📢 Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection

📢 Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection

· json · rss
Subscribe:

About

Date: 2026-06-29T23:33:09
Source: The Register Security
Read more: https://www.theregister.com/ai-and-ml/2026/06/30/security-researchers-tricked-llms-into-giving-them-cocaine-recipes-by-abusing-role-models-for-prompt-injection/5264115?utm_source=dstif.io