DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot | WIRED
Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.
wired.com
AI News
Posted on
DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot
wired.com
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (0)