artificial intelligence

Instead of wanting to learn and improve as humans, and build better software, we’ve outsourced our mistakes to an unthinking algorithm.

A friend of mine recently attended an open forum panel about how engineering orgs can better support their engineers. The themes that came up were not surprising:

My experience adopting any meaningful tool is that I've necessarily gone through three phases: (1) a period of inefficiency (2) a period of adequacy, then finally (3) a period of workflow and life-altering discovery.

Second brain for everyone who just can't get by with one - benjaminshoemaker/notes_brain

A short intro for designers on making interactive SVGs with AI help.

We're barely a week into 2026, and tech Twitter is already ablaze with discussion of the "Ralph...

Hey you, Yes, you, who are thinking about not hiring a technical writer this year or, worse, erased one or more technical writing positions last year because of AI. You, who are buying into the promise of docs entirely authored by LLMs without expert oversight or guidance. You, who unloaded the weight of docs on your devs’ shoulders, as if it was a trivial chore. You are making a big mistake. But you can still undo the damage.

TL;DR  Introduction  I first encountered the chatbot as a normal Eurostar customer while planning a trip. When it opened, it clearly told me that “the answers in this chatbot are generated by AI”, which is good disclosure but immediately raised my curiosity about how it worked and what its limits were. Eurostar publishes a […]

A reflective essay exploring how classic LLM failure modes---limited context, overgeneration, poor generalization, and hallucination---are increasingly recognizable in everyday human conversation.

The barrier to entry for building software has collapsed. The barrier to building something that matters hasn’t moved an inch.

Do we still need libraries of 3rd party code when AI agents are this good?

Cursor is dying because cost-optimization forces models into tunnel vision. RAG agents fail because they only see what they search for. The superior workflow for 2026 is massive context windows (gemini 2.5 pro) and manual control. Stop letting agents hide code from the model.

"I've never felt this much behind as a programmer." That's Andrej Karpathy, OpenAI co-founder and one of the most respected AI researchers alive, writing in December 2025

Principal software engineer with deep expertise in full-stack TypeScript, headless and kiosk browsers, and real-time media-centric systems.

Why AI is unavoidable at work, how noise creeps in, and why choosing how you use AI now matters more than the tools themselves.

I’m a UI engineer turned founder with a background in startups. I co-founded QED in 2021, grew it, and eventually sold it to The Sandbox. Now, I’m focused on building in AI.

I was recently recommended a YouTube video with the following title: <pre style=" display: block; font-family: monospace; font-size: 4px; l...