.@POTUS hoy: ¡Felicitaciones al Candidato Presidencial Colombiano, “El Tigre (THE TIGER)”, Abelardo De la Espriella, un Líder Inteligente, Fuerte y Duro, por su decisiva Victoria en la primera vuelta de la Elección Presidencial Colombiana! Abelardo lucha incansablemente por, y ama a, su Gran País y Pueblo, justo como yo lo hago por los Estados Unidos de América.
¡Como Presidente, Abelardo tendrá un éxito tremendo al liderar a Colombia para Hacer Crecer la Economía, Crear Empleos, Promover el Comercio, Detener la Inmigración Ilegal, Combatir el Crimen y las Drogas, y Restaurar la LEY Y EL ORDEN!
Abelardo se enfrentará a un Marxista de Izquierda Radical en la Segunda Vuelta el 21 de junio — Los resultados de esta Elección son muy importantes para el futuro de Colombia y su relación con los Estados Unidos la cual, si Abelardo gana, y debido a su competencia y amor por su País, tendrá todo el apoyo y la fuerza de los Estados Unidos detrás de él.
Debido a sus tremendos logros en la vida, y su apoyo político hacia mí, es mi Honor darle a Abelardo mi Respaldo Completo y Total. “EL TIGRE” ABELARDO DE LA ESPRIELLA NO DEFRAUDARÁ AL MARAVILLOSO PUEBLO DE COLOMBIA. ¡Se elevará a una nueva altura de Grandeza!
Presidente DONALD J. TRUMP
The creator of Ruby on Rails is all in on AI...but that doesn't mean he's rushing to build it into the framework just yet.
On the newest On Rails, @DHH joins @robbyrussell to talk Rails, the Basecamp 5 launch, and AI-assisted development: "It is a professional obligation of every programmer to take this revolution seriously."
Curious where Rails is headed? Listen or watch the full episode on YouTube (link in thread). https://t.co/23Gil4jzYZ
Computer use is now in Claude Code.
Claude can open your apps, click through your UI, and test what it built, right from the CLI.
Now in research preview on Pro and Max plans.
a lot of engineering orgs (Stripe, Ramp, Coinbase) are building internal cloud coding agents
we're releasing a fully OSS one today - every company should have the power of cloud agents at their fingertips
ONCE is back! It's now a full-fledged application server for running dockerized web apps, like Campfire/Writebook/Fizzy or your own vibe-coded adventures. Zero-downtime upgrades, scheduled backups, and a gorgeous TUI with hyperdrive graphics. Enjoy! https://t.co/WaLSMms2fr
@tomfgoodwin I’ve used em dashes for 20 years. Love them. Now every time I see one I think “AI”. I'm ready to start using hyphens instead, just to prove there’s still a human at the other end. I’ll take the heat from the grammar purists.
Jack Dorsey just laid off half of his company in a single tweet. 4,000 people gone
Not because business is down
But because AI made them unnecessary
If you aren’t AI native, you have become expendable to execs.
You need to learn these skills now:
1. How to build software in Claude Code
2. How to automate in OpenClaw
3. How to create artifacts in Claude Cowork
4. How to orchestrate multiple agents in Codex
5. How to use ChatGPT as a copilot for everything you do
These aren’t optional skills anymore. They’re mandatory.
And the time you have left to learn them has quickly disappeared.
An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently.
When the agent is confused it runs git-blame and messages the right engineers in Slack. By Monday the agents finished the plugin feature.
That's one example of how the best engineers are shipping software right now.
Developers will soon orchestrate 50 AI agents in parallel and the difference between a good engineer & a great one would come down to specs.
You can't write a spec that holds up at that scale without genuinely understanding what you're building at a deeper level.
The next-gen developer who understands the fundamentals, can architect well and orchestrate agent is going to be a 1000x developer!
Kimi K2.5 on @opencode Zen is hilariously cheap. I bought $20 worth of tokens two weeks ago, and I still have $10.89 left! After 3M tokens! If there's a bubble in AI, it's pricing a million tokens at $25 (and beyond).
Hoy Bogotá me falló y me duele profundamente, de verdad. Me rompieron el vidrio del carro, mientras comia en un restaurante, me robaron TODO en un parqueadero público del Distrito, Calle 70 # 9-95.
Pagué lo que la ciudad me cobró. Llegué desde Medellín enamorada de Bogotá, pero aquí no cuidan a la ciudadanía: la Policía minimiza, el cuadrante ni me tomó los datos, no hicieron nada, nadie responde.
@CarlosFGalan, Bogotá da miedo y reina la impunidad. La inseguridad se normalizó, la autoridad desapareció y la ciudadanía quedó sola. Gobernar no es posar para la foto, es garantizar seguridad. Hoy fallaron. Y mucho. 💔😡
Alcalde, de verdad le pido que por lo menos vean las cámaras, identifiquen a los responsables o algooooo. Que horror saber que eso le pasa a mucha gente todos los días y mi caso es uno del montón.
This Ralph Wiggum tool for Claude is unbelievable btw.
I’ve been wanting to make a post on it, but I think it’s so far beyond the average person’s understanding, it’s not even worth it.
If you’re somewhat proficient with tech, you need to set this up and start figuring it out.
Start with this article.
Ruby is not just highly token efficient for the LLMs, but even more so for humans. Being able to quickly read and verify what's been written by AI is a real advantage. And AI just doesn't need the types that some programmers cling to. Great design foresight, Matz!
twitter is cool.
but it’s 100x better when your timeline is full with people who code and build things.
if you’re into tech, AI, startups, design, web dev, web3, or programming, say hi 👋
Hey @screenstudio I bought a lifetime access a year ago and it auto updated to latest. Now it says it "failed to downgrade"..
Is there a way to extend the lifetime license to another year?
This is a really poor way of treating your lifetime customers
Seems like Ruby is pretty well positioned as a language that is token-efficient when used with LLMs.
Source "Which programming languages are most token-efficient?" by Martin Alderson https://t.co/MwBLJnI2Fg