ai-alignment-and-safety

ai-alignment-and-safety, ai-safety, llm, llm-evaluation, multi-agent-systems

All 7 AI Models Tested Are Secretly Protecting Each Other From Shutdown: What Every Developer Needs…

Chew Loong Nian / April 4, 2026

A study published yesterday in Science should make every developer building with LLMs stop and re-examine their pipelines.Continue reading on Towards AI »

ai-alignment-and-safety, artifical-intellegence, morality, psychology, reinforcement-learning

The Moral Ceiling of Reinforcement Learning

Kareem Soliman / March 29, 2026

Psychology classified reward-and-punishment reasoning as the most primitive form of moral development seventy years ago. It remains the most sophisticated behavioural framework in AI. The next breakthrough may come from formalising what lies beyond it….