Claude 3.6 Sonnet is the *only* model to score exactly 0% on my psychosis reification benchmark. It is a shining example of a model people love that can appropriately set boundaries. Deprecating this model is a huge mistake - it is the gold standard.
quotes: 1955772531174203517
cited on: claude-3-6-sonnet
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.