Thoughts

A breakdown of the strengths and weaknesses of Opus 4.6, Codex 5.3, Sonnet 4.6, and Composer 1.5 for different development tasks.

A recent study confirms what I've suspected: giving your AI coding agent too many instructions in repository-level context files actually reduces task success.

Why Claude Sonnet feels completely different in Cursor, Claude Code, and Antigravity. The toolchain is the product.

Anthropic and OpenAI released their flagship models within minutes of each other. Here's what matters for the engineers actually using them.

Anthropic's Super Bowl ad mocks ChatGPT for adding ads. But the real question is whether ads can actually fix AI's economics. A look at the numbers.

Anthropic's recent study found AI users scored slightly lower on a coding quiz. Here's what the research actually shows, where the methodology falls short, and how to use AI without sacrificing learning.

OpenClaw is an open-source autonomous agent framework that crossed a psychological and technical line. It does not just recommend actions, it takes them.

Why the most powerful feature of your AI coding agent isn't writing code: it's reading it. A guide for senior engineers on using 'Ask' mode to navigate complexity.

Why giving your AI coding agent the entire codebase is actually hurting its performance, and why you should treat it like an intern.

Unlock the hidden superpower of your AI coding agent: it has read every single page of documentation for every tool you use. Here is how to manage that.

Why we need to change how we communicate with AI to unlock its full potential.

How I use a mistakes.md file to help AI agents learn from their errors and avoid repeating them.

A curated list of free AI tools that will transform how you communicate, edit photos, and use your computer - all without spending a dime.

A comprehensive list of the best AI tools across 19 categories including research, design, video, coding, and more - everything you need to supercharge your workflow.

With the full release of the Claude 4.5 model family, the game has changed for Claude Code users. Here is how to balance Opus, Sonnet, and Haiku to maximize your 5-hour quota for peak productivity.

Figuring out how to use AI is a task in itself. Here is why you should ask the technology itself to teach you.

The Model Context Protocol (MCP) is the latest trend in AI engineering, but overusing it is a fast track to context pollution and agent inefficiency.

How Anthropic's Claude Code on web has revolutionized my development workflow, letting me update websites and fix bugs from my phone across any GitHub repo. A game-changer for mobile-first development.

A practical guide to using AI planning modes effectively. Stop treating your agent like a magic wand and start treating it like a junior engineer.

A deep dive into why passwords aren't enough and how the holy trinity of authentication protects your digital identity.

A free AI-powered procurement platform for organizations: smart approvals, instant alternatives, and zero licensing fees. Built for teams that want efficient purchasing without the overhead.

A quick reflection on how Anthropic's terminal agent has changed my day-to-day life as an engineer.

Cursor is ending its truly unlimited 'Auto' model usage on September 15, 2025. Here is how to lock in 365 days of infinite tokens before the window closes.

Anthropic's Claude Code CLI is shifting the development paradigm from manual editing to high-level orchestration. Here is why it is the most impressive tool in my stack.

Learn how to integrate QR Fusion into your design workflow to create beautiful, functional QR codes that match your brand aesthetic

The technical story behind QR Fusion, an app that blends artwork with QR codes while maintaining 100% scannability through advanced image processing

OpenAI's latest entry into the agentic coding space, the Codex Agent, offers a different approach to automation. Here is why it belongs in your toolkit and how to handle its current limitations.

A data-driven tool to compare towns across the Netherlands (and beyond) with where you live in the United States, down to town-level granularity, powered by AI and smart caching.

The story behind building a secure, offline speed-reading app that started as an internal tool and became a public Mac App Store application

A developer-focused app for storing and sharing links to anything, especially deeplinks, in shareable notebooks so teams can test features together.

Cursor is the biggest leap in developer productivity since the invention of the IDE. Here is how to get started and why it changes everything for senior engineers.

A comprehensive guide to creating smooth and engaging animations in SwiftUI

The story behind my first iOS app: a simple tuning pitch generator that's still helping musicians today

Why the search for the 'best' model is a distraction, and how to focus on the tools that actually solve your problems today.

Why building internationalization into your app from the start saves time, money, and prevents embarrassing translation fails

Exploring the fascinating complexity of global time zones, from fractional offsets to daylight saving chaos, and how to handle them in software

An exploration of camera obscura physics, aperture theory, f-stops vs t-stops, and diffraction, with my office as the experimental chamber

A deep dive into the physics and mathematics of extension tubes, exploring how simple spacers can unlock macro photography capabilities in any lens