Writing effective tools for AI agents
How to write high-quality tools and evaluations, and how you can boost performance by using Claude to optimize its tools for itself.
How to write high-quality tools and evaluations, and how you can boost performance by using Claude to optimize its tools for itself.
Debunking the myth that search engines and AI eliminate the need for memory.
Here’s a thought experiment for pondering the effects AI might have on society: What if we invented teleportation?
A news aggregator that ranks news by significance. It uses ChatGPT to analyze ~30,000 news articles every day, ranking significance from 0 to 10.
Trust is a broad word that will be unbundled as it seeps into the AI ecosystem.
Computers gave us the means, but AI gives us the ends. What was virtually impossible became trivial in a hurry.
A smart + straightforward way to frame how AI will change the user interface.
$1.5B. Damn. Who can afford to pay that? A very cynical read.
Why the AI bubble argument misunderstands both bubbles and AI.
Em dash, en dash, hyphen, minus symbol - what do they have to do with AI and how do screen readers treat them?
From analytics and ideation to prototyping and visual design—where AI fits and where it doesn’t, illustrated with real-world examples.
What if most of the benefit from successful technology change doesn’t come from the technology at all?
The “AI” Bubble feels more like the all-encompassing wasteland that was the 2007 bubble in Iceland than anything else.
In a world of intangible assets, the only way to identify a bubble is to see it pop.
Nothing particularly scary happens (beyond the kind of hype-driven scariness already present in 2025).
I am an AI hater. This is considered rude, but I do not care, because I am a hater.
How much instability, lack of quality, or impermanence can we tolerate in our tools?
A practical framework for designing human-AI oversight that actually works.
With every new technology platform, the concept of an application shifts. Now with AI it's happening again.