joca

Backend engineer thinking about architectures for AI-driven systems. Building at

[gus @igus_ai]

CURSOR está regalando 1 año de Pro GRATIS

solo necesitas conseguir un correo de estudiante, tuyo o de alguien que conozcas

lo que incluye:

→ 12 meses de Cursor Pro (valor $240)
→ acceso completo a GPT, Claude y Gemini
→ sin tarjeta tras la verificación

cómo conseguirlo:

1. entra en https://t.co/hA5iiAXMqj
2. regístrate con un email universitario
3. pasa la verificación de estudiante

en algunos países es con un email .edu, pero cada país tiene su propio sistema de verificación estudiantil

mientras todos pagan $20/mes, tú puedes programar proyectos enteros GRATIS durante un año

aprovecha antes de que termine el plazo

[santi @santtiagom_]

vale la pena cada minuto

[joca @devjoca]

@benln Hope Lima can be next in the list

[joca @devjoca]

@garrytan Do I need a frontier model for this? Or I can use something cheaper like deepseekv4 pro

[Cursor @cursor_ai]

With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript.

This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!

[joca @devjoca]

@PizarraCrema que t kche fertoli

[Matt Pocock @mattpocockuk]

AI is making me obsessed with language

Taking abstract business processes and naming them is INSANELY powerful for aligning AI with how you work

I don't scan X for inspiration for course material/socials

I capture notes (either as hooks and bricks) from the X channel

This brevity makes communicating with AI so much faster, and helps you think more clearly

[Guillermo Rauch @rauchg]

𝚗𝚙𝚡 𝚍𝚎𝚎𝚙𝚜𝚎𝚌

We're introducing an open-source agent orchestrator for deep security reviews.

We built it for internal use, and after running it against some major OSS projects, we gained conviction to share it with the world.

Coding agents can now find critical vulnerabilities in minutes that would take teams of people months (if they can spot them at all). Since 𝚍𝚎𝚎𝚙𝚜𝚎𝚌 is optimized to work with Vercel Sandbox, you can effectively harness the power of thousands of agents scrutinizing your codebase in parallel.

I encourage you to try this on your repositories. BTW: If you run an OSS project and want us to sponsor a run, my DMs are open.

[Cline @cline]

We spent the last two months rewriting Cline from the ground up.

The original Cline shipped right after Claude 3.5 Sonnet dropped. It was the first coding agent that actually worked, and we built it extension-first for the IDE. Great in its time, but the architecture got tightly coupled to IDE semantics, which made it painful to evolve the harness for the CLI and to extend into things like flexible agent profiles and agent teams..

So we took every hard lesson from the past year and started fresh. Built an SDK with better performance and token efficiency, with a plugin architecture for providers, models, LSPs, code search, themes, all of it. Then rebuilt the CLI and the extension on top.

We're at the last mile and want folks in the beta with us. There will be breaking changes and missing features, and we'd like your help to close the gaps.

We are offering $20 in credits to get started, plus a bounty program for contributors who help us fix bugs and make plugins.

Join the #beta channel in our Discord and build with us! 👇

[Mauricio Reatto Duarte @mauriciord]

"/grill-me" skill really helps me understand the implementation of the new feature. It also allows me to further explore the design review with my teammates before creating the complete plan for that feature.

@mattpocockuk

[Erik Sombroek @ErikSombroek]

That moment when you boot into the main menu of your childhood..

Cross-compiled Warsmash (a LibGDX-based Warcraft III engine reimplementation in Java) to JavaScript using TeaVM so the whole game runs directly in the browser, with map files served from OPFS. Still some quirks left but great progress.

Credits to Retera for his hard work.

#Warcraft3 #RetroGaming #Gamedev #TeaVM #LibGDX #WebGL #Java #OpenSource #BrowserGaming #IndieDev #RTS

[Jamie Birch @birch_js]

Hey, maybe we don’t need husky anymore!

[joca @devjoca]

@MilksandMatcha @dabit3 @cerebras I want it because I’m Peruvian, gaaaaaaaa

[Shopify Engineering @ShopifyEng]

Since we open-sourced pi-autoresearch, @Shopify teams have been running it on everything.

Results so far:
Unit tests: 300x faster
React component mounting: 20% faster
CI build time: 65% reduction
Made pnpm run faster

Autoresearch never stops trying things you'd never have time to try.

Repo: https://t.co/473UFWKanV

[Greg Brockman @gdb]

We've changed our pricing so it's now possible to try Codex at work without any up-front commitment.

Codex (especially through the app!) has gotten *really* good. Happy building!

[joca @devjoca]

@MilksandMatcha need it

[joca @devjoca]

@ElonMuskAOC hmm

[Not Elon Musk @ElonMuskAOC]

You can no longer copy the links of video posts

Go touch grass

[Jordan Hochenbaum @Jnatanh]

pi-autoresearch has been incredible for running experiments against our codebase, but I wanted a way to more selectively cherry-pick which ones become PRs, plus a few other bells and whistles.

So I built pi-autoresearch-studio: granular experiment-to-PR selection with auto-resolved dependencies. My first @badlogicgames Pi extension.

[Andrej Karpathy @karpathy]

- Drafted a blog post
- Used an LLM to meticulously improve the argument over 4 hours.
- Wow, feeling great, it’s so convincing!
- Fun idea let’s ask it to argue the opposite.
- LLM demolishes the entire argument and convinces me that the opposite is in fact true.
- lol

The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.

[joca @devjoca]

Just write post about how I ordered my kitty medical documents using AI
https://t.co/U5ZkCVlBf3