How many Rs are in the word strawberry?

There's a viral Mastodon post that demonstrates a supposed deficiency in large language models (LLMs), specifically ChatGPT, because it apparently can't count the number of letters in the English word "strawberry".

> How many R's are in the word strawberry

ChatGPT: There are two "R's" in the word "strawberry."

> Are you sure?

ChatGPT: Yes, I'm sure. There are two "R's" in the word "strawberry."

[...]

> Count the Rs in the word straw and the word berry separately.

ChatGPT: Sure. Let's break it down:

* The word "straw" has 1 "R."
* The word "berry" has 2 "R's."

So, together they have 3 "R's." But in the combined word "strawberry," there are still only 2 "R's."

At first glance, that's a big yikes. (I was able to reproduce the inital result using ChatGPT 4o.)

But I get annoyed by this kind of post for two main reasons: 1) if you ask slightly differently, ChatGPT can easily get this question right, and 2) it's a missed opportunity to explain how LLMs work, specifically with regards to tokenization.

Let's try again#

Here's the prompt I used with ChatGPT 4o:

> Write and then run a Python program to determine how many R's are in the word strawberry

ChatGPT: The word "strawberry" contains 3 occurrences of the letter 'R'. 

It's not really well known that ChatGPT has a feature to execute Python code in a sandbox and use the result in answers.

The Python code it generated was:

# Python program to count the number of 'R's in the word 'strawberry'

word = "strawberry"
count_Rs = word.lower().count('r')  # Convert the word to lowercase and count 'r'
count_Rs

The code is pretty simple, and I think we'd all agree that this is a place where Python code can quite accurately answer this question. Having the LLM generate the code and execute it nicely sidesteps the underlying issue.

Of course, the problem is you have to prompt it to use Python in the first place, knowing that this is a subject where an LLM without code execution would fail. Which brings me to...

Tokenization#

When you provide a prompt for an LLM, it breaks down each word into tokens. OpenAI provides a visualization tool for this; you can see that using the GPT-4 tokenizer, the string "strawberry" is broken down into "str", "aw" and "berry", which get transformed to numerical values of [496, 675, 15717]. Or in other words, the LLM doesn't have access to individual characters, it just sees the tokens.

In this case, you can try to bypass the tokenizer by using spaces, so each letter is now its own word and tokenized separately:

> How many r characters are in the letters s t r a w b e r r y

ChatGPT: The word "strawberry" contains 3 instances of the letter "r."

Success, though I've had mixed success with approach this in the past.

Closing thoughts#

There are plenty of problems, both technically and ethically, with LLMs and I don't want to be (or even appear to be) an apologist for them. But I think it's important that we all understand how LLMs work to actually tackle and address those problems.