Comment on Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.

<- View Parent
Letstakealook@lemm.ee ⁨3⁩ ⁨weeks⁩ ago

Not from this technology, regardless of the hype behind it. The only dangers this technology presents are excessive carbon emissions, and if some idiot “true believer” implements this predictive text generator into some critical system where the algorithm can’t perform.

source
Sort:hotnewtop