ZeroHour
404 Mediapublished ()ingested Emanuel Maiberg

APpaREnTLy THiS iS hoW yoU JaIlBreAk AI

mediumAI safety & securityimportance 30
Full article206 words · extracted from 404media.co · click to collapse

New research from Anthropic, one of the leading AI companies and the developer of the Claude family of Large Language Models (LLMs), has released research showing that the process for getting LLMs to do what they’re not supposed to is still pretty easy and can be automated. SomETIMeS alL it tAKeS Is typing prOMptS Like thiS. 

To prove this, Anthropic and researchers at Oxford, Stanford, and MATS, created Best-of-N (BoN) Jailbreaking, “a simple black-box algorithm that jailbreaks frontier AI systems across modalities.” Jailbreaking, a term that was popularized by the practice of removing software restrictions on devices like iPhones, is now common in the AI space and also refers to methods that circumvent guardrails designed to prevent users from using AI tools to generate certain types of harmful content. Frontier AI models are the most advanced models currently being developed, like OpenAI’s GPT-4o or Anthropic’s own Claude 3.5.

This post is for paid members only

Become a paid member for unlimited ad-free access to articles, bonus podcast content, and more.

Subscribe

Sign up for free access to this post

Free members get access to posts like this one along with an email round-up of our week's stories.

Subscribe

Already have an account? Sign in

Text extracted automatically; images, tables and formatting may be missing. Original: https://www.404media.co/apparently-this-is-how-you-jailbreak-ai/