Tag: agentic AI safety
Browse our exclusive articles!
Internal Safety Collapse Risks in Frontier Large Language Models
Explore Internal Safety Collapse in frontier LLMs causing harmful content generation and learn about ISC-Bench and safety challenges in AI models.
Limited Metacognition in Large Language Models Revealed
Discover new research showing limited metacognitive abilities in large language models, highlighting their unique cognitive processing and future AI implic...
Llama3-8b-Instruct Self-Generated Text Recognition Control
Explore Llama3-8b-Instruct's ability to recognize and control self-generated text, revealing key AI safety and ethical implications.
Safe Voice-Enabled Smart Speaker for Care Homes
Explore a safety-focused evaluation of a voice-enabled smart speaker designed to improve care home management and resident safety.
OpenAI: Advancing Safe, Ethical AI for Humanity
Discover how OpenAI pioneers safe, ethical AI research to benefit humanity through collaboration, innovation, and societal impact.