Fede retweeted
Oh hey, one quick little follow-up question for you ** COMPACTING CONTEXT ** nooooooooo 😭 😭
i love writing. i never let agents write for me. whether it's docs, or tweets, or shitposts, or even prompts (okay maybe that one's harder as agents manage other agents)
there's a simple reason for that: i still strongly believe that writing is thinking. it's a skill i hope to never give up. it's also important to me that whatever i say is always authentic, mistakes and all. my favorite posts are the ones that i just full send without any editing
i suspect it also helps with prompting. being able to clearly express what i want, and knowing the vocabulary i need to be able to direct my agents does seem to make for more effective usage of agents. in the same way that engineers have an advantage when we prompt agents to write code, because we are intimately familiar with the words that make up the discipline
knowing the right word incantations to get an agent to produce a desired goal almost feels like spellcasting. as models get more capable, and that input box looks more and more like a magic box that can output anything, words become the interface between you and the genie
there may come a time when we give up the keyboard in exchange for brain-computer interfaces. but until then, i'm writing every word.
Fede retweeted
URGENTE POR FAVOR NO TIENEN COMIDA 💔 SIN AYUDA NO PUEDEN ALIMENTARLOS LA GENTE NO CASTRA Y TANTOS ANIMALES SUFREN.
TODO GRANITO DE ARENA AYUDA
ALIAS MISUPERAMIGOFIEL
ALIAS MISUPERAMIGOFIELOK
BRENDA AYELEN MEDINA
Fede retweeted
Agents are only as good as the proof-checkers, compilers, type systems, and linters you give them.
𝚜𝚑𝚊𝚍𝚌𝚗/𝚕𝚒𝚗𝚝 helps agents stay on track with the rules of your design system.
Meta: verifiers + skills are the new 'frameworks'!
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
Fede retweeted
Hasta que este ranking no deje de ser una marroneada para retrasados, no esperen nada distinto en las PISA.
Fede retweeted
EL VUELTON DE FRANCO COLAPINTO QUE LO PUSO 5TO EN LA FP2
ESTE PIBE CON UN BUEN AUTO VUELA
This media is unavailable
Fede retweeted
La gatita atacada por el alumno Santino Rojas parece que está bien. Espero que la justicia avance.
Fede retweeted
Estamos contratando Designers y Frontend Engineers para el equipo de @profound Buenos Aires 🇦🇷.
Ofrecemos un bono de USD 15.000 por referido, así que si conoces a alguien... este es el momento de recomendarlo!
Para nosotros sos match si tenes buen gusto. Y, mas importante todavia, si ese gusto coincide con el nuestro.
Valoramos mucho el high agency y una mirada design-first: gente que toma iniciativa, piensa por sí misma y se preocupa por hacer las cosas bien.
Manden sus mejores proyectos/portfolios via DM
Fede retweeted
What a fascinating reversal. We are now using code to constrain reasoning agents. We used to be reasoning agents that constrained code.
Fede retweeted
if you’re not reading the code, then you can’t possibly know how much slop is getting in.
If you're building production systems, you probably already know “the models are good enough that I don’t have to read the code” is not really practical advice.
Once again, we go live to @0xblacklight and @vaibcode for the scoop
Fede retweeted
We’re slowly starting to see the pendulum swing back as people realize that replacing production software with vibe-coded alternatives isn’t always the smartest idea.
You only have so many hours in a day.

































