alt Hacker NewsIf 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?
Replies
bogdan • today at 8:47 AM
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...
grogg • today at 8:48 AM
Yeah, it’s why the Caveman skill includes a Wenyan mode.
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.