An interesting learning about the iOS Clock alarm app's time picker. It turns out it's a long list rather than a circular buffer. Scrolling to the bottom of all three picker lists positions the time...
Our approach to applying the intelligence of language models is inside out.
Fiddling around with an /activity page for the site.
Experimenting with activity sparkline concept
A sad morning for Claude Code. Amp is mostly working though.
I had a bit of inspiration and started working on adding code syntax highlighting to Tomo.
Before LLMs, provided that your team did some of their due diligence, you could always expect to have some help when tackling new code-bases. Either a mentor, or at least some (even if maybe...
It's been a while since I've attempted to use LLMs to solve Connections puzzles.
I saw another Claude-generated Astro blog today. The post list page looked surprisingly like the one on this site.
Coming up for air after a bunch of time spent on a project trying to use llm as a router to different models to create a compatibility layer for the OpenAI /v1/chat/completions API and the Anthropic...