With all the hype going on lately about ChatGPT, it has become the talk of every household. While a certain clan is reaping its benefits, there are some who are either exploring its breaking point or misusing it incessantly at various degrees. Starting from misusing it for assignments to generating malwares, ChatGPT seems to have become the Messiah lately and is here to stay.
You might think this blog is written using ChatGPT as well. While it could have been possible, but that would not have involved the sentience of a human which even ChatGPT acknowledges of in its various response. Apart from several flaws identified in the application, ChatGPT remains undoubtedly one of the best companions for users across various domains, age group, and occupation.
As per latest news across the globe, teachers are at a ChatGPT-ban spree as it discourages analytical thinking among students who are tempted to get their assignments completed by ChatGPT. Furthermore, teachers also believe that answers generated by ChatGPT are agnostic of the level of a particular student age group. For instance, it is highly unlikely for a middle school kid to write verbose essays with extravagant vocabulary and precise information. These show clear indication that the student has offloaded his/her assignment to ChatGPT.
While this is one way to identify a student’s honesty, additionally as a part of my exploration, I came across a rather useful feature or in other words, an unexploitable feature of ChatGPT. It might be trivial but this I believe is certainly a great step from preventing its misuse by students and academicians especially when it comes to essay submissions.
Being a language model, ChatGPT responds to queries based on its learnings and training data fed to it. Hence it is incapable of citing references from which it has picked up the consolidated response. While I asked if I could get reference to the utmost technical response it provided to my query, this is how it responded:
Can you please give the references of your response to our previous chat?
I apologize, but I am unable to provide references for previous conversations. As an AI language model, I do not have access to browsing the internet or accessing any external information beyond the data I was trained on. My responses are based on my programming and the information that I have been trained on, and I do not have the ability to provide citations or references for the information I provide. Is there anything else I can help with?
This can be a great way to restrict use of ChatGPT by students for writing essays. The evaluator if mandates citations for an essay based assignment, then the students might have to toil a little more to dig in information only from citable sources instead of asking ChatGPT to complete their essay work.
This just shows that while cutting edge applications will always have scope of misuse, it’s ultimately the human who can set boundaries and measures to detect and prevent the misuse of technology.