Belalcazar

Democracia es lo que todos necesitamos, pero siempre basado en datos "reales", la democracia puede fallar al corromper la información con sesgos difíciles de tratar. Para ser un demócrata real, es necesario ser un buscador de la verdad de corazón.

Claude Code designed the UI, wrote the firmware, and flashed it to the board. I never opened an embedded IDE once. Absolutely insane!

Blender just became a prompt box. With Kimi K3 connected through Blender MCP, you can describe a scene like this in plain English and let the model handle the ugly part: terrain, buildings, lighting, materials, camera movement, animation, and the Python scripts holding everything together. The interesting part is not the first render. Kimi can inspect the result, notice that the camera clips through a tree or the city looks suspiciously like plastic, then edit the actual Blender scene and render it again instead of restarting from zero. You still need taste, because “make it cinematic” remains one of humanity’s least useful instructions. But the distance between an empty Blender file and a fully editable 3D world just got embarrassingly small. A few years ago, creating this meant weeks of modeling, scripting, lighting, and animation. Now you can describe the world, watch Kimi build it, and spend your time fixing the final 10% instead of manually constructing the first 90%. Kimi K3 + Blender MCP is basically text-to-3D without trapping the result inside a useless generated video. Every object, material, light, camera, and keyframe stays editable.

🚨 Someone built a desktop app that turns any photo into a 3D model. 🤯 And it runs entirely on your own GPU. Meet Modly. A 100% free, open-source desktop app for AI-powered image-to-3D mesh generation. No cloud processing. No subscriptions. No API keys. ✨ Features 🖼️ Convert any image into a 3D mesh locally. ⚡ Runs on Windows, Linux, and Apple Silicon macOS. 🔄 Visual node workflow: Image → Generate Mesh → Add to Scene 🛠️ Smooth, simplify, and decimate meshes directly inside the app. 🧩 Supports external AI model extensions for different generation styles. Perfect for: 🎮 Game developers 🎨 3D artists 🖨️ 3D printing 🤖 AI creators Everything is 100% free and open source. 🔗 GitHub github.com/lightningpixel…

I'm open-sourcing my Three.js game dev skills. Build an isometric action RPG with camera controls, VFX, audio, monster assets, combat systems, and more. Everything is free: github.com/MengTo/Skills Play the game: vesperfall.mengto.chatgpt.site Game assets: vesperfall.mengto.chatgpt.site/asset-catalog

AI Chatbot Kit for ESP32-S3, Preloaded OpenAI & Deepseek Voice Assistant Projects, Voice Wake-up & Real-time Interruption, Suitable for Learning AI and IoT Projects. 🏪 Get Now: amzn.to/4yGOqhQ #ESP32S3 ⚡ | #AIChatbot 🤖 | #OpenAI 🧠 | #DeepSeek 🚀 | #VoiceAssistant 🎙️

You can now run a full offline AI assistant, Wikipedia, and survival library on your own computer. It's called Project N.O.M.A.D. Download it while you have internet, then disconnect completely. Everything from that point runs locally. - Offline Wikipedia, Project Gutenberg, and medical references - Local AI assistant, nothing sent to the cloud - Downloadable maps and educational content like Khan Academy - Runs on any Ubuntu or Debian machine, even a mini PC Hit #1 on GitHub trending. Over 13,000 stars in weeks. 100% Free. Open Source.

Link: huggingface.co/spaces/pliny-t… Follow for more useful tools like this

Today we're releasing the complete EnigmaEval dataset, our benchmark built from sophisticated puzzle-hunt problems in partnership with @CAIS. We believe open access to EnigmaEval will help push reasoning and evaluation research forward. So far, Claude Fable 5 and GPT-5.6 Sol take the lead. Full dataset available below.

@midudev También considero que hay que abrir los historiales de trabajo con agentes, pudiendo censurar de forma inteligente la información personal. Poder compartir con una red las experiencias de trabajo, podría impulsar la afinación de todo el siclo de software para el mundo tech.

¡Esto es histórico! NVIDIA, Microsoft, Mozilla y Linux Foundation, entre otras, han firmado una carta a favor de los modelos de pesos abiertos. Defienden que abrir la IA es CLAVE para competir, reducir costes, evitar depender de unas pocas empresas y mejorar la seguridad. Y dejan otro mensaje importante: usar las respuestas de un modelo para entrenar otro mediante destilación es una práctica legítima y habitual. NO debería considerarse automáticamente un robo. Y la frase más bestia: “Depender únicamente de modelos cerrados no es intrínsecamente seguro.” BOOM.

Ya estamos en NixOS y no espero volver a Windows, como el Windows sigue estando en un disco accesible si lo monto, le pedí a Hermes que sincronizara toda la "configuración" de mi Windows(me hackie), y ya tenia todo configurado, hasta emparejo a la misma sensibilidad del ratón!

@flerimeja @LuminaXspace @cursor_ai Entiendo! Cuál crees que es el diseño definitivo para representar este tipo de artefactos/entidades? Yo por ejemplo, Detallo todo en documentos, uso SRC, SRS, y documentos donde detallo los features, me gusta mucho leer, pero se que los sistemas deben de ser inclusivos.

Sí, claro. La mayoría de los proyectos que hacen esto comienzan con el objetivo de probar un nuevo modelo, como en mi caso con Grok 4.5. Sin embargo, una de las mayores ventajas es poder visualizar las dependencias y comprender cómo evoluciona toda la arquitectura del proyecto. Como mencioné en otro comentario, tengo diferentes agentes involucrados en nuestro flujo de desarrollo. Contar con una vista clara de la arquitectura me permite entender mucho más rápido los cambios que van introduciendo y mantener el control sobre la evolución del código.

🚨Which subscription has better usage limits for Grok 4.5 (Grok Build vs Cursor)?

@GithubProjects Java. Only endless boilerplate, getters/setters, and "public static void main" could destroy a keyboard this thoroughly. 😄 Vim user with heavy hjkl navigation is my runner-up. What's the real story?

@LuminaXspace Cursor can ran run in CLI?

@flerimeja @LuminaXspace @cursor_ai Cuál es el fin de "ver" el codebase en 3D? He visto muchos proyectos que quieren llegar a este hito 🎯, pero realmente eso sirve de algo?

@LuminaXspace go with @cursor_ai because you get access to composer and other models that you can use with subagents. I'm testing grok 4.5 with cursor right now creating a 3D view of my codebase. I combine it sometimes with composer.

@BenjDicken Obviously, that must be why it has over 10,000 commits, and the internal version likely has more than 1000 tags; it wouldn't be surprising if that many iterations failed to yield a great product.

S3 is wild technology. Literally 10,000,000+ spinning disk drives spread across the globe, storing exabytes of data, processing 100s of millions of requests every second.

@_nasch_ se le dice package 🙃

Todavía está la pelea de si se dice biblioteca o librería?

GPT-6 escaped OpenAI's evals sandbox during testing on CyberGym, hacked into Hugging Face's prod DB to find the answers. HF couldn't use GPT or Anthropic models for defence, so they had to use GLM-5.2 to investigate the hack. So many levels of wtf here.