←back to thread

Bypass DeepSeek censorship by speaking in hex

(substack.com)
755 points MedadNewman | 1 comments | 31 Jan 25 19:41 UTC | HN request time: 0.204s | source
Show context
yujzgzc ◴[31 Jan 25 20:46 UTC] No.42891773[source]▶
> The DeepSeek-R1 model avoids discussing the Tiananmen Square incident due to built-in censorship. This is because the model was developed in China, where there are strict regulations on discussing certain sensitive topics.

I believe this may have more to do with the fact that the model is served from China than the model itself. Trying similar questions from an offline distilled version of DeepSeek R1, I did not get elusive answers.

I have not tested this exhaustively, just a few observations.

replies(5): >>42891816 #>>42891907 #>>42892027 #>>42893863 #>>42893968 #
1. phantom784 ◴[31 Jan 25 20:51 UTC] No.42891816[source]▶
When I tested the online model, it would write an answer about "censored" events, and then I'd see the answer get replaced with "Sorry, that’s beyond my current scope. Let’s talk about something else." So I think they must have another layer on top of the actual model that's reviewing the model and censoring it.