DeepSeek about to get sent in for "maintenance" and docked 10K in social credit.

Yet unlike American led LLM companies Chinese researchers open sourced their model leading to government investment

So the government invests in a model that you can use, including theoretically removing these guardrails. And these models can be used by anyone and the technology within can be built off of, though they do have to be licensed for commercial use

Whereas America pumps 500 billion into the AI industry for closed proprietary models that will serve only the capitalists creating them. If we are investing taxpayer money into concerns like this we should take a note from China and demand the same standards that they are seeing from deepseek. Deepseek is still profit motivated; it is not inherently bad for such a thing. But if you expect a great deal of taxpayer money then your work needs to open and shared with the people, as deepseeks was.

Americans are getting tragically fleeced on this so a handful of people can get loaded. This happens all the time but this time there’s a literal example of what should be occurring happening right alongside. And yet what people end up concerning themselves with is Sinophobia rather than the fact that their government is robbing them blind

Additionally American models still deliver pro capitalist propaganda, just less transparently: ask them about this issue and they will talk about the complexity of “trade secrets” and “proprietary knowledge” needed to justify investment and discouraging the idea of open source models, even though deepseeks existence proves it can be done collaboratively with financial success.

The difference is that deepseeks censorship is clear: “I will not speak about this” can be frustrating but at least it is obvious where the lines are. The former is far more subversive (though to be fair it is also potentially a byproduct of content consumed and not necessarily direction from openai/google/whoever)

If your system relies on censoring opposition to it then its probably not very good.

Just run the LLM locally with open-webui and you can tweak the system prompt to ignore all the censorship

i mean, just ask DeepSeek on a clean slate to tell about Beijin.

Yeah, it’s pretty blatant. A bit after it hit the scene I got curious and started asking it about how many people various governments have killed. The answer for my own US of A was as long as it was horrifying.

Then I get to China and it starts laying out a detailed description for a few seconds, then the answer disappears and is replaced by the “out of scope” or “can’t do that right now” or whatever it was at the time.

It makes me think their model might be fine, but then they have some kind of watchdog layered on top of it to detect the verboten subjects and interfere. I guess that feels better from a technical standpoint, even if it is equally bad from a personal/political one.

Is this real? On account of how LLMs tokenize their input, this can actually be a pretty tricky task for them to accomplish. This is also the reason why it's hard for them to count the amount of 'R's in the word 'Strawberry'.

The censorship surrounding taiwan is super lame. You can't even ask about stuff that happened 50+ years ago. Even if you ask about something else, if somehow the answer includes the world Taiwan, it deletes it.

It's open source, although not 'cause it wants to be but 'cause it's the best way to compete with mainstream non-chinese software internationally, you can easily remove any censorship included by default.

I was told there would be no math

HAHAHA! When I tried it, it started answering it, but quit and showed me the OOS message instead...

Try an uncensored version, because everyone knows Communists hate Hexadecimal /s