Will's Blog: Researchers at Anthropic, Oxford, Stanford, and MATS create Best-of-N Jailbreaking, a black-box algorithm that jailbreaks frontier AI systems across modalities (Emanuel Maiberg/404 Media)

21 December 2024

Researchers at Anthropic, Oxford, Stanford, and MATS create Best-of-N Jailbreaking, a black-box algorithm that jailbreaks frontier AI systems across modalities (Emanuel Maiberg/404 Media)

Emanuel Maiberg / 404 Media:
Researchers at Anthropic, Oxford, Stanford, and MATS create Best-of-N Jailbreaking, a black-box algorithm that jailbreaks frontier AI systems across modalities — Anthropic created an AI jailbreaking algorithm that keeps tweaking prompts until it gets a harmful response.

Posted from: this blog via Microsoft Power Automate.