All topics
Topic
agentic-coding
2 articles on this topic.
-
My Agent Kept 'Improving' My Prompts. The Eval Harness Said Otherwise.
Agentic development without evals is approving diffs on vibes. How a small Swift eval harness caught real prompt regressions, killed a temperature theory, and told me when to stop iterating.
-
I Went All In on Claude Code Desktop for a Day. Here's What Happened.
First impressions of the new Claude Code desktop app from someone who lives in the terminal version. What's better, what's missing, and why /rewind not being there is kind of a big deal.