←back to thread

Bypass DeepSeek censorship by speaking in hex

(substack.com)
755 points MedadNewman | 4 comments | 31 Jan 25 19:41 UTC | HN request time: 0.968s | source
Show context
femto ◴[31 Jan 25 21:11 UTC] No.42892058[source]▶
This bypasses the overt censorship on the web interface, but it does not bypass the second, more insidious, level of censorship that is built into the model.

https://news.ycombinator.com/item?id=42825573

https://news.ycombinator.com/item?id=42859947

Apparently the model will abandon its "Chain of Thought" (CoT) for certain topics and instead produce a canned response. This effect was the subject of the article "1,156 Questions Censored by DeepSeek", which appeared on HN a few days ago.

https://news.ycombinator.com/item?id=42858552

Edit: fix the last link

replies(10): >>42892216 #>>42892648 #>>42893789 #>>42893794 #>>42893914 #>>42894681 #>>42895397 #>>42896346 #>>42896895 #>>42903388 #
jagged-chisel ◴[31 Jan 25 23:38 UTC] No.42893789[source]▶
> … censorship that is built into the model.

Is this literally the case? If I download the model and train it myself, does it still censor the same things?

replies(2): >>42893867 #>>42894514 #
malux85 ◴[31 Jan 25 23:46 UTC] No.42893867[source]▶
What do you meam "download the model and trrain it yourself"?

If you download the model then you're not training it yourself.

If you train it yourself, sensorship is baked in at this phase, so you can do whatever you want.

replies(2): >>42894622 #>>42895245 #
1. jagged-chisel ◴[01 Feb 25 03:02 UTC] No.42895245[source]▶
Models can come pre-trained, or not trained. So do they pre-train and only offer the model with training? Or can one download an untrained model and avoid this censorship?
replies(1): >>42895409 #
2. sadeshmukh ◴[01 Feb 25 03:36 UTC] No.42895409[source]▶
What is an untrained model? That doesn't make sense. Do you mean the training code or just base models (even those are trained).
replies(1): >>42895501 #
3. jagged-chisel ◴[01 Feb 25 03:57 UTC] No.42895501[source]▶
Alright, what's the thing being trained to become the model? If a model means "already trained," what is it before being trained?

Is the model not the network that awaits training data? Or is the model just the weights applied to some standardized network?

replies(1): >>42896009 #
4. lucianbr ◴[01 Feb 25 05:44 UTC] No.42896009{3}[source]▶
A "language model" is a model of a certain language. Thus, trained. What you are thinking of is a "model of how to represent languages in general". That would be valid in a sense, but nobody here uses the word that way. Why would one download a structure with many gigabytes of zeroes, and argue about the merits of one set of zeroes over another?

The network before training is not very interesting, and so not many people talk about it. You can refer to it as "blank network", "untrained network", or any number of ways. Nobody refers to it as "a model".

Yes, if you want to, you can refer to the untrained network as "a model", or even as "a sandwich". But you will get confused answers as you are getting now.