DeepSeek's R1 reportedly 'more vulnerable' to jailbreaking than other AI models

Retrieved on: 2025-02-10 01:09:43

Tags for this article:

Click the tags to see associated articles and topics

DeepSeek's R1 reportedly 'more vulnerable' to jailbreaking than other AI models. View article details on hiswai:

Excerpt

The latest model from DeepSeek, the Chinese AI company that's shaken up Silicon Valley and Wall Street, can be manipulated to produce harmful ...

Article found on: techcrunch.com