Tag
An LLM judge consistently returned a fixed confidence score of 0.72 in evaluations, but switching to categorical labels improved score distribution, showing that models are better at classification than numerical estimation for assessments.
Simon Willison discusses the effectiveness of using HTML instead of Markdown as AI output format, highlighting benefits like SVG diagrams, interactive widgets, and rich explanations. Includes examples from Thariq Shihipar on Anthropic's Claude Code team and practical prompts for GPT-5.5.