Welcome ton !nlprog where anything Natural Language Programming related is game, prompts, ideas, projects and more for any model are welcome.
We follow Lemmy’s code of conduct.
I’ve been using it to translate my own software from English to my native language. I don’t live in my home country anymore and I notice my own speech is a bit awkward at times. Also because I typically use the English terms for common words like saving or clipboard.
Either way, I found it’s very good for these purposes giving a much more natural use of language than Google translate and with great context awareness. I wouldn’t dare using it on a language I’m not fluent in though.
This was a very interesting read. I tried very basic translation myself with chat gpt before although I was weary of it's reliably. This however makes me more hopeful.
I'm wondering about the randomness issue, are you only using the web interface and not the API? Couldn't you set the temp=0 to get the output to be more reliable? (I'm assuming you most likely don't have chat gpt 4 API access so I know you would have to wait for that.)
Translation to Chat GPT is really a loose term, because actually what you are telling it to do is create a story in language B that follows the plot of the story in language A. So naturally it is going to take some creative license with the translation, and you'll get a more accurate response if you give it the context of what you're translating.
It seems like it would be very good at translating between languages because the language model means it is breaking prompts into a tree based on meaning, and then rebuilding with words of the other language. This should be much more accurate and context aware than Google translates approach, which was advanced for it's time, to translate phrases based on a combination of known book translations and dictionary lookups.