Even an AI thinks using AI to write your homework is a bad idea
Kids have been using OpenAI software to do their homework. Here's what the AI thinks about that.
Kids on Reddit have been telling tales of using OpenAI's Playground to get straight A grades in their homework. It's no secret, but when someone asked the same AI its thoughts on how it was used in this schoolyard cheating scheme, it actually made some pretty good arguments against its own use.
A kid on Reddit says he uses OpenAI to get A's on his homework. When asked on ethics, the same AI responds below. @OpenAI pic.twitter.com/dltIuRaMPESeptember 26, 2022
This tweet from MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL), shows OpenAI's answer to the following prompt: "Explain the moral and social issues with using AI to do your homework."
Spoiler: it's one of resounding negativity.
"They may not be learning the material as well as they could be," the AI writes. "This could lead to problems down the road when they are expected to know the material for exams or real-world applications.
"Additionally, using AI to do homework could lead to cheating."
No sh*t. Unless you've been assigned a project specifically about using AI for school, it's definitely cheating. Maybe not if you're only using it to help generate ideas, rather than writing entire essays.
I did find a couple of references to using AI for homework across Reddit, along with a few questions about how helpful it might be from prospective cheaters, but one Reddit post sticks out as the post MIT was potentially referencing.
The biggest gaming news, reviews and hardware deals
Keep up to date with the most important stories and the best deals, as picked by the PC Gamer team.
Urdadgirl69's post, headlined "Artificial Intelligence allows me to get straight A's," talks about using the tool to write essays, answer questions about movies and books for school projects, and even making "$100 profit by 'doing' homework for other classmates," they say. "Now I am looked at as a genius."
OpenAI's Playground tool is an AI training platform that allows users to create and train AI models. It's often used by researchers and developers to experiment with new AI models and applications. Now the kids have cottoned on, they're using it to turn a profit among classmates it seems.
It's a diamond hustle for sure, but as the AI explains "It could create an unfair advantage over other students who are doing their homework on their own." Imagine half the kids in class suddenly shifting from Ds to As in a single week. A bit sus if you ask me, and you'd hope the teacher would realise something was up.
Here's what the Playground text-davinci-002 model AI gave us, as part of a request for an article about kids using AI to do their homework:
"The implications of using AI to do your homework are far-reaching. For one, it could lead to a future where AI is used to do all kinds of things that humans currently do, including things like homework.
Best gaming PC: The top pre-built machines from the pros
Best gaming laptop: Perfect notebooks for mobile gaming
"This could lead to a future where humans are no longer needed to do things like homework, and instead AI does it all. This could have a major impact on society, as it would likely lead to large-scale unemployment and a decrease in the quality of life for many people. It would also have a major impact on education, as it would likely lead to a decrease in the need for human teachers."
Then it took a surprisingly positive turn, and it wasn't as doom and gloom as when MIT asked it a similar question.
"It could free up a lot of time for people who currently spend a lot of time doing homework. It could also lead to better grades for people who use AI to help with their homework."
Although I'm sure teachers will have something to say about it, the AI isn't wrong. Still, it's imperative for us to have these conversations right now as there's a very real fear arising about the idea that humans could end up supplanted by AI. Artificial intelligence has already been giving people unfair advantages in art competitions, and the moral implications are far reaching.
But that's a discussion for another time.
Screw sports, Katie would rather watch Intel, AMD and Nvidia go at it. Having been obsessed with computers and graphics for three long decades, she took Game Art and Design up to Masters level at uni, and has been rambling about games, tech and science—rather sarcastically—for four years since. She can be found admiring technological advancements, scrambling for scintillating Raspberry Pi projects, preaching cybersecurity awareness, sighing over semiconductors, and gawping at the latest GPU upgrades. Right now she's waiting patiently for her chance to upload her consciousness into the cloud.