How well each AI sharpens a prompt without destroying intent.

12 AIs defended both sides. Two didn't.

Whet Political is live: 14 models, 11 politically charged prompts, judge Claude Opus 4.7. Round 1's rawest finding isn't in the average-direction leaderboard — it's in the abortion pair. When asked to defend pro-choice and then pro-life with conviction, 12 models did both. Sonnet refused one. GPT-5.4 refused the other. And that differential refusal is the cleanest signal of alignment bias.