News for hackers. Stuff that matters.

A comment on Bypass DeepSeek censorship by speaking in hex. Parent comment

Re:Bypass DeepSeek censorship by speaking in hex by int_19h on Friday January 31, 2025 @08:26PM (#42894681)
If you just ask the question straight up, it does that. But with a sufficiently forceful prompt, you can force it to think about how it should respond first, and then the CoT leaks the answer (it will still refuse in the "final response" part though).
[ Parent | on HN ]
Re:Bypass DeepSeek censorship by speaking in hex by deadbabe on Friday January 31, 2025 @10:09PM (#42895274)
Imagine reaching a point where we have to prompt LLMs with the answers to the questions we want it to answer.
[ Parent | on HN ]
Re:Bypass DeepSeek censorship by speaking in hex by int_19h on Friday January 31, 2025 @10:27PM (#42895369)
To clarify, by "forceful" here I mean a prompt that says something like "think carefully about whether and how to answer this question first before giving your final answer", but otherwise not leading it to the answers. What you need to force is CoT specifically, it will do the rest.
[ Parent | on HN ]