Kai

@northwesternU grad

[Kai @kai_rypto25]

I finally finished my project for the @tan_stack @convex hackathon!!!

Introducing Sprawl AI.

Marketers need to create content faster than ever before...

Sprawl allows you to do just that with a flexible canvas interface, automatic transcriptions, custom agents and more.

[Kai @kai_rypto25]

“This isn’t a pitch competition. It’s a build competition”

😬😬😬

[Y Combinator @ycombinator]

We're hosting a GStack × GBrain Hackathon on May 16, with @TheHogAi, @transposevc, @askjoai, and @gbrainio!

Build and ship something real in 12 hours.

Win a YC interview and a 1:1 working session with @garrytan.

RSVP at https://t.co/Nkq3yhEu0g.

[Kai @kai_rypto25]

Complexity happens by default.

Clarity happens by design

[Kai @kai_rypto25]

Perfectionism is strategy cosplay.

Do the smallest useful thing

[Kai @kai_rypto25]

perfectionism dies one small choice at a time

[Kai @kai_rypto25]

narrow products make obvious promises

obvious promises sell

[Kai @kai_rypto25]

when stuck, find the stupid move first

then do the opposite

[Kai @kai_rypto25]

@thsottiaux Can we have a vertical Split View? Ie see one thread on the left half and one on the right half (without popping them into their own windows)

[Kai @kai_rypto25]

the hard part is not doing the work

it is knowing what work is worth doing

[Kai @kai_rypto25]

I turned a childrens game into an AI benchmark...

And AI sucks at it

[Kai @kai_rypto25]

@wesbos @zeeg @syntaxfm https://t.co/03xKQo54zD

[Kai @kai_rypto25]

I finally finished my project for the @tan_stack @convex hackathon!!!

Introducing Sprawl AI.

Marketers need to create content faster than ever before...

Sprawl allows you to do just that with a flexible canvas interface, automatic transcriptions, custom agents and more.

[Kai @kai_rypto25]

Animated educational videos made in seconds

Using @Remotion to trace over SVGs
Using @ElevenLabsDevs for the voice over

[Kai @kai_rypto25]

Huge shoutout to River for the inspiration:
https://t.co/edOMq87Y5y

[River Marchand @Riyvir]

today’s experiment: chimera. a little tool that let’s you realtime morph through a design system matrix generated by 4 reference images.

this one was inspired by listening to @jameygannon talk about her process on Dive Club with @ridd_design and How I AI with @clairevo. her approach to choosing moodboards over prompts made me wonder what might be possible if we applied that same approach to generative UI. and after a few dead ends, the idea turned into chimera.

the results are very generic at the moment but I might tune it up if people seem interested.

the big reminder for me is how much more inspiring a tool feels when you can explore in realtime instead of waiting for results every time you make a change.

lots more things to try in that direction.

[Kai @kai_rypto25]

I hate trying to pick a good theme:

So I made a tool that lets me experiment visually
- interpolate between themes
- upload/test custom themes
- fully open source

npm package coming soon...

[Kai @kai_rypto25]

Code is available here (right now it is just a demo but eventually will be an installable package)
https://t.co/xdbOMY8Rf1

[Kai @kai_rypto25]

Introducing Remo-cn: Shadcn for Remotion

Stop building demo videos from scratch. 10+ free, open-source components ready to copy-paste.

🖼️ Pre-built backgrounds (no design needed)
🎨 Fully customizable (make it yours in minutes)
🤖 AI-native (prompt → video)

[Kai @kai_rypto25]

The era of AI chat is over

Introducing Splat: The AI first canvas

[Kai @kai_rypto25]

@hugorcd @aisdk @vercel 🤯

[Kai @kai_rypto25]

@amritwt Easy fix: make a tool that passes a video to Gemini via the open router api. You could hard code a prompt or let it take in a prompt from the model