OrcDev
@orcdev
I ship real products in public and show you exactly how โ๏ธ
๐ฅ
๐ฌ
๐ข
๐
๐พ
278 Following 10K Followers
@vburojevic @shadcn I'm using Copper every day ๐ฅ
Introducing @AskMyAds
You connect your ads (Google today, more platforms next), ask how things are doing, and get answers in plain English with real numbers. Nothing changes until you approve.
Free Waste Scan to start. 25 founding spots open.
๐งต
Show more
I expect a lot from Grok 4.7.
Grok 4.6 is already a really solid model, and its token efficiency is actually crazy.
If Grok 4.7 lands somewhere between Fable and Sol, it'll probably become my go to model for 80% of my tasks.
Show more
Grok 4.7 comes out in 10 days
What kind of age are we living in?
I made a mobile app literally in a couple of prompts.
And it looks crazy good.
It follows my design, my branding, my style, everything.
npx shadcn@latest migrate cn
We are open sourcing `cn`, a new engine for Tailwind class merging and conflict resolution. It is a drop-in replacement for tailwind-merge and clsx.
It works with all frameworks, runs everywhere and is 30x faster.
Brought to you by @aidenybai and me.
Show more
New project coming soon.
I literally can't wait to show you this one.
I'm putting so much of my brain into every tiny detail of this project.
And for the first time everโฆ I built a mobile app too ๐
Show more
I expect a lot from Grok 4.7.
Grok 4.6 is already a really solid model, and its token efficiency is actually crazy.
If Grok 4.7 lands somewhere between Fable and Sol, it'll probably become my go to model for 80% of my tasks.
Show more
Grok 4.7 comes out in 10 days
Fable 5.1 is really good.
One of the biggest things Iโm noticing is that it's crazy good at design.
Even starting from scratch, with very little context or guidance, it gives great results.
And Fable 5.1 Medium is definitely my sweet spot.
Show more
I don't think people realize how big this actually is.
๐๏ธ + โฒ = ๐
TanStack and @Vercel are officially teaming up!
Weโre working together to make Vercel a first-class home for TanStack Start with better support for deploying and running anything you can dream up with TanStack on Vercel.
Start here! ๐
Show more
Cheaper Fable ftw
Cache reads with Fable 5.1 cost 75% less than Fable 5โs.
This reduces the cost of the model in practice by around 25% for typical workloads, and up to 45% for highly agentic ones.
Show more
Claude Max gives you 20x usage, BUT only for the 5-hour session limit.
Not for the weekly limit!
What the heck is wrong with these AI companies?
The number of likes on this post says it all.
We need laws for AI companies.
1. Subscriptions must clearly say what we're paying for, and the limits shouldn't magically change.
If you advertise 20x usage, you can't hide in small letters that it's 20x for the 5-hour limit but NOT the weekly limit.
2. Once a model is released and benchmarked, those benchmarks should be continuously verified.
You shouldn't be able to release the "best model", slowly make it worse over time, then release the next "best model" and push everyone toward it.
We need transparency.
Show more
If you're looking for an amazing medior-level engineer skilled in both open-source and closed-source work @AlminaBrulic is looking for a job.
I mentored and personally trained her for over two years and she worked for me on various projects, both open-source and not.
If your company is looking for an engineer or know someone DM her, or me!
Show more
What Grok @bot actually is, how it compares to OpenClaw and Hermes, the best use cases for it, and how I use it every single day.
We need laws for AI companies.
1. Subscriptions must clearly say what we're paying for, and the limits shouldn't magically change.
If you advertise 20x usage, you can't hide in small letters that it's 20x for the 5-hour limit but NOT the weekly limit.
2. Once a model is released and benchmarked, those benchmarks should be continuously verified.
You shouldn't be able to release the "best model", slowly make it worse over time, then release the next "best model" and push everyone toward it.
We need transparency.
Show more
Tomorrow we're picking the second winner of a Vercel Ship ticket in San Francisco! ๐ข
We're picking randomly from Shipper Club's third batch.
Only 35 members are in right now, so your chances are pretty damn good ๐
Join us before the draw:
Show more
What Grok @bot actually is, how it compares to OpenClaw and Hermes, the best use cases for it, and how I use it every single day.
We need laws for AI companies.
1. Subscriptions must clearly say what we're paying for, and the limits shouldn't magically change.
If you advertise 20x usage, you can't hide in small letters that it's 20x for the 5-hour limit but NOT the weekly limit.
2. Once a model is released and benchmarked, those benchmarks should be continuously verified.
You shouldn't be able to release the "best model", slowly make it worse over time, then release the next "best model" and push everyone toward it.
We need transparency.
Show more
