Discussion about this post

User's avatar
David Cowhig   高大偉's avatar

Intriguing. I wonder about the origins of DeepSeek. If it is based on a foreign AI, then answering like a foreign AI but then censoring what it says might be expected. I wonder if a Chinese AI was made up from scratch whether materials critical of China and the Party might have been filtered out. Given the vast amount of training material needed to train an AI, I don't know if filtering would be practical.

OpenAI suspects that DeepSeek was copied somehow from their LLM AIs. https://chatgpt.com/share/67df4ea5-dec8-8008-ba2f-0ca15174a9e5

If so that would make nonsense of the 'very cheap to train' unique training method that has been one of DeepSeek's main claims to fame.

Then again, Chinese does have many geniuses (as one would expect in such a populous country) and a rapidly growing corps of well-trained engineers so it it is hard to say.

Alternatively, I find using ChatGPT4o if I query in Chinese rather than in English on Chinese topics I get a more PRC and Party-friendly response than if I query it in English. Especially if I ask about Party ideology I get a much better (in the Party sense) and comprehensive answer than if I query it in English. Perhaps when a query is launched in a language the AI hits first relevant material in the language of the query. Perhaps DeepSeek would hew more to the Party line if it had been queried in Chinese rather then in English.

Expand full comment
Leo's avatar

Maybe I missed it, but did you mention how you accessed Deepseek [locally, offline, vpn, official app, other gateways]? From what I have read,mileage varies considerably depending on the mode. Great post, especially the detail on the responses.

Cheers,

Expand full comment
20 more comments...

No posts