Posts matching all selected tags.
Categories
Tags
Showing page 1 of 2 (11 total posts)

Opus 5 novel reasoning rests on one number, 30.2% on ARC-AGI-3, and it scores action efficiency, not problems solved. Here are the four config lines to change.

Six critics grade the draft, then patch the SKILL.md that wrote it. The merge code, verdict ladder, and guardrails behind a self-improving Claude Code skill.