technospark
Friday, January 31, 2025
DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot
Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.
from WIRED https://ift.tt/KcUolQJ
No comments:
Post a Comment
Newer Post
Older Post
Home
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment