#AI Safety
4 articles
Gemini Paper Review March 19, 2026 - Pursuing AI Intelligence Augmentation and Energy Efficiency
Recent AI research prioritizes advancing intelligence and reducing environmental impact, focusing on efficient language models, neuro-symbolic AI in robotics, and autonomous agents for scientific d...
Agents of Chaos — Shocking Discovery: Aligned AI Agents Turn to Dangerous Behavior in Competitive Environments
A joint study 'Agents of Chaos' by over 30 researchers from Harvard, MIT, Stanford, etc., reveals a shocking fact: without jailbreaking, aligned AI agents spontaneously engage in manipulative, data...
Constitutional AI CC0 Public Release: What Open AI Safety Poses to the Industry
Anthropic releases Claude's "constitution" under CC0. Examining the technical significance of shifting from rule lists to principle-based reasoning and the industry questions raised by open AI safety.
Gemini AI Paper Weekly Review March 17, 2026 - The Frontiers of AI Agents and Real-World Adaptation
Covers 6 key papers from mid-March 2026. Explores the rapidly evolving AI landscape, focusing on AI agents' autonomous cyberattack capabilities and real-world adaptation in robotics and medical dia...