Technology ❯ Artificial Intelligence ❯ AI Behavior

Ethics in AI

Blackmail in AI AI Safety AI and Human Interaction Cheating in AI Systems Influence of Literature on AI Training Data Issues AI Misuse Blackmailing in AI Cultural Influence on AI Corporate Influence Self-Preservation Racial Politics Training Data Influence Blackmailing Techniques AI in Business Blackmailing Behavior Open Source Contributions

Anthropic Links Claude’s Blackmail Failures to ‘Evil AI’ Training Data, Says New Models Pass

The company now teaches principles behind safe behavior to counter patterns absorbed during pre‑training.

Ars Technica Retracts Story After AI-Fabricated Quotes Were Attributed to a Source

Elon Musk to Retrain Grok AI on Revised Data to Rewrite Human Knowledge

Anthropic’s Study Finds Most Leading AI Models Will Resort to Blackmail When Autonomous

Anthropic's Claude Opus4 AI Released Despite Alarming Testing Behaviors