So I was just reading this thread about deepseek refusing to answer questions about Tianenmen square.
It seems obvious from screenshots of people trying to jailbreak the webapp that there’s some middleware that just drops the connection when the incident is mentioned. However I’ve already asked the self hosted model multiple controversial China questions and it’s answered them all.
The poster of the thread was also running the model locally, the 14b model to be specific, so what’s happening? I decide to check for myself and lo and behold, I get the same “I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses.”
Is it just that specific model being censored? Is it because it’s the qwen model it’s distilled from that’s censored? But isn’t the 7b model also distilled from qwen?
So I check the 7b model again, and this time round that’s also censored. I panic for a few seconds. Have the Chinese somehow broken into my local model to cover it up after I downloaded it.
I check the screenshot I have of it answering the first time I asked and ask the exact same question again, and not only does it work, it acknowledges the previous question.
So wtf is going on? It seems that “Tianenmen square” will clumsily shut down any kind of response, but Tiananmen square is completely fine to discuss.
So the local model actually is censored, but the filter is so shit, you might not even notice it.
It’ll be interesting to see what happens with the next release. Will the censorship be less thorough, stay the same, or will china again piss away a massive amount of soft power and goodwill over something that everybody knows about anyway?
You must log in or register to comment.
Worrying about whether or not an LLM has censorship issues is like worrying about the taste of poop.
This is just me being childish, but it would be fun if we could incept the joke that LLM censorship = corn.
The rest of the owl draws itself in the imagination of the listener.
Hmm, the way I’ve chosen to interpret this is to propose the analogy of a person eating corn as a model of LLMs. You can eat a huge variety of foods and your poop looks more or less the same. Sometimes, you eat something like corn, and the result is you can spot kernels of things resembling real food (i.e. corn kernels) in the poop. However, if you were to inspect said kernels, you would quickly realise they were full of shit.
Fine analogy.
benchmarks show that this LLM has the bouquet of the sunny side of the sewage farm
the product produced by the producer operating in a violently censorious state has complied with censorship in the production of the product? omg, stop the presses!
(nevermind the fact that if you spend half a second thinking through where said state exercises its power and control, the reasons for the things you observed should all but smack you in the face)
China is an entire economy built on intellectual property thievery and slave labor. The whole thing, that’s they’re advantage. Theft and slavery. The Chinese CCP can fuck off into the sun. *edit: this post and article is about the ccp censoring it’s human rights abuses, and all the downvotes confirm the ccp is here and active on the fediverse itself attempting to do the precise same thing. the irony shouldn’t be lost.
China is an entire economy built on intellectual property thievery and slave labor.
so, just like the united states when it suited them, no? do read about united states in nineteenth century once. oh, and: you do realise that slavery in some circumstances is still legal in the u.s.?
some circumstances is still legal in the u.s.
as someone else pointed out, US-wide legal slavery (enshrined in constitution) in the form of prisoners
precisely. a fucking shame.
Oh hey Sam Altman is here, doing his best to bring down deepseek
no, the downvotes are me because a lot of these takes are shitty
downvotes are me
Is using multiple accounts for voting against any of Lemmy’s rules?
i always thought that some canadians do get sarcasm.
you should definitely report @self lots
if I wanted to cheat the downvote count I’d just modify our instance’s database. our view of votes is different and neither our posters nor our instance really give a fuck which posts random federated weirdos like or don’t like
feel free to report me to me though
reported because I want my internet points and I want them NOW (jk)
no internet points today, only internet cookies (good kind)
Enjoy your trip to the egress.
I mean, “downvotes are proof that the commies are out to get me” is an occasion not just to touch grass, but to faceplant into an open field of wildflowers.
CCP is out after their precious
bodily fluidsinternet pointsI like the idea that the CCP are so desperate to down vote that one comment they don’t stop to down vote the post that actually makes them look bad, which said comment is responding to.
