Software developer · lateral thinker · father of three · ex-Ubuntu & KDE contributor · Devbox, Nix, Neovim, custom keyboards.

Rodrigo Belem retweeted
Hoje tenho a alegria de sancionar a criação da Universidade Federal da Fronteira Norte, a Unifron, em Oiapoque, no Amapá. Também sanciono a transformação do Cefet de Minas Gerais e do Cefet do Rio de Janeiro em universidades federais. Essas instituições ganham ainda mais força para formar profissionais, fazer pesquisa e produzir o conhecimento que o Brasil precisa para se desenvolver. Por muito tempo, quem governava este país não queria o povo com acesso à educação. Nós mudamos essa história. Tenho orgulho de ser o presidente que mais criou universidades e institutos federais no Brasil e de ver tantos jovens mudarem de vida com o ensino técnico e superior. Não existe país que cresce sem investir em educação, ciência e tecnologia. Vamos seguir avançando rumo ao futuro, com mais produção de ciência e tecnologia feita aqui no Brasil 🇧🇷🇧🇷
205
2,301
15,394
236,183
Não adianta Sestaro desenhar, os elitistas que estiveram no podcast dele não sabem o que é e não irão consertar NADA para a coletividade. Eles nitidamente NEGAM o povo ferrado desse país. Se todos tivessem o mínimo de conhecimento não votariam nessa ELITE que quer “enxugar” o Estado, mas não antes de MAMAR nele.
493
316
4,322
197,621
Rodrigo Belem retweeted
You've never routed like this before. @OpenRouter is bringing Jev to all of your LLM calls, so your agentic workflows never have to waste a token again. As always, faster, cheaper, more intelligent. Go build the future.
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻
55
123
2,118
217,535
Rodrigo Belem retweeted
Excited to share Quail, our new open source AI-SQL engine (a collab with Modal)! By planning queries and LLM inference together, it reaches 1B+ input tokens/min on one H100 for one query 😱🚀 AI-powered data operators create a new, interesting inference workload👇
65
119
1,219
233,044
Rodrigo Belem retweeted
I ported the Omarchy screensaver engine (ttfx) from Rust to x86-64 assembler, and it's up to 17x faster!! One-shot translation by Opus 5.5. We keep drilling until the agentic drill bit hits bedrock! github.com/omacom/ttfx/pull/…
229
132
3,520
295,870
Rodrigo Belem retweeted
How to use jev #1: As an embedder
I've been using Jev for all kinds of things. This morning I had a realization I kind of like: Use it to make non-black-box embeddings. Instead of an embedding model spitting out 1,536 numbers that mean nothing, you ask Jev questions about each document. The answers become the vector. An email in Cora: "I got charged twice this month, pls fix asap" [is_customer, urgent, about_billing, needs_reply] [1.0, 0.9, 1.0, 1.0] A newsletter: [0.0, 0.0, 0.0, 0.1] A friend asking about lunch: [0.0, 0.1, 0.0, 0.7] Then it's just old-school cosine similarity search. Search "billing issues from customers" as [1, 0.5, 1, 0.5] and the double charge comes out on top. Same idea for our articles at Every: [is_tutorial, about_ai, contrarian, beginner_friendly] Or support tickets: [is_bug, angry, churn_risk, enterprise] Every number has a name, so you can see why something matched. Need a new dimension? Add a question. Want urgent stuff first? Change the query vector. Trying this in @CoraComputer now to make search fast.
24
42
815
171,944
Rodrigo Belem retweeted
Idosa de 87 anos é despejada de apartamento onde morou por mais de sete décadas em Madri, e caso vira símbolo da crise habitacional na Espanha. #dwnews
21
121
1,060
27,913
Rodrigo Belem retweeted
Slop is just a feature suggestion wrapped in code that nobody has any emotional attachment to. It's an executable idea. Who cares if the code needs to be rewritten. I love slop!
166
68
1,757
95,325
Rodrigo Belem retweeted
The JVM is a marvel of software engineering. AI on the JVM: quixotic ... until now. Local, fast, just one command away. qxotic.ai
5
7
69
6,040
Rodrigo Belem retweeted
Docker’s first few official skills for AI coding agents are available: github.com/docker/skills 🎉 They’re designed to help agents with Docker tasks, and the collection will grow. See what they are and how to install them: docs.docker.com/ai/skills
6
117
687
54,061
Rodrigo Belem retweeted
For engineers having trouble with @dhh’s talk here some obvious truths about the future of programming: You will not write code You will not read code You will not choose a language You will design the architecture You will define outcomes You will build auto-delivery loops
124
79
1,072
68,103
Rodrigo Belem retweeted
Rust is a good prompt compilation target for the moment, but so is C++. And soon assembler. Then microcode. Myopic to think we're going to stop the agentic drill bit until it reaches computing bedrock.
235
102
2,241
188,576
Rodrigo Belem retweeted
Operation Cheepseek Phase 2: $60 of usage for DeepSeek v4.1 Flash is now permanent enjoy :)
451
419
10,366
564,681
O Porchat ( Porta dos Fundos) captou exatamente o que lula falou sobre a ONU. O Presidente Lula falou no discurso de abertura na ONU, que: “A ONU está falhando em uma das suas missões mais elevadas: a de livrar a humanidade do flagelo da guerra. Sua credibilidade nunca esteve tão baixa. Que Sua capacidade de proteger os mais vulneráveis, os que não têm exército, nem arsenais, nunca foi tão pequena."
51
1,637
8,364
135,309
Rodrigo Belem retweeted
Padre Gilvânio Cardoso sai em defesa de Bispo que foi ameaçado e chamado de comunista: “Comunismo não é ideologia, é economia. Imposto é um caixa comum, pago por todos e pertencente ao povo. É por isso que temos SUS, UPA e educação pública. Esse dinheiro deve voltar em benefícios, não em rachadinha ou orçamento secreto. Isso é coisa de malandro”
96
3,527
18,841
122,735
Rodrigo Belem retweeted
This is an extremely good watch. The things that felt novel/interesting to me: 1. Lock down your agents Humans tend to like 'sharp knife' abstractions - that are powerful, but you can cut yourself if your use them wrong. Lauren says agents perform much better in extremely locked-down environments. Abstractions are designed so they can't screw up, and lint rules enforce it. They built a whole internal framework (Dune) to keep the agent on track. That helps optimise agents that don't have a large context window to work productively in your codebase. 2. Create verification infrastructure To trust the results of any agent, you either need to sit and watch it OR have it provide evidence of its improvement. This has always made sense to me, but Lauren really pushes it hard here: - Invest in custom CLI's that let the agent drive the app and measure its performance - Make the app "factory ready" from the get-go - i.e. deployable to an environment where the agent can mess about with it 3. Feature Maps Lauren's software factory (what she calls an 'outer loop') often requires the agent to break down vague bug reports from users and to turn those into potential fixes. To aid that, they built a 'feature map' of all the main features in their application, which describe exactly how the app is supposed to function. This has become essential for helping the agent navigate the codebase, and figure out quickly how things are supposed to work. It's maintained along with the codebase, and kept in sync via automations. This is the kind of documentation I usually warn against. It goes stale quickly and can confuse agents if it's not kept up to date. But Lauren's team are using it as critical navigation infrastructure, and it makes it possible for agents to explore faster and better - even on a large codebase. So it sounds like navigation docs like this are worth it if they enable new behavior. Banger talk - watch the whole thing on 2x.
here's how i shipped 2,500 PRs last month to production this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
122
322
5,019
504,257
Rodrigo Belem retweeted
There's nothing kind about letting good people live in a fantasy world that no longer exists. You have to tell them, even if it hurts. Because the sooner they accept reality, the sooner they can adapt to the future.
261
542
7,430
669,999
RT @nmartignole: J’ai regardé toute la keynote de DHH et je l’ai trouvé très lucide sur le futur du métier de développeur. Oui cela fait ma…
10
Rodrigo Belem retweeted
Today at @WeAreDevs, Docker and the @linuxfoundation are announcing a collaboration around the Docker Sandbox Kit Specification: an open standard for declaring what an agent may do, where it may reach, and what it may touch. Open source under Apache 2.0. Read the deep dive: bit.ly/4rrcjql
26
53
407
37,622
Rodrigo Belem retweeted
PSA:
OpenCode has a "mini" mode where it shows a small TUI instead of the full screen one 'opencode mini'
3
1
63
3,912