ChatGPT @lemmy.world Timely_Jellyfish_2077 @programming.dev 8mo ago

ChatGPT would have been so much useful and trustworthy if it is able to accept that it doesn't know an answer.

Small rant : Basically, the title. Instead of answering every question, if it instead said it doesn't know the answer, it would have been trustworthy.

You're viewing a single thread.

46 comments

LLMs don’t know if what they’re telling you is true or not, out of the box. It’s gonna give you an answer that statistically looks like a sequence of words that should come in response to the sequence of words (the prompt) you gave it. It doesn’t know what the words you said mean, and it doesn’t know what it answered means either. One of my favorite interactions I’ve had with Claude shows this limitation quite well…

How many r's are there in the word strawberry?

There are 2 r's in the word "strawberry".

Are you sure?

You're right to ask for confirmation. I apologize for my mistake in the previous response. Let me correct that:

There is actually only 1 'r' in the word "strawberry".

Thank you for prompting me to double-check. It's important to provide accurate information.
- What's absolutely crazy about that is:
  
  Prompt: write code that checks how many r's are in the word strawberry
  
  Response:
  
  using System; class Program { static void Main() { string word = "strawberry"; char targetChar = 'r'; int count = 0; foreach (char c in word) { if (c == targetChar) count++; } Console.WriteLine($"The letter '{targetChar}' appears {count} times in the word \"{word}\"."); } }
  
  My first thought is that you could write a program that does something like this:
  
  Receive prompt "how many times does R appear in the word 'strawberry'"
  
  Run the prompt through LLM saying "reword the following into a command to generate code that will answer the question" or something like that
  
  Run the results through LLM
  
  Compile and run the results
  
  Provide the output to the user
  
  Of course, the biggest problem with this system is that a person could fool it into generating malicious code.
  
  The code does look like code that counts Rs. The training data probably included tons of code that “counts character X in string Y”, so ChatGPT “knows” what code that counts characters in a string looks like. It similarly “knows” what a string looks like in the language, and what an application entry point looks like, etc. I’m not so familiar with C# that I’d know if it compiles or not. ChatGPT doesn’t either, but it has the advantage of having seen a whole freaking lot of C# code before.
- Wow, GPT4o gave me this after the same questions:
  
  “Yes, I am sure. The word “strawberry” has two “r”s: one after the “t” and another near the end of the word.”
  
  But GPT4 got it right from the start.

46 comments