7 Nov 2025
Why AI can't be debugged like traditional software
Boyd Kane explains why treating AI like debuggable code misses the fundamental difference in how these systems work.
Digesting
A collection of interesting articles, tools, and ideas I've stumbled upon shared here as bookmarks and notes.
4 Nov 2025
Plenty to learn from Fedora's approach to AI code
The first community-driven policy I've seen that treats AI as a tool requiring human accountability, not a shortcut.
13 Oct 2025
It's true, short disruptions costs lots of time
Meeting creep, quick questions and context switching crush flow.
13 Oct 2025
Output: An HTML-native tag once again saves JS befuddling
Use the native HTML output element to announce dynamic results — semantic, accessible, and simple.
3 Oct 2025
Context engineering beats prompt tricks for AI agents
Anthropic argues that “context engineering” — not prompt tricks — is how agents stay accurate at long horizons.
29 Sep 2025
Developers are becoming context technical writers for AI
Fabrizio Ferri Benedetti highlights docs-driven development and the rise of technical writers as “context curators” so AI can truly RTFM.
27 Sep 2025
Embracing px and rem for CSS
Miriam Suzanne from OddBird explains how combining CSS units can lead to more robust and user-friendly typography.
19 Sep 2025
Thoughtful AI integration beats bolted-on Clippy
Lullabot's thoughts on 'How to build your AI integration strategy right'.