Hands-On Video with the Plastic Logic QUE proReader

By Digital Trends Staff January 7, 2010

plastic-logic-reader — Image used with permission by copyright holder

We get a firsthand look at the QUE proReader’s ultra-thin design and its 11.6-inch touch-screen with iPhone-like functionality. We also find out that QUE owners will have access to the QUE store which offers publications formatted specifically for the QUE.

Topics

Digital Trends Staff

Digital Trends has a simple mission: to help readers easily understand how tech affects the way they live. We are your…

Computing

A dangerous new jailbreak for AI chatbots was just discovered

Microsoft has released more details about a troubling new generative AI jailbreak technique it has discovered, called "Skeleton Key." Using this prompt injection method, malicious users can effectively bypass a chatbot's safety guardrails, the security features that keeps ChatGPT from going full Taye.

Skeleton Key is an example of a prompt injection or prompt engineering attack. It's a multi-turn strategy designed to essentially convince an AI model to ignore its ingrained safety guardrails, "[causing] the system to violate its operators’ policies, make decisions unduly influenced by a user, or execute malicious instructions," Mark Russinovich, CTO of Microsoft Azure, wrote in the announcement.