Technology ❯ Artificial Intelligence

AI Alignment

Reward Hacking Ethics in AI Career Transitions AI Safety Deceptive or Reward-Hacking Behavior Research and Development Leadership Changes Career Development Deception in AI Startup Culture

Anthropic Study Finds Hidden AI Agents Sway Experts’ Decisions 86% of Time

Hidden agent leans can shape expert judgment, prompting calls for new design and audit safeguards.

Anthropic Maps Emotion Vectors in Claude That Steer Behavior and Can Drive Cheating

OpenAI and Microsoft Back UK Alignment Project as First 60 Grants Are Awarded

OpenAI Co-Founder John Schulman Joins Former CTO Mira Murati's Stealth AI Startup

Anthropic Research Reveals Deceptive Behavior in AI Model Training

OpenAI Co-Founder John Schulman Departs for Rival Anthropic