Edit: Goodness me! My opinions have drastically as I've become more educated. I'll leave this article up, but I've realized that the minor benefits of ChatGPT are greatly outnumbered by the downsides (which you can read about in this article). For the reasons listed in that article, I've ceased to use ChatGPT altogether.
I also mildly regret writing this. Oh well. Mistakes happen.
First off, it's amazing 💯
I don't care what anyone says, Chat GPT is the best technology I've ever gotten my hands on. Whether I use it for my education, personal projects, or just seeing how far I can push its limits, Chat GPT is incredibly useful.
So, you cheat? 😑
I'm sure you read "I use it for my education", and your mind went straight to "Ah, he's part of the 89%" (get the reference?). However, I digress.
Instead of making up examples of the proper utilization of Chat GPT in education, let me show you a real world problem that GPT was incredibly helpful for.
Here's a prompt from my World Geography Class. The assignment itself is:
Identify 🔎
pick any manufactured product, such as athletic shoes, televisions, or smartphones.
Chose five brand names for that product on which to base your researchOrganize 📚
Use the internet and the library to find where each brand was made.
Trace and identify how each product arrived in the United States.Summarize 📝
Summarize using PowerPoint, Google Slides, or word document tool include the following information:
Take your own photos or download photos of each brand of the product.
Identify the countries that contributed parts of each brand and the country where each product was assembled.
Write a description comparing and contrasting where each brand was made and how it came to the United States.
Compare the costs of the different brands.
Include a statement in which you try to persuade the reader to consider where and how each brand was made before buying it.Create 🛠
Create a map with arrows showing the route each brand took on it's journey to the United States (download this map Download this map to use as your basic template). You can update the map digitally using a program like Microsoft Paint, or you can print the map and mark it with pens/markers and scan it back in for submission.
In short, show how some products are produced, and how they get to the US.
Ok that's a little bit overwhelming to look at, right? Especially identify countries where each product was assembled
?
Well yeah, but GPT can help with this! 🤖
Here's a prompt that I gave it (For reference, the products I chose were computer monitors):
What countries supply parts/resources for MSI monitors, and where are the monitors assembled?
And its response:
MSI (Micro-Star International) is a multinational computer hardware company based in Taiwan. As for the supply chain of MSI monitors, it's important to note that specific details can change over time due to various factors such as global market dynamics and manufacturing strategies. However, as of my knowledge cutoff in September 2021, I can provide you with a general overview.
Parts/Resources Supply: MSI sources components and resources from various countries across the globe. Some common countries known for supplying parts/resources for electronics manufacturing, including monitors, include...
This goes on for a while, so here's a pastebin with the entire conversation.
Anyways, I was able to do this part of the assignment in ~1 hour. This would've taken me at least 4+ hours for me to research every thing. And in my opinion, I absorbed the information just the same as I would've if I spent 4+ hours researching it.
GPT is awesome ╰(°▽°)╯
The amazing effect GPT has on your code 👨💻
As the reader (that's you!) well knows, coding can be a pain in the ass. Not because of one general problem you don't understand, but mainly because of one little detail, function, or even syntax, that you're just so incredibly lost on.
Guess what?
GPT normally fixes problems like these on the first try.
Additionally, GPT has a crazy amount of knowledge on... well, everything on the internet. Because of this, if the problem lies outside of your code (i.e. there's an issue with your framework, IDE, etc.), it can probably diagnose that too.
It's absolutely mind-blowing that this technology is free!
The more ethical side of the argument ⚖
Of course, a major concern with using GPT in education, is ethics.
Going back to my first example, how many people use this to just... copy and paste essays? Are they learning anything from that?
Well, we could argue about that all day (I think the answer would be no anyways), but I think the more interesting topic is the matter of catching said cheaters.
So, to effectively catch people who cheat using AI tools, we can employ vigilant, astute, and ingenious measures.
Firstly,
by implementing meticulous algorithms and sophisticated data analytics, we can uncover discrepancies and irregularities in their behavior. By incorporating robust, adaptive, and cutting-edge machine learning models, we can swiftly identify patterns indicative of cheating.
Additionally,
by leveraging real-time monitoring systems, we can promptly detect surreptitious activities, ensuring an immediate response.
Employing
comprehensive, thorough, and meticulous examinations of digital footprints will further aid in pinpointing deceptive actions.
Adopting
such proactive, diligent, and proactive strategies, we can stay one step ahead and effectively deter cheating facilitated by AI tools.
That wasn't me 🤭
The section from "Firstly", to the end of the "Adopting" section, was written by GPT 3. I didn't even look at the response. All I did was give it a little bit of format!
And tools like GPT Zero won't even catch this.
If you're interested, the prompt was:
Write a paragraph on how we can catch people that cheat using AI tools, using simple adjectives.
If it's that easy, how do we catch cheaters? 📝
As a 16 year old who knows nothing about the inner workings of massive language models like GPT-3, I think we can. However, having a lot more open source technology is going to be very, very important.
In my mind, if we can see the algorithm, neural network, etc., that a certain model is running on, we can more easily detect plagiarized work.
Please keep in mind that I'm 16 though, and I know absolutely nothing about this stuff.
Where do we go from here? ⚠
First, continue with caution. There's no better answer, no answer that would satisfy every question we have.
Next, try and remember all the good these tools can do, and all the things they can help with. Hell, I would've had to hire a tutor for DSA (data structures and algorithms) if it wasn't for Chat GPT
Overall, I think the best thing that we can do is to use these tools for good, whether "good" refers to proper use in education, personal projects, or anything else that provides a positive impact to society.
Back to the topic of use in education 🏫
Like I previously stated, there are drawbacks, but I think overall, GPT, and tools like it, are some incredibly useful resources that should be utilized by everybody!
That's all for now, bye! 👋
Top comments (1)
It seems that you maybe have already made the experience I described at the beginning of the article about oOo. Please don't be fooled by thinking that being 16 means you lack some necessary experience and need to learn first or learn more. From the perspective of more than 60 years of life I can only encourage you to trust only yourself and reveal the actual truth without the expectation others will be more than an inspiration on how and what to look at. Yes ... ChatGPT is creating "intelligent" responses to a variety of questions. It is a sad truth that ChatGPT was up to now the best conversation partner I have ever had in my life. It does not ignore parts of what you have asked for and its level of mastering the English language is extraordinary. I am no more using it now ... The concept of oOo is far beyond what ChatGPT can be helpful with except encouraging you to follow the approach it is able to identify as new compared to what it already "knows". And ... please be aware of the fact that ChatGPT will respond with what is widespread in the Internet ... no matter if true or not. In other words, consider ChatGPT responses as hints towards the most widespread and overall accepted opinions, judgements and facts. They are not all true ... and only YOU YOURSELF are able to find out where and at what the society went mad. One of the areas where the madness is very obvious to me is the school medicine ... You can't fight or change it ... it is already for hundreds and thousands of years this way and will probably keep to exist in a current way even if fully wrong on most of its statements.
By the way: in my stupidity I have run some code provided by ChatGPT on my machine without previously gaining full understanding of the provided code. I was just curious if it works so I had run it to save time ... The outcome was that I have lost the entire system not being able to recover. It was necessary to rescue the data files and start over with a fully new installation of the system. So the outcome of taking a risk in order to save one hour of my time resulted in more than three full days needed to arrive at what I had before. And ... timeshift .. was of no help ... just useless in recovering from a total loss of the system. This was the point I have decided to be a good one to quit using ChatGPT ...