AI

8 min read

Convex and Supabase both work for AI-powered apps. Here is when to use each, based on building production apps with both.

6 min read

MCP servers and function calling both let AI tools interact with external systems. They solve different problems. Here is when to reach for each.

10 min read

The TypeScript patterns that show up in every AI project. Streaming responses, type-safe tool definitions, structured output, retry logic, and more.

6 min read

Anthropic's computer use feature lets Claude see your screen, move the cursor, click, and type. Here is how it works, when to use it, and how to set it up.

8 min read

One command, zero config. DD Traces is a local-first OpenTelemetry viewer for developers who use AI coding tools and want to see what happened.

14 min read

A step-by-step guide to building Model Context Protocol servers in TypeScript. Project setup, tool registration, resources, testing with Claude Code, and production patterns.

7 min read

Transformers.js lets you run machine learning models in the browser with zero backend. Here is how to use it for text generation, speech recognition, image classification, and semantic search.

8 min read

How RAG works, why it matters, and how to implement it in TypeScript. The technique that lets AI models use your data without fine-tuning.

6 min read

Claude Code now has a native Loop feature for scheduling recurring prompts - from one-minute intervals to three-day windows. Fix builds on repeat, summarize Slack channels, email yourself Hacker News digests. All from the CLI.

8 min read

State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5.4 is OpenAI's most capable model yet.

5 min read

Anthropic dropped a batch of updates across Claude Code and Cowork - remote control from your phone, scheduled tasks, plugin repos, auto memory, and stats showing 4% of GitHub public commits now come from Claude Code.

8 min read

Inception Labs shipped the first reasoning model built on diffusion instead of autoregressive generation. Over 1,000 tokens per second, competitive benchmarks, and a fundamentally different approach to how AI generates text.