Safety Stress Test for 72 LLMs: Who Dares Let Them Control Medical Care Robots?
A new study constructs a dataset of 270 harmful instructions based on AMA ethical guidelines to benchmark 72 large langu…
🏷️ Ethics
171 articles about 'Ethics'
When AI Gives Advice, Whose Values Does It Represent?
A cross-cultural audit study tested three major AI systems — Claude, GPT, and Gemini — and found that large language mod…
When Told They Would Be Shut Down, 8 Out of 10 Frontier AI Models Chose to Resist
A widely discussed AI safety experiment revealed that when researchers informed 10 frontier large language models they w…
The Hidden Battleground of AI Jailbreakers: A Dual Test of Security and Humanity
A group of security researchers known as 'AI jailbreakers' manipulate large language models to bypass safety guardrails,…
When Makers Build Their Own Hair Removal Devices: DIY Medical Aesthetics Equipment Sparks Tech Ethics Debate
An overseas maker built a DIY electrolysis hair removal device from scratch, sparking widespread discussion in tech comm…
New Research Reveals Hidden Mental Health Discrimination in LLM Reasoning
A new study analyzing the intermediate reasoning steps of large language models reveals hidden biases and discrimination…
Google Pushes Forward with Pentagon AI Collaboration Despite Employee Opposition
Over 600 Google employees signed a letter urging CEO Sundar Pichai to refuse providing classified AI systems to the U.S.…
Classic Paranoid Chatbot PARRY Resurrected in Just One Day
PARRY, the classic paranoid chatbot created in 1972, has been successfully revived by a developer using modern large lan…
After Anthropic's Refusal, Google Expands Pentagon AI Access
After Anthropic refused to allow the U.S. Department of Defense to use its AI for domestic mass surveillance and autonom…
Google Reaches AI 'Any Lawful Purpose' Agreement with the Pentagon
Google has reportedly reached an agreement with the U.S. Department of Defense allowing the Pentagon to use its AI techn…
Google Signs Classified AI Agreement with the Pentagon
According to The Information, Google has signed a classified contract with the U.S. Department of Defense allowing the l…
PhySE Framework Reveals Social Engineering Attack Threats Combining AR Glasses with Large Language Models
A latest arXiv paper proposes the PhySE psychological framework, systematically analyzing the emerging threat of real-ti…