V2
just released the 2.0 version of the un-slop AI-looking apps skill
a guy already told me he cancelled his $15/month mobbin sub after trying V2
i spent over a week rebuilding it based on your feedback
new stuff:
→ native iPhone + Android designs
→ animated MP4 app demos
→ better UI copy, onboarding & paywalls
→ App Store + Google Play assets
→ much better design taste
it also includes everything from V1
the original stays free, Pro is just €5 (still ridiculously underpriced)
retweet + comment "V2" and i'll send you both free and paid version
(follow so i can dm)
125
Bruh just use Opus 5.5
It should be impossible for AI to make a bad UI.
Tell your agent today: "Install and set up github.com/gholtzap/lintappl… in this project"
88
Tibo would never haha
We’re rolling out monthly Claude Platform API credits for Max and Team plans:
Max 5x: $100
Max 20x: $200
Team: up to $500, pooled
Works on any model, including Haiku 5.5, in your code or third-party harnesses.
How it works and full terms: support.claude.com/en/articl…
1
64
Separate weekly limit for fable? But you cant use it when you reached the other percent meter of your weekly limit?
Am i understanding this right?
@AnthropicAI @claudeai @ClaudeDevs @trq212
1
96
codex useless app after all
Found out the hard way (again) that you can't use a Codex reset whenever you want.
I had a full reset (weekly + 5 hour) expiring tonight at 12:58 AM, and I'd already used 82% of my week. So I tried to use it before it disappeared.
Codex said "Your usage does not need a reset right now"
Turns out OpenAI only lets you use it when you've hit your limit or you're very close.
So basically I just lost one. Guess I was too busy with Opus 5.5 and GLM to burn enough Codex tokens to deserve it.
71
Built 2 apps via Claude just to see what happens:
Flutter gave me a production-ready, custom-designed beast that runs like a dream.
Expo gave me a liquid glass UI with 5 tabs and simple lists that's lagging as fvck.
Make it make sense. 😂
1
100
please add more description to your eval like speed and cost
we open-sourced Supabase Evals
it's our benchmark for how well AI coding agents build with @supabase. we run agents against real tasks and score them
see how Claude Code, Codex, and OpenCode perform:
91
I slept with 17% usage in @cursor_ai
I woke up and check my usage and its 26%? Didnt run anything during sleep. WTF @cursor_ai ?!
198
Jesse Ezell is the flutter team itself
FlockerPad running on iOS, compiling a flutter app by launching dart2wasm as a plan9 child process and then using the plan9 view device to embed launch the wasm output and render in a child view in the parent app. All native rendering with Flutter + Skia Graphite + Dawn. Editor is using tree-sitter compiled to WASM for the syntax highlighting.
3
253