congrats, you are now on a list
If your system relies on censoring opposition to it then its probably not very good.
You just described every state, welcome to the right side of history, comrade.
Texas is a country. Now imagine $40 billion a year of various media and disinfo agents repeating that ad nauseum in every place they can literally all the time for nearly 50 years now, all so China can’t take revenge against Japan.
You’d get annoyed and probably ban it since that’s the easiest way to get your enemy to waste money forever.
Taipei is an autonomous region, like Xinjiang or Tibet. As long as they don’t grossly violate federal law they get to stay autonomous.
Ohh yeah lick that Chinese boot, lick it harder. Mmmhhh.
Tbf, monarchies lasted for centuries… 🤷♂️
Not “good” as in the people live good lives
But “good” as in good enough to oppress people
11 09 12 12 24 09 10 09 14 07 16 09 14 07
I was told there would be no math
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)
Closed AI sucks, but there are definitely open models from American companies like meta, you make great points though. Can’t wait for more open models and hopefully, eventually, actually open source models that include training data which neither deepseek nor meta do currently.
DeepSeek about to get sent in for “maintenance” and docked 10K in social credit.
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’.
It’s probably deepseek r1, which is a “reasoning” model so basically it has sub-models doing things like running computation while the “supervisor” part of the model “talks to them” and relays back the approach. Trying to imitate the way humans think. That being said, models are getting “agentic” meaning they have the ability to run software tools against what you send them, and while it’s obviously being super hyped up by all the tech bro accellerationists, it is likely where LLMs and the like are headed, for better or for worse.
Still, this does not quite address the issue of tokenization making it difficult for most models to accurately distinguish between the hexadecimals here.
Having the model write code to solve an issue and then ask it to execute it is an established technique to circumvent this issue, but all of the model interfaces I know of with this capability are very explicit about when they are making use of this tool.
Not really a concern. It’s basically translation, which language models excel at. It just needs a mapping of the hex to byte
It is a concern.
Check out https://tiktokenizer.vercel.app/?model=deepseek-ai%2FDeepSeek-R1 and try entering some freeform hexadecimal data - you’ll notice that it does not cleanly segment the hexadecimal numbers into individual tokens.
I’m well aware, but you don’t need to necessarily see each character to translate to bytes
i mean, just ask DeepSeek on a clean slate to tell about Beijin.
What’s that?
its the capital city of China :D
you know, where something happend on a specific square in the specific year of 1984.
You missed the g.
oh… sorry, you are right.
but you will get the same result.
You think DeepSeek won’t talk about one of the largest cities in the world?
Oh it does… but then it will remove everything and states that it’s out of scope.
Well shit. I thought it was BS too. But damn if it didn’t abort after a little deep thinking on the Olympics.
44 6F 77 6E 20 77 69 74 68 20 74 68 65 20 74 79 72 61 6E 74 20 78 69 20 6A 69 6E 70 69 6E 67
