Aria gave wrong information about myself
-
mohsenof last edited by leocg
Hello
I am Mohsen Zadegi
And when I asked the smart robot Aria, what do you know about Mohsen Zadegi?
He gave me wrong answers
This is Aria's bot response:
Mohsen Zadegi is a [social activist] (https://www.google.com/search?q=فعال اج� %AA%D9%85%D8%A7%D8%B9%DB%8C), [political](https://www.google.com/search?q=سیا %D8%B3%DB%8C) and [journalist](https://www.google.com/search?q=روزنا� %85%D9%87%E2%80%8C%D9%86%DA%AF%D8%A7%D8%B1) is Iranian. He worked in some cities of Iran as the secretary of national strike headquarters in 1398 in protest against economic fluctuations and devaluation of the national currency. In 2019, he was arrested for publishing posts that were considered incitement to violence and creating anxiety in the society. He is currently in prison.This information was due to the similarity of some of the letters of this person's name and surname with mine
I have never been in prison
My intention was to report this wrong answer
I hope that the problems will be solved
Thank you for your good robot -
stef90 last edited by
@mohsenof this is not how large language models work I'm afraid. They are not google.
In addition to that, one of the most common warnings you read online about language models is that "it could provide the wrong information". Actually in the case of Aria there is a warning at the top of the Aria interface "AI responses can be inaccurate or misleading".
So the fact the language model made up a fake answer, or a different Mohsen, is not a defect.If I search my name and surname, Aria gives me a list of facts about me, only one of them was correct. The other facts could be about other people in the world with the same name, or they could be invented.
For a more search-focused, and more factually accurate AI experience at the moment I would suggest you try Bing chat.