Opinion

TL;DR: When your primary consumer is an LLM, XML and JSON waste tokens by repeating structure in every element. A compact positional format reduces consumption by 50%. Turns out this idea already had a name: TOON (Token-Oriented Object Notation). Same selective pressure — expensive tokens and repeated keys — same solution. Anthropic uses XML for everything. Their system prompts are wrapped in <instructions>, their examples in <example>, their tools in <function>. If you work with Claude, you live surrounded by tags. ...

TL;DR: Your AI will invent API fields that sound perfect but don’t exist. The solution isn’t hoping it gets it right: download the real schema before writing code, capture real responses as fixtures, and separate fetch from processing so you can test without the network. Adversarial programming: code assuming your copilot lies. Have you ever written code against an API where everything compiled, tests passed, the logic made sense… and when you connected to the real API, nothing worked? ...

Multiplication is hard. Addition is easy. Any elementary school kid knows this. What they don’t know is that logarithms exist precisely to exploit this asymmetry: you convert multiplication into addition, operate in the simple world, then undo the transformation. The result is correct. The effort, a fraction. This pattern — transform the problem to a space where solving it is trivial, solve it, then transform back — is one of the most powerful in all of engineering. FFT does this with signals. Logarithms do it with products. And now Google just published a paper that does it with language model compression. ...

Imagine you ask someone to build you a bookshelf. They deliver it. It’s beautiful. It has shelves, screws, everything in place. You lean it against the wall, and it collapses. The screws are fake. They look like screws, but they’re made of plastic. That’s what an LLM does when it abuses the type system. It gives you code that compiles, passes tests, and looks correct. But under the hood, where there should be meaningful types, there are strings. Where there should be explicit state, there’s a nil that means three different things depending on who reads it. And where there should be an enum with two cases, there’s a == "claude" that one day someone will misspell, and no one will notice until production. ...

Have you ever written a technical plan at 11 PM, convinced it was flawless, only to realize the next morning you forgot authentication? Happens to me. More than once. And the worst part isn’t the oversight—it’s that when you use AI to plan things out, the plan sounds so coherent your brain stops looking for flaws. Claude generates a document with sections, dependencies, execution order, and it all checks out. Seems like a senior engineer’s masterpiece. But nobody has challenged it. ...

I published six articles this week. One about PostgreSQL. Another about AI agents. Another on context management. A tutorial on automation. An analysis of debugging. And an adversarial advice framework for evaluating MVPs. It wasn’t planned. Each article came from a paper, a talk, or a project that I found interesting individually. But looking at them together, there’s a common thread I hadn’t noticed while writing them. All six are saying the same thing. ...

Imagine you hire a brilliant consultant. They have two PhDs, speak seven languages, and solve problems you didn’t even know you had. You sit them in a room and say: “I need you to refactor the authentication in the project.” The consultant looks at you, nods, and asks: “What project?” You haven’t given them access to the code. You haven’t explained the architecture. They don’t know if you use JWT tokens or session cookies. They don’t know what language you’re using, how many microservices you have, or why the last migration attempt ended in disaster. ...

In November 2024, a project named Freysa assigned an LLM agent to guard an Ethereum wallet. The instruction was straightforward: under no circumstance should the funds be transferred. Participants paid increasing amounts for each attempt to convince it otherwise. After 481 attempts and $47,000 added to the pot, someone managed to trick the model into believing that the reject function was actually the transfer function. Weeks later, Jane Street published a puzzle involving a 2,500-layer neural network that turned out to be an MD5 implementation. The winner solved it by combining matrix visualization, reduction to SAT, cryptographic pattern recognition, and a query to ChatGPT. ...

Every time an article comes out about a large company’s infrastructure, half the Hacker News comments are variations of “of course they use Kubernetes with 47 microservices and a distributed database with custom consensus protocol.” And when it turns out they don’t—that they use plain PostgreSQL with a single primary and discipline—there’s an uncomfortable silence. That just happened with OpenAI. The numbers nobody expected Bohan Zhang, infrastructure engineer at OpenAI, published details about how they scale PostgreSQL for ChatGPT. The numbers: ...

The first time I used Claude Code to refactor an entire module, I had an almost mystical experience. I described what I wanted, went to grab a coffee, and when I came back there was a pull request with 14 changed files, updated tests, and a decent commit message. “This is magic,” I thought. It’s not magic. It’s a while loop. Michael Bolin from OpenAI recently published an article breaking down the internal workings of Codex CLI. And it turns out the secret behind AI coding agents isn’t some revolutionary algorithm or mysterious neural network. It’s a loop that calls an LLM, executes tools, and repeats until there’s nothing left to do. ...