AI Chatbots Easily Tricked Into Giving Elicit Responses: UK Researchers
Related Articles
-
AI film festival gives glimpse of cinema's future
With fantastical characters including mud people and giant grandmothers, an AI film festival is giving a glimpse of the storytelling made possible by the novel technology.Nearly 3,000 short films were submitted to the festival organized by Runway AI, one of the leading start-ups in the field of AI-powered video generation.The 10 films selected put the filmmakers' vivid imaginations on display, with their stories set in aesthetically stunning universes. There is a perception of AI- driven...
-
Presto Automation pilots bilingual AI for drive-thru orders
SAN CARLOS, Calif. - Presto Automation Inc. (NASDAQ: PRST), a prominent provider of AI and automation technology for the restaurant industry...
-
UK's AI Safety Institute easily jailbreaks major LLMs
In a shocking turn of events, AI systems might not be as safe as their creators make them out to be — who saw that coming, right? In a new report, the UK government's AI Safety Institute (AISI) found that the four undisclosed LLMs tested were "highly vulnerable to basic jailbreaks." Some unjailbroken models even generated "harmful outputs" without researchers attempting to produce them. Most publicly available LLMs have certain safeguards built in to prevent them from generating harmful or...