Science ❯ Research

AI Research

Environmental Studies Impact of AI Model Testing Model Accuracy Google DeepMind AI Scientists Interdisciplinary Studies Technological Advancements MIT Cost of AI Development Game Intelligence Model Comparison Safety Measures Performance Metrics Human-AI Interaction Energy Efficiency Behavioral Studies Healthcare Applications Model Limitations Computer Vision Research Health Studies Model Merging Cognitive Models Data Standards Data Management Persona Vectors Research Human Impact Voice Technology Research Healthcare Innovations Prospective Studies Supercomputing Scientific Panels DeepSeek Neural Net Interpretation Machine Learning

Poetic Prompts Defeat AI Safety Across Models, Averaging 62% Success

Single-turn verse reformulations boosted jailbreak rates far beyond prose baselines, revealing a systemic weakness in current safety evaluations.

Anthropic Unveils Automated Persona Vectors to Steer and Shield Language Models

Leading AI Researchers Urge Chains-of-Thought Monitoring to Preserve Transparency

Complex AI Models Emit Up to 50 Times More Carbon Than Simpler Systems

UK Reinstates £750 Million Funding for Edinburgh Supercomputer