06 Jul 26
Agents can write code faster than we can absorb it. Here’s why it still matters for humans to understand what they build — and some techniques for doing that efficiently: explainer docs, quizzes, micro-worlds, and shared spaces.
03 Jul 26
How I use AI as a design engineer on a daily basis.
02 Jul 26
A fun skill (Trump-like PR summaries), but also a great example of a what a good skill looks like.
A set of skills and skill tool (for skill management) that follows an end-to-end methodology and claims great results.
01 Jul 26
part 1 dropped on february 16th. 53 megabytes of source code from a government endpoint. 269 verification checks. biometric face databases. SAR filings to FinCEN. the full codebase of the platform that verifies your ChatGPT account.
what happened next was… definitely not what i expected.
You get HTML, trackers, cookie banners, popups, and JavaScript. This needs a browser built by thousands of engineers just to show you a paragraph.
Machines get the clean version.
see: https://blog.cloudflare.com/markdown-for-agents/
How Rust prevents data races, and how languages like it could influence future code generation.
29 Jun 26
LLMs are built to automate a complex web of reification. They are designed to tell us what we want to hear. As we write, “Trained on an enormous corpus of human writing, speech, and code, and tuned to refine responses around context and memory as user interactions unroll, a model of this kind is designed to provide the sense that one’s expectation is being exceeded.”
Artificial intelligence is a bizarre technology that participates in its own mythmaking.
see: https://www.theideasletter.org/essay/reify-this/
Clever Hans was a horse that could do maths, or was it using some other trick? Is AI music classification working like a ‘Clever Hans?
see: https://arxiv.org/abs/2601.16675
For however futuristic the new genies seem, there is never actually progress in genies. Magic is not a measurement of their capability, but a description of our irresponsibility. Effortless wish-fulfillment is a perpetual hypothetical, no matter how perilously it is ever approximated.
I want you to explore. I want you to want to explore. If you walk into the darkness with a lamp, you will come upon all sorts of things you did not already know were there. One of them might be the thing you would have told the genie to fetch, but the more you explore the darkness, the better you will understand what else you might want from it, or from yourself. Everything you do changes you: exploring cultivates your curiosity and discernment and perspective and humility; settling for wish-fulfillment impoverishes your experience and then even your wishes.
28 Jun 26
As tech companies race to build hyperscale data centers, communities are coming together to push back. Saul Levin joins Paris Marx to discuss how rising opposition to data center construction is uniting people across party lines and prompting broader conversations around what infrastructure people want instead.
27 Jun 26
Keep your Mac awake only while AI coding agents are working - kageroumado/adrafinil
25 Jun 26
A mix of Notion/Obsidian with integrated AI and CRDT-backed editor.
I don’t know what will happen to us. I don’t trust the people in charge of the future, but humanity isn’t going to change any time soon. I refuse to be incurious about magic just because we can’t be trusted with it.