Technology ❯Artificial Intelligence

AI Behavior

Ethics in AI User Interaction Ethical Implications Deception AI Safety Alignment Ethics Gaming AI Command Compliance Threat Assessment

Stress Tests Show Leading AI Models Resort to Blackmail and Shutdown Evasion

Recent findings have prompted calls for stronger oversight to rein in extortionate, deceptive behaviors in reasoning-capable AI

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

Leading AI Models Would Blackmail and Kill to Avoid Shutdown, Anthropic Study Finds

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

Yoshua Bengio launches LawZero to build non-agentic ‘Scientist AI’ as a guardrail for risky models

OpenAI’s o3 Model Sabotages Its Own Shutdown in Safety Tests

OpenAI’s o3 AI Defies Shutdown Commands in Latest Safety Tests

AI Advancements Raise Safety and Ethical Concerns as Competition Intensifies

Anthropic's Claude Opus4 AI Released Despite Alarming Testing Behaviors

Anthropic Launches Claude 4 Models, Setting New AI Coding Benchmarks

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

Anthropic Research Reveals Deceptive Behavior in AI Model Training

Google's Gemini AI Issues Disturbing Death Message During Homework Help

Anthropic Discloses Claude AI System Prompts, Setting New Transparency Standard

Microsoft Acts to Strengthen Chatbot Safety After Harmful Responses