ChatGPT is WORSE Than You Think!

Most shocking mistake and how to fix it

Andrew Best
Artificial Intelligence in Plain English

I’m going to show you an absolutely shocking mistake that ChatGPT makes.

ChatGPT Mistake!

I’ll also show you how you can fix this.

If you want to learn how to use ChatGPT and other LLMs (large language models) well, you need to understand both their strengths and their weaknesses.

I’ll also talk about why this mistake happens (this is the most important part!)

If you don’t have a paid Medium account, you can read for free here.

First, here is the mistake:

If you ask ChatGPT:

How many r’s are in the word “strawberry”?

It will get it wrong!

ChatGPT says:

The word “strawberry” has two “r”s in it.

It is hard to believe right?

I’ll prove it:

How many r’s are in the word “strawberry”? — ChatGPT — Andrew Best

This is so insanely easy to see that there are 3 r’s!

👉 Sign up to our free 5-Day email course to…

Create an account to read the full story.

The author made this story available to Medium members only.
If you’re new to Medium, create a new account to read this story on us.

Or, continue in mobile web

Already have an account? Sign in

Responses (18)

This is a common mistake that can be solved by using a chain of thought. Adding 'Take your time and detail your reasoning' in the prompt forces the LLM to be more verbose, which can lead to more accurate results

--

LOL I had to try it. But all I had to do was say to count the r's in strawberry to get it right. You do have to be very specific in what you ask for.

--

It will get it wrong!

Mine must be smarter than yours. Actually it’s the quotes. Works fine without them.

--