Friday, April 26, 2024
Home > guardrails

Researchers at ETH Zurich created a jailbreak attack that bypasses AI guardrails

A pair of researchers from ETH Zurich, in Switzerland, have developed a method by which, theoretically, any artificial intelligence (AI) model that relies on human feedback, including the most popular large language models (LLMs), could potentially be jailbroken.Jailbreaking is a colloquial term for bypassing a device or system’s intended security

Read More

Microsoft urges lawmakers, companies to ‘step up’ with AI guardrails

Brad Smith, the president of Big Tech firm Microsoft, has called on governments to “move faster” and corporations “step up” amid a massive acceleration in artificial intelligence development.Speaking at a May 25 panel in front of United States lawmakers in Washington D.C., Smith made the call as he proposed regulations

Read More