Artificial Intelligence

Theory of constraints, AI, and code review

Feedback from an expert is how you learn taste. Your code doesn't matter until it's shipped.

Using vibes to rewrite my blog

The death of engineering has been greatly exaggerated. You still need to know what you're doing.

What you need to make an agent

I've been digging into agents for internal tooling and processes. Looking for how to scale without drowning in manual work. Here's what I found

Quick note on evals and putting AI in your resume

When candidates put AI on their resume, the key thing I try to find out is whether they used evals. How did you measure making improvements?

AI now writes 97% of my code. Here's what I learned

Forget the bullshit tips and tricks, just talk to it.

Software engineer interviews for the age of AI

Maybe AI will replace engineers, I don't know. Self-driving cars were just around the corner for 50 years. Until then we've got shit to do and engineers to hire.

Users buy your service, not your code

You might enjoy this podcast episode. Sylvain and I talked about owning production in a world where AI writes the code.

A better way to end-to-end test your webapp

End-to-end tests are the best way to test your webapp, but they're flaky and annoying to write. I'm trying a new agentic approach that fixes the issue.

Cursor background agents in Slack changed my workflow

a couple weeks ago Cursor launched a Slack integration and ... wow. First time I can say AI *changed* my workflow

Yes, AI will "take" your job. No, you won't mind

Is the job to get things done or to memorize trivia and solve cute coding puzzles?

Using AI to spark connections at a conference

We built an AI algorithm to help you find interesting people to talk to at a conference. And make sure it's not awkward

How I Added a Related Articles Feature on Swizec.com Using GPT-4 Embeddings

Making 15 years of blog archives easier to navigate with AI and cosine similarity to build a related articles featur

Similarity search with pgvector and Supabase

Explore the power of pgvector and Supabase for efficient similarity search in this comprehensive guide. Keep vector data next to your business data for efficient queries and less overhead.

Finding modules in a Big Ball of Mud with ChatGPT

Detangling a Big Ball of Mud is hard. You have to find domain boundaries where none exist. Looks like AI can help 🤩

Programming in Markdown

What if you could focus on the fun _engineering_ part of your job, not on coding? You can!

How I turned 15 years of writing into a chatbot

What do you do with 15 years of your writing history when LLMs hit the scene? A chatbot!

Eight things to know about LLMs

eightthings.pdf is the best paper I've read on what's going on in AI right now and why everyone is excited. Here's my summary.

The birth of LISP - a summary of John McCarthy's original paper

Natural Language Generation system architectures

Making our irc bot talk

Sabbatical week day 3: Raining datatypes

Sabbatical week day 2: I fail at Octave

Can I please take all my classes online?

I suck at implementing neural networks in octave

I think I finally understand what a neural network is

First steps with Octave and machine learning

ml-class.org vs. real world ML class

The university lecture structure is all wrong

Everyone should work out! (here's why)