I have a theory that it should have a very different “personality” (probably more like writing style) depending on language because it’s an entirely different set of training data
In English chatGPT is rather academic and has a recognisable style of writing, if you’ve used it a bit you can usually get hints something was written by it just by reading it.
Does it speak in a similar tone, with similar mannerisms in other languages? (where possible, obviously some things don’t translate)
I don’t know a second language well enough to have natural conversation so I’m unable to test this myself, and may have worded things awkwardly from a lack of understanding
In two languages I’m learning, German and Chinese, I’ve found it to suffer from “translationese”. It’s grammatically correct, but the sentence structure and word choice feel like the answer was first written in English then translated.
No single sentence is wrong, but overall it sounds unnatural and has none of the “flavor” of the language. That also makes it bad for learning - it avoids a lot of sentence patterns you’ll see/hear in day to day life.
Curious, maybe it was trained using existing translation tech rather than being trained on actual examples of the language like it was for English?
As a native German speaker I agree that ChatGPT is very English-flavored. I think it’s just because the sheer amount of English training data is so much larger that the patterns it learned from that bleed over into other languages. Traditional machine translations are also often pretty obvious in German, but they are more fundamentally wrong in a way that ChatGPT isn’t.
It’s also somewhat cultural. The output you get from ChatGPT often sounds overly verbose and downright ass-kissing in German, even though I know I wouldn’t get that impression from the same output in English, simply because the way you communicate in professional environments is vastly different. (There is no German equivalent to “I hope this email finds you well”, for example.)
“Ich hoffe, diese Nachricht erreicht Sie.” Would work, but I haven’t seen it used too. I also haven’t seen the English version, but that makes sense, as I work for a German company.
Pro tipp: translate with both ChatGPT and Deepl and pick what sounds or reads best.
Bard can’t speak my language Tulu. I teach it some phrases in romanized letter, because the script is yet to be added in Unicode and might take another ten years. So far, only some improvements.
Here’s an example:
Prompt: “Eerna poodar enchina?”
Exact translation: “Your name what?”
Normalized translation: “What is your name?”
Output:
“Eerna poodar enchina?” is a Tulu phrase that means “Whose house is this?”. It is typically used to ask for directions or to find out who owns a particular house.
Here are some other ways to ask for directions in Tulu:
“Namma poodar enchina?” (Our house is where?)
“Nanna poodar enchina?” (My house is where?)
“Enda poodar enchina?” (Their house is where?)
“Enda poodar ninna?” (Whose house is this?)
“Enda poodar yen?” (Whose house is that?)
Expected output:
“Eerna poodar enchina?” is a Tulu phrase that means “What’s your name?”. My name is Bard, an AI assistant.
As you can see, everything about this is so wrong. It also mixes Kannada with Tulu. And none of this is intelligible - it’s all gibberish. They’re not even the same language.
Bard also sucks at Hindi/Urdu translation. I’ve asked it to translate “Bheegi Bheegi Raaton Mein”, which is a pretty old Bollywood song, but it just fails. And even if it does after carefully crafting the prompt, it fails to capture the beauty of the lyrics in the actual source. I’m not good with French, although I’ve learnt about it before, so I’ve not bothered trying.
