@DamianCatanzaro @evilrabbit_ Podes usar esto para cuando necesitan correcciones: spritefusion.com/pixel-snapper
Español
Martin Llano
1.5K posts
Martin Llano
@amllano
Automating workflows, multiplying results.
Beigetreten Nisan 2009
492 Folgt158 Follower
@evilrabbit_ Estoy fascinado lo bien que hace sprites el nuevo modelo de imagenes de ChatGPT, estoy probando varias para AOWeb y ayer hice estas 2:
Español
Had a blast last night with the folks at @HackTandil 🚀
Love seeing the tech community thriving, so many builders focused on what matters.
Huge thanks @d4rm_, @tadeodonegana, and @NodoSerrano for making it happen.
dantesito@d4rm_
El 17 de abril vuelve @HackTandil de la mano de la primer Coding Night en @NodoSerrano! 🔗 luma.com/q0013zi6
English
Too much dogfooding here.
Outsourcing cognitive judgment, no hitl, no easy escalation path besides screaming the loudest on X. It’s a bad combo.
Gergely Orosz@GergelyOrosz
Pretty telling how Anthropic 1. Thinks it’s perfectly acceptable to ban a 60-person paying org without justification 2. Are comfortable outsourcing this to some automated system 3. Do no human review nor offer human contact 4. Get it wrong and customer now super pissed
English
Martin Llano retweetet
Pretty telling how Anthropic
1. Thinks it’s perfectly acceptable to ban a 60-person paying org without justification
2. Are comfortable outsourcing this to some automated system
3. Do no human review nor offer human contact
4. Get it wrong and customer now super pissed
Pato Molina@patomolina
Anthropic decidió dar de baja a toda nuestra organización por una supuesta infracción de sus condiciones de uso. Qué política específica infringimos no tengo ni la menor idea: simplemente recibimos un mail y listo, adiós Claude. Si querés apelar la medida hay que completar un Google Form, así de ridículo como suena. De golpe más de 60 personas se quedaron sin una herramienta fundamental para trabajar. Integraciones, skills, historial de conversaciones: todo perdido o, en el mejor de los casos, parado por tiempo indeterminado. Enorme aprendizaje para cualquier empresa de software que dependa de herramientas de IA en procesos críticos. Nunca hay que poner todos los huevos en una canasta.
English
Shopify just keeps delivering 🔥
Shopify@Shopify
the Shopify AI Toolkit is here manage your store with your favorite agent Claude Code, Codex, Cursor, VS Code, and more
English
We solved character consistency. Forever
Avatar V captures you in 15 seconds and holds your identity across every video.
Change the look, outfit, and setting to create unlimited versions of you.
RT + comment "AvatarV" below and I'll DM 100 credits to test it out (must follow)
English
A while ago I got so frustrated with cursor-the-editor that I churned back to VSCode.
Now that agents write most of the code I don't want fancy autocomplete second-guessing what I want to do. I literally only go to the editor when I know exactly what to do.
Turns out VSCode was even worse at this. It constantly refuses to save files. Like it has one job. And this is for trivial edits like package.json or .gitignore.
So, I moved on again. Giving zed a try.
English
The pace shift is remarkable—decisions that once took quarters now happen in weeks. I have watched SMEs move from "we need to think about data" to full analytics deployment in under a month. The real unlock is not just speed, but that non-technical teams can now drive their own insights instead of waiting on specialists. 💡
English
Met with the CEO of a food delivery company with a massive presence across the Americas.
They’re internally vibing solutions for critical workflows at an incredible pace.
Software demand is only going up.
Very bullish on the economic expansion AI is about to unlock.
English
tbf, that’s biz defining category: Nice UX on top of something free (free as bird though)
George Pu@TheGeorgePu
Almost signed up for ElevenLabs to narrate my blog. $330/month. Then I tried running an open-source model on my own laptop. Qwen 3.5 14B. Sounds fine. 200 posts a month. Costs me electricity. I almost paid $4,000 a year to rent a model I can run myself. Most AI subscriptions right now are just a nice UI on top of something free.
English
Martin Llano retweetet
Almost signed up for ElevenLabs to narrate my blog. $330/month.
Then I tried running an open-source model on my own laptop. Qwen 3.5 14B.
Sounds fine. 200 posts a month. Costs me electricity.
I almost paid $4,000 a year to rent a model I can run myself.
Most AI subscriptions right now are just a nice UI on top of something free.
English
Martin Llano retweetet
People of pi, if you're brave and run pi.dev on Windows under bun.sh this is for you:
github.com/rcarmo/piclaw/… (MIT)
Fully native FFI-based tools to automate Windows - who needs Claude to do desktop automation? WE DON'T!!!! /cc @badlogicgames
English
@cramforce Tangential: there should be a tool that generates a suite of test cases and evals from repo that one can use to create subagents (possibly would help with skills too).
English
Test your SKILL.md
Now that code is free, you can just test things.
Here is Chat SDK's chat-skill.test.ts
github.com/vercel/chat/bl…
- Does the inline TypeScript compile?
- Do the mentioned paths references into node_modules/ exist when you pack the repo with npm?
- Does it list all built-in adapters that exist in the repo?
- Does it list all community adapters listed in the docs?
- Etc.
English