Comment by ClassyJacket
1 year ago
LLMs can't count the Rs in strawberry because of tokenization. Words are converted to vectors (numbers), so the actual transformer network never sees the letters that make up the word.
ChatGPT doesn't see "strawberry", it sees [302, 1618, 19772]
Hm but if that is the case, then why did LLMs only fail at the tasks for a few word/letter combinations (like r's in "Strawberry"), and not all words?