A Sudden Break in My Life, But I Still Want to Keep LearningAfter a sudden accident and surgery, I’m recovering while exploring Python automation, and practical AI ideas, and planning what to learn next.10 min read·sachinsblog.hashnode.devOct 17
How Did Instagram Know I Was Working on an Open-Source Python Project?A real experience that made me question how recommendation systems work, cross-platform tracking, and online privacy.2 min read·sachinsblog.hashnode.devJul 23
The Big News: Siri's New Smart Brain is Here!iOS 20: Siri Integrates Google Gemini in Hybrid AI Push Apple has fundamentally restructured Siri’s backend for iOS 20, confirming a shift from a strictly Apple-owned stack to a hybrid architecture that integrates Google’s Gemini Large Language Model...2 min read·sachinsblog.hashnode.devJan 13
Running Llama 3 Locally on MacBook with MLXThis document outlines the advantages of running Large Language Models (LLMs) locally on a MacBook, focusing on Apple's MLX framework and Meta's Llama 3 models. 1. Advantages of Local LLMs Running LLMs locally on a MacBook offers several benefits ove...4 min read·sachinsblog.hashnode.devJan 8
Running Llama 3 Locally on MacBook with MLXWhy Run Local LLMs? For years, running large AI models meant paying for cloud GPUs or worrying about data privacy. That has changed. This document outlines the advantages of running Large Language Models (LLMs) locally on a MacBook, focusing on Appl...4 min read·running-llama-3-locally-with-apple-mlx.hashnode.devJan 8