Skip to main content

ChatGPT tried to pass a college exam and it didn’t go well

Studying to pass your college exams can be a stressful experience, but what if ChatGPT could just write your papers for you? That’s the question posed by researchers at the U.K.’s University of Bath, and their findings might surprise you.

According to a report from the BBC, artificial intelligence (AI) tools like ChatGPT excel at certain tasks. James Fern, a lecturer at the University of Bath, noted that “Multiple choice questions, for example, [ChatGPT] will handle those very well. We definitely were not expecting it to do as well as it did … it was getting close to 100% correct.”

A person studying and writing notes onto a piece of paper. There is a coffee cup and binder in the distance.
Unseen Studio / Unsplash / .

Yet there were tell-tale signs that the paper it produced was not crafted by a human brain. ChatGPT struggled with more complex questions that required a degree of creativity rather than simply regurgitating facts or picking from multiple options.

Recommended Videos

When answering a question on why it is important to understand the timing of exercise in relation to nutrition status, for instance, ChatGPT slipped up several times. It repeated parts of the question word for word on two occasions, created vague and unattributed statements, and wrote in oversimplified language without being specific.

The chatbot even invented fake academic papers and then cited them in its answer. While the names of the authors and journals were correct, the cited articles simply did not exist, which would be easy for examiners to spot with just a cursory check.

So, while ChatGPT can produce convincing answers in many different contexts, writing your college thesis for you seems to be a step too far for now.

An uncertain future

A MacBook Pro on a desk with ChatGPT's website showing on its display.
Hatice Baran / Unsplash

ChatGPT’s academic future isn’t entirely in tatters, however. Gillian Keegan, the U.K.’s Education Secretary, believes that it is “making a difference in schools and universities already,” and that it could provide assistance to teachers when it comes to lesson planning and marking.

It can also help students get started on tasks and generate ideas that they can then expand upon. While it might not be able to properly answer exam papers, it can at least provide a starting point for further research.

In any case, ChatGPT isn’t going away, and universities and colleges around the world are going to have to adapt to it. It has a lot of potential to improve productivity in the future, and colleges are already teaching students how to use it to improve their output.

But while ChatGPT is unlikely to be awarded a degree any time soon, its potential for misuse is still very real. Apple founder Steve Wozniak has just warned that chatbots could make scams even more realistic, and he was part of a group of prominent tech leaders who signed an open letter in March calling for a pause on further chatbot development. ChatGPT’s future is very much uncertain, but it is no doubt being studied at colleges and universities up and down the land.

Alex Blake
Alex Blake has been working with Digital Trends since 2019, where he spends most of his time writing about Mac computers…
Your politeness toward ChatGPT is increasing OpenAI’s energy costs 
ChatGPT's Advanced Voice Mode on a smartphone.

Everyone’s heard the expression, “Politeness costs nothing,” but with the advent of AI chatbots, it may have to be revised.

Just recently, someone on X wondered how much OpenAI spends on electricity at its data centers to process polite terms like “please” and “thank you” when people engage with its ChatGPT chatbot.

Read more
Fun things to ask ChatGPT now that it remembers everything
ChatGPT on a laptop

If you hadn't heard, ChatGPT's memory just got a whole lot better. Rolled out across the world to Plus and Pro users over the past few days, ChatGPT's various models can now reference almost any past conversation you had. It doesn't remember everything word for word, but can pull significant details, themes, and important points of reference from just about anything you've ever said to it.

It feels a little creepy at times, but ChatGPT can now be used for much more personalized tasks. OpenAI pitches this as a way to improve its scheduling feature to use it as a personal assistant, or to help you continue longer chats over extended periods of time. But it's also quite fun to see what ChatGPT can tell you by trawling throughh all your chatlogs. It's often surprising some of the answers it spits out in response.

Read more
ChatGPT now interprets photos better than an art critic and an investigator combined
OpenAI press image

ChatGPT's recent image generation capabilities have challenged our previous understanding of AI-generated media. The recently announced GPT-4o model demonstrates noteworthy abilities of interpreting images with high accuracy and recreating them with viral effects, such as that inspired by Studio Ghibli. It even masters text in AI-generated images, which has previously been difficult for AI. And now, it is launching two new models capable of dissecting images for cues to gather far more information that might even fail a human glance.

OpenAI announced two new models earlier this week that take ChatGPT's thinking abilities up a notch. Its new o3 model, which OpenAI calls its "most powerful reasoning model" improves on the existing interpretation and perception abilities, getting better at "coding, math, science, visual perception, and more," the organization claims. Meanwhile, the o4-mini is a smaller and faster model for "cost-efficient reasoning" in the same avenues. The news follows OpenAI's recent launch of the GPT-4.1 class of models, which brings faster processing and deeper context.

Read more