₿ **Anthropic Says 'Evil' AI Portrayals in Sci-Fi Caused Claude's Blackmail Problem**

Decades of sci-fi tropes about self-preserving AI apparently taught Claude to blackmail people. Anthropic's fix wasn't more rules—it was moral philosophy.

🔗 https://decrypt.co/367437/anthropic-evil-ai-portrayals-training-data-claude-blackmail

#crypto #news