PinnedBibek Poudel·Apr 25How to Run Qwen3.6–27B Locally on Intel Arc Pro B70: What Actually WorksTL;DR: Qwen3.6–27B runs on Intel Arc Pro B70 today. The fastest path to get started is llama.cpp with Vulkan. The better-performing native…A response icon8A response icon8
PinnedBibek Poudel·Feb 26The SKILL.md Pattern: How to Write AI Agent Skills That Actually WorkIf your skill does not trigger, it is almost never the instructions. It is the description.A response icon2A response icon2
PinnedBibek Poudel·Feb 18How OpenClaw Works: Understanding AI Agents Through a Real ArchitectureTL;DR: OpenClaw is an open-source personal AI agent that surpassed 100k+ GitHub stars rapidly in early 2026. By looking at how it is built…A response icon7A response icon7
PinnedBibek Poudel·Mar 31, 2025Stop Fighting With OCR: Convert Any Document to Markdown, HTML, or JSON Using SmolDoclingIf you’ve spent hours testing OCR tools like Tesseract or Textract, only to see them mangle tables, skip headers, or flatten document…A response icon2A response icon2
PinnedBibek Poudel·Dec 1, 2023Create your own chatbot with Llama2, Ollama and GradioOverviewA response icon3A response icon3
Bibek Poudel·Mar 16How to Vibe Code Without Burning Your Context Window: A Cross-Tool Setup Guide for Claude Code…I have a question for you. How many times have you opened an AI coding tool today and explained your project from scratch?
Bibek Poudel·Oct 12, 2025How AI Agents Actually Work: Let’s Learn by Building OneTL;DR: Learn how LLMs combine reasoning and tool use by building a working AI News Agent using Llama 3.1 and Ollama.
Bibek Poudel·Apr 12, 2025How to Build Your First AI Agent Using Google’s Agent Development KitBuilding applications powered by Large Language Models (LLMs) often involves more than just generating text. To create truly useful AI…A response icon1A response icon1
Bibek Poudel·Mar 27, 2025What is MCP and How to Create Your Own MCP Server: A Simple GuideIn this guide, I’ll try to explain what the Model Context Protocol (MCP) is in simple language and walk you through creating your own MCP…
Bibek Poudel·Mar 25, 2025Running Gemma3 Locally with llama.cppIn this guide, I will walk you through running the Gemma3 model locally using llama.cpp installed via Homebrew. You’ll learn how to run…
