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.
Have it cite it’s source.
Even with early GPT-4 it would also cite real citations that weren’t actually about the topic. So you may be doing a lot of work double checking as opposed to just looking into an answer yourself from the start.
If you use kagi its AI gives sources https://kagi.com/fastgpt https://imgur.com/TYQErhC
This wasn’t an intentional feature; they’re actually trying to train it with fine-tuning to add this as an ability. It’s one area that highlights the difference between it imitating the text it’s been seeing, instead of actually understanding what it’s saying – since most of its training data is of the form “(ask a question) (response to question)” overwhelmingly more often than “(ask a question) (say you don’t know, the end)”, it is trying to be a good imitator and do the same, and come up with some plausible nonsense even if it doesn’t know the answer.
And sometimes that’s exactly what I want, too. I use LLMs like ChatGPT when brainstorming and fleshing out fictional scenarios for tabletop roleplaying games, for example, and in those situations coming up with plausible nonsense is specifically the job at hand. I wouldn’t want to go “ChatGPT, I need a description of the interior of a wizard’s tower is like” and get the response “I don’t know what the interior of a wizard’s tower is like.”
At one point I messed around with a lore generator that would chop up sections of “The Dungeon Alphabet” and “Fire on the Velvet Horizon” along with some other stuff, and feed random sections of them into the LLM for inspiration and then ask it to lay out a little map, and it pretty reliably came up with all kind of badass stuff.
Part of the problem is fine tuning is very shallow, and that a contributing issue for claiming to be right when it isn’t is the pretraining on a bunch of training data of people online claiming to be right when they aren’t.
Yeah. It is fairly weird to me that it’s such a common thing to do to take the raw output of the LLM and send that to the user, and to try use fine-tuning to get that raw output to look some way that you want.
To me it is obvious that something like having the LLM emit a little JSON block which includes some field which covers “how sure are you that this is actually true” or something, is more flexible and simpler and cheaper and works better.
But what do I know
The problem is that they are prone to making up why they are correct too.
There’s various techniques to try and identify and correct hallucinations, but they all increase the cost and none are a silver bullet.
But the rate at which it occurs decreased with the jump in pretrained models, and will likely decrease further with the next jump too.
Good look getting it to reply consistently with a json object
Edit: maybe i’m shit at prompting but for me it’s almost impossible to even get it to just shut up and consistently reply yes or no to my questions
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.
Even a response that it doesn’t know an answer would be untrustworthy
I specifically ask for sources to my questions and to notify me of any possible controversies or counterclaims.
Some of the capabilities of todays’ AI’s are incumbent on the user, not the system itself.
Before AI’s existed you could also get badly sourced claims or outright misinformation. The key is to remain critical and sceptical about ALL your sources. I don’t see AI as a new source of information, just as a new way to get and organize that information.