In attempting to write a certain number of words per chapter, ChatGPT has been asked to write 2,500 words. It reports, at the end of the chapter written, that the word count is 2,506 words. However, when using a Google Docs word count tool, the count is 1,236.
This happens on every chapter, but with different word counts, different from what ChatGPT reports and always lower by more than 1,000 words per chapter.
Short answer is that LLMs in general cannot approximate word counts well. This is something intrinsic to the LLMs, both due to how “words” are represented (as tokens, which may be sub-words, and may contain whitespaces), and also due to LLMs not really understanding the concept of words counts as a whole. You can tell them to be in depth, concise, long, or short, but then you have to build solutions over the top to take care of word counts.
There have been multiple such topics in the past, e.g. see: