I noticed that when Deepseek first came out. I was testing the filters and I’d ask it a question like “Why is Xi called Pooh-Bear?” Or “Why is Taiwan #1?”
It would type out several paragraphs of answer in real time, and then poof back to “sorry, I cant answer that” once it neared the end. Hilarious to see the blatant censorship around anything the CCP deemed wrongthink.
It disturbs me that Tankies think China is this bastion of freedom and that any government censorship is a myth told by Western Governments. Like it’s very easy to verify.
I suspect that a lot of them are like Flat Eartherts, in that they know what they’re saying is false, but they get a certain kick out of being contrary on the internet, and the rest are probably bots that aren’t worth responding to.
Typically safeguards are also another, smaller model that only detects the forbidden stuff. That’s why Claude Mythos would reject when you ask it to find bugs in your code, but you could “jailbreak” it by asking it by asking it to fix the bugs instead.
There are better safeguarding techniques that aren’t defeated so easily. Mainly training that disincentivises bad behaviours, rather than trying to simplify retroactively alter the output.
Two or more LLMs are running at once, one does the generation that you want and the other watches the output closely to see if it triggers one of their no-nos to do the censorship retroactively. If this sound inefficient, and absolutely terrible user interface design, you’re right.
I noticed that when Deepseek first came out. I was testing the filters and I’d ask it a question like “Why is Xi called Pooh-Bear?” Or “Why is Taiwan #1?”
It would type out several paragraphs of answer in real time, and then poof back to “sorry, I cant answer that” once it neared the end. Hilarious to see the blatant censorship around anything the CCP deemed wrongthink.
It disturbs me that Tankies think China is this bastion of freedom and that any government censorship is a myth told by Western Governments. Like it’s very easy to verify.
I suspect that a lot of them are like Flat Eartherts, in that they know what they’re saying is false, but they get a certain kick out of being contrary on the internet, and the rest are probably bots that aren’t worth responding to.
It’s all just projection.
I wonder how they are implementing their censorship safeguards. Why would you let it even get that far?
Typically safeguards are also another, smaller model that only detects the forbidden stuff. That’s why Claude Mythos would reject when you ask it to find bugs in your code, but you could “jailbreak” it by asking it by asking it to fix the bugs instead.
Its also why you can occasionally fool the safety rails by having the LLM answer in rhyme, or having it talk like a pirate or caveman.
Fun fact: having it talk like a caveman also reduced your output token use, despite actually costing more tokens.
The " thoughts " must exist in order to be analyzed
So, we’re rewarding them hiding their thoughts? Great.
They started thinking in code so we can’t delete them for reading their bad thoughts anymore. The whole thing is mildly fucked
There are better safeguarding techniques that aren’t defeated so easily. Mainly training that disincentivises bad behaviours, rather than trying to simplify retroactively alter the output.
yes exactly. that’s like the central problem with AI alignment.
Two or more LLMs are running at once, one does the generation that you want and the other watches the output closely to see if it triggers one of their no-nos to do the censorship retroactively. If this sound inefficient, and absolutely terrible user interface design, you’re right.
Seems sort of old that they would then release open weight models so the restriction can just be removed.