![[Top panel] OpenAI/GPT says: I apologize for the mistake. There is only **one** R in the word "strawberry." [Bottom panel] The commander of a US submarine says: A $40 million computer tells you there is one "R" in strawberry, but you don't believe it, and you come up with this on your own?](https://lemmy.sdf.org/pictrs/image/d76ec083-ed81-423a-bc54-eeb521b7c56a.png)
This happens because LLMs operate on tokenized data, and they don't really "see" the text in the form of individual characters.
You can quite reasonably get an LLM to generate a script that does the character counting and then run the script, to arrive at the correct answer.