When I mean learning I do not mean translating big sentences or something like that, I mean things like: “Is this japanese sentence correctly written? 雲の日が好きです” In this example it answered: "
Yes, the Japanese sentence “雲の日が好きです” is correctly written. It translates to “I like cloudy days” in English. Here’s a breakdown of the sentence:
- 雲 (くも/kumo): This means “cloud.”
- の (no): This is a possessive particle that indicates the relationship between “cloud” and “day” in this context.
- 日 (ひ/hi): This means “day.”
- が (ga): This is a subject marker particle that marks “cloudy day” as the subject of the sentence.
- 好きです (すきです/suki desu): This means “like” or “to like” and is a polite way of expressing one’s preference. The verb 好き (suki) means “to like,” and です (desu) is a polite copula used to indicate politeness and formality.
Therefore, the sentence “雲の日が好きです” correctly conveys the meaning “I like cloudy days” in Japanese.
"
Is this correct,do you consider it reliable?
Sometimes I also ask some questions like: "What function does ‘こと’ grammatically fulfill on this sentence? … "
This is almost true. I’m a C++ developer, and since the language, its syntax and standard libraries are so well documented, ChatGPT can answer almost anything about them with great accuracy and well written code.
But any developer knows the real meat of most programs is in external libraries, and ChatGPT’s quality falls off very quickly and sharply once you get into those. I tried asking it to explain how to write a specific audio filter for a program I was working on, and what’s really scary is that the code looks right at a first glance, but once you run it, it doesn’t behave how you would expect it to.
So by analogy, the same thing can happen with any subject. ChatGPT knows exactly how a well-written answer looks like but a lot of the time it doesn’t know what the right answer is, which means it’s incredibly easy to be fooled by ChatGPT and believe even its wrong answers.
deleted by creator