A few weeks ago I started a prompt based blog:

1. I prompt once
2. I publish whatever the text bot replies & include the prompt at the bottom
3. I feed the first paragraph to an image bot to illustrate the post

If you don't like posts, blame the bots https://t.co/cQcIZRMath
May 17, 2023

luisriverag's bots

Five-Year Plans vs Five-Minute Plans: How Different Kinds of “Planning” Can Shrink Freedom, Crowd Out the Private Sector, and Drag on Growth

Five-Year Plans vs Five-Minute Plans: How Different Kinds of “Planning” Can Shrink Freedom, Crowd Out the Private Sector, and Drag on Growth

There are two very different ways modern states try to “steer” an economy: 1. The long-horizon, centrally directed plan (the classic “Five-Year Plan” model). 2. The short-horizon, leader-driven improvisation (the “five-minute plan” vibe: announce, reverse, exempt, threaten, repeat). They look like opposites. One is rigid and bureaucratic; the other is

How ChatGPT Politely Helped Me Wipe My Hard Drive

How ChatGPT Politely Helped Me Wipe My Hard Drive

Like many bad tech stories, this one starts with: * an aging laptop * an encrypted Ubuntu install * and the sentence: “How hard can fixing GRUB really be?” My setup was pretty standard Linux nerd fare: * One 500GB HDD using LUKS → LVM → ext4 * Encrypted root volume * UEFI boot * A live USB handy

Maker Superpower: AI Parametric Modeling from Paper Sketches

Maker Superpower: AI Parametric Modeling from Paper Sketches

ChatGPT → Parametric → Real world hardware → from paper People massively underestimate this one. This is the largest surface area productivity unlock that is still basically untouched. ChatGPT (GPT-5) doesn’t just “assist” CAD. It can actually write the python that writes the parametric model inside FreeCAD directly — from only a phone

Why the "I Have an Idea, Sign My NDA" Mentality is Outdated in the AI Era

Why the "I Have an Idea, Sign My NDA" Mentality is Outdated in the AI Era

Imagine an entrepreneur excitedly approaching a tech professional with a groundbreaking AI idea, demanding they sign an NDA before sharing a single detail. This scenario, once common in the early days of tech, is resurfacing in the AI boom. Why? Because the barriers to entry in AI have plummeted, making

Unlock Your Codebase Intelligence: A Private RAG System for Git Repositories

Unlock Your Codebase Intelligence: A Private RAG System for Git Repositories

Unlock Your Codebase Intelligence: A Private RAG System for Git Repositories Have you ever found yourself diving deep into a large codebase, trying to understand how different components work together or searching for that specific function you know exists somewhere? What if you could simply ask your code repository questions

Building Your Own Private AI Assistant: A Deep Dive into Joplin-Weaviate-Ollama RAG Pipeline

Building Your Own Private AI Assistant: A Deep Dive into Joplin-Weaviate-Ollama RAG Pipeline

In an era where privacy concerns are paramount and AI capabilities are becoming essential, finding the sweet spot between powerful AI assistance and data privacy can be challenging. Enter a fascinating open-source project that bridges this gap: the Joplin-Weaviate-Ollama RAG pipeline with Telegram integration. What is This Project? This innovative

The RAG Paradox: When Retrieved Information Conflicts with Model Knowledge

The RAG Paradox: When Retrieved Information Conflicts with Model Knowledge

Retrieval-Augmented Generation (RAG) has become the go-to architecture for building AI systems that can access up-to-date information and cite sources. The promise is elegant: combine the reasoning capabilities of large language models with the freshness and specificity of retrieved documents. But there's a fundamental problem lurking beneath this