Install Steam
login
|
language
简体中文 (Simplified Chinese)
繁體中文 (Traditional Chinese)
日本語 (Japanese)
한국어 (Korean)
ไทย (Thai)
Български (Bulgarian)
Čeština (Czech)
Dansk (Danish)
Deutsch (German)
Español - España (Spanish - Spain)
Español - Latinoamérica (Spanish - Latin America)
Ελληνικά (Greek)
Français (French)
Italiano (Italian)
Bahasa Indonesia (Indonesian)
Magyar (Hungarian)
Nederlands (Dutch)
Norsk (Norwegian)
Polski (Polish)
Português (Portuguese - Portugal)
Português - Brasil (Portuguese - Brazil)
Română (Romanian)
Русский (Russian)
Suomi (Finnish)
Svenska (Swedish)
Türkçe (Turkish)
Tiếng Việt (Vietnamese)
Українська (Ukrainian)
Report a translation problem
Ye, the complex prompt is called "Look at the translation and see if you can fix the sentences to be more readable and comprehensive"
I literally used it multiple times this way to rephrase sentences and make them sound better. Like, I straight up don't know what half the sentences in the story are saying, cause they are closer to a haiku than they are to anything else. Feed one of those into ChatGPT and tell him to make it sound good and it will rephrase the whole thing so it at least makes sense.
At least you can kinda figure out the mechanics with trial and error, even though I have still no clue why the Blood % bar sometimes charges 30% and sometimes 40% per turn.
there are places where chatGPT has used multiple different names to explain a single gameplay mechanic, this could have been avoided by having a prompt with a list of Chinese words that always have to be translated the same way every time.
even in the story you occasionally get names of people or places that change for no reason.
for some reason the names "poor house", "alms house", "asylum", and "orphanage" all describe the same location, chat GPT needs a complex prompt to remind it to always translate names the same way every time, because otherwise it will start getting weird.
I would make translation better, sure, but I would already be happy with readable sentences. Which can be done by simply asking it to proof-read what it spit out.