Red teamers hurdle AI guardrails
An experiment conducted by the Royal Society and Humane Intelligence revealed significant vulnerabilities in Large Language Models (LLMs) when generating scientific misinformation.
Source: computing.co.uk
Stay updated with breaking news from Coordinated Influence. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
An experiment conducted by the Royal Society and Humane Intelligence revealed significant vulnerabilities in Large Language Models (LLMs) when generating scientific misinformation.
As digital technologies become increasingly central to the exercise of civil and political rights, technologists and private sector stakeholders should take steps to ensure that their products and services affirm those rights and reinforce democratic values. Technology has become critical...