My Education Platform: https://xitter.cf/t.co/64WffDsLsj My YouTube (400k+): https://xitter.cf/t.co/nQ9Z71MyW4

Joined June 2023
📢 I've spent the last month building an open-source AI browser automation platform from scratch. Today I'm releasing the entire project in a completely free 7-hour tutorial ⬇️ 🚗 Configure a Porsche 911 💼 Apply for jobs 🛍️ Shop for the best deals 🏠 Find your next apartment ✈️ Plan your next vacation 🚀 Deployment @Railway 🔐 Authentication @clerk 🗃️ Postgres DB @neondatabase 🔁 AI workflows @triggerdotdev 🌐 Browser agents @browserbase 🤝 Live collaboration @liveblocks 📊 Logs & Monitoring @sentry
20
14
2
175
20,478
Code With Antonio retweeted
Death to clickops 💀. Our new @bot plugin lets you stay out of our dashboard
4
5
3
54
3,466
Code With Antonio retweeted
Today we're announcing a $60M Series B at a $1B valuation, led by @FirstMarkCap to build the agent cloud. The round also saw participation from some top-tier founders, including @patrickc (Stripe), @tobi (Shopify), @AravSrinivas (Perplexity), @BrendanFoody (Mercor), @oliveur (Datadog), @adamdangelo (Quora) and @ericsyuan (Zoom). Full announcement👇
24
24
13
216
21,296
fun weekend project making claude code add every single IoT device in my household suprisingly, even managed to add "closed-off" devices like dyson robot vacuum hardware: @Raspberry_Pi 5 software: @home_assistant design: @mobbin + @paper MCP
16
2
1
116
5,244
Code With Antonio retweeted
We just raised a $60M Series B at a $1B valuation to build @daytonaio into the Agent Cloud. @FirstMarkCap led the round, with all key existing investors and angels doubling down. We're also thrilled to welcome the founders of some generational companies aboard, including @patrickc (Stripe), @tobi (Shopify), @AravSrinivas (Perplexity), @BrendanFoody (Mercor), @oliveur (Datadog), @adamdangelo (Quora) and @ericsyuan (Zoom) We're a 35-person team. But that's about to change; we're hiring across the board, and we'd love for you to join us.
444
194
147
1,369
257,535
Code With Antonio retweeted
Greptile has raised a $50M Series B led by Menlo Ventures. The round values the company at $750M. Greptile reviews and tests more than 1% of all PRs opened on GitHub every day. Thousands of engineering teams including Nvidia, Coinbase, Decagon, and Vanta use Greptile as their independent and central validation layer. Fewer than 50 people, we are a small, talent-dense team of engineers and researchers in a quiet corner of San Francisco. If you’re interested in joining us, we’d love to hear from you.
128
54
76
891
258,316
repeat this loop for every feature in your app and watch the ai slop disappear 1. add primitives 2. add skills 3. implement the feature using skills examples: 1. add shadcn/ui primitives (button, sidebar, dialog...) 2. add shadcn skills 3. implement dashboard ui using shadcn skills - no more ui slop 1. add neon primitives (db, object storage, functions...) 2. add neon skills 3. implement backend using neon skills - no more backend slop 1. add clerk primitives (clerk/ui, clerk/nextjs) 2. add clerk skills 3. implement authentication using clerk skills - no more auth slop eventually, your codebase becomes the primitive, and your AGENTS.md the skill itself
20
17
267
12,704
i cannot believe this website is free
39
54
10
4,107
106,700
i cannot believe i have to clarify that this is kingbass0 categorizing itself as a stupid hater, and not theo being owned 😭
6
158
7,568
Code With Antonio retweeted
Introducing Alexandria in Claude. Access over 100 data providers and 113M+ indexed sources easily through Firecrawl. Agents using Alexandria score 21% higher on answer quality than those using built-in web tools. Get started using the Firecrawl connector today!
39
30
11
432
38,365
haven't used plan mode in months
we’re thinking of killing plan mode and using the shift+tab hotkey to adjust effort levels I don’t think the models need plan mode anymore, but if you’re a plan mode diehard would love to get your feedback on why
6
30
6,746
i've been obsessed with this saying for days and it's making me realize how stupid i am being by hiding my work public because it's not finished or perfect i geniunely have to start retardmaxxing
A retard in motion is always better than a genius at rest
5
2
49
4,067
i've been rocking @exedev + @herdrdev as my remote agentic coding environment throughout for the past 2 weeks and i don't think i'm ever going back to running agents on my laptop. this setup survived flaky wifi on planes, trains, low coverage zones, and gave me easy mobile handoff. the most annoying parts of this setup by far is the terminal ssh lag, which can be reduced by moving the vm closer (does not help on planes), or by adding something like mosh (not compatible with exe vm's out of the box) so it feels like adding a GUI control plane like @t3dotcodes is the ultimate solution
17
1
104
8,935
shoutout to @reidRMC for putting me on @exedev 🙌
5
775
Opus 5.5 helped me avoid having to purchase Wi-Fi access for two devices on my flight so I'd say it's pretty good
4
52
6,728
Code With Antonio retweeted
Introducing Alexandria. We raised a $75M Series B led by Smash Capital to build the world’s largest knowledge library for superintelligence. Supercharge your agents with instant access to the most powerful data sets & providers. firecrawl.dev/alexandria
111
102
80
1,187
287,975
THANK YOU! Now let’s do .agents/ support as well
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.
2
33
4,327
Code With Antonio retweeted
Here's a 45-second TL;DR on Jev. I find the core idea beautifully simple, but the video made it really hard to understand. Hope you find it helpful.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
246
731
283
9,882
1,769,161
Code With Antonio retweeted
Introducing shadcn/lint. An agent-first linter for Tailwind design systems. You define what’s allowed. When an agent breaks a rule, the error explains what’s wrong and how to fix it using your components, variants and theme. There’s a lot you can do with this. Let me show you ↓ github.com/shadcn-ui/lint
220
446
167
6,584
1,204,804
i spent months editing out silent parts in my hour long clips by hand, only to find out there is a built in feature with silence threshold, pre-tail, post-head... serves me right for not bothering to learn the first thing about davinci 🫠
6
40
3,464