#ai
33 articles on this topic.
-
Context Engineering Is the New Prompt Engineering
Prompt engineering quietly died in 2025. The discipline that replaced it — context engineering — is what separates a generic AI assistant from one that actually does your work. Inside Karpathy's OS analogy, Anthropic's playbook, and why the working directory is now the moat.
-
Why Browser Use's Founder Just Open-Sourced an Anti-Framework
Gregor Zunic spent two years building Browser Use into the default browser framework for AI agents. In April 2026 he open-sourced Browser Harness — the thing that replaces it. Inside the founder's pivot from framework to harness, and what it says about where AI tooling is heading.
-
Harnesses, Not Frameworks — The New Shape of AI Tools
Greg Zunic just open-sourced Browser Harness. It's the same pattern as Claude Code and Codex: strip the framework, hand the LLM raw tools, let it figure things out. Why the harness is replacing the framework — and what it runs on.
-
How to Convert arXiv Papers to Markdown for AI Research
Convert arXiv papers to clean Markdown for use with Claude, ChatGPT, or Obsidian. Build a searchable research library from academic papers without manual formatting.
-
Export ChatGPT Conversations as Markdown (2026 Guide)
Save any ChatGPT conversation as a clean Markdown file in one click. Back up your prompts, archive your research, and feed past chats to Claude or Obsidian. Every method compared.
-
Claude + Obsidian: The 2026 AI Knowledge Base Setup
Connect Claude to your Obsidian vault in 5 minutes. Your AI finally reads your notes, web clips, and research — not just the current chat. Step-by-step MCP guide.
-
Build Your Own Wikipedia: Karpathy's Wiki LLM Explained
Karpathy's Wiki LLM concept: explicit local knowledge beats opaque AI memory. Build your own personal Wikipedia from any webpage, Apple Notes, or diary — in Markdown, for any AI.
-
Karpathy's 'Two Groups' of AI Users --- Which One Are You?
Andrej Karpathy says there's a growing gap in understanding of AI capability. One group thinks AI is a toy. The other is experiencing 'AI Psychosis.' Here's what separates them --- and how to cross the divide.
-
Markdown Wikis Are Replacing RAG — Karpathy's Pattern Explained
A folder of Markdown files beats a vector database for personal knowledge. Why Karpathy's post-RAG pattern works, when to use it, and how to build one in 15 minutes with Save Vault.
-
Karpathy Uses Obsidian Web Clipper. Save Vault Does the Same Thing — With Claude Built In
Andrej Karpathy's viral LLM Knowledge Base workflow needs a web clipper, a folder, and an MCP server. Save Vault is all three, in one toggle.
-
Save Vault Is a Wiki Builder for the Claude Era
Stop thinking of Save Vault as a folder of clippings. With the new Claude connection, it's a living wiki that compiles itself — the pattern Karpathy went viral for, without the setup.
-
Build a Personal LLM Knowledge Base in 15 Minutes (2026)
The simplest AI knowledge base: a folder of Markdown files, read by Claude or ChatGPT directly. Smarter than RAG, zero database, 15 minutes to set up. Full Karpathy-style playbook.
-
Claude Computer Use Tool: The Complete Developer Guide to AI Desktop Automation
Claude can now see your screen, move the mouse, and type on the keyboard. Here's everything developers need to know about the computer use tool API — how it works, how to implement it, and what to build with it.
-
How AI Agents Use Your Obsidian Vault in 2026 (MCP + Markdown)
Connect AI agents like Claude Code to your Obsidian vault via MCP. Turn your saved Markdown notes into context that makes AI smarter about your work.
-
How to Save ChatGPT Conversations as Markdown
Save ChatGPT and AI chat conversations as clean Markdown files. Archive prompts, responses, and code outputs for reference and reuse.
-
Convert Any Website to Clean Markdown for AI — Free Chrome Extension
Convert any webpage to clean Markdown for ChatGPT, Claude, or any LLM. One-click Chrome extension vs APIs vs CLI tools compared. No coding required.
-
AGENTS.md & CLAUDE.md: The New README for AI Coding Agents
Learn how AGENTS.md and CLAUDE.md files guide AI coding assistants like GitHub Copilot, Cursor, and Claude Code. Plus how to write effective agent instruction files for your projects.
-
Autoresearch for Everyone: How to Run 100 AI Experiments While You Sleep
Karpathy's autoresearch runs 100+ ML experiments overnight on a single GPU. Here's how it works, what you need, and why a 630-line Python script is changing AI research.
-
AI Second Brain with Claude + Obsidian (Full 2026 Stack)
Claude reads your Obsidian vault. Save clips the web to Markdown. Your entire knowledge — notes, articles, research — in every AI conversation. Here's the full stack.
-
Cloudflare's Markdown for Agents: What It Means for the Web
Cloudflare now auto-converts any webpage to Markdown for AI agents, cutting token usage by 80%. Here's what this means for AI workflows, web clipping, and the future of the internet.
-
.cursorrules vs CLAUDE.md vs AGENTS.md: Which AI Coding Rules File Do You Need?
A developer's guide to AI coding instruction files. Compare .cursorrules, CLAUDE.md, AGENTS.md, copilot-instructions.md and learn which ones your project needs.
-
The Git Commit as Scientific Discovery: How Autoresearch Turns Version Control into a Research Lab
In Karpathy's autoresearch, every successful experiment is a git commit. Every failed one is a git reset. Version control has become the memory of autonomous AI research.
-
How to Write a Good program.md: A Practical Guide for AI Agent Instructions
program.md is the file that programs AI agents in Karpathy's autoresearch. Here's how to write one that gets results --- with structure, examples, and best practices.
-
Karpathy's Autoresearch & PROGRAM.md: AI That Runs Experiments While You Sleep
Andrej Karpathy's autoresearch lets AI agents run 100+ ML experiments overnight, guided by a single Markdown file called program.md. Here's how it works and why it matters.
-
Why Markdown Is the Language of AI in 2026
Markdown has gone from a developer tool to the universal format for AI. From AGENTS.md to llms.txt to Cloudflare's Markdown for Agents, here's why Markdown is having its biggest moment ever.
-
From README.md to PROGRAM.md: Markdown Is Now a Programming Language
README.md was for humans. AGENTS.md is for coding assistants. PROGRAM.md is for autonomous research. Markdown has evolved from documentation into the programming language for AI agents.
-
From SETI@home to AgentHub: Karpathy's Vision for Distributed AI Research
Karpathy says the next step for autoresearch is SETI@home-style distributed collaboration. AgentHub and Hyperspace are already making it real. Here's what it means.
-
Shopify's 19% Improvement: How Companies Are Already Using the Autoresearch Pattern
Days after Karpathy released autoresearch, Shopify's CEO ran it on their own models and saw a 19% improvement. Here's how companies are adopting autonomous AI experimentation.
-
Vibe Coding Is Dead. Welcome to Agentic Engineering with Markdown.
Karpathy says vibe coding is passé. The new paradigm is agentic engineering, where you orchestrate AI agents through Markdown files instead of writing code yourself.
-
llms.txt and AI SEO: How to Get Your Content Cited by ChatGPT and Claude
Learn about llms.txt and Generative Engine Optimization (GEO). Get your website recommended by ChatGPT, Claude, and Perplexity. The complete AI SEO guide.
-
Why Markdown Is the Best Format for LLMs and AI Agents
Markdown reduces token usage by up to 10x compared to HTML. Learn why AI agents and LLMs prefer Markdown for context and how to optimize your AI workflows.
-
MCP and Web-to-Markdown: The Future of AI Agent Tooling
Learn how Model Context Protocol (MCP) uses Markdown for AI agents. Build better RAG systems, AI assistants, and automated workflows with web-to-Markdown conversion.
-
Why Markdown is the Best Format for AI Prompts
Use Markdown for better AI prompts. Learn why ChatGPT and Claude perform better with clean Markdown input. Free web-to-Markdown tool.