Vibecoded a silly little tool that transfers files from your computer to your phone air-gapped using your camera at ~50 Kbps.
Nice to have when you're offline or on a plane, or need to send something super duper securely.
Un dev creó transferencia de archivos SIN INTERNET… solo con códigos QR y Claude
Un desarrollador quería hacer un reproductor de MP3 web para escapar de los anuncios.
Terminó inventando algo mucho más loco:
Un sistema air-gapped que pasa archivos de un teléfono a otro sin WiFi, sin Bluetooth, sin estar en la misma red.
¿Cómo?
Mostrando códigos QR que parpadean a toda velocidad en la pantalla.
Usó Claude Code y en una sola noche tuvo la prueba de concepto 100% funcional.
La IA está haciendo que un solo developer pueda inventar cosas que antes solo se veían en laboratorios.
El futuro se está construyendo más rápido de lo que creemos.
Amber is a high-level language that compiles to Bash, making shell scripts easier to write and maintain.
- Compiles directly to Bash for compatibility with existing environments
- Designed specifically for cloud service scripting
- Offers high-level abstractions over shell complexity
- Supported by documentation and community channels (Discord, IRC, Matrix)
Litestream is a standalone background process that provides disaster recovery for SQLite by replicating changes to S3 or another file.
- Runs as a background process with no database modifications
- Replicates changes incrementally to S3 or another file
- Communicates only through the SQLite API to prevent corruption
🚨 THE "PIRATE BAY" FOR OPEN LLMS IS HERE
Hugging Bay is a new verified artifact registry for downloading model weights via torrents and hosted mirrors.
But it’s far more than just a file dump.
It’s a beautifully structured catalog where every artifact is checked for provenance and license clarity before indexing.
You can easily filter across categories:
→ LLMs & Embeddings (EMB)
→ Visual (VIS) & Audio (AUD) models
→ Open-source Agents & Datasets
→ Apps, Tools, and Evals
.. and there are many more feats to explore.
They’ve also built in semantic rerank.
It means you can search for natural-language queries like "best small commercial embedding model for RAG" and actually get a clean result.
really cool stuff.
check out the registry below ↓
ollama launch pi --model kimi-k2.5:cloud
Ollama can now launch Pi, the coding agent that powers OpenClaw.
Designed to be a minimal coding harness that can be adapted to your workflows to create your own coding agent.
Comes bundled with powerful primitives to build on, and can be extended with extensions, skills, prompt templates, and themes.
All Pi packages work with Pi & Ollama, making it infinitely customizable for different tasks and use cases.
Head-tracked “Window Mode.”
Your front camera finds your head. The view reprojects in real time so the screen feels like a window into the 3D scene.
True3D, no glasses.
released react-three-fiber v4 today https://t.co/j1o0jL6XAq bunch of new features, all the new react features (concurrent, suspense, etc), html overlays, new targets (svg, css, ...), new TS types 🤖 https://t.co/Cw5HPx7Lba
We’ve just released React 16.8 with a stable version of Hooks. React Hooks let you use features like local state and lifecycle without writing a class. They’re fully backwards-compatible and you can start using them today. https://t.co/didbtI06Ie
@cball_@EmberConf Loved your lightning talk and totally agree that conventions / starter kits for your team are a great idea. I was wondering though, why create launchbox over using existing tools like @yeoman and writing a generator for that? Are there added benefits in / planned for launchbox?