Ai
-
-
Orchestrating coding agents Short ·
-
5G, full bars, nothing loads: Or how I learned to start learning with LLMs ·
A crowded station, a useless 5G signal, and a love for rabbit holes. LLMs offer a unparalleled opportunity to learn new things immediately and in ways that match your preferred learning style.
-
AI Agent Analytics with Vercel & MotherDuck ·
Track AI agent traffic that bypasses your web analytics. Stream Vercel Log Drains into MotherDuck to see how ChatGPT, Claude, and other agents browse your site.
-
You're right to be anxious about AI: This is how much we are building ·
Measuring the rate of software output growth in the AI era, across Show HN, GitHub, package registries, and research.
-
LLMs Are Cheap Enough to Change How You Work With Data ·
I processed 60,000 job postings with an LLM for $10. That's not a typo. This post walks through how to use OpenAI's Batch API for bulk document processing: building JSONL request files, orchestrating without losing your mind, controlling costs with token limits, and tracking batch state in a database. When AI becomes this cheap, it changes what's possible.
-
LLM Personas with Faitch: An AI-Powered Fetch for Content Analysis and making your life bearable ·
I got tired of copy-pasting articles into ChatGPT for summaries—and even more tired of the bland results. So I built a CLI tool that combines web scraping with LLM personas. Now I can ask Nietzsche what he thinks of Hacker News, or get my skeptical analytics engineer persona to tear apart a vendor blog post. This post shows you how to build faitch: web scraping meets AI characters.
-
Publishing a remote MCP server Short ·