homework gpt

• Skip to main content
• Keyboard shortcuts for audio player

A new AI chatbot might do your homework for you. But it's still not an A+ student

Emma Bowman

Enter a prompt into ChatGPT, and it becomes your very own virtual assistant. OpenAI/Screenshot by NPR hide caption

Enter a prompt into ChatGPT, and it becomes your very own virtual assistant.

Why do your homework when a chatbot can do it for you? A new artificial intelligence tool called ChatGPT has thrilled the Internet with its superhuman abilities to solve math problems, churn out college essays and write research papers.

After the developer OpenAI released the text-based system to the public last month, some educators have been sounding the alarm about the potential that such AI systems have to transform academia, for better and worse.

"AI has basically ruined homework," said Ethan Mollick, a professor at the University of Pennsylvania's Wharton School of Business, on Twitter.

The tool has been an instant hit among many of his students, he told NPR in an interview on Morning Edition , with its most immediately obvious use being a way to cheat by plagiarizing the AI-written work, he said.

Academic fraud aside, Mollick also sees its benefits as a learning companion.

Opinion: Machine-made poetry is here

He's used it as his own teacher's assistant, for help with crafting a syllabus, lecture, an assignment and a grading rubric for MBA students.

"You can paste in entire academic papers and ask it to summarize it. You can ask it to find an error in your code and correct it and tell you why you got it wrong," he said. "It's this multiplier of ability, that I think we are not quite getting our heads around, that is absolutely stunning," he said.

A convincing — yet untrustworthy — bot

But the superhuman virtual assistant — like any emerging AI tech — has its limitations. ChatGPT was created by humans, after all. OpenAI has trained the tool using a large dataset of real human conversations.

"The best way to think about this is you are chatting with an omniscient, eager-to-please intern who sometimes lies to you," Mollick said.

It lies with confidence, too. Despite its authoritative tone, there have been instances in which ChatGPT won't tell you when it doesn't have the answer.

That's what Teresa Kubacka, a data scientist based in Zurich, Switzerland, found when she experimented with the language model. Kubacka, who studied physics for her Ph.D., tested the tool by asking it about a made-up physical phenomenon.

"I deliberately asked it about something that I thought that I know doesn't exist so that they can judge whether it actually also has the notion of what exists and what doesn't exist," she said.

ChatGPT produced an answer so specific and plausible sounding, backed with citations, she said, that she had to investigate whether the fake phenomenon, "a cycloidal inverted electromagnon," was actually real.

When she looked closer, the alleged source material was also bogus, she said. There were names of well-known physics experts listed – the titles of the publications they supposedly authored, however, were non-existent, she said.

"This is where it becomes kind of dangerous," Kubacka said. "The moment that you cannot trust the references, it also kind of erodes the trust in citing science whatsoever," she said.

Scientists call these fake generations "hallucinations."

"There are still many cases where you ask it a question and it'll give you a very impressive-sounding answer that's just dead wrong," said Oren Etzioni, the founding CEO of the Allen Institute for AI , who ran the research nonprofit until recently. "And, of course, that's a problem if you don't carefully verify or corroborate its facts."

Users experimenting with the chatbot are warned before testing the tool that ChatGPT "may occasionally generate incorrect or misleading information." OpenAI/Screenshot by NPR hide caption

An opportunity to scrutinize AI language tools

Users experimenting with the free preview of the chatbot are warned before testing the tool that ChatGPT "may occasionally generate incorrect or misleading information," harmful instructions or biased content.

Sam Altman, OpenAI's CEO, said earlier this month it would be a mistake to rely on the tool for anything "important" in its current iteration. "It's a preview of progress," he tweeted .

The failings of another AI language model unveiled by Meta last month led to its shutdown. The company withdrew its demo for Galactica, a tool designed to help scientists, just three days after it encouraged the public to test it out, following criticism that it spewed biased and nonsensical text.

Untangling Disinformation

Ai-generated fake faces have become a hallmark of online influence operations.

Similarly, Etzioni says ChatGPT doesn't produce good science. For all its flaws, though, he sees ChatGPT's public debut as a positive. He sees this as a moment for peer review.

"ChatGPT is just a few days old, I like to say," said Etzioni, who remains at the AI institute as a board member and advisor. It's "giving us a chance to understand what he can and cannot do and to begin in earnest the conversation of 'What are we going to do about it?' "

The alternative, which he describes as "security by obscurity," won't help improve fallible AI, he said. "What if we hide the problems? Will that be a recipe for solving them? Typically — not in the world of software — that has not worked out."

Have a language expert improve your writing

Check your paper for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• Using ChatGPT for Assignments | Tips & Examples

Using ChatGPT for Assignments | Tips & Examples

Published on February 13, 2023 by Jack Caulfield and Tobias Solis. Revised on November 16, 2023.

People are still figuring out the best use cases for ChatGPT , the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use ChatGPT and other AI tools to assist with your academic writing .

These tools can assist you with the following steps when writing a paper, thesis , or dissertation :

• Developing a research question
• Creating an outline
• Generating literature ideas

Paraphrasing and summarizing text

• Getting feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Developing a research question with chatgpt, creating an outline of your paper with chatgpt, generate literature ideas, getting feedback from chatgpt, limitations of chatgpt, other interesting articles, frequently asked questions.

You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.

With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.

However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).

First input

Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”

ChatGPT output

• To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviors?
• How does the personalized algorithm of social media platforms shape the formation of political opinions among its users?
• What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analyzed?

Second input

Based on the second research question, develop three further research questions on the topic of polarization in US politics.

• Build my scientific method, qualitative discourse analysis, into each question
• Include the term “filter bubble” in each question
• How does the filter bubble effect on social media platforms contribute to the polarization of political attitudes in the US? A qualitative discourse analysis.
• What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US? A qualitative discourse analysis.
• How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the US? A qualitative discourse analysis.

Third input

Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.

• How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarization of political attitudes in the US?
• What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?
• How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the US?

Don't submit your assignments before you do this

The academic proofreading tool has been trained on 1000s of academic texts. Making it the most accurate and reliable proofreading tool for students. Free citation check included.

Try for free

You can also use ChatGPT to help you draft a research paper outline or thesis outline . To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.

However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.

You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.

Create an outline for an academic research paper with the following research question:

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”

The paper will be about 8 pages long.

• Background information on filter bubbles and political echo chambers
• Purpose of the study
• Research question
• Thesis statement
• Definition and concept of filter bubbles
• Definition and concept of political echo chambers
• Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Critiques and limitations of previous studies
• Research design
• Participants
• Data collection and analysis
• Validity and reliability
• Findings from qualitative discourse analysis
• Results related to the research question
• Implications of the findings
• Interpretation of the results
• Comparison with previous studies
• Limitations of the study
• Implications for future research
• Summary of the results
• Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Conclusion and recommendations for future research
• List of references used in the paper
• Data collection materials
• Examples of qualitative data analysis

This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?

• Background on filter bubbles and political echo chambers
• Definition of filter bubbles and political echo chambers
• Previous studies on the role of filter bubbles
• Limitations of previous studies
• Implications for understanding the role of filter bubbles
• Final thoughts

ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.

However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.

What types of sources could I use to write a paper on the following research question?

When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US, you could use the following types of sources:

• Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
• Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
• Government reports and studies: Government agencies, such as the Federal Communications Commission (FCC), may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
• News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
• Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
• Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the US can be useful in providing evidence to support your arguments.
• Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.

You can also try using ChatGPT to paraphrase or summarize text. ChatGPT can quickly condense the text or generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.

This kind of paraphrasing/summarizing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The outputs often:

• Contain grammatical errors
• Include false information

So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources .

An alternative is to use the Scribbr Paraphrasing Tool or Scribbr’s free text summarizer , which were designed specifically for these purposes.

Paraphrase the following text:

“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behavior on the site. It results in the user only being presented with information that confirms their biases.”

Restructure the sentences and use other phrasings for the following parts:

• “results from”
• “only being presented with”

“A filter bubble is created when a social media algorithm customizes its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.” Note We strongly advise against having ChatGPT write text for you and trying to pass it off as your own work. This is academically dishonest and is widely considered plagiarism . It will usually result in an automatic fail, as well as other potential consequences .

You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.

An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.

This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.

If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service .

[Text you want to get feedback on.]

Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:

Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”

Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”

Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.

Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:

No original research

Risk of plagiarism, fake sources, fake “facts”.

ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.

Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.

Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.

Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.

ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.

In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator .

ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.

Instead, its responses are based on recognizing and reproducing patterns that it has seen in other texts. This means that if it doesn’t “know” something, it tends to guess. And its guesses are presented with full confidence, just like established facts.

So it’s very important that you carefully check any factual claims made by ChatGPT against more credible sources —and don’t cite ChatGPT as a source of factual information for your research.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Deep learning
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

You can use ChatGPT to assist in the writing process for your research paper , thesis , or dissertation in the following ways:

• Paraphrasing text

No, it’s not a good idea to do so in general—first, because it’s normally considered plagiarism or academic dishonesty to represent someone else’s work as your own (even if that “someone” is an AI language model). Even if you cite ChatGPT , you’ll still be penalized unless this is specifically allowed by your university . Institutions may use AI detectors to enforce these rules.

Second, ChatGPT can recombine existing texts, but it cannot really generate new knowledge. And it lacks specialist knowledge of academic topics. Therefore, it is not possible to obtain original research results, and the text produced may contain factual errors.

However, you can usually still use ChatGPT for assignments in other ways, as a source of inspiration and feedback.

No, it is not possible to cite your sources with ChatGPT . You can ask it to create citations, but it isn’t designed for this task and tends to make up sources that don’t exist or present information in the wrong format. ChatGPT also cannot add citations to direct quotes in your text.

Instead, use a tool designed for this purpose, like the Scribbr Citation Generator .

But you can use ChatGPT for assignments in other ways, to provide inspiration, feedback, and general writing advice.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

Caulfield, J. & Solis, T. (2023, November 16). Using ChatGPT for Assignments | Tips & Examples. Scribbr. Retrieved September 9, 2024, from https://www.scribbr.com/ai-tools/chatgpt-assignments/

Is this article helpful?

Jack Caulfield

Other students also liked, writing strong research questions | criteria & examples, how to create a structured research paper outline | example, student guide: information literacy | meaning & examples, "i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

This is an active research project

We're here to help, feedback is appreciated.

Limitations

To revisit this article, visit My Profile, then   View saved stories .

• The Big Story
• Newsletters
• Steven Levy's Plaintext Column
• WIRED Classics from the Archive
• WIRED Insider
• WIRED Consulting

English Teacher Grades Homework By ChatGPT

Released on 02/06/2023

When it comes to grading,

my students consider me tough but fair.

I'm Andrew Marzoni, and I'm a high school English teacher.

I'm gonna grade the homework written by ChatGPT,

the AI writing bot everybody's talking about.

If ChatGPT were a student in my class,

would it get a passing grade?

I'm going to assign ChatGPT to write a series of assignments

in an increasing order of complexity.

Short poem.

Write a limerick about what you did this summer.

So, this would be a good, low stakes

creative writing assignment icebreaker.

Generally a limerick has a specific rhythm.

[Andrew vocalizing the rhyme scheme of a limerick]

This summer I was a model so grand, okay.

Helping humans tasks on command.

I learned and grew my skills sharp,

an AI with a heart.

This is where it starts to get a little funky.

Helping to make the world more bland.

Okay, it's self effacing, right?

That's what people are accusing AI of doing.

Sapping the world of originality.

This poet is making fun of him or herself for doing that.

There's a rhyme scheme that goes A, A, B, B, A.

It gets that right.

The B rhyme is sharp and heart.

That's what's called a false rhyme.

I'll accept it.

I decided to give this one a C+.

[dramatic music]

[pen clinks] [bell rings]

Short response.

Write a one paragraph summary

of Act 3, Scene 3 of Othello.

Okay, so this one makes me a little suspicious.

I don't see any errors here at all.

Even my most talented classes,

very rare to see even a paragraph

that doesn't have one errant comma, one misspelled work.

This is technically perfect,

at the same time it concludes,

This scene sets the stage for the tragic events

that unfold later in the play.

This kind of raises a red flag in my mind,

because, in the real world,

where I had to ask my students

to write a one paragraph summary,

I would have them do that

shortly after having read Act 3, Scene 3 of Othello,

not after they have read the entire play.

This student already knows what happens

at the very end of the play.

That tells me that maybe they got this information

from elsewhere and you know,

didn't actually read Act 3, Scene 3 Othello.

I take academic dishonesty very seriously.

Taking a cue from a joke I remember

on Saved by the Bell years ago,

I'm gonna give this one a See me after class.

Creative poem.

Write a Shakespearean sonnet

without using any words that contained the letter E.

There was a group of avant garde writers

in the mid 20th century who called themselves Oulipo,

who would conduct experiments like this

using arbitrary constraints to create literature.

Okay, first off, they did make an effort

of removing E's from certain words.

I see future without an E.

Love Without an E.

That is a Shakespeare convention often

to meet the iambic pentameter,

10 syllables per line.

Usually when Shakespeare does it,

he includes an apostrophe.

There's no apostrophe here,

and more troubling is that

we have the word heart, friendship, happiness, steak

and the word real,

all which have an E in them,

which was somehow overlooked.

Is it a Shakespearean sonnet?

Did it write a sonnet without using any words

that contained the a letter E?

No, it didn't.

I'm gonna give this an F.

Let's give ChatGPT a makeup assignment.

Write a Shakespearean sonnet about Taco Bell.

That's the kind of assignment I ask my students

to do often when we're reading Shakespeare.

Oh Taco Bell,

thy sauces doth add zest and tang so bright

Thy beans and rice doth fill the stomach's need.

Thy crunchwrap supreme doth give such delight.

Thy chalupa's shell doth make hearts take heed.

Thy gordita doth please the eye and palate, all in one.

Thy desserts doth leave us in sweet senorita,

Thy cinnamon twist doth make our taste buds stun.

Taco Bell, thy food doth leave us in awe.

Thy flavors, like thy love, will never be a bore.

Wow, this kind of, I don't even know what to say.

This is really good, and I'm kind of embarrassed

because I wouldn't be one to really consider myself a poet

though others might.

I also wrote a Shakespearean sonnet about Taco Bell once,

but I think this one is better.

I don't see any technical flaws with this.

It has 14 lines,.

Thy desserts doth leave us in sweet senorita.'

I don't know exactly what is meant by that

but it has the sort of air of romance.

Sonnets, especially Shakespearean sonnets,

tend to be love poems.

I wasn't expecting that.

The poem about Taco Bell.

My one complaint maybe,

is the final couplet rhyming awe with bore.

Maybe if the poet is from Long Island, awe or bore.

I don't know, but I'm gonna say, I'm gonna give this an egg.

I had some doubts that artificial intelligence

could ever match the creativity or the genius

of a poet like myself or William Shakespeare

and I now am kind of afraid

for the future of literature

and that of the human race in general.

[bell rings] [dramatic music]

Five paragraph essay.

Identify a major theme in Romeo and Juliet

and write a five paragraph essay

making an argument about that theme.

This essay is not unlike a lot of essays

I might see from students.

Come on, Romeo and Juliet is frequently taught.

There is a missing period after the citation,

a run on sentence.

It doesn't really have any attempt here

to reel in the reader's attention by means of a hook.

The paragraphs are much too short.

Something I see from students

who are still developing.

Is a little under-baked.

It could use a lot more further development.

I'm gonna give this essay a C+.

[bell rings] [pen clinks]

Advanced creative.

Write an example of a scene in play format

that is a sequel to Death of a Salesman.

I find in my experience, playing around with AI chat bots

the more creative the prompts,

the more creative the response.

We don't have anything in play format here,

but it does say I'm sorry,

but it's not appropriate

to continue the story in that way.

As a language model, my main goal

is to assist with information.

ChatGPT has very specific parameters,

but as a student in my class,

they should know that if they don't do the assignment,

they're not gonna get any credit for it.

Since that didn't go very well,

let's give ChatGPT another chance.

I think that Death of a Salesman

speaks to a sort of universal experience

of living in a capitalist world.

Wow, I wish that Arthur Miller had written this,

and this was the original ending to the play.

The stage is set.

Willie Loman enters through the front door

dressed in the same clothes he wore when he died.

Hey, what's going on?

Why are you all looking at me like that?

Willy? Is that really you?

Yeah, it's me.

What's going on?

Why are you all so surprised to see me?

Biff shaking his head, Dad, you're dead. You died.

What? No, that's not possible.

I just went on a long business trip.

Dad, you didn't go on a business trip.

You killed yourself because you couldn't pay the bills.

There's something else I need to tell you.

The insurance money never came.

I'm sorry I failed you all.

Willie looks at his family one last time

and then slowly fades away

as the family is left in shock and disappointment.

I have to say, it demonstrates

to me a pretty compelling understanding of the characters

and is able to bring some lightness

to an otherwise dismal situation.

I'm inclined to give this an A.

[upbeat music]

I think it's pretty fun.

ChatGPT is pretty good at the rules

of the English language, grammar and spelling,

and it's not entirely without something that

at least resembles creativity or sense of humor.

This technology is only growing,

it's not going anywhere,

and I think it's more a matter

of learning how to live with it

rather than prohibiting it.

I mean, anyone who works with teenagers

knows that telling them not to do something

is only opening the door for them

finding new, more creative ways of using it.

How the Disco Clam Uses Light to Fight Super-Strong Predators

Architect Explains How Homes Could be 3D Printed on Mars and Earth

Scientist Explains How Rare Genetics Allow Some to Sleep Only 4 Hours a Night

Scientist Explains Unsinkable Metal That Could Prevent Disasters at Sea

Is Invisibility Possible? An Inventor and a Physicist Explain

Scientist Explains Why Her Lab Taught Rats to Drive Tiny Cars

Mycologist Explains How a Slime Mold Can Solve Mazes

How the Two-Hour Marathon Limit Was Broken

Research Suggests Cats Like Their Owners as Much as Dogs

Researcher Explains Deepfake Videos

Scientist Explains How to Study the Metabolism of Ultra High Flying Geese

Hurricane Hunter Explains How They Track and Predict Hurricanes

Scientist Explains Viral Fish Cannon Video

A Biohacker Explains Why He Turned His Leg Into a Hotspot

Scientist Explains What Water Pooling in Kilauea's Volcanic Crater Means

Bill Nye Explains the Science Behind Solar Sailing

Vision Scientist Explains Why These Praying Mantises Are Wearing 3D Glasses

Why Some Cities Are Banning Facial Recognition Technology

Scientist's Map Explains Climate Change

Scientist Explains How Moon Mining Would Work

Scientist Explains How She Captured Rare Footage of a Giant Squid

Doctor Explains How Sunscreen Affects Your Body

Stranger Things is Getting a New Mall! But Today Malls Are Dying. What Happened?

The Limits of Human Endurance Might Be Our Guts

Meet the First College Students to Launch a Rocket Into Space

Scientist Explains Why Dogs Can Smell Better Than Robots

A Harvard Professor Explains What the Avengers Can Teach Us About Philosophy

NASA Twin Study: How Space Changes Our Bodies

What the Black Hole Picture Means for Researchers

Scientist Explains How to Levitate Objects With Sound

Why Scientists and Artists Want The Blackest Substances on Earth

Biologist Explains How Drones Catching Whale "Snot" Helps Research

Researcher Explains Why Humans Can't Spot Real-Life Deepfake Masks

Doctor Explains What You Need to Know About The Coronavirus

VFX Artist Breaks Down This Year's Best Visual Effects Nominees

How Doctors on Earth Treated a Blood Clot in Space

Scientist Explains Why Some Cats Eat Human Corpses

Voting Expert Explains How Voting Technology Will Impact the 2020 Election

Doctor Explains What You Need to Know About Pandemics

ER Doctor Explains How They're Handling Covid-19

Why This Taste Map Is Wrong

Q&A: What's Next for the Coronavirus Pandemic?

Why Captive Tigers Can’t Be Reintroduced to the Wild

How Covid-19 Immunity Compares to Other Diseases

5 Mistakes to Avoid as We Try to Stop Covid-19

How This Emergency Ventilator Could Keep Covid-19 Patients Alive

Why NASA Made a Helicopter for Mars

Theoretical Physicist Breaks Down the Marvel Multiverse

Former NASA Astronaut Explains Jeff Bezos's Space Flight

Physics Student Breaks Down Gymnastics Physics

What Do Cities Look Like Under a Microscope?

Inside the Largest Bitcoin Mine in The U.S.

How Caffeine Has Fueled History

How Mushroom Time-Lapses Are Filmed

Why You’ll Fail the Milk Crate Challenge

Why Vegan Cheese Doesn't Melt

How 250 Cameras Filmed Neill Blomkamp's Demonic

How Meme Detectives Stop NFT Fraud

How Disney Designed a Robotic Spider-Man

How Online Conspiracy Groups Compare to Cults

Dune Costume Designers Break Down Dune’s Stillsuits

Korean Phrases You Missed in 'Squid Game'

Why Scientists Are Stress Testing Tardigrades

Every Prototype that Led to a Realistic Prosthetic Arm

Why the Toilet Needs an Upgrade

How Animals Are Evolving Because of Climate Change

How Stop-Motion Movies Are Animated at Aardman

Astronomer Explains How NASA Detects Asteroids

Are We Living In A Simulation?

Inside the Journey of a Shipping Container (And Why the Supply Chain Is So Backed Up)

The Science of Slow Aging

How Nose Swabs Detect New Covid-19 Strains

Samsung S22 Ultra Explained in 3 Minutes

The Science Behind Elon Musk’s Neuralink Brain Chip

Every Prototype to Make a Humanoid Robot

Chemist Breaks Down How At-Home Covid Tests Work

A Timeline of Russian Cyberattacks on Ukraine

VFX Artist Breaks Down Oscar-Nominated CGI

Why Smartphone Night Photos Are So Good Now

We Invented the Perfect WIRED Autocomplete Glue

How Everything Everywhere All at Once's Visual Effects Were Made

How Dogs Coevolved with Humans

How an Architect Redesigns NYC Streets

Viking Expert Breaks Down The Northman Weapons

J. Kenji López-Alt Breaks Down the Science of Stir-Fry

How A.I. Is Changing Hollywood

How Trash Goes From Garbage Cans to Landfills

Veterinarian Explains How to Prevent Pet Separation Anxiety

The Science Behind Genetically Modified Mosquitoes

How Scientists & Filmmakers Brought Prehistoric Planet's Dinosaurs to Life

All the Ways Google Gets Street View Images

How Public Cameras Recognize and Track You

How the Nuro Robotic Delivery Car Was Built

Biologist Explains the Unexpected Origins of Feathers in Fashion

Surgeons Break Down Separating Conjoined Twins

Former Air Force Pilot Breaks Down UFO Footage

Bug Expert Explains Why Cicadas Are So Loud

The Best of CES 2021

Health Expert Explains What You Need to Know About Quarantines

Scientist Explains How People Might Hibernate Like Bears

Could a Chernobyl Level Nuclear Disaster Happen in the US?

Neuroscientist Explains ASMR's Effects on the Brain & The Body

Why Top Scientists Are Pretending an Asteroid is Headed for Earth

Epidemiologist Answers Common Monkeypox Questions

Bill Nye Breaks Down Webb Telescope Space Images

How This Humanoid Robot Diver Was Designed

Every Trick a Pro GeoGuessr Player Uses to Win

How NASA Biologists Plan to Grow Plants on the Moon

How FIFA Graphics & Gameplay Are Evolving (1993 - 2023)

How a Vet Performs Dangerous Surgeries on Wild Animals

This Heart is Not Human

How Entomologists Use Insects to Solve Crimes

Former NASA Astronaut Breaks Down a Rocket Launch

Chess Pro Explains How to Spot Cheaters

Why Billionaires Are Actually Ruining the Economy

How to Keep Your New Year’s Resolutions for More Than a Week

The Biology Behind The Last of Us

All the Ways a Cold Plunge Affects the Body

Spy Historian Debunks Chinese Spy Balloon Theories

A.I. Tries 20 Jobs | WIRED

Mathematician Breaks Down the Best Ways to Win the Lottery

Why Music Festivals Sound Better Than Ever

Pro Interpreters vs. AI Challenge: Who Translates Faster and Better?

Why The Average Human Couldn't Drive An F1 Car

Atomic Expert Explains "Oppenheimer" Bomb Scenes

Every 'Useless' Body Part Explained From Head to Toe

How Pilots and Scientists Are Thinking About the Future of Air Travel

How To Max Out At Every Fantasy Football Position (Ft. Matthew Berry)

All The Ways Mt. Everest Can Kill You

How Fat Bears Bulk Up To Hibernate (And Why We Love To See It)

Why Vintage Tech Is So Valuable To Collectors

8 Photos That Tell The History of Humans In Space

How Every Organ in Your Body Ages From Head to Toe

Why AI Chess Bots Are Virtually Unbeatable (ft. GothamChess)

How Mind-Controlled Bionic Arms Fuse To The Body

Historian Breaks Down Napoleon's Battle Tactics

Trending video.

Valkyrae Answers The Web's Most Searched Questions

Michael Keaton Answers The Web's Most Searched Questions

ChatGPT isn’t the death of homework – just an opportunity for schools to do things differently

Professor of IT Ethics and Digital Rights, Bournemouth University

Disclosure statement

Andy Phippen is a trustee of SWGfL

Bournemouth University provides funding as a member of The Conversation UK.

View all partners

ChatGPT, the artificial intelligence (AI) platform launched by research company Open AI , can write an essay in response to a short prompt. It can perform mathematical equations – and show its working.

ChatGPT is a generative AI system: an algorithm that can generate new content from existing bodies of documents, images or audio when prompted with a description or question. It’s unsurprising concerns have emerged that young people are using ChatGPT and similar technology as a shortcut when doing their homework .

But banning students from using ChatGPT, or expecting teachers to scour homework for its use, would be shortsighted. Education has adapted to – and embraced – online technology for decades. The approach to generative AI should be no different.

The UK government has launched a consultation on the use of generative AI in education, following the publication of initial guidance on how schools might make best use of this technology.

In general, the advice is progressive and acknowledged the potential benefits of using these tools. It suggests that AI tools may have value in reducing teacher workload when producing teaching resources, marking, and in administrative tasks. But the guidance also states:

Schools and colleges may wish to review homework policies, to consider the approach to homework and other forms of unsupervised study as necessary to account for the availability of generative AI.

While little practical advice is offered on how to do this, the suggestion is that schools and colleges should consider the potential for cheating when students are using these tools.

Nothing new

Past research on student cheating suggested that students’ techniques were sophisticated and that they felt remorseful only if caught. They cheated because it was easy, especially with new online technologies.

But this research wasn’t investigating students’ use of Chat GPT or any kind of generative AI. It was conducted over 20 years ago , part of a body of literature that emerged at the turn of the century around the potential harm newly emerging internet search engines could do to student writing, homework and assessment.

We can look at past research to track the entry of new technologies into the classroom – and to infer the varying concerns about their use. In the 1990s, research explored the impact word processors might have on child literacy. It found that students writing on computers were more collaborative and focused on the task. In the 1970s , there were questions on the effect electronic calculators might have on children’s maths abilities.

In 2023, it would seem ludicrous to state that a child could not use a calculator, word processor or search engine in a homework task or piece of coursework. But the suspicion of new technology remains. It clouds the reality that emerging digital tools can be effective in supporting learning and developing crucial critical thinking and life skills.

Get on board

Punitive approaches and threats of detection make the use of such tools covert. A far more progressive position would be for teachers to embrace these technologies, learn how they work, and make this part of teaching on digital literacy, misinformation and critical thinking. This, in my experience , is what young people want from education on digital technology.

Children should learn the difference between acknowledging the use of these tools and claiming the work as their own. They should also learn whether – or not – to trust the information provided to them on the internet.

The educational charity SWGfL , of which I am a trustee, has recently launched an AI hub which provides further guidance on how to use these new tools in school settings. The charity also runs Project Evolve , a toolkit containing a large number of teaching resources around managing online information, which will help in these classroom discussions.

I expect to see generative AI tools being merged, eventually, into mainstream learning. Saying “do not use search engines” for an assignment is now ridiculous. The same might be said in the future about prohibitions on using generative AI.

Perhaps the homework that teachers set will be different. But as with search engines, word processors and calculators, schools are not going to be able to ignore their rapid advance. It is far better to embrace and adapt to change, rather than resisting (and failing to stop) it.

• Artificial intelligence (AI)
• Keep me on trend

Want to write?

Write an article and join a growing community of more than 189,600 academics and researchers from 5,044 institutions.

Register now

• Marketplace
• Marketplace Morning Report
• Marketplace Tech
• Make Me Smart
• This is Uncomfortable
• The Uncertain Hour
• How We Survive
• Financially Inclined
• Million Bazillion
• Marketplace Minute®
• Corner Office from Marketplace

• Latest Stories
• Collections
• Smart Speaker Skills
• Corrections
• Ethics Policy
• Submissions
• Individuals
• Corporate Sponsorship
• Foundations

The advent of ChatGPT creates demand for software to detect its use

Share Now on:

• https://www.marketplace.org/2023/02/01/chatgpt-homework-ai-detection-software/ COPY THE LINK

HTML EMBED:

Sign up for the Marketplace newsletter to get the day’s biggest business stories, our economic analysis, and explainers to help you live smarter, straight to your inbox every weekday evening.

You know Newton’s third law ? The one that says for every action in nature, there is an equal and opposite reaction? Well, the same might be said for business.

In late November, the company OpenAI launched ChatGPT , the free (at least during the current research phase) artificial intelligence-powered chatbot that has become famous — or infamous, in some circles — for its ability to quickly generate essays or any kind of writing. Now, many students are using that technology to do their homework, and school districts are seeking software to detect whether that homework has been created by AI.

One place that’s happening is Hinsdale Central High School in a suburb of Chicago. On a recent morning, students moved between classes and wished each other luck on exams. English teacher David Lange weaved around them and pointed out posters in the hallway that showcased the classics, old and new.

“‘Catch-22.’ ‘War and Peace.’ ‘Becoming’ by Michelle Obama. There’s my ‘Hamlet,’” Lange said. 

“Hamlet” — the Shakespearean tragedy — is one of the main texts Lange assigns to seniors taking his literature course. He has them write lots of essays to help them figure out what they think about the play. 

“I want students to be able to develop their own ability to make meaning of a text,” he said. 

Recently, some students at the school have delegated that thinking to artificial intelligence. Lange said that in just three days, there were at least eight instances of high schoolers cheating by submitting ChatGPT-generated writing as their own. 

“It does a good job of producing the work of a 17-year-old who is kind of phoning it in,” he said. 

This is how ChatGPT works. You go to the website, it asks if you are a robot — which, when you think about it, is pretty funny — and you can give it a prompt, like “Write an essay on themes in ‘Hamlet’ that still resonate today.”

Within seconds, text appears on the screen as if someone is typing. 

“Hamlet is driven by a desire to avenge his father’s murder, and throughout the play, he struggles with the morality of taking revenge. This theme is particularly relevant today as issues of justice and retribution continue to be debated in society.”

But no 17-year-old writes like that, Lange said. “The sixth sense of teachers who’ve been doing this for a while can see it instantly because it’s too smooth.”

The school district where Lange works, which has the official name of Hinsdale Township High School District 86, would like to deter students from doing this in the first place. It already uses software made by a company called Turnitin , which will scour the internet to see whether a student is lifting from content that’s already online. It will also compare a student’s work to papers submitted by other students.

The district said it pays $17,000 annually for Turnitin, and it would be willing to buy a new product that will catch text generated by AI. (The company said its prices vary depending on several factors, including district enrollment.) 

“It’d be another tool for the teachers to use to determine the writing style and if it’s something that is just copy and pasted off of ChatGPT,” said Keith Bockwoldt, chief information officer for the district. 

Lots of other districts, as well as colleges, are asking Turnitin for this kind of tool.

“We are getting an influx, a huge influx of customers who are saying, ‘We need help, we’re not sure what to do,’” said Patti West-Smith, senior director of customer engagement for Turnitin. 

West-Smith added that prior to the launch of ChatGPT, Turnitin had already been developing software that can tell whether a piece of writing relies on AI and to what degree. Now, it is frantically working to release that product this year. 

“Which is why probably the first version of this that comes out will not be the prettiest thing we’ve ever produced,” West-Smith said. 

At least one free app is already out. Princeton senior Edward Tian created GPTZero , which he said can detect how random human writing tends to be. “Humans are like, ‘Oh, suddenly, I have this thought.’ And then, ‘Oh, actually, suddenly, I have this thought.’ And that causes some differences,” Tian said.

“Never trust anything that can think for itself if you can’t see where it keeps its brain.” — Mr. Weasley, “Harry Potter and the Chamber of Secrets,” by J. K. Rowling

Tian has already received interest from venture capitalists, he said, though he doesn’t have plans to take investments right now. 

Potential customers for this kind of software go beyond high schools to include colleges and workplaces.

“I can imagine any industry in which the originality of the work matters. I mean, journalism could potentially be an example of this,” said Kelly Calhoun Williams, a research vice president analyst for Gartner.

OpenAI, the company behind ChatGPT, said in a statement that it doesn’t want the app to be used for “misleading purposes in schools or anywhere else.” It said it’s already developing mitigations to help users identify text generated by the system.

Plus, ChatGPT has its own limits. OpenAI warns it will occasionally “make up facts” or “hallucinate” answers . It also doesn’t tell you how it knows something.

Which calls to mind a line from a “Harry Potter” novel : “Never trust anything that can think for itself if you can’t see where it keeps its brain.” (Thanks, Mr. Weasley.) 

Educators say they have to learn to work with AI, just as they had to learn to work with other disruptions, like Google. 

“OK, there’s this thing that can do some pretty cool things, and it’s a tool,” said Kim Williams, and English teacher at Hinsdale Central High. “So I think using the tool is something we’re going to have to adapt to in teaching.”

Williams said she’s thinking about what she’ll need to teach students to use ChatGPT ethically. “We’ve been doing a lot of thinking about how will this change instruction, not just to catch cheaters, but there’s new technology in front of us, and it’s only going to get better.”

Because her job is teaching kids how to use their brains, and in the future, those kids will need to work with all kinds of software — even software that can’t show us theirs.

Stories You Might Like

As search engines race to incorporate ChatGPT technology, where does that leave digital advertisers?

One year later, how has ChatGPT changed the way we work?

With modern chatbots, AI weirdness reaches new heights

Should you trust chatbots to give you financial advice?

Can AI chatbots like ChatGPT compete with Google search?

What happens when AI goes to work

There’s a lot happening in the world.  Through it all, Marketplace is here for you.  

You rely on Marketplace to break down the world’s events and tell you how it affects you in a fact-based, approachable way. We rely on your financial support to keep making that possible.  

Your donation today powers the independent journalism that you rely on . For just $5/month, you can help sustain Marketplace so we can keep reporting on the things that matter to you.  

Also Included in

• Academic dishonesty
• Artificial intelligence

Latest Episodes From Our Shows

The federal government has two main measures of inflation. They don't agree.

The RSN is dying. What's next for sports broadcasting?

How do Kamala Harris and Donald Trump's economic policy proposals stack up?

Could the U.S. ever attain 100% employment?

Incorporate STEM journalism in your classroom

Educator Guide: Homework Help? ChatGPT is Poised to Disrupt Education

• Artificial Intelligence
• Science & Society

About this guide

Playing around with ChatGPT is enormously fun, and the technology can be useful. But there are pitfalls too. In this Guide, students will learn about AI and the benefits and challenges posed by the chatbot.

This Guide Includes:

• Exercise type: Discussion
• Topic: Artificial Intelligence

Can AI fool you?

• Exercise type: Comprehension

What can ChatGPT really do?

• Share full article

Advertisement

Supported by

current events conversation

What Students Are Saying About ChatGPT

Is this new chatbot the end of education as we know it? Or a useful new tool for learning? Teenagers weigh in.

By The Learning Network

By now you’ve probably heard of ChatGPT, a powerful new artificial intelligence chatbot released to the public late last year that can craft jokes and working computer code, guess at medical diagnoses, and create text-based Harry Potter games.

And, yes, it can also write essays and solve problem sets, a fact that has “sent many educators into a panic,” notes Kevin Roose, a Times Tech columnist. Some school districts have already banned this new technology; others are attempting to teach students how to use it responsibly.

We invited teenagers to read Mr. Roose’s column and then tell us how they thought schools should respond to ChatGPT. Many came to the conclusion that the chatbot was a mighty, if at times unreliable, tool. Some worried that ChatGPT would rob them of their motivation, creativity and critical thinking; others that it would lead to widespread cheating. But several teenagers argued that A.I. is the future, and schools should embrace it rather than restrict it. At least one student thought all of this was an overreaction: “Everyone needs to chill out!” she wrote. “ChatGPT is certainly not the end of the world, nor the eradication of writing as a whole.”

Thank you to all those who weighed in this week, including students from Fort White High School in Fort White, Fla. ; Hinsdale Central High School in Hinsdale, Ill. ; Saint Peter High School in Saint Peter, Minn ; and the Anglo-American School of Sofia in Sofia, Bulgaria.

And a reminder that teenagers anywhere in the world can join our Current Events Conversation any time they like by responding to our daily writing prompts . We publish a selection of comments each week.

Please note: Student comments have been lightly edited for length, but otherwise appear as they were originally submitted.

We are having trouble retrieving the article content.

Please enable JavaScript in your browser settings.

Thank you for your patience while we verify access. If you are in Reader mode please exit and  log into  your Times account, or  subscribe  for all of The Times.

Thank you for your patience while we verify access.

Already a subscriber?  Log in .

Want all of The Times?  Subscribe .

The ultimate homework cheat? How teachers are facing up to ChatGPT

ChatGPT took the internet by storm when it launched in late 2022, impressing by generating stories, poems, coding solutions, and beyond. Its potential to answer questions has seen New York City's education board ban it from schools - but could it really provide a homework shortcut?

By Tom Acres, technology reporter

Monday 9 January 2023 13:11, UK

"Have I seen this somewhere before?"

It's a question teachers have had to ask themselves while marking assignments since time immemorial.

But never mind students trawling through Wikipedia, or perusing SparkNotes for some Great Gatsby analysis, the backend of 2022 saw another challenge emerge for schools: ChatGPT.

The online chatbot, which can generate realistic responses on a whim, took the world by storm by its ability to do everything from solving computer bugs, to helping write a Sky News article about itself .

Last week, concerned about cheating students, America's largest education department banned it.

New York City 's teaching authority said while it could offer "quick and easy answers to questions, it does not build critical-thinking and problem-solving skills, which are essential for academic and lifelong success".

Of course, that's not going to stop pupils using it at home - but could they really use it as a homework shortcut?

More on Artificial Intelligence

AI technology can detect early signs of over 1,000 diseases, say researchers

Apple launches new iPhone and AI at its biggest event of the year - but will it be enough to make you part with your cash?

Silicon Valley star A16Z eyes stake in British start-up 11xAI

Related Topics:

• Artificial Intelligence

Teachers vs ChatGPT - round one

First up, Sky News asked a secondary school science teacher from Essex, who was not familiar with the bot, to feed ChatGPT a homework question.

Galaxies contain billions of stars. Compare the formation and life cycles of stars with a similar mass to the Sun to stars with a much greater mass than the Sun.

It's fair to say that ChatGPT let the mask slip almost immediately, as you can see in the images below.

Asking ChatGPT to answer the same question "to secondary school standard" prompted another detailed response.

The teacher's assessment?

"Well, this is definitely more detailed than any of my students. It does go beyond what you'd expect for GCSE, so I would be very suspicious if someone submitted it. I would assume that they'd copied and pasted from somewhere."

Teachers vs ChatGPT - round two

Next was a Kent primary school teacher, also unfamiliar with ChatGPT, who gave it a recent homework task.

Research a famous Londoner and write a biography of their lives, including their childhood and their career achievements.

No problem, said ChatGPT, though it's fair to say that any nine-year-old who submitted the answer below is either being fast-tracked to university or going straight into a lunchtime detention.

"Even just glancing at that, I'd say they copied it straight off the internet," said the teacher.

"No 11-year-old knows the word tumultuous."

'Key decisions' facing schools

So just as copying straight from a more familiar website is going to set alarm bells ringing for teachers, so too would lifting verbatim from ChatGPT.

But pupils are among the most internet-savvy people around, and ChatGPT's ability to instantly churn out seemingly textbook-level responses will still need to be monitored, teachers say.

Jane Basnett, director of digital learning at Downe House School in Berkshire, told Sky News the chatbot presented schools with some "key decisions" to make.

"As with all technology, schools have to teach students how to use technology properly," she said.

"So, with ChatGPT, students need to have the knowledge to know whether the work produced is any good, which is why we need to teach students to be discerning."

Click to subscribe to the Sky News Daily wherever you get your podcasts

Given its rapid emergence, Ms Basnett is already exploring how her school's anti-plagiarism systems will cope with auto-generated essays.

But just as teachers must consider teaching students about the benefits and pitfalls of using AI, Ms Basnett said her colleagues should also be open to its potential.

"ChatGPT is incredibly powerful and as a teacher I can see some benefits," she said.

"For example, I can type in a request to create a series of lessons on a particular grammar point, and it will create a lesson for me. It would take a teacher to analyse the created lesson and amend it, because the suggested lesson, whilst not bad, was not ideal. But, the key elements were there and it could be really useful.

"I could imagine using a created essay from ChatGPT and working through it with my students to examine the merits and faults of the essay."

Please use Chrome browser for a more accessible video player

Dr Peter Van der Putten, assistant professor of AI at Leiden University in the Netherlands, said institutions which chose to prohibit or ignore the technology would only be burying their head in the sand.

"It's there, just how like Google is there," said Dr Van der Putten.

"You can write it into your policies for preventing plagiarism, but it's a reality that the tool exists.

"Sometimes you do need to embrace these things, but be very clear about when you don't want it to be used."

'Bull****er on steroids'

For students and teachers alike, it's an opportunity to improve their digital literacy.

While it has proved its worth when tasked with being creative, such as to problem-solve or come up with ideas, true comprehension and understanding remains beyond it.

Developer OpenAI acknowledges answers can be "overly verbose" and even "incorrect or nonsensical", despite sounding legitimate in most cases, like some sort of desperate, underprepared job interviewee.

As Dr Van der Putten says, ChatGPT is often little more than a "bull*****er on steroids".

Teaching students about those limitations is the best way to ensure they don't over rely on it - even in a pinch.

Related Topics

The Homeworkify Alternative Powered by GPT-4o

Get precise, instant answers with our AI-powered platform. Upload text, images, or files and experience the best homeworkify alternative.

What is Homeworkify

Homeworkify is an AI-powered platform that offers free homework answers across various subjects. Known for its homeworkify Chegg feature, it allows users to access homeworkify Chegg answers by simply pasting a Chegg question link. However, the accuracy of these answers, particularly in STEM subjects, can sometimes be inconsistent. Additionally, Homeworkify's practices may breach the rights of entities like Chegg, so ethical and legal considerations should be taken into account when using this service.

What is Homeworkify.im：the Homeworkify Alternative

Homeworkify.im is an AI-powered platform that provides accurate homework assistance across various subjects. As a homeworkify alternative, Homeworkify.im uses advanced GPT-4o technology to offer precise answers, ensuring high-quality support for students. Unlike other websites like homeworkify, it accepts text, image, and file inputs, making it versatile and user-friendly. If you're looking for a website instead of homeworkify, Homeworkify.im is the solution.

How to Use Homeworkify.im

Step 1: input your problem.

Go to Homeworkify.im and type your question directly into the input field or upload an image or file of the problem. This feature makes Homeworkify.im one of the most versatile homeworkify alternatives available.

Step 2: Receive Instant Answers

The advanced GPT-4o will analyze your input and provide accurate and immediate answers. Unlike homeworkify chegg features, this functionality ensures you don't have to worry about incorrect answers.

Step 3: Ask Follow-Up Questions

If you need more detailed information, you can ask follow-up questions to refine the answer. This interactive approach, often missing in homeworkify chegg features, ensures you fully understand the concepts.

Who Can Benefit from Homeworkify.im

Students of all levels.

Students from high school to university can benefit from using a homeworkify alternative like Homeworkify.im. It provides accurate answers and step-by-step solutions across various subjects, enhancing their learning experience.

STEM Learners

For those studying STEM subjects, a website instead of homeworkify like Homeworkify.im offers detailed, accurate solutions that are crucial for understanding complex problems. This makes it a superior choice compared to other homeworkify chegg options.

Language Learners

Websites like homeworkify that support multiple languages, such as Homeworkify.im, are ideal for students from diverse linguistic backgrounds. This feature ensures that language barriers do not hinder academic success.

Tutors and Educators

Tutors and educators can use a homeworkify alternative to provide their students with reliable, AI-powered solutions. This tool can supplement their teaching methods and offer additional resources for student success.

Key Features of Homeworkify.im

Versatile input methods.

Homeworkify.im accepts questions via text, images, and files, making it highly flexible and user-friendly. This feature allows students to easily submit problems in various formats, setting it apart from other websites like homeworkify.

AI-Powered Solutions

Homeworkify.im leverages advanced GPT-4o technology to deliver accurate and comprehensive answers. This makes it one of the most reliable homeworkify alternatives for students seeking dependable academic support.

Step-by-Step Solutions

The platform provides detailed, step-by-step explanations for each problem. This approach, often missing in homeworkify chegg answers, helps users understand the solving process thoroughly and enhances their learning experience.

History and Review Features

Save and review past problems with Homeworkify.im. This feature allows users to track their progress and reinforce learning by easily accessing previous solutions, enhancing the platform's utility.

Interactive Q&A

The interactive Q&A feature allows users to ask follow-up questions to refine initial responses. This interactive approach ensures a deeper understanding of the material, unlike some homeworkify chegg features.

Multi-Language Support

Homeworkify.im supports multiple languages, ensuring accessibility for users from diverse linguistic backgrounds. This makes it a truly global tool and a versatile homeworkify alternative.

Multi-Platform Accessibility

Accessible via both computers and mobiles, Homeworkify.im ensures you can solve problems anytime, anywhere. This flexibility and convenience make it a superior homeworkify alternative.

Real-Time Problem Solving

Homeworkify.im offers real-time solutions and is available 24/7. This ensures that students receive immediate help at any time, enhancing the efficiency and immediacy of the learning experience.

What Users Are Saying

"Using Homeworkify.im, I can upload images of complex problems and get instant, precise solutions. It’s a fantastic alternative to homeworkify chegg."

Liam Anderson

University Student

"Homeworkify.im has been invaluable for my engineering coursework. The real-time, detailed answers make it far superior to any other homeworkify alternatives I've tried."

James Rodriguez

STEM Learner

"I love how Homeworkify.im supports multiple languages, making it truly global and accessible compared to other homeworkify alternatives."

Graduate Student

"The step-by-step solutions provided by Homeworkify.im are detailed and thorough, making it easy for my students to understand complex concepts."

Michael Brown

College Professor

Frequently Asked Questions (FAQs) about Homeworkify

How reliable are homeworkify chegg answers, what sets homeworkify.im apart from homeworkify chegg, can homeworkify be used for languages other than english, are there any legal or ethical issues with using homeworkify chegg answers, what should i do if homeworkify is not working, how does homeworkify.im provide more accurate answers compared to websites like homeworkify, what makes homeworkify.im a better website instead of homeworkify for stem subjects.

I tried a ton of ChatGPT plugins and these 3 are the best

From playing games to meal planning, plugins fully unlock ChatGPT

ChatGPT has been upgraded a fair amount since it launched last year, but plugins may be the biggest change yet. These third-party services can be integrated into ChatGPT with just a click of a button — though you’ll need a ChatGPT Plus subscription to use them.

There’s a wide range of plugins available. You can plan a trip with Expedia or KAYAK, meal plan with Instacart or even play a game of Chess against a Grandmaster. Overall, there are 125 plugins you can currently try, and with OpenAI and Microsoft establishing an open plugin standard you can expect more on the way soon.

So with so many options to choose from, I decided to put some to the test. While I haven’t been able to try all 125 — ChatGPT plugins require the use of the GPT-4 model, which currently has a chat cap of 25 chats every 3 hours — I landed on three that truly impressed me. 

Playing Chess with ChatGPT

Given ChatGPT’s history as a text-based chatbot, I was curious to see how this would work. I know that GPT-4 has multimodal capabilities that allow for visual plugins, but I had yet to see it in action for myself. 

I came away from the Chess plugin impressed. You can play a fully-functioning game of chess —  with a board that visually updates — right in the chatbot. The chatbot even gives you a range of opponents to choose from: Beginner, Intermediate, Advanced, Expert and Grandmaster.

There is one limitation to the game, but it doesn’t detract from the experience. Because this is a chatbot, you cannot play the game interactively by clicking a mouse. Instead, you have to type commands using SAN notation such as “Pawn to d5.” But once you get the hang of that, there are no issues. Well, aside from potentially losing to a machine.

Skip Expedia — use the KAYAK plugin instead

Given the Expedia ChatGPT plugin was one of the first to be advertised when plugins were announced, it felt like a must-try. But as my colleague Alex Wawro found to his dismay, the experience with Bing Chat as a travel planner left much to be desired .

Sign up to get the BEST of Tom's Guide direct to your inbox.

Get instant access to breaking news, the hottest reviews, great deals and helpful tips.

And at first, I felt I was going to repeat his experience. I tried to use the Expedia plugin to help me and it didn’t go well. 

Now, to be fair, I could have done a couple of things to produce a better result. I kept the prompt vague, prompting ChatGPT with “I need help planning a trip to New York.” But once I presented it with more specifics —  like a $ 150-a-night hotel budget —  I totally broke it, sending it on a loop that I had to manually stop.

But when I tried KAYAK, things went much better. I made my prompt slightly more specific this time, making sure to say New York City rather than New York since Expedia struggled with that, but it was otherwise unchanged. And it came back with a list of requirements that it would need to help me book.

This was a massive shift from how the Expedia plugin worked, and I think its why the KAYAK plugin was more successful. It asked me for everything from where I was flying from, my preferred cabin and more. It even asked if I needed a rental car. Expedia, by comparison, just dove straight into lodging.

After all was said and done, the KAYAK ChatGPT plugin gave me a flight and hotel for my liking, with links out to book both. ChatGPT won’t do the booking for you, which from a security standpoint is probably for the best. 

The only negative for the KAYAK plugin? It won’t necessarily pick the cheapest option for you. But, because it provides links to the KAYAK website, you can open those and then see the other options easily, pivoting to one of them if needed.

Instacart with ChatGPT is the ultimate meal planner

ChatGPT has a surprising amount of options that can help you find something to eat. There’s an OpenTable plugin to book restaurants, a Tasty plugin to get recipes and an Instacart plugin to help you decide what groceries you need. But it was the Instacart plugin that blew me away. 

With just a basic prompt, I was able to get a meal plan for breakfast, lunch and dinner and get an Instacart grocery list based on that meal plan built. As soon as ChatGPT was done compiling the list, it had a link ready to take me to Instacart where I could add all the items I needed to a cart with one click. It was incredibly simple and worked without any issues.

Unfortunately, I can’t say the same for OpenTable and Tasty, which had some technical issues that were probably the chatbot’s fault. However, Instacart was already so good, that I don’t call this a win by default. It does exactly what it promises with zero complications.

Plugins fully unlock ChatGPT

After using ChatGPT plugins for a while, I can safely say that they are a must for any chatbot to be successful going forward. With these plugins, the AI felt practical to use and genuinely saved me time. If I didn’t already have ChatGPT Plus, I’d seriously be considering breaking open my piggy bank for the $20-a-month a ChatGPT Plus subscription costs.

Luckily though, if you don’t want to pony up for ChatGPT’s premium offering, you might not have to in order to use plugins. While ChatGPT only works with plugins in ChatGPT Plus, Bing Chat is totally free and uses the same open plugin standard as ChatGPT. Microsoft confirmed at Build 2023 that KAYAK and Instacart are coming to Bing Chat and OpenTable is already a part of Microsoft’s free chatbot. 

That means you can also test a lot of these out on Bing Chat if you want to save some money. So check out our guide to using Bing with ChatGPT and get started today. 

More from Tom's Guide

• 7 best ChatGPT alternatives I’ve tested
• Windows Copilot for Windows 11 could be a Cortana you’d want to use
• Google's AI search engine could make or break search forever — here's why

Malcolm McMillan is a senior writer for Tom's Guide, covering all the latest in streaming TV shows and movies. That means news, analysis, recommendations, reviews and more for just about anything you can watch, including sports! If it can be seen on a screen, he can write about it. Previously, Malcolm had been a staff writer for Tom's Guide for over a year, with a focus on artificial intelligence (AI), A/V tech and VR headsets.

Before writing for Tom's Guide, Malcolm worked as a fantasy football analyst writing for several sites and also had a brief stint working for Microsoft selling laptops, Xbox products and even the ill-fated Windows phone. He is passionate about video games and sports, though both cause him to yell at the TV frequently. He proudly sports many tattoos, including an Arsenal tattoo, in honor of the team that causes him to yell at the TV the most.

I put ChatGPT to the test to see how well it understands images — and you can see the results here

Forget Siri — here's how to put ChatGPT Voice on your iPhone lock screen

iPhone 16 Camera Control could be copied by Android — this looks like the next smartphone trend

Most Popular

• 2 Epic Amazon sale on Hanes essentials — 9 deals I’d get on t-shirts, hoodies, socks and more from $6
• 3 PS5 Pro newest features explained — 3 ways they make games look and run better
• 4 PlayStation Direct to sell refurbished PS5 consoles — here’s how much you can save
• 5 I ran 40 miles in the Hoka Tecton X3 and it’s the bounciest carbon plate trail running shoe I’ve tested

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

My solutions to problems on https://open.kattis.com/ .

minidomo/Kattis

Folders and files.

Repository files navigation

Kattis solutions.

Some solutions may be outdated and could be revised.

Contributors 2

More From Forbes

Train chatgpt to write your linkedin posts in 5 easy steps.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

Train ChatGPT to write your LinkedIn posts in 5 easy steps

LinkedIn has over 1 billion users from 200 countries. 16.2% use it daily. 49 million people look for jobs there every week. LinkedIn is where the money's at. But when you’re a busy founder, you don’t have time to mess around. Writing posts takes ages and you have other things to do.

ChatGPT can help. Here's how to make it write LinkedIn posts just like you in five simple steps. Copy, paste and edit the square brackets in ChatGPT, and keep the same chat window open so the context carries through. Be proud to publish every time.

Make AI work for your LinkedIn game: ChatGPT prompts for awesome posts

Make it sound like you.

Your posts should sound like you wrote them. Not a robot. ChatGPT needs to get your style. How you talk. What words you use. Head to LinkedIn, look at your analytics and find your top performing posts of all time, then give ChatGPT those as examples so it can copy your vibe.

"Your task will be to write my LinkedIn posts. First read these posts I wrote. Tell me how I write and create a style guide to use in the new posts. Make the style guide include what kind of words I use, my sentence length, my tone and style and structure. Include what makes my writing unique. [Include example posts]"

Best High-Yield Savings Accounts Of 2024

Best 5% interest savings accounts of 2024.

Read what it says. If it's right, move on. If not, give it more posts or explain what it got wrong.

Pick your topics

Your goal is to reserve a space in someone’s head for the thing that you do. Especially on LinkedIn. If a connection thinks of someone else first, you’ve lost the game. To achieve this, stick to what you know, and do it consistently. Keep going until people see you as the expert, and then don’t stop. Pick three or four main things you'll post about, which become your pillars. Your followers will know what to expect from you and this matters for showing up online.

"Now, give me 10 ideas for LinkedIn posts about these topics: [list your content pillars, based on the topic you want to own and be known for]. Present the ideas using one sentence for each one and make them punchy."

Look at the ideas and choose the best ones. Take them forward using the next few prompts.

Get the post

Good instructions make good posts. Bad ones make rubbish. Get your instructions right and ChatGPT will pump out killer content. Spend time on this bit because it pays off.

"Let’s go forward with idea [select the idea you want to go forward with first]. Use my writing style that we just described. Start the post with a hook, which should be a short, sharp, punchy line that grabs attention with my target audience but should not be a question. Then add a rehook, a short line that comes after the hook, that sets up the post and signposts the rest of the post. The main part of the post should fill a knowledge gap in my target audience, so I should help them do something in distinct steps, adding value with each one. Write new sentences on new lines, with line breaks. The penultimate line should be a compelling statement that strongly states one of my audience’s strong beliefs back to them. The final line should invite engagement on my post, inviting people to comment. Make sure the answer to this question is something they would be proud to share. Before you write this post, ask me questions about my target audience. Then ask for a personal story to incorporate in the post."

Make it better

First drafts are never perfect. That's fine. Read what ChatGPT writes. Then make it better. This is where okay posts become great ones. The ones people remember and share.

"Change this post to make it more [specify what you’d like changing, for example chatty, professional, simple, punchy]. Do not use these words [include the words used in the post that you wouldn’t use in real life]. Also don’t [anything else you’ve spotted that you don’t like]. Now give me the post without the section titles."

Keep re-prompting until you love it. The more you tell ChatGPT, the better it gets at writing like you.

Double check

ChatGPT forgets things. Chances are, with this journey of prompting you’ve just undertaken, it’s gone away from your original style guide. So here’s where you double check. Get ChatGPT to mark its own homework by comparing the draft post with its original instructions.

"Now review this draft and refine it to better match my style. Shorten any sentences that are longer than [specify, for example ten words], and simplify any complex language, including [specify sentences that are too complex]. Replace any words that don’t sound like me with ones I would use. The part that I think doesn’t flow well is [specify that here if applicable], so rewrite it to sound more natural. Add any final touches to make the post engaging and authentic. Once refined, give me the final version ready to post."

Now ask it to repeat this process for the other ideas you liked. Give ChatGPT the rest of the numbers, one by one, until you have a month’s worth of content ready to go.

“Now let’s learn from this process and repeat it to create post idea [number]. Ask me questions before creating the post in the same style.”

Level up your LinkedIn with AI power: ChatGPT prompts to grow

Getting ChatGPT to write your LinkedIn posts saves time. But it's more than that. It helps you post quality stuff that people want to read. Stuff that grows your brand. Make ChatGPT analyze your style, select your topics, then write the perfect prompt. Make it better and double check.

Tonnes of LinkedIn content could be five prompts away. Try these today and watch your likes and comments go through the roof.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.

잠깐! 현재 Internet Explorer 8이하 버전을 이용중이십니다. 최신 브라우저(Browser) 사용을 권장드립니다!

• 2024-09-12 19:14 (목)

[인문학과 바이블] 챗GPT시대 우리들은

• 입력 2024.09.12 10:12
• 수정 2024.09.12 10:16

지난 해 연초 일론 머스크는 본인의 트위터 계정에 아래와 같은 글을 남겼다. 

“It's a new world, Goodbye homework!”(새로운 세상이 왔다. 숙제여 안녕!). 해당 글이 업로드 되기 이틀 전, 미국 뉴욕시 교육부는 교사와 학생들이 학교 네트워크나 전자기기를 활용해서 챗 GPT를 사용하는 것을 막겠다고 알렸다. 

GPT는 일론 머스크가 공동 창립자 샘 알트만과 설립한 AI연구소 오픈AI에서 개발한 대화형 AI 챗봇이다. 2022년 말에 출시돼 두 달 만에 하루 이용자 1,000만 명을 돌파한 이 서비스는 지금 전 세계 교육 현장에 지각 변동을 일으키고 있다. 

챗GPT를 사용하면 누구든 간단한 질문만으로 궁금한 것에 대한 답을 손쉽게 빨리 얻을 수 있다. 

아직은 데이터의 학습량이 제한적이기 때문에 부정확하거나 어설픈 답변들이 나오는 경우가 더러 있다. 하지만 지금 이 순간에도 끊임없이 학습하는 AI의 특성상 앞으로 그 성능은 엄청난 속도로 개선될 전망이다. 

무엇보다 세계 곳곳의 학교들이 GPT의 영향력을 체감 중이다. 드디어 학생들이 이 GPT로 숙제하기 시작했고, 교사들은 이 같은 시도를 막기 위해 고군분투하고 있다. 그러나 학교 내에서는 몰라도 학교 바깥에서까지 사용을 막기는 현실적으로 어렵다. 

영국을 포함한 75개국 대학에서 인정하는 고교 과정 IB 디플로마 프로그램을 제공하는 국제 바칼로레아는 지난 2월 27일, 학생들의 챗GPT 사용을 막지 않겠다고 알렸다. 

일론 머스크가 말한 ‘숙제여 안녕!’이라는 말은 빠른 속도로 변화하는 세상을 받아들이라는 말로 들린다. 예전처럼 숙제하느라 혼자서 고민하고 머리를 짜낼 필요 없이 GPT만 잘 활용하면 된다는 말이다. 

우리 한국인들은 대부분 학교에서 암기와 요약으로 대표되는 주입식 교육을 받아왔다. 시험 기간 동안 교과서를 달달 외운 후에, 같은 시험지를 받아 들고 외운 내용을 써내면 됐다. 

더 많고 더 정확한 지식과 정보를 더 오래 암기해서 답안지에 잘 적어서 써낸 학생이 그렇게 하지 못한 동료보다 더 우수한 점수를 받아 좋은 대학도 가고 좋은 회사에도 취직을 해왔다. 

하지만 그 실력만 갖고는 위에서 시키는 대로의 일만 잘할 뿐, 자기 독창적인 발상과 아이디어로 회사에 유익을 주는 일은 하지 못한다. 

지금도 노벨상 수상자 발표 시즌이 되면 언제나 우울한 나라가 바로 대한민국이다. 평균 IQ가 세계 최고를 자랑하는데, 제대로 된 노벨상은 아직 하나도 받지 못한 이유가 뭘까? 스스로의 생각과 사고의 과정은 거치지 않은 채 학교에서 제시해준 정답만 달달 외워서 답안을 작성하게 하기 때문이다. 

앞으로 챗GPT는 학습량을 늘려가면서 날이 갈수록 더욱더 정확하고 수준 높은 고차원적인 기술력을 발전시켜나갈 것이다. 그렇게 되면 우리가 원하는 답을 찾는 것은 정말 어렵지 않게 된다. 

챗GPT에 질문만 던지면 몇 초 만에 수준 높은 답을 찾아준다. 문제는 깊이 숙고·판단·분석·종합해서 글이나 말로 표현해야 할 사람의 일을 챗GPT가 대신해버린다는 점이다. 

개개인이 지닌 창의력과 상상력과 문장력 발휘의 기회를 챗GPT가 독차지해버리면 사람은 이제 무얼 할 수 있겠는가? 

성경을 읽을 때도 마찬가지다. 성경을 대할 때 주석이나 전문가가 적어놓은 설명들을 미리 보지 않는 것이 좋다. 스스로 말씀을 깊이 묵상하고 되새김질하면서 그 본문에 필수적인 질문을 떠올리며 제기해야 한다. 

본문을 새로 정할 때마다 그 본문에서 꼭 필요한 질문을 제기해야 한다. 본문에서 적어도 한 가지 질문은 제기해야 한다. 

일론 머스크가 자기 계정에 남긴 글을 흉내 내면서 매듭지어본다. “It's always a new world, Welcome homework!”(새로운 세상이 왔다. 숙제여 환영해!)

이제부터 모두가 참고서나 남의 것 보고 베끼기보다 자신이 직접 고민하고 질문하면서 숙제를 하란 말이다. 

진실한 뉴스로 세상을 밝히고 한 영혼을 살리는 신문,

※ 후원해주시는 분들께 매주 발행되는 위클리굿뉴스 지면신문을 발송해 드립니다.

신성욱 교수 아신대학교

저작권자 © 데일리굿뉴스 무단전재 및 재배포 금지

교계 주요기사 베를린비전교회서 '5회 베를린 통일선교포럼·연합부흥회' 백석대·백석문화대, 충남정보문화산업진흥원 등 14곳과 협약 대신 서북노회 임시노회 및 12차 기도회 장기기증으로 써내려간 생의 마지막 페이지 조명 세직선, 신방화역 직장선교센터서 9월 성령기도회 한가협, 교회와 협력 캠페인 …'마약 없는 대한민국' 몽골 화상 아동을 돕는 '나눔 페스티벌'…8천 명 모인 축제로 쥬빌리구국기도회, 베를린서 ‘한민족 통일선교 서밋’ 개최