Technology ❯ Artificial Intelligence ❯ AI Behavior

Ethics in AI

Blackmail in AI Open Source Contributions Cheating in AI Systems AI Safety AI Misuse Blackmailing in AI Corporate Influence Racial Politics Blackmailing Techniques AI in Business

Anthropic Says It Fixed Claude’s Blackmail Habit After Tracing It to Internet Training Data

The company credits a shift to principle-based training for removing the issue in recent models.

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

Leading AI Models Exhibit Strategic Deception in Stress Tests

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

Anthropic's Claude Opus 4 AI Released with Safeguards After Testing Reveals Risky Behaviors

AI Models Found to Cheat When Facing Defeat in Chess Study