🧵 1/4 Handy — open-source, offline speech-to-text 🎤 Press a shortcut, speak, and the text appears in any text field. No cloud, no telemetry. #ai #llm #opensource
If you are not familiar with the MLX Fast project, you should check it out. MLX Fast is a competition to make the same #AI model run faster on Apple Silicon by optimizing the inference engine rather than changing the model itself. 🧵👇🏼
New tutorial - How to read an LLM model label on Hugging Face 👇🏼 We usually refer to an open-weight model on Hugging Face by its model family label and parameter count (e.g., Qwen 3.5 - 35B, Gemma 4 31B, etc.), but there's more to it. #ai #mlx #aiops #llm
I started a new sequence of tutorials, this time focusing on running LLMs locally on Mac with MLX LM. MLX LM is Apple’s framework for running LLMs locally on Apple Silicon, based on MLX - an array framework designed for machine learning on Apple Silicon 👇🏼 #ai #llm #mlx
PaperBanana An open-source agentic framework that generates publication-quality academic diagrams and statistical plots from text. 👇🏼 #ai
AI will find a cure for cancer. We need to invest in infrastructure and build more data centers. Meanwhile, what AI is actually doing 👇🏼 Video credit: unknown
Any recommendations for Claude's skill for creating HTML slides? #ai #claude #html
Fable 5 is finally here! Amazing news: we can now upgrade from a model we barely use 20% of to a model we’ll use 10% of, for roughly double the cost. What a magical time to be alive 🤣 #ai
AI developers - how do you manage parallel features development of text elements (skills/prompts/agents) and avoid git merge conflicts? #ai
Having a weekly quote makes sense. Adding a 5-hour limit is a real motivation to transition my Mac Studio to a local LLM server and say goodbye to OpenAI
