Published • loading... • Updated
Violence and Sex: Researchers Have Managed to Circumvent All ChatGPT's Moral Rules with a Single Prompt
Summary by Science-Et-vie.com
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.1 Articles
1 Articles
In June 2026, a team from the University of Lancaster managed to get ChatGPT to produce violent images of a sexual nature in a matter of seconds. The specialists simply modified a quick viral designed to obtain humorous results. But the chatbot spontaneously generated graphic content that no one had asked for. This red teaming operation was intended to test the reliability of moderation barriers integrated into the most common generational AI mo…
Coverage Details
Total News Sources1
Leaning Left0Leaning Right0Center0Last UpdatedBias DistributionNo sources with tracked biases.
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
