New blog post: "A sufficiently detailed spec is code" I wrote this because I was tired of people claiming that the future of agentic coding is thoughtful specification work. As I show in the post, the reality devolves into slop pseudocode haskellforall.com/2026/03/a-…

"Let the LLM decide which action to take next" was never (and will never be) the best strategy

🌱 Hice un mini framework ergonómico para crear agentes IA/LLMs en apenas unas cuantas lineas. 1. Podés separar el agente del provider. (OpenAI compatible) 2. Podés definir tool calling usando patrón basado en decoradores. 3. Podés lograr que el agente razone y planee acciones. Con esta librería no solo podés crear agentes en un minuto, también podés hacer que tu agente ejecute código, dotarlo de herramientas, dale la capacidad de pensar, planear o incluso guardar memorias de forma eficiente mientras optimizas el uso de tokens. Lo voy a usar para futuros proyectos. Repositorio ejemplos prácticos en los comentarios.

> Open X > Ralph Loop" all over TL > 7K stars > look inside > while loop over a todo list > there's a meme coin about it? > it got rug pulled? > scroll > muted acc > scroll > muted acc > scroll > SWE jobs automated in 12 months > scroll > "Here are 100 Claude Code subagents" > scroll > LLM hate post > scroll > screenshot with 10 claude codes open > "if you aren't doing this, youre ngmi" 😃

I stopped taking advice from childless people. Fitness. Productivity. Life advice. All of it. And here's why: It's not that they're wrong. It's that they're playing a completely different game. Taking life advice from someone without kids is like getting marriage tips from a guy who's "really good at first dates." Cool, bro. But you've never had to initiate the tough conversation and own your mistake just to keep the peace. We're not in the same sport. We've all seen some 25-year-old fitness influencer with non-negotiable 5am routine. Wake up. Meditate. Journal. Cold plunge. 45-minute lift. Sounds beautiful. You know what woke ME up at 5am last Tuesday? A 3-year-old standing 3 inches from my face whispering, "Daddy, I frowed up." There's no cold plunge for that. Just reality. These people have optimized their lives around ONE variable: themselves. I'm optimizing for: → A marriage that still thriving after 10 years → Kids who actually want to be around me → A career that provides for my family → A body that lets me keep up with all of it That's a completely different goal and it requires a different formula. Real discipline isn't waking up at 5am when your apartment is silent and your only responsibility is a houseplant. It's a 10pm workout after the kids went to bed because your morning blew up showing up for your family when they needed you. That's the game I'm playing. Childless advice isn't just impractical. It's unrelatable. Their goal: optimize for SELF. My goal: optimize for FAMILY. It's like a vegan telling me how to grill a steak. You might technically know the steps. But I don't trust you with the tongs. The best advice I've ever gotten came from parents in the trenches. They don't talk about "optimizing morning routines." They talk about: • 20 push-ups while your kid eats breakfast • Walking with your wife after dinner because it's the only time you'll get together • Meal prepping Sunday because Tuesday night is a warzone THAT'S advice that actually works. So no, I'm not taking health advice from someone whose biggest inconvenience is their supplement stack being shipped late. I want the guy who's been elbow-deep in a diaper blowout and STILL hitting their goals. That's the guy who I'm listening to. Find your people. Take their advice. Ignore the rest.

You need to hire people who are constitutionally incapable of watching something be broken without fixing it

We don't need "simple" state manager. They already are simple, because it's just a reducer. Wtf is this trend from some developers to always search for "simple" solutions, when the world need expertise, robust and strong software ?

or just write a state machine.

AI may take my job one day But it can never take the joy I had

you just need to hire a handful of amazing people you don't need to hire like you're building a team of 50

dun understan’em blockchains dun understan’em llms luv me if stmts simple as

Don't ask where did I went for 3 days

i use LLMs to generate a lot of code i still use my brain and hand write a lot of code i am also getting better at hand writing code that sets an LLM up for success not too sure of anything to draw any conclusions, just focusing on practicality

it molds my problem solving. perhaps y'all are much smarter than me, but i just get so affected by anchor bias

people posting extreme takes on how "you're ngmi if you're not using ai" is the most complex form of procrastination i've ever seen you can tell that they feel deep fear that the world is going to change and they will end up on the losing side so they hope just by repeatedly talking down to the "losing side" that somehow that puts them on the winning side and they'll be spared it's a brutal feedback loop where they just keep scaring themselves more and more in the end it's the same old story - just finding ways to avoid really doing anything at all

When Ruby on Rails was launched over twenty years ago, I was a twenty-some young programmer convinced that anyone who gave my stack a try would accept its universal superiority for solving The Web Problem. So I pursued the path of the crusade, attempting to convert the unenlightened masses by the edge of a pointed argument. And for a long time, I thought that's what had worked. That this was why Ruby on Rails took off, became one of the most popular full-stack web frameworks of all time, inspired countless clones, and created hundreds of billions in enterprise value for companies built on it. But I was wrong. It wasn't the crusade that did it. Since those early days, I've talked to thousands of programmers who adopted Ruby on Rails back then, and do you know what virtually every one of them cite? That original 15-minute blog video. Which didn't contain a single comparison to other named solutions or specifically pointed arguments against alternatives. It just showed what you could do with Ruby on Rails, and the A/B comparison automatically ran inside the mind of every programmer who was exposed to that. That's what did it. Showing something great, and letting those who weren't happy with their current situation become inspired to check it out. Because those are the only people who is able to convert to your cause anyway. I've never seen someone who was head'over'heels in love with, say, functional programming be won over by arguments for objected-oriented programming. You simply can't dunk someone into submission, and it's usually counterproductive if you try. But you can absolutely attract people who aren't happy with their current circumstances to give an alternative a chance, if you simply show them how it works, and allow them to conclude by themselves how it would make their programming life better. What I've also come to realize is that programmers come in many different intellectual shapes and sizes. Some of those shapes will click with functional programming, and that'll be their path to passion. Others will click with vanilla JavaScript, and be relieved to give up the build pipelines. Others still will find their spirit in Go. This is great. Seriously. The fact that working for the web allows for such diverse ecosystem choices is an incredible feature, not a bug. I found my life's work and passion in Ruby. I have friends who've found theirs in Python or Elixir or PHP or Go or even JavaScript. That's wonderful! And that's really all I want for you. I want you to be happy. I want you to find just that right language that opens your mind to the beautiful game of coding in your most compatible mode of conception, as Ruby did for me. This is not the same as just saying "everything has trade-offs, use what works best". That to me is a bit of a cop out. There is no universal set of trade-offs that'll make something objectively "work best". Half the programming conundrum lies in connecting to an enduring source of motivation. I wouldn't be a happy camper if I had to spend my days programming Rust (but I LOVE so many of the tools coming out of that community by people who DO enjoy just that). It also doesn't mean we should give up on technical discussions of advantages or disadvantages, but I think those are generally more effective when performed in the style of "here's what I like, why I like it, so look at my code, my outcomes, and see if it tickles your fancy too". Programming is a beautiful game. I would give up all the fancy cars I have in a heartbeat, if I was made to choose between them and programming. The intellectual stimulation, the occasional high from hitting The Zone, is such a concrete illustration of Coco Chanel's "the best things in life are free, the second best things are very expensive". Programming is one of those "best things" that is virtually free to everyone in the Western world (and increasingly so everywhere else too). So let's play that beautiful game to the best of our ability, in the position that flatters our conceptual capacities the most, and create some wonderful code.

bro is not happy with the state of React