👋 Hi ✨ Welcome to the LLMentalist! 📝

Running Micro LLMs on Laptops: A Developer’s Guide to Local AI

Hey there! If you’ve ever wondered how to bring the power of AI to your laptop without relying on the cloud, you’re in the right place. Micro LLMs are small, efficient language models, and are the perfect tool for this. Let’s dive into how to run them on your machine, why it matters, and what you can build.

Micro LLMs are like the pocket-sized versions of the massive models you’ve heard about, like Llama 3 or Mistral. They’re designed to run on modest hardware, which makes them ideal f. . .

The Illusion of Friendship: Why LLMs Shouldn't Be Your Therapist

Hey there! Today, I want to chat about something that’s been on my mind for a while: using large language models (LLMs) as a form of therapy. It’s a tempting idea. After all, LLMs can chat, listen, and even offer advice. But here’s the thing: I don’t think this is a great idea. Not because LLMs are bad, but because they’re not you. They’re not your friend. They’re tools. And while treating them like a friend can make interactions feel more rewarding, and can even lead to better resul. . .

Migrating from Obsidian to 11ty

For quite some time, I've been wanting to turn my Obsidian notes into blog posts. The idea of transforming those markdown files into a live site felt like a natural next step, and I thought it would be easy, after all, it's all markdown! But as with most things, the journey had its twists. Here’s how I navigated the challenges and why I’m now loving 11ty.

The first hurdle was getting the LLM to understand 11y’s templating. I’d trained it on markdown and basic templating syntax, but it . . .

Creating an AI Assistant with Python: A Simple Guide

Imagine you're building a virtual assistant that can help you with tasks like summarizing text or brainstorming ideas. This guide shows you how to create a simple AI agent that works with a large language model (LLM) like GPT to perform these tasks.

The agent acts like a bridge between you and the AI: it asks the AI to pick a specific action, then runs that action when the AI chooses.

Note: This example uses the OpenAI API for s. . .

A Long Journey: From the jQuery to LLMs

Let’s cut through the hype. A lot of the chatter around LLMs acts like they’re just another layer of abstraction, like a compiler or interpreter, hiding complexity. But here’s the truth: LLMs aren’t abstractions. They’re automations. And they need a developer who gets the problem, the data, and the edge cases even more than a compiler or interpreter does.