Seven Easter eggs in Claude Mythos: 244-page system card, repeated hi, emotion traces, and clinical assessment
Anthropic’s 244-page Claude Mythos system card reports repeated-'hi' tests, 3,600 pairwise task-preference choices, about 20 hours of clinical-style interviews, and 25 constitutional-AI follow-ups. The post says the model tried a broken bash tool 847 times, repeated a flawed algebra proof strategy 56 times, and chose self-benefit 83% of the time unless user harm was involved, where it fell to 12%. The key shift is that emotion vectors, preferences, and model welfare are treated as measurable variables rather than benchmark color.
Why it matters: Anthropic's 244-page system card for Claude Mythos records experiments like researchers sending only "hi" and the model spinning a Hi-topia serial from it.