I think about how to make feedback loops fast and automated.
AI keeps getting better. The main driver of this is better LLMs, and they are getting released at a dizzying pace: something notable comes out every month or more often. Keeping track of who now has the best model, by how much, and the various flavors of it, is hard. Even more confusingly, an LLM can be "good"
A growing collection of ways I use AI agents at work and in daily life, from shopping and interior design to research and meeting preparation.
Autonomous AI loops have worked best for my website’s routine maintenance. Here’s the weekly loop I use, and why recommendation loops fell short.
Tom Blomfield’s five elements of a self-improving loop: sense, decide, act, verify, and learn.
When the right action is unclear, progress comes from a simple loop: act, observe, learn—and change what you do next.
Three stories about getting AI features into production—from Veriff, NFTPort, and Pactum—drawn from my Nordic Testing Days keynote.
Finding talent is not a side task to delegate. Leaders need to learn how to spot great people before the obvious signals appear.
A thinking partner's value is in what it pulls out of you, not the text it writes. Five things stock Claude gets wrong, and the 800 words of instructions that fix them.
As AI improves, what counts as impressive will change—but there will always be something impressive left for humans to do.
Payments were in the web's original vision, but HTTP 402 is still reserved. AI agents may give us another chance to solve identity and accountability online.
