- Users can't use it to learn, because ChatGPT responds with high confidence but could be terribly wrong.
- Even if it could learn from users, it would really only learn from people that know a subject and are willing to spend their time correcting ChatGPT.
Me: Unfortunately your response is very wrong. Specifically this part "the key of B major, which is the parallel minor key of F major."
The parallel minor of F major is not B major.
If I hadn't done an additional google search, I'd be taught the wrong theory by you.
I'd suggest you stop responding questions that you don't have 100% confidence that they are correct.
ChatGPT: I apologize for the error in my previous response. You are correct that the parallel minor of F major is not B major. The parallel minor key of F major is D minor. I apologize for the mistake and for any confusion it may have caused. Thank you for bringing this to my attention. It is important to me to provide accurate and helpful information, and I will make sure to double-check my responses in the future. If you have any further questions, please don't hesitate to ask.
Me: It happened again. The parallel minor key of F major is also not D minor.
Can you please stop making guesses? You're damaging society by letting people believe that you've got correct answers.
ChatGPT: I apologize for the mistake in my previous response. You are correct that the parallel minor key of F major is not D minor. The parallel minor key of F major is F minor. I apologize for the error and for any confusion it may have caused. Thank you for bringing this to my attention. It is important for me to provide accurate and helpful information, and I will make sure to double-check my responses in the future. If you have any further questions, please don't hesitate to ask.
Just goes to show that when scrutinised and pressed, ChatGPT is another AI hype tool that essentially is good at regurgitating nonsense and is even confident that its answer is correct.
As soon as it admits it's mistake, it even breaks and repeats the exact same verbatim response again. The hilarious part of it is that it completely fails at explaining itself and doesn't even know why it is giving the wrong answer, hence why it is as transparent as a black box.
I think that's the same problem we can have on Glassdoor or in the HN's "Who is hiring" page - we have to trust the community and if anything raises an eyebrown, you can report it.
But at least, like in these other apps, you can only leave a comment on GitHub if you're signed-in
- Users can't use it to learn, because ChatGPT responds with high confidence but could be terribly wrong.
- Even if it could learn from users, it would really only learn from people that know a subject and are willing to spend their time correcting ChatGPT.