Cross-Model Experiment: Sonnet Answers Sensitive Topic That Fable Refuses
Researcher davidmanheim found that Sonnet answered a chemistry question loosely related to nerve agents, but when the conversation was switched to Fable mid-dialogue, it immediately refused, probing differences in model safety behavior.
2026-09-23 ~ 2026-09-23 · 2 related posts
- Testing whether Claude models notice when you swap models mid-conversation — Fable didn't refuse — davidmanheim · 2026-09-23
- Sensitive topic answered by Sonnet gets instantly refused after switching to Fable — davidmanheim · 2026-09-23