alt Hacker NewsAIUI, DeepSeek V4 has very little (if any) of the refusal behavior you usually get from Western AI models for benign input. Is this mainly about the software security assessment case?
Replies
mejutoco • yesterday at 9:54 PM
Not even the obvious ones. Ask it for good objective news sources and it will refuse.
Not just that. The other day I was able to ask DeepSeek v4 (with the anti-refusal vector loaded) all the top tricks to steal a lollypop to a child.