Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek Introduces Vision

chat.deepseek.com

Post reply on HN
Print view View original

41–50 of 218 posts

Re: DeepSeek Introduces Vision

#41

Post by Razengan »

bogdan wrote: post #37
Shank wrote: post #11

Earlier quoted context omitted.

Well, it is a Chinese model, maybe it thinks better in Chinese?

Hànzì can use 30%-40% fewer tokens than English. So, yes, it probably thinks better in Chinese.

If so, would other models like ChatGPT benefit from translating the user's prompt to Chinese/Japanese and thinking in Hanzi/Kanji and then converting the response back to the user's language before displaying it?

Re: DeepSeek Introduces Vision

#43

Post by cocoflunchy »

Razengan wrote: post #41
bogdan wrote: post #37

Earlier quoted context omitted.

Hànzì can use 30%-40% fewer tokens than English. So, yes, it probably thinks better in Chinese.

If so, would other models like ChatGPT benefit from translating the user's prompt to Chinese/Japanese and thinking in Hanzi/Kanji and then converting the response back to the user's language before displaying it?

I believe that most reasoning models actually think in their own "language" which is not really understandable by humans. The thinking traces that are shown in the UI are actually summaries generated by a smaller model in plain english (or user language). Sometimes this leaks through and you see some chinese/japanese characters in e.g. Claude's reasoning.

Re: DeepSeek Introduces Vision

#44

Post by bogdan »

Razengan wrote: post #41
bogdan wrote: post #37

Earlier quoted context omitted.

Hànzì can use 30%-40% fewer tokens than English. So, yes, it probably thinks better in Chinese.

If so, would other models like ChatGPT benefit from translating the user's prompt to Chinese/Japanese and thinking in Hanzi/Kanji and then converting the response back to the user's language before displaying it?

There are other even more efficient ways of doing this, i.e. using images instead of raw text https://xcancel.com/karpathy/status/1980397031542989305?lang...

Re: DeepSeek Introduces Vision

#46

Post by grogg »

Razengan wrote: post #41
bogdan wrote: post #37

Earlier quoted context omitted.

Hànzì can use 30%-40% fewer tokens than English. So, yes, it probably thinks better in Chinese.

If so, would other models like ChatGPT benefit from translating the user's prompt to Chinese/Japanese and thinking in Hanzi/Kanji and then converting the response back to the user's language before displaying it?

Yeah, it’s why the Caveman skill includes a Wenyan mode.

https://github.com/JuliusBrussee/caveman

Re: DeepSeek Introduces Vision

#48

Post by stranded22 »

paulluuk wrote: post #38
jiehong wrote: post #26

For those not trying, this allows Deepseek to understand a picture (instead of just extracting text from it), and it can describe what's in the picture, but this is not an image generation system, so you can't ask it to modify an image. Personally, I'm a bit surprised the DS chat app still doesn't offer its own text to speech and speech to text features (I know DS doesn't have any ASR model for example, but there are…

Can you explain what the benefits are of actually "talking" with the bot instead of typing and reading? As someone who would rather send a slack message to a coworker rather than actually walking over and talk to them, the idea of having to talk with my laptop is not appealing at all, haha.

Accessibility.
Post reply on HN