault to Fable 5 and asked it to brutally review what I’m doing wrong that I’m not aware of.
The output blew my mind.
It connected patterns across my decision-making, highlighted pitfalls I was blind to, and showed exactly why some goals weren’t going to happen.
Now I have a clear guidebook to fix them.
If you have a big Obsidian vault (or any personal knowledge base), try this. The insights are scarily good.
What’s the most valuable AI review you’ve ever run on your own data?
I love the famous metaphors from Bird by Bird
"The fantasy of publication is like a set of plastic keys to a set of plastic handcuffs."
Building products feels the same sometimes. You think you're solving a real problem… but it might just be an illusion.
Building with AI has become my favorite escape hatch from distribution.
I can ship features insanely fast, but actually getting people to see them? Still feels like dark magic.
Anyone else using AI to procrastinate on marketing? 😂
What’s your current distribution hack?
I don't manually write code anymore. Most of my time goes into figuring out what I want. Then I review the plan AI drafts and let it run. Implementation is delegated, testing too.
At first this felt like a superpower. Then I noticed it's equally cheap for everyone, and people with more experience can point AI in the right direction from day one. They get amplified harder than I do.
I used to think you build the thing first and figure out distribution later. The order is backwards. Being able to build stopped being rare. What is rare is having people who wait for what you ship, and that kind of waiting can't be rushed a month before launch.
Looking to connect with builders on @X 👋
If you’re into:
- Design
- Building SaaS
- Vibe coding
- AI tools
- Shipping in public
- Figuring it out as you go
Drop what you’re working on or just say hi.
I’ll follow back active builders. Let’s grow together