Disclaimer: This article was not written using ChatGPT

ChatGPT is the reason why you can easily ace your college essays with zero effort.

It’s also the reason why I’ll flunk my exams: I’m addicted to chatting with it. 

This new AI chatbot, developed by Open AI, has been the talk of the town lately. You can ask it almost anything via text, only for it to reply in an interactive, intelligent manner. All you have to do is sign up for an OpenAI account (for free), and you can ask it to:

• Summarise or generate essays of your desired word count
• Suggest alternative plotlines for your favorite movies (it completely ruined Dead Poet’s Society for me)
• Identify what’s wrong with your code and suggest solutions
• Create applications (people on Twitter have verified-this works)
• Give research ideas for you to work on 
• Generate recipes 
• Talk to you (when asked why the earth is flat, it very convincingly tried to prove to me that the earth is an oblate spheroid, and how my geography teacher might simply have been mistaken)
• Admit its mistakes 
• Disregard inappropriate requests (sad, but no murder plans or gory movie ideas were generated)

Apparently, people on Tinder are also using ChatGPT to generate poems or fancy pick-up lines to hit on people they’re texting. Taking betrayals to new levels, aren’t we?

So what is ChatGPT, again?

Of course, if you still haven’t understood, I asked the chatbot to answer this question in its own words. Here’s what it had to say:

ChatGPT: ChatGPT is a natural language processing model that can generate human-like text in a conversational style. It is trained on massive amounts of data and is able to understand context, making it useful for chatbots and customer service systems. In addition to its conversational capabilities, ChatGPT can also perform all sorts of language processing tasks like translation, summarisation, and text classification tasks. It is a versatile tool that has the potential to improve efficiency and effectiveness in language processing across various industries. 

Aysha: Umm, could you please make it more quirky and interesting?

ChatGPT: Have you ever wanted to have a conversation with a robot that sounds like a real human? Well, now you can with ChatGPT! This natural language processing model was developed by the brilliant minds at OpenAI and is capable of generating text that reads like it was written by a human. Plus, it’s super smart and can understand context, so you can have a real conversation with it (almost) like you would with a real person. But it’s not just a chatbot- ChatGPT can also perform all sorts of language processing tasks lie translation, summarisation, and text classification. So go ahead and have a chat with ChatGPT, but be warned- it might be so convincing that you forget it’s not a real person! 

Isn’t it genuinely fascinating- how you can adjust the tonality of the text too? My teacher would be SO impressed, considering I can tailor it and get a beyond-decent essay in less than a minute. Here’s another example, because why not:

Blurring the lines

So, we have an AI chatbot that can write and program basic codes. Does that mean we’re at the doom of humanity? 

I’ve never understood this question. Why does everything we do have to be in absolutes? Things can co-exist, and I genuinely believe that ChatGPT isn’t here to replace anyone, but rather, to assist and co-exist with writers, journalists, and programmers. And let’s be honest: a professional coder or exceptional writer may find ChatGPT’s responses rather ordinary.

Nonetheless, it’s still a close call to producing more-than-decent content within minutes. The human-like conversations it has also bring to the surface the Turing Test- the lines between humanity and AI are blurring, and it’s getting way too exciting.

What’s more- ChatGPT is also relatively ethical. Previous AI chatbots have been known to respond with obscene language and erroneous results. ChatGPT has come a long way in ameliorating this issue, but it can still be inaccurate. Also, it has a knowledge base of events only before 2021. So according to ChatGPT, the 2022 Qatar football world cup has still not taken place, nor has Russia invaded Ukraine.

Talking about the limitations of a language model, a Deep Mind publication reads:

ChatGPT is a language model, and it’s only an extension of the problems that come along with it. Not everything it returns is accurate, and it could potentially disclose information or reinforce pre-existing stereotypes. 

The American magazine Wired also sheds light on this by claiming:

Several of the potential and realized harms of these models have been exhaustively studied. For instance, these models are known to have serious issues with robustness. The sensitivity of the models to simple typos and misspellings in the prompts and the differences in responses caused by even a simple rewording of the same question make them unreliable for high-stakes use, such as translation in medical settings or content moderation, especially for those with marginalized identities.

Copy that, Sir

Now that we’ve set the base, let’s get down to the real work. If you’d like to use AI to generate your assignments without any plagiarism claims, here’s a trick that you can use:

1. Ask ChatGPT to do your assignment (whether it’s summarising a topic, generating a new essay, or the other gazillion things it can do)
2. Copy the text that ChatGPT returns and rephrase it in Quillbot. For those who don’t know, Quillbot is another excellent AI writing tool that can help you rephrase texts instantly. The free version allows only 125 words at a time, but if you have enough patience, all is well. 

I highly suggest you explore this phenomenal chatbot before they shut the research version and make it paid. It’s so good, even the almighty Google is worried now.

Cheers, you came this far! Drop by a comment if you liked what you read- I’ll see you next Sunday.

ft. brownie points to Halima Sadia