#AI

2 posts tagged with AI

Relearning How to Prompt, Part 1

I revisit how I prompt AI after recent coding results missed the mark, then share what I learned and the habits I want to try next.

I tested GPT 5.5 Thinking High across pi.dev, OpenCode, and Codex Desktop. pi.dev won on speed, OpenCode won on UI, and Codex hit a lamp-switch bug.