Global Feed Post Login
Replying to Avatar TechHelpK₿ 💜

Cisco’s research team managed to "jailbreak" DeepSeek R1 model with a 100% attack success rate. This means the new kid on the AI block failed to stop a single harmful prompt.

https://www.pcmag.com/news/deepseek-fails-every-safety-test-thrown-at-it-by-researchers

Avatar
DasFrettchen 11mo ago

so is not sensored? that does not sound like failing to me.

Reply to this note

Please Login to reply.

Discussion

No replies yet.