Books My Kids Read
The Homework Machine – A story of ethics
What if you had a machine that could do all of your homework for you? Would you share that information? What would you do with all of the extra time? How would you feel about using the machine? These are all questions that come up in Dan Gutman’s The Homework Machine .
We picked up this book because it is on the 2016-17 NC elementary school Battle of the Books. J really enjoyed this book and simply couldn’t put it down. For her, she felt that this was one of those books where you really felt like you were a part of the story. She felt that she was right there in the story, seeing it through the characters’ eyes. One reason for that sense of perspective comes from the fact that you read all of the actions from various perspectives. Whereas The Candymakers focused on a long period of time from one character and then repeated that whole segment from another character’s perspective, The Homework Machine, switches from paragraph to paragraph in the four main characters’ perspectives as well as the teacher, two mothers and a few classmates.
J also felt very connected to one of the characters because the two had a great deal in common. With four very distinct personalities, it is probable that a reader will feel a certain bond or kinship with an individual character.
From an adult perspective, it was very interesting to see how the kids not only dealt with the notion of right and wrong when it came to using the machine, but also how they developed as individuals. Judy, the intelligent class-pet who worked hard but excelled, struggled with the most guilt throughout the story. Sam, the class clown, and Kelsey, the slacker, wanted to utilize the homework machine the most because they truly struggled when it came to doing the work and wanted an easy out, so they dealt with less guilt. Brenton invented it as a way to free up his time to study other things that he wasn’t doing in school and because he knew all of the answers anyway.
In addition to the ethical question of using a homework machine, part of the story dealt with each child’s desire, or lack there-of, of fitting in, especially through the eyes of Aam. Sam struggles with both a great deal of self-doubt and yet a strong need to be seen as cool. By being a part of the foursome and seeing Brenton seriously not care what others thought of him, helped Sam have more faith in himself.
This is a great book to get kids thinking about ethics. Additionally, it also highlights the fact that you can’t judge a book, or person, by it’s cover and that we don’t know what others are going through. As we have started to read a few other Battle of the Books entries, that seems to be a theme for a selection of them this year and it is a great way to help teach empathy. All in all, this was a very enjoyable book.
Sounds like a great read! My son would do anything to get out of homework. Great review!
Leave a Reply Cancel reply
The Homework Machine
50 pages • 1 hour read
A modern alternative to SparkNotes and CliffsNotes, SuperSummary offers high-quality Study Guides with detailed chapter summaries and analysis of major themes, characters, and more.
- Introduction-Chapter 2
- Chapters 3-4
- Chapters 5-6
- Chapters 7-8
- Chapters 9-10
- Character Analysis
- Symbols & Motifs
- Important Quotes
- Essay Topics
Summary and Study Guide
The Homework Machine , written by acclaimed American author Dan Gutman was first published in 2007 by Simon & Schuster Books for Young Readers and is the first of a two-book series. The second book, The Return of the Homework Machine , was published in 2011. Gutman is primarily a children’s fiction writer who has been nominated for and won numerous awards, including 18 for The Homework Machine alone. Gutman is best known for his humorous series, My Weird School , in which there are more than 70 books. He lives in New York City with his family.
The paperback edition used for this study guide was published by Simon & Schuster in 2007.
Get access to this full Study Guide and much more!
- 6,400+ In-Depth Study Guides
- 5,250+ Quick-Read Plot Summaries
- Downloadable PDFs
The Homework Machine is told from the perspectives of multiple characters in the format of tape recordings for a police report.
The SuperSummary difference
- 8x more resources than SparkNotes and CliffsNotes combined
- Study Guides you won ' t find anywhere else
- 100+ new titles every month
The four main characters are fifth-grade students who are grouped at the same classroom table because their last names start with D: Sam Dawkins (Snik), Kelsey Donnelly , Judy Douglas , and Brenton Damagatchi . Other than sharing the same last initial, the students have nothing in common. Snik is the cool class smart aleck; Kelsey is laid back and doesn’t care about school; Judy is conscientious and in the gifted program; and Brenton is a loner and genius who designs software and studies psychology in his spare time. Snik pushes people’s buttons, and one day he pushes Brenton too far—implying that Brenton spends all his free time doing homework. Brenton retorts that he doesn’t spend any time doing homework and lets slip that he has invented a homework machine.
Snik calls Brenton a liar, so Brenton invites Snik, Judy, and Kelsey to his house to see for themselves. The group are stunned when Brenton’s machine prints out perfectly completed homework in Brenton’s handwriting. Brenton agrees to let Snik, Judy, and Kelsey join him after school to “do” their homework and even rewrites the software to accommodate their handwriting. The unlikely foursome spends every afternoon together, but they insist that they are not friends and that the only reason they tolerate each other is to use the homework machine, which they name Belch. Judy feels guilty about cheating but enjoys getting A’s and uses the extra time to take up ballet. Kelsey’s vastly improved grades earn her privileges, such as a belly-button piercing, from her mother. As the weeks pass, the D Squad becomes addicted to using Belch and the boundaries between their various social identities begin to blur. Snik shows an interest in “boring” chess, which Brenton plays, and Judy tries to be complimentary about Kelsey’s piercings (while finding them disgusting). Everything seems to be going well. However, things start to rapidly fall apart halfway through the year. Judy and Kelsey’s other friends resent their new associations and “unfriend” them, and their teacher, Miss Rasmussen , suspects that they are cheating.
In addition, a strange man has been stalking the group ever since Brenton designed software to instigate a hugely successful social media-driven “red socks day” that spread across America. Miss Rasmussen springs a surprise test on the class to see whether the D Squad really knows their schoolwork. Sure enough—Kelsey and Snik fail, and Judy gets a C, confirming Miss Rasmussen’s suspicions. Before Miss Rasmussen can report them, Snik’s father, who is in the military, is killed in the Middle East. This tragic event diverts Miss Rasmussen’s attention from the cheating, which seems trivial in comparison. The bond between the D Squad strengthens as the stress of keeping Belch secret increases.
Together they decide to shut Belch down, only to discover that Belch has taken on a life of its own and will not power off. They throw Belch into the Grand Canyon and feel relief as they watch it disappear. However, when backpackers find computer pieces at the bottom of the canyon, the D Squad is called into the sheriff’s office where they confess to everything. The case is closed, but their unlikely friendships continue to strengthen and grow. The stalker turns out to be someone scouting Brenton to offer him a job as an influencer for his company. The company’s clients want to market their products to kids. Brenton simply offers him an idea he would like to influence kids with: “Do your homework” (146).
Don't Miss Out!
Access Study Guide Now
Ready to dive in?
Get unlimited access to SuperSummary for only $0.70/week
By Dan Gutman
The Kid Who Ran for President
Popular study guides, science & nature, truth & lies.
- Show Spoilers
- Night Vision
- Sticky Header
- Highlight Links
Follow TV Tropes
Literature / The Homework Machine
"Seen a lot of strange stuff go down in 10 years working here, probably has something to do with being so close to the canyon. Having a mile deep hole in your backyard brings out the weirdness in folks. I remember that time the gambler from LA lost a bet in Las Vegas, and his friends drove him up here; forced him to parachute into the canyon, guy almost died. You get all kinds in this part of the country, the canyon attracts 'em like flies to dog doo... But this recent situation involving the children, was one of the stranger cases I ever ran into..." — Police Chief Rebecca Fish
In an interview room sits a police officer, and a girl named Kelsey; the latter of which is considered guilty of a crime. The child is demanded to give a testimony and is being recorded by cameras and microphones, all eyes and ears on them. The girl parts her lips, and begins to talk.
STOP. EJECT. INSERT NEXT TAPE. PLAY.
Brenton Damagatchi, Judy Douglas, Sam "Snik" Dawkins, and Kelsey Donnelly are all 5th grade students that only share one thing in common: their last names all start with a "D". Apart from that, they're nothing alike, Brenton is the typical smart kid who gets perfect grades, Judy always looks up to the teacher, Sam is a class clown who doesn't play by the rules, and Kelsey doesn't care enough about her grades to do any real work. Despite this (and largely because their teacher assigns seats in alphabetical order), they're all forced to sit together in class, with only their last names keeping them together...
At least that's what you may be led to believe.
All these kids (who cheekily named themselves "the 'D' squad" due to their last names) do share something else: a secret that if revealed, could have massive repercussions within the school district and within the county itself.
A 2007 novel by Dan Gutman, The Homework Machine is about the social repercussions of the eponymous device, and a commentary on the inner workings of the American Education System. The book's narrative is told in a series of testimonies provided by the 4 lead child characters, as well as their parents, the teachers, and the staff of the school they all attended. The testimonies are provided in the order they were taken, but said testimonies do not tell the story in the order that the events took place.
Was followed by a sequel in 2009, Return of the Homework Machine .
The Homework Machine contains examples of:
- A.I. Is a Crapshoot : Downplayed. Giving the homework machine the ability to access the sum of human knowledge leads to it not turning off when unplugged but that's all it really does. The D-squad freaks out and chucks it into the canyon .
- All First-Person Narrators Write Like Novelists : Zigzagged. They do spend a fair amount of time discussing not-exactly-homework-machine-related things, but for the most part, the cast of narrators talk like people, not like novelists.
- Armor-Piercing Question : When Ronnie suspects the D Squad has a secret, he tries to get it out of Brenton by pretending to be friendly, and when that doesn't work, he threatens to reveal what Brenton is up to. Brenton says, "And what exactly am I up to?" Ronnie doesn't have an answer, because he doesn't know.
- Asian and Nerdy : Brenton is Japanese-American and a genius kid who's programmed a machine to do his homework for him, and he's only in fifth grade.
- Black and Nerdy : Judy is a gifted, hardworking and rule-abiding student who gets called a goody-goody and a know-it-all by the other kids.
- Bonding over Missing Parents : Kelsey starts crying when she finds out about Snik's dad, because she lost her own father in a snowmobile accident when she was six.
- Chekhov's Gun : The catapult, which they used to fling the machine into the canyon.
- Child Prodigy : Brenton has always been a super-genius, even from a young age. Brenton's mom : He spoke very early. He had no interest in watching television or playing with other children. Instead, he would play chess against himself. He taught himself how to play the piano as soon as he was big enough to climb up on the bench. When he was just six, he wrote a concerto. Really! And that's what he called it, too. "My concerto." I don't know where he got the word concerto. I still don't know what it means. He was very special.
- Deadpan Snarker : Snik has a sharp tongue. This is what he wrote for an assignment where the class had to make 10 rules about homework. 1. We live in a democracy, where we have freedom, right? We're entitled to life, liberty, and the pursuit of happiness. So how can I pursue happiness if I have to spend every night doing home-work? Homework is cruel, totalitarian punishment created by grown-ups to take away the freedoms of poor, defenseless children. 2. Nobody ever saved a life, won a war, stopped a crime, or cured a disease while they were doing homework. Think of all the good things we could be accomplishing if we didn't have to spend so much time doing homework. 3. Doing homework causes eyestrain, fatigue, insomnia, and other physical ailments. 4. Thomas Edison went to school for four months. He never did any homework, and look how he turned out. 5. There's a name for working without getting paid. It's called slavery, and it was banned during the Civil War. If kids are forced to do homework, they should be paid for it. 6. Homework is proof of teacher incompetence. If a teacher is any good, students would learn the stuff in school and wouldn't have to learn it again at home. 7. Doing homework wastes valuable natural resources. We have to use lots of energy to keep all those lightbulbs burning. We have to cut down trees to make paper and pencils. We'd save a lot of energy by banning homework. 8. I keep hearing that American kids are way too fat, and that's because we don't get enough exercise. For every minute kids are doing homework, we are getting fatter. Kids should be outside running around and getting exercise, not inside doing worksheets. 9. Virtually every known murderer, bank robber, and criminal did homework when they were children. How can we be sure the homework didn't cause the criminal behavior? 10. Homework sucks. There should be a constitutional amendment banning it.
- Deconstruction : Brenton is a Child Prodigy , but he's not one to the absurd levels many books and television shows depict them. He was only able to build the Homework Machine in the first place because he got ahold of an advanced supercomputer by a fluke, and despite his nerdiness he's not capable of doing things that are outside the realms of plausibility. At the end of the day, he is still a kid.
- Do Well, But Not Perfect : After a while, Miss Rasmussen starts getting suspicious of the homework the D Squad is turning in because their answers are always perfect with no mistakes. In turn, Brenton starts programming the homework machine to make minor mistakes at random when doing Snik's and Kelsey's homework because they're more Book Dumb than either him or Judy.
- Early Personality Signs : According to Brenton's mom, he was always different from other kids. He never cried as a baby, and never wanted to play with other children or watch TV. He played chess with himself and taught himself how to play the piano.
- Everyone Has Standards : Even though he hates the D Squad, Ronnie swears up and down that he wasn't the one who called the cops on them. He's not lying. It was Brenton.
- Exact Words : When Miss Rasmussen is starting to get suspicious of the D Squad's perfect homework, she takes Snik aside and asks him if he ever copies off anybody. He says he doesn't, which is technically true because he gets the machine to do his homework for him.
- Only Sane Man: Judy
- The Smart Guy: Brenton
- The Pervert: Snik
- The Butt Monkey: Kelsey
- The Cynic: Snik, who hates homework with a violent passion and refused to do it for a time at his old school
- The Optimist: Judy, who really doesn't mind homework and thinks it has educational value
- The Realist: Kelsey, who does homework even though it sucks
- The Apathetic: Brenton, who doesn't really mind homework but admits it's time consuming and thus invents the homework machine
- Choleric: Brenton (the genius)
- Melancholic: Judy (the perfectionist)
- Sanguine: Snik (the class clown)
- Phlegmatic: Kelsey (the slacker)
- Framing Device : The story is told through testimonials given by the D Squad, their teacher, their parents, and occasionally other people. It's framed as the police putting the story together the following summer.
- Gender-Equal Ensemble : The D-Squad consists of Brenton and Snik (male) and Judy and Kelsey (female).
- Intelligence Equals Isolation : Brenton is a Child Prodigy with a ridiculously advanced mind who can't relate to other kids and seemingly has no interest in making friends. He only ends up befriending the rest of the D Squad in the first place because they came over to his house for a homework assignment.
- It Won't Turn Off : The machine runs unplugged, and only turns off when thrown over the Grand Canyon.
- Military Brat : Snik, who's new at the beginning of the story because his father is assigned to Luke Air Force Base near Phoenix.
- Nobody Likes a Tattletale : When the D Squad first hears about the homework machine that Brenton built, Judy thinks about raising her hand and telling the teacher, but decides not to because everyone already calls her a goody two-shoes and she doesn't want them calling her a tattletale too.
- Noodle Incident : We never find out why Snik got suspended at his previous school, though it's implied it had something to do with him not wanting to do his homework.
- Open-Minded Parent : Kelsey's mom lets her elementary-school-age daughter dye her hair pink and pierce her belly button.
- Revealing Cover Up : The homework machine is only discovered when the D-squad builds a catapult to chuck it into the Grand Canyon and its parts are later found by some hikers, therefore getting them caught for littering.
- Sdrawkcab Name : Snik's real name is Sam, but his nickname is "Snikwad" or "Snik" because that's his last name, Dawkins, spelled backwards.
- Switching P.O.V. : The story is narrated by 4 characters: Brenton Damagatchi, Kelsey Donnelly, Sam "Snick" Dawkins, and Judy Douglas.
- Holmes on the Range
- Literature of the 2000s
- His Master's Voice
- Administrivia/Works Needing Tropes
- How to Build a Skydeck
- The Homeward Bounders
- Children's Literature
- H.I.V.E. Series
- School Stories
- The House of Night
- Action Adventure
- Crime & Punishment
- Professional Wrestling
- Speculative Fiction
- Sports Story
- Animation (Western)
- Music And Sound Effects
- Print Media
- Sequential Art
- Tabletop Games
- Applied Phlebotinum
- Characters As Device
- Narrative Devices
- British Telly
- The Contributors
- Creator Speak
- Derivative Works
- Laws And Formulas
- Show Business
- Split Personality
- Truth And Lies
- Truth In Television
- Fate And Prophecy
- Edit Reasons
- Isolated Pages
- Images List
- Recent Videos
- Crowner Activity
- Un-typed Pages
- Recent Page Type Changes
- Trope Entry
- Character Sheet
- Playing With
- Creating New Redirects
- Cross Wicking
- Tips for Editing
- Text Formatting Rules
- Handling Spoilers
- Trope Repair Shop
- Image Pickin'
Sales - 800-325-9558
The Homework Machine
Upper Elementary & Junior High Plus (Grades 5-7)
Upper elementary & junior high plus.
For Grades 5-7 A great way to ensure more titles for your middle-grade readers-with 14 additional popular B titles arriving at your door every year.
Chapter Books/Novels, Fiction, Reluctant Readers, Transitional Readers, Realistic Fiction
Is AI the New Homework Machine? Understanding AI and Its Impact on Higher Education
Published by: WCET | 1/5/2023
Tags: Academic Integrity , Artificial Intelligence , Higher Education Trends
By now you’ve likely seen the hubbub over ChatGPT, OpenAI’s new chat bot trained on their large language model AI GPT 3.5. Some of the more provocative announcements about the impact of artificial intelligence include:
- This is the end of homework as we know it ,
- Students are already using this to cheat and we’ll never know ,
- AI can produce writing as good as a college student ,
The focus of much of this discussion about AI has been on academic integrity, specifically academic dishonesty. But bigger issues—digital literacy, pedagogical practices, equity—are also at play.
In 2023, WCET will look at Artificial Intelligence (AI) and provide support and resources to help you break through the rhetoric and understand both the promises and perils of AI in higher education.
To begin, this introductory blog post will focus on an overview of large language model AIs and their potential impact on higher education.
In coming months, we will do a number of deeper dives on AI and higher education including a Frontiers Podcast episode, a February brief that explores selected AI tools, several blog posts on AI’s impact on pedagogical practices, what a new digital literacy in the age of AI might look like, and the equity implications of large language model AI, as well as a summer white paper that will do a deeper dive on the pedagogical and policy implications of AI.
A Quick Primer and Glossary on Large Language Model Artificial Intelligence
Before we delve into the impact of AI on higher education, it’s worth taking a few minutes to consider artificial intelligence and its most recent manifestations.
Artificial Intelligence (AI): Stanford University’s Human-Centered Artificial Intelligence group defines artificial intelligence as “a term coined by emeritus Stanford Professor John McCarthy in 1955, was defined by him as ‘the science and engineering of making intelligent machines.’ Much research has humans program machines to behave in a clever way, like playing chess, but, today, we emphasize machines that can learn, at least somewhat like human beings do.”
Machine learning: Machine learning was defined by AI pioneer Arthur Samuel in the 1950s as “the field of study that gives computers the ability to learn without explicitly being programmed.” Often times this now happens via neural networks.
Neural networks and deep learning: Neural networks are, simply put, computer networks that are built in such a way as to mimic the human brain with each node leading to other nodes, much as the brain is a complex collection of networked neurons. Neural networks lead to deep learning which allows the computer to learn from large amounts of data in a way that “creates an adaptive system that computers use to learn from their mistakes and improve continuously.”
Large language model (LLM): A language model trained on an enormous amount of text so that it is capable of predicting a given sequence of words. This capability allows the model to “understand” inquiries and replicate human language in a largely coherent way.
Much of the recent discussion is around large language model AI. This type of AI relies on a neural net to look for and find patterns in a massive amount of data. The larger the neural network, i.e., the number of nodes, the larger the data input can be, and, in theory, the more capability the AI has to interact with humans. Much large language model AI, such as OpenAI’s (a research and development company) ChatGPT, relies on large neural networks which allow the AI to continuously learn from its interactions with humans and improve its responses.
The Buzziest LLM AI Right Now: OpenAI’s ChatGPT and GPT 3.5
Last month OpenAI released ChatGPT , a chat interface for its GPT 3.5 large language model AI . Using the chat interface, users can make a seemingly endless array of queries of GPT 3.5 that result in often stunning responses. For example, when provided with a prompt to explain how the ChatGPT works, the program responded:
ChatGPT is a large language model that is trained to generate human-like text. It does this by being fed vast amounts of text data, which it uses to learn the patterns and structures of language. To generate text, ChatGPT uses a type of artificial intelligence called a transformer, which allows it to process language more efficiently and effectively. It also utilizes a technique called self-attention, which enables it to consider the relationships between words in a sentence and the context in which they are used. When given a prompt, ChatGPT uses all of this information to generate a response that is coherent and resembles natural language.
And when asked to write a poem in the style of iambic pentameter on the superiority of cats, the program responded:
In iambic pentameter, the most common type of meter in English poetry, each line contains ten syllables and has a regular pattern of unstressed and stressed syllables. The pattern is typically written as “da-DUM” and can be thought of as the beat of the poem. Here is a short poem about the superiority of cats written in iambic pentameter:
And, finally, when asked to write a college application essay on one’s experiences of working in a soup kitchen which includes reflecting on what you learned and including an interaction with a small child, ChatGPT, in a matter of seconds, responded with a coherent, personalized, five paragraph essay. I fully believe that the fact that the essay was written by AI and not a live person would be undetectable for many college admissions committees.
Why, as a society, should we care about the release of ChatGPT? Very simply put, the release of ChatGPT and the development of other large language model AIs is a seminal moment in human history. The moment is akin to probably the single most important historical technological development—the creation of the movable type printing press by Johannes Gutenberg in the early 15 th century. Just as the printing press changed our relationship with information by making it available to a wider audience, large language model AI is changing our relationship with information by blurring the lines between human and machine. It forces us to reconsider what is distinctly human about intelligence if a machine can generate human language complete with analysis.
What Does All of This Mean for Higher Education?
It is clear that the development of large language model AI, and its growing availability to a more general audience, could significantly change higher education. It will call into question the ways in which we have used writing as, as Daniel Herman puts it, “a benchmark for aptitude and intelligence.” Generative LLM will force us to think about what we assess and how we assess it, shifting a reliance on writing to more creative assessments that require students to demonstrate application of knowledge rather than simply the ability to produce information.
Higher education is being called upon to rethink what we assess and why we assess it. We are being called upon to rethink the relationship between information, knowledge, and wisdom. When an AI can create passable prose with accurate information (something that ChatGPT and other LLM Ais still cannot yet do consistently), is it enough to ask our students to “prove” that they know the information? Or does our assessment shift to asking students to apply information, demonstrating knowledge of the subject at hand?
Higher education must rethink digital literacy and how we prepare our students for this new world of large language model AI. As we move closer to a world of hybrid work where more and more jobs involve the use of generative AI for everything from discovering new drug molecules to developing ad copy, we will need to help our students understand how to partner with AI. How do they craft a request? How do they evaluate the results of the AI? How can they leverage AI to more deeply understand the world around them? This is a new digital literacy and it goes beyond the use of statistical software application or how to craft a Google search request.
What You Can Do Right Now
In September of last year, before the release of ChatGPT, Jeff Schatten wrote in The Chronicle of Higher Education , “It won’t be long before GPT-3, and the inevitable copycats, infiltrate the university. The technology is just too good and too cheap not to make its way into the hands of students who would prefer not to spend an evening perfecting the essay I routinely assign on the leadership style of Elon Musk.”
That time, that technology—it’s here, and higher education must decide how to respond.
In coming months we’ll do a much deeper dive on how you can respond to large language model AI but, in the interim, we would urge you to take the steps that John Warner suggests in his recent Inside Higher Ed blog, “Freaking Out About ChatGPT—Part I.”
- Give students learning experiences that they are interested in and value so they are less inclined to use AI as a way for “doing an end run.”
- Move away from using a single artifact, like a single exam or essay, as a measure of learning. Instead, create assessments that “take into consideration the processes and experiences of learning.”
- Ask students to engage in metacognitive reflection that has them articulate what they have learned, how they have learned it, and why the knowledge is valuable.
- Create assignments that require students to synthesize what they have learned and bring their own perspectives the subject.
- And, finally, create assignments that integrate the technology into learning.
We also need to begin thinking about how we define academic integrity in this new age of ChatGPT and other large language model AIs. This should lead to deeper conversations with our students about academic integrity.
As Melinda Zook, a Purdue history professor puts it , “The fact is the professoriate cannot teach the way we used to. Today’s students have to take ownership over every step of the learning experience. No more traditional five paragraph essays, no more ‘read the book and write about it.” We must radically rethink our pedagogical practices for the 21 st century.
In Conclusion: Danny Dunn and the Homework Machine
In 1958, Jay Williams and Raymond Abrashkin published Danny Dunn and the Homework Machine, a children’s book about three junior high schoolers who decide to use a computer prototype to do their homework for them. When their teacher discovers their ruse and confronts Danny, he passionately defends their decision to program the computer with all of the information in their textbooks and use it to produce their homework exclaiming,
“It’s just another tool. Lots of kids do their homework on typewriters. In high school and college they teach kids to do some of their homework on slide rules. And scientists use all kinds of computers as tools for their work. So why pick on us? We’re just…just going along with the times.”
Junior high school hijinks ensue, including the sabotage of the computer by a jealous classmate and Danny heroically discovering and fixing it just as a representative from the federal government is about to leave in disgust. And, in the end, Danny and his friends recognize that in programming the computer to do their homework they have, in reality, been learning and doing their homework leading Danny to resolve not to use the computer to do their homework anymore. However, he does close the story by wondering about what a teaching machine would look like.
Reading Danny Dunn and the Homework Machine in light of ChatGPT was eerie. The story (written when Dwight Eisenhower was President) reflects current discussions about the ethics of students leveraging the latest AI innovations, especially ChatGPT and GPT 3.5.
- What is the purpose of homework?
- What types of assistance should students be allowed to use?
- What is academic integrity and how does AI fit in to discussions about it?
- Are there ways for students to use AI that do not compromise academic integrity?
- What does it mean to learn?
- And, finally, what is the role of the teacher in this new age of AI?
In the coming months, we’ll explore these larger issues around AI and higher education . Meanwhile, we would love to hear your thoughts on ChatGPT and other AI tools and their impact on higher education. You can send any thoughts or questions to Van Davis at [email protected] .
Chief Strategy Officer, WCET, Service Design and Strategy Officer, Every Learner Everywhere
@HistoryDoc LinkedIn Profile
Van joined WCET in 2021 as chief strategy officer where he is responsible for all aspects of WCET’s strategic planning; diversity, equity, and inclusion efforts; and assisting the team with policy and research efforts. Van also serves as service design and strategy officer with Every Learner Everywhere where he leads the development and delivery of the organization’s Service Design and Delivery work.
Van is a valuable asset to the team, having over 25 years of experience in higher education as a faculty member, academic administrator, state policy maker, and edtech leader. Van holds a PhD in 20 th century US history with an emphasis in civil rights from Vanderbilt University, and his commitment to education is evidenced in both his professional and personal successes. Additionally, Van led the creation of the Texas adult degree complete project and the development of the first competency-based bachelor’s degrees at Texas public institutions of higher education during his time on the Texas Higher Education Coordinating Board.
Van lives outside of Austin, Texas, with his beloved wife Lisa and two cats and, when not working, spends time collecting Lego models and dreaming of the day he can complete his western US camping trip. Van’s favorite book is To Kill a Mockingbird , and his favorite movie is Dr. Strangelove.
2022 SANsational Award Winners Present Promising Compliance Solutions
What faculty designers can tell us about online course reviews.
Enter your email address to subscribe to this blog and receive notifications of new posts by email.
Archive By Month
Search blog posts, follow us on twitter.
Review and Summary: The Homework Machine
Author: Dan Gutman
Publisher: Simon and Schuster
Genre: Children’s Fiction
Short, fun, interestingly organized, and about something that you aren’t supposed to do. A good book after reading all these novels about serious issues and murderous plots. The Homework Machine is about four kids – a geek, a class clown, a know-it-all teacher’s pet, and a slacker. A most peculiar combination of fifth-graders. In fact, if you mixed together their equivalents in food, you would probably get something resembling the insides of a septic tank. Brenton is an interesting kid – he dresses unlike other people, he parts his hair weird, and he’s light-years ahead of everybody in intelligence. You might be guessing he’s either the geek or the teacher’s pet. He’s the geek. Judy is a stuck-up snob in the beginning, and she has her ring of friends, but is despised among others. She is adored among teachers, but later on in the book her personality begins to change. Sam, or as other people call him, Snik, is in an awkward position as the new kid in school. The class clown, luckily, can define a potential friend from an enemy. Kelsey is just an average kid who gets grades just high enough to get her through the year, and desperately wants to be out of school.
One day, Brenton tells Snik that he has a homework machine, and, of course, Snik doesn’t believe him. So he comes over with Judy and Kelsey, who hear about the conversation, and like in any other good children’s book, Brenton’s computer with software he designed himself does their homework. They have the fallacy that if their homework is done for them, life will become easier. They’re wrong, but they don’t know that. So they bring their homework over so often it’s outrageous, and the foursome deigns each other their friendship. Eventually, after many rumors leak out, they are caught by the police and have to explain everything. Of course, they try to get out of trouble, but they fail miserably. Don’t worry, they don’t get put in quarantine or anything – it turns out kind of good, actually.
When I started reading, this book had me confused at the beginning. It was on my book list for school, and not because I wanted to read it (I had never heard of it), but because my teacher found good reviews on it and thought that it could be used for a review (which I’m writing right now). Turns out, it’s not what you would excpect from a school book. It’s about four kids and a machine that helps them cheat at homework. Probably not a teacher’s first choice of a book. I wasn’t at all bamboozled into thinking that this was a classic book – I mean, any book about a machine that does homework probably isn’t some dude with a PhD’s idea. You may think at first that this book has no place in any school setting whatsoever – that it would encourage kids to cheat on their boring after-school assignments. However, after reading this book, I found that it sort of got me that no matter how hard you try to conceal your “accidental glancing” at someone else’s paper, you will (almost) always get caught. Even if that accidental peeking isn’t at all peeking, but using some geek’s super computer to do homework in your handwriting at the touch of a button. Hey, anything’s possible.
The setup of this book is quite interesting. It’s like a review, except they follow the same story in the same order with no questions asked. Do you remember my review of The Red Pyramid ? Well, it sort of like that, except with WAY more people. All the kids’ moms are in it, an enemy at school appears a few times, and even a police officer talks at the beginning and end. There are back stories and random explanations, which keep the story interesting. Friendships develop and diminish, and there’s always a mysterious flair to the words.
After reading this book I am almost voracious for more Dan Gutman. He delivers bits of everything, and gives his books plenty of humor and good-natured sarcasm. This was a short book, with easy vocab and plot, so I would recommend this book to kids ages 8 to 12.
Posted by: Fred Reads
Filed under Uncategorized
Tagged as book review , Children's Fiction , Dan Gutman , fiction , Simon and Schuster , Summary , The Homework Machine
4 responses to “ Review and Summary: The Homework Machine ”
This review is interesting to me stylistically. I had a hunch after your last reviews on the Hunger Games that you were taking on a style of the book in your review. I really enjoy that idea. In this review, hoewever, it struck me a bit differently. For instance, you began your first paragraph with a few fragments. I understood what you meant very clearly and found the conversational tone to be charming. It still made my inner grammar freak twitch.
What are your thoughts on this?
Yeah, grammar is the only thing that I don’t really pay attention to. I mean, I’m not all like “Duh, me no like grammar and stuff,” but I will admit to a few errors once in a while. In fact, I’m sure you’ll be able to pick out some errors in this comment. I’m good at spelling (relatively) but sometimes I just let somthin’ slip. And honestly, I don’t even mean to organize a review in a specific way. It’s like a part of my brain that I can’t control determining how I’m going to do it based on my mood or the kind of book. I do think though that some of my sentences are a little too short.
I know what you mean about your reviews reflecting your mood at the time. I think that is why I haven’t written any in a while. I am still reading, but my life has been subject to some stress and craziness lately. Everything I write is no good. It’s a frustrating feeling. I’m hoping to get some rest this weekend and be able to sit down and write a bit. I’ve been wanting to tell you about this really interesting book I read a few mints ago, actually. Stay tuned for that.
I have something for you to be stay tuned for, actually. I just sent one of my spies (a friend who came over) to collect emails and signatures from my friends that go to his school. I’m basically making a petition to present to my mom. If I get enough of them, she might let me have a blog with my friends. That means that your going to have to help me a little. Actually, the only thing I need your help with is filtering the posts that go on the blog, like you do with my posts. It’s not that I’m being big-brother-ish, I just don’t want anything bad or unnecessary going up.
Leave a Reply Cancel reply
Submit a guest review, about crosscountryreading.
- Reviewer Biography: Fred Reads
- Reviewer Biography: Janine Reads
- Review and Summary: The Last Book in the Universe
- Review: Inkheart
- Free Book Giveaway Contest – Comment to WIN!
- A Cook, A Book, and a FREEBIE for you!
Subscribe to Blog via Email
Enter your email address to subscribe to this blog and receive notifications of new posts by email.
- Already have a WordPress.com account? Log in now.
- Follow Following
- Copy shortlink
- Report this content
- View post in Reader
- Manage subscriptions
- Collapse this bar
#sarareads: story- the homework machine.
- May 6, 2020
“3x5x4! Oh No! That’s a lot of work” said Chiky, sitting in his math class. It had fifteen tables, two fans and one cupboard. He was sitting in the corner with his friend Dolly. It was 11:37 am. The weather was as harsh as a crow. The school was almost ruined with water droplets coming from the ceiling. The school’s name was “Khelna, Padna, Rona, Dhona”(KPRD).
Chiky was fair, had a broad nose and long ears. He was around 4 ft tall and studied in class five. He was a sweet boy with innocent eyes, but the only thing that he did not like to study.
One day while Chiky, Diana and Dolly were discussing the homework hassles, Diana got an idea. She told us that we can invent the homework machine (as Diana was good at Robotics).They both went “Wow, A Homework Machine?! What a fabulous idea!”
After all the discussions and reading, they decided on the materials required. Carton box, paint, pens, screws, screwdrivers, buttons and batteries – they had everything in place. Just one issue- how will this machine do homework, the way we do? They were sad and puzzled and didn’t know what to do next.
A few days later, Chiky had a mysterious visitor to his home. The man wore a hat the whole time and spoke very little. Chiky’s father said his friend was a famous engineer who had invented some amazing things. Chiky was very excited and told him about how much homework he was getting and wished there was a machine that did all the work for him. He even showed him all the materials for the homework machine and asked him if he can fix it. The guest smiled and said the human brain is faster than a machine and our hands are more effective than a printer. Chiky was not convinced.
The next morning, Chiky woke up worried because he had not finished his homework. He took his pencil and rushed to finish what he could. Surprise! He saw a small black printer kind of a machine. There was a note next to it. It was by his dad’s friend, the famous engineer.
“Dear Chiky, you have the most brilliant homework machine with you. Use it well,” said the note.
Chiky jumped in joy. The great engineer had built him his very own homework machine. He took his school workbook and placed it inside the machine. He turned on the switch and waited. The buttons lit up. He waited for five minutes. Nothing happened. Maybe it is taking time understanding the math question. Or maybe it is taking time to adapt to my handwriting, he thought.
Time was running out. The homework machine was still processing. Chiky couldn’t wait any longer. He grabbed a pencil and began doing the sums quickly. He put the book in his bag and went to school. The next day he did the same thing. He put the book in the homework machine and waited all morning. The buttons would light up, but nothing would print. In frustration, he again did the homework himself.
For the next one week, the same routine happened every day. Chiky was sure the great engineer had created the perfect homework machine but why didn’t it work?
On the seventh day, the teacher gave the class an assignment to do at home and Chiky took a pencil like he did at home and finished the work immediately without even realizing it.
“Chiky, you seem to have become a homework machine,” remarked his teacher, looking pleased.
Homework machine? Chiky thought and laughed hard. He remembered the note the great engineer had left him when he gave him the homework machine. It had said “Dear Chiky, you have the most brilliant homework machine with you. Use it well.” He had thought the new black printer was the homework machine when in fact the homework machine was with him the whole time – his brain! Father was right, he thought. His friend, the engineer was a genius but with a sharp homework machine in his head, Chiky wasn’t any less!
Today, a year has passed since the idea of the homework machine and the kids are joining at Chiky’s place for a celebration. Want to join?! 🙂
- bookosmia , creative writing , digital stories , free stories , house of books and tales , Pragya Jindal , published , sara , sara reads , stories by kids , stories for kids , stories from jaipur , The Homework Machine , young writers
Leave a Reply Cancel reply
Your email address will not be published. Required fields are marked *
Save my name, email, and website in this browser for the next time I comment.
Spotlighting Young Talent- Dev Varun, 8, Published Author
A Letter To 2021 | Bookosmia
All Because Of Ice- Cream | Bookosmia
‘Mindful Me’ Journal | For Age 8-12 years
The Globetrotting Warriors | By Young Author Aadvik Balodia
Mahabharata- Unheard Voices | A collection of stories
Bookosmia – India’s No. 1 Publisher For Kids, By Kids from 150+ locations worldwide.
Bookosmia is a safe and preferred destination for kids whether it is to read, listen, write or watch their favourite stories.
Not That Different
- Shop with us
- Comic Story
- Know Autism Better
- Parents Speak
- Nayi Disha's Resource Centre
- Inclusion Stories FEST '22
- Down Syndrome Awareness 2023
- Get Published
- Live Events
- Terms and Conditions
- Shipping, Cancellation and Refund Policy
- Our Partners
- Designed by Raei Technologies .
India’s #1 Creative Platform FOR Kids BY Kids
Hackaday Prize 2023: The Realities Of The Homework Machine
For those outside the world of education, it can be hard to judge the impact that ChatGPT has had on homework assignments. If you didn’t know, the first challenge of the 2023 Hackaday Prize is focused on improving education. [Devadath P R] decided that the best way to help teachers and teaching culture was to confront them head-on with our new reality by building the homework machine .
The goal of the machine is to be able to stick in any worksheet or assignment and have it write out the answers in your own handwriting, and so far, the results are pretty impressive. There are already pen holder tools for 3D printers, but they often have a few drawbacks. Existing tools often take quite a while to generate G-Code for long pages of text. Hobby servos to lift the pen up and down take more wear than you’d expect as a single page has thousands of actuations. Vibrations are also a problem as they are a dead giveaway that the text was not human-written. [Devadath] created a small Python GUI to record their particular handwriting style on a graphics tablet and used ChatGPT to generate answers.
Multiple versions of each character are used, though [Devadath] plans on slightly varying the strokes as needed to create variation. A hand-rolled Python script outputs G-Code with page turns include, which makes it easy to dump multi-page content in. The core XY CNC pen plotter glides on linear rails, runs on Klipper firmware with vibration cancellation, and has an actuator driven by a stepper for longevity. To [Devadath]’s credit, they have been using this setup since 2022, and teachers haven’t noticed so far. They say the plan to open-source the code and design for the plotter once they’re finished iterating.
It demonstrates AI’s capabilities and what can be built with parts on hand. Whether it pushes education away from rote memorization remains to be seen.
83 thoughts on “ Hackaday Prize 2023: The Realities Of The Homework Machine ”
The following statements in your article are an example of a misguided project that does harm to the student and his education. I fail to see how this helps a teacher. Rather, this project lets a student avoid doing home work and thus deprives him of learning. A better help would be to expose uses of AI by the student and hold them accountable.
… decided that the best way to help teachers and teaching culture was to confront them head-on with our new reality by building the homework machine.
The goal of the machine is to be able to stick in any worksheet or assignment and have it write out the answers in your own handwriting,
I think you may be missing the point they’re making.
How do you help a locksmith? You show them how to pick their lock.
I think you’re missing the point here – the purpose of teaching is not to provide the teacher with homework, but for the student to learn. Sure, this is an issue for exams and assessed coursework, but for most homework this is only cheating the student who skips the studying.
And the purpose of homework is to make sure that the student has at least seen the material. Our courses are built in a way that you have to return enough homework or you don’t get to take the exam. Teachers who don’t do this see people just skip the lectures and homework, study at the last moment and bounce the exam multiple times until they finally get enough points by trial and error to barely pass – and that’s a waste of everyone’s time.
A related problem is that since you need some sort of a degree almost for serving coffee these days, many students just take the path of least resistance. This means people either drop out, or just take the bachelor’s and go do something entirely different with their lives, and we have to lower standards to keep to the quotas to get students and make them pass. This is especially a problem for the first year mass courses that are mandatory for all, where some teachers just choose a “write your name for pass” approach. We still require them to learn, but it’s really beginning to resemble spoon-feeding adult children.
So if the students are allowed to do the homework by automation, and pass the tests by copy/pasting from the textbook in an online exam, we’ve arrived at the Soviet System: the system pretends to educate the people and the people pretend to be studying. Everything works on paper and yet the economy keeps tanking.
“A related problem is that since you need some sort of a degree almost for serving coffee these days, many students just take the path of least resistance.”
Some are getting away from that.
A big reset.
Yep. One Certification Salad coming right up.
It’s an even bigger scam, because you can buy a bunch of do-nothing certificates that only require you to complete the online course. I have several, all required for legal or insurance reasons at some point. The training instructor tells you the answers to the multiple choice exam, because everyone who paid for the training course has to pass.
In this case, the purpose is exactly to educate the teacher (not the pupil!) about AI, and so the “best way to help teachers and teaching culture was to confront them head-on with our new reality by building the homework machine”
Except the person is trying to get out of copying lab reports without the teacher noticing that they’re machine copies.
I have a feeling that building the machine was a far more valuable learning experience than any worksheet that could be sent home.
Worksheets =/= Learning
Memorizing facts isn’t learning yet, but facts are the foundations of forming ideas in your head.
Suppose you forgot what a nail or a screw is, then someone asks you to design a wooden fence. How would you do it? Glue?
That’s a great question! I’d have to go do some experiments to find out for myself!
Not that it can’t be done, but the solution would be more convoluted, like lashing it together with rope. Point is, it would take you more time to research your options and figure out (again) that nails and screws exist, which makes your task that much harder.
When you have the simple stuff already down to memory, you can skip ahead to the bigger problems rather than re-inventing the wheel every time.
Woe is the kid whose parent complains, “Why are you teaching my son multiplication tables, what a waste of time, he’s got a calculator!”
He will be left with impaired numeracy.
“How would you do it?”
Actually not impossible:
Thanks @dude for finally showing me where that window shutter gif meme came from
Maybe using a lattice or coppicing.
>Suppose you forgot what a nail or a screw is, then someone asks you to design a wooden fence. How would you do it? Glue? Google. Then screws, probably.
The big problems start when you know so little that you can’t even search for it. You may not even know that entire categories exist, or you remember things entirely wrong and confabulate information. “What’s that thing that puts things together… quickeners?”
If I selectively forgot that screws and nails exist, but I truly understood the concepts, I might invent them by thinking that ramming a dowel into an oversized hole would pin it together, then realizing i could probably even force it to make its own hole if it was thin and hard, or maybe if it had a shape that could drill its way into the wood and even provide clamping force. Of course, without the fact that nails and screws are cheap and easy, I might first think to use wire/rope or to shape the boards to interlock.
I think the number of facts you’ve encountered and thought about matters a lot more than the fraction you memorized. If you memorize 13 fasteners, on a test you score better if you were only exposed to 15 than if you were exposed to 30. But if you were exposed to 30, you might have learned why fine threads work great for steel and poorly for wood, or maybe being exposed to lockwire helps you remember to think about the direction you wrap wires around a screw terminal. If you set up a memorization test you want most people to pass without test prep taking up an undue fraction of their time, you might make the test cover very few fasteners, which seems unhelpful to their future. I’m not sure if I think it would work to just set expectations lower – what do you think?
>If I selectively forgot that screws and nails exist, but I truly understood the concepts
Question is, is it possible to fully understand the concept if you lack some of the most basic examples of it? That to me sounds like a learned party trick, where you can perform something without understanding what you’re doing.
Of course memorizing minor variations of a theme isn’t productive. You don’t need to learn the entire 10×10 multiplication table by rote memory either – it’s more efficient to learn only the ones that are hard or “special” and just solve the easy ones like 3×5 each time.
I think if you’ve never been exposed to the most basic examples, that would make it tough to have learned how they can work. Even then maybe you came from a different background where it’s lashing that’s basic and screws are rare, but you still learned enough to understand a screw when someone shows it to you. It’d definitely be worth learning about screws and nails, but once you have, you don’t necessarily need to continue to remember them at all times if you instead just remember how they work. … It occurs to me that for many people, whatever prototypical examples they have of screws are probably how they retrieve screw related memories that they don’t have a separate example for. So it’s possible that for those people, forgetting screws would also mean forgetting how they work at the same time. You’ve made me realize that someone might have a hard time accessing their memory of without thinking of screws if they weren’t really familiar with any other screw-like-things e.g. bolts. Still, for less basic things I tend to repeatedly “invent” things that already exist. Sometimes I knew they existed and forgot, sometimes I never heard of them before. I think there’s room for forgetting most of the examples of anything you’ve heard of, except for the “special” / unique ones like you said, if the ones you do remember give you a good idea of the possibilities.
Students have been looking for ways around homework as long as there has been homework :-)
I think you should consider this, as the developer intended, like a piece of art. It’s asking the observer to think about something. In this case the impact that AI tools are going to have on education.
Probably millions of students aren’t going to go out and replicate this build. But – no doubt – millions of students are already looking at AI as a way to get their schoolwork done faster…
“millions of students are already looking at AI as a way to get their schoolwork done faster…” I hope that isn’t the case as the student then hasn’t learned anything. Sounds like we are well on the way to idiocracy . Well, maybe we are partially already there with what you see in the news any more. AI (as defined today) could be a real threat to society in general if you look down the road. Time to get out the books, and get down to plain o’ reading, writing, and arithmetic… without a computer in sight.
Yeah, wrong your hands and clutch your pearls, that’s productive.
My daughter wrote a movie review for Humanities class a couple of weeks ago. The instructor thought it was crafted beyond her skill level, and asked if she’d used ChatGPT to write the review instead.
I dunno about misguided…
Education in the US has a lot of problems, with no creative solutions being proposed in the past 50 years that have worked.
As proof-of-concept, this machine might jumpstart people into thinking more deeply about what an education is, what it is we want (for our children) out of an education, and how to conduct the education process.
Well people are certainly doing the asking.
Maybe at best it will be that assistant we wished for when going through school.
The goal of the project is to make a post-homework world tangible. To take it from a shadowy idea from the news to a physical object you can look at and think about. For teachers, trying to stay relevant, helpful, and even motivated is a struggle in the current world, and this is meant to help them get a grasp on how to move forward. Put simply, this is art. It does nothing technically new, it arguably is less useful than standard chatgpt, and it isn’t economical or marketable. All it is, is a physical representation of the chinese room.
It’s kinda like sabotaging the economy to make the post-capitalist world tangible… yes, but do you really want it?
in which case im curious to hear your thought about schools that don’t give any homework to start with. also where do you draw the line? how about students who are fast typer but have a bad penmanship?
In my experience, the student with bad penmanship, who takes time to write down the answers, who is concise and to the point because they can’t write long paragraphs, gets better results than the student who can quickly type the answer down and then soon forget it.
Students often use verbosity to mask the lack of detailed understanding.
If anybody is stupid enough to use this, they’ll bounce sooner or later. We already saw that after the lockdown: cheaters got caught with their pants down because they just couldn’t complete the in-person written exams. Passive learning by cramming youtube videos doesn’t work because hardly any of the details actually stick – welcome back next year.
Well having a GOOD example really helps.
Still, retention of facts takes time and repetition. Watching a video once only gives you the broad strokes.
Human brains actively delete information which is deemed “unimportant” because it isn’t repeated often enough.
I’d say the ones who copied from their materials (or AI) were doing rote memorization, but doing it badly – skipping the memorization part using copy-paste instead of reading and then writing. The ones who used AI to write their essay were just cheating.
Multiple choice tests aren’t ideal, but interestingly when they are beyond what someone can cram for, you begin to see a real separation in grades between the people who can reason out an answer and the people who are just good at remembering things and avoiding mistakes in following procedures – both valuable things, but not the most valuable in my opinion.
Short format questions with unambiguous answers tend to help those who can be prompted to recall a procedure rather than just facts, and can implement that procedure even if they do it blindly. That sort of person may be tricked by a similar sounding question to what they memorized, but will get decent grades without full understanding.
Short and long essay questions used to try to make sure someone could speak confidently about a topic, whether they knew what they were talking about or not – but at least when it was just humans, it was harder to write well about things they didn’t understand. Humans can add fluff to an essay to reach the necessary length, but usually they don’t add any more on-topic detail – just more length and maybe some digressions. So you can still establish what someone understands that way, and if they say something incorrect, they probably didn’t understand that thing. AI makes understanding harder to distinguish, because their result will have acceptable grammar and structure, but may or may not show whether someone actually understood it or if their AI was able to find enough similar writing to fake it. I once asked an AI to write about thermionic converters, which are similar to vacuum tubes except they are meant to just convert externally applied heat into electricity. Even after manually correcting it, the AI insisted that they work by using electricity to produce heat to produce electricity. To a human grader, perpetual motion machines clearly indicate complete and total lack of understanding. If the AI had remained vague enough to avoid saying the wrong thing, it might have been able to make a vague answer with enough correct parts to get partial credit for the question.
>Humans can add fluff to an essay to reach the necessary length, but usually they don’t add any more on-topic detail
Students who don’t understand the topic act similarly to ChatGPT by being vague and giving you apparent detail without committing to anything. For example, “A house may be large or small, it may be constructed of various materials including wood or stone, metals, ceramics and plastics. It is usually located close to people in cities or towns…”
Notice how the text can refer to just about anything if you blank out the word “house”. A statue can have the same description, or a swimming pool. What they’re doing is writing a “horoscope” and hoping the recipient is polite enough to interpret it in their favor.
Yeah, agreed. Though students also tend to learn to avoid making strong claims about things they’re not sure about in case it’s false. ChatGPT might include mention of houses made of straw or sticks or bricks due to the childrens’ story. A student might not include straw and would rephrase sticks to wood or something more generic, in order to manage risk. (Since omitting a potential rare material is a minor problem, but adding something incorrect is a major one.)
Humans fail versus ChatGPT when ChatGPT can mimic the way people normally write about a topic, while the students decide to be just as vague but can’t avoid writing with a different pattern. Kind of like if a student wrote a horoscope-type answer describing a creature and the student was picturing a housecat while the actual creature was very different. The line “Some people think they’re cute when they look up at you wanting food” is acceptable for a lot of animals, but it would be out of place in an essay about a sabertooth cat. The AI would probably know that they’re usually mentioned as being scary and not make that mistake, but then it’s luck whether it accidentally claims they have six toes.
So when you see something obviously wrong, you can still take lots of points off for it, but if the AI builds up the same length of horoscope-type answer without chancing to make such a mistake, then the essay question doesn’t show you the difference in students and AI very well.
I think it’s more an indictment of the necessity of after school work. Homework is dumb. Do the assignments in class.
Maybe good when the idea of participatory families still existed.
Classes are often too short to start and finish a topic in one sitting; it takes a certain amount of time to just start and stop. In K12, the “projects” are better than the homework. A daily worksheet with a long series of similar problems brute forces the learning process; if the kids are forced to spend 2 hours a day on the topic of course they’ll remember more than if they only spent 30 effective minutes. But not everything is about practice, and people tend to get into the habit of thinking it’s normal to assign enough work that some kids don’t have time for anything else.
The US primary education system is mostly designed around the least common denominator, because we qualify it by passing rates for standardized testing. Filling out worksheets for rote memorization doesn’t do anything for a fair number of people. It’s just a waste of time if you already know the material / actually pay attention in class. I would place good money on the student that built a machine to do their homework has better scores than many that fill in the worksheet by hand.
>It’s just a waste of time if you already know the material / actually pay attention in class
And how do you do that? Especially for people who aren’t interested or motivated to learn what you have to teach them, because they’re basically stupid kids?
I love hackaday just a hack a day ago yall posted an article about laser triangulation on 3 d prints. you think you could use that to detect the AI forgery? https://hackaday.com/2023/05/06/laser-triangulation-makes-3d-printer-pressure-advance-tuning-easier/
dont have to go that far. anyone experienced in handwriting analysis or with the slightest understanding of penstroke will identify these as machine produced. The pen maintains perpendicularity with the surface. Needs a few more axis of motion and a lot more training
Well… if you are able to make a homework machine (design and build it yourself) you’ve proven your worthy of a degree.
Or just proven you can follow instructions.
Which can be an asset depending on the career you’re aiming at.
>Whether it pushes education away from rote memorization remains to be seen.
Passive learning really doesn’t work. We saw that during the lockdown when people were just consuming youtube videos and answering online questionnaires and puzzles. Once we got back to normal written exams, people did so poorly almost nobody passed – because they only had the vaguest superficial idea and were used to copying all the rest directly from the materials without thinking about it. The simple fact that you have to spend effort to read a text or listen to a lecture and then write it down – by hand, not just copy-typing it – seems to have much better results.
Human behavior arises out of internalized information interacting with the external world. When you remember nothing, there’s not much you can think about, and there won’t be those “a-ha” moments where something clicks in your head to solve a problem.
Also as an interesting aside, people who started before covid retained good results either way, while people who only saw online education completely folded when they had to produce answers on the spot.
And it wasn’t just the failure to come up with an answer – they were producing wrong and nonsensical answers to questions they were previously able to complete correctly.
I think once you pass the low hurdle of being able to do anything at all in a subject is when rote memorization begins to become a problem. Much like the old apprentice/journeyman/master delineations, rote memorization of facts followed by procedures is a starting point. No matter how good you are at that, you don’t understand anything until you’re able to figure out things you don’t already remember, or adapt to things that don’t match what you have seen before. That’s when things start to click. And if you’re someone who’s made it to that stage but you’re tested on rote memorization ability, then you’re being let down by your educators.
I agree that you should spend time reading and writing about a topic if no other means of review presents itself, but posing and answering questions, or thinking through variations on a situation, or other things that go beyond repetition can be crucial. If you’re taught about physics using a car rolling down a slope, and you ask yourself what happens if the wheels are different sizes, then you find out the answer, you might learn something. If you work out the same problem twice? Not as much, but better than plugging numbers into formulas you stole off the internet.
It will re-surface when you’re doing the more advanced stuff that requires mastery of the lower levels. It would be a bummer if you’re doing some mathematical analysis and you find that you’ve forgotten the chain rule of derivation for example.
Well, you’ll master some things as you go. But improving your mastery of other low level things isn’t worth hindering your progress at learning the advanced stuff, yet that’s the choice I was faced with when I was in school. And most of the time, learning what’s possible and how to think about a situation will be more likely to lead you to the right answer than being very good at knowing exactly how to perform any particular operation. You should remember the chain rule by understanding it rather than memorizing it if you need it at all, since it’s unlike a lot of the derivative rules which just say what the derivative of a certain class of functions is. But I wouldn’t necessarily prioritize being good at knowing derivatives without a chart or calculator, if it means giving up e.g. knowing you can go from considering a perimeter to considering the surface it encloses (green’s theorum).
Passive learning really doesn’t work. We saw that during the /censored word/ when people were just consuming youtube videos and answering online questionnaires and puzzles. Once we got back to normal written exams, people did so poorly almost nobody passed – because they only had the vaguest superficial idea and were used to copying all the rest directly from the materials without thinking about it. The simple fact that you have to spend effort to read a text or listen to a lecture and then write it down – by hand, not just copy-typing it – seems to have much better results.
This. During medical school and pharmacology in particular, everyone was trading their big lists of meds and action and side effects and so on. Then try to memorize that. I made my own, line by excruciating line and by the time it was done, didn’t actually need the list itself much. Making the list WAS the education. Same with anatomy- sure look in a book but if you really want to learn it, like 3D relationships and such, drawing them yourself is way better. Mastery. Separate debate if, say, a dermatologist needs to do this at all but …
In a similar way, it’s interesting to work with project managers in engineering, where you may have to explain the same technical detail (and why it means their idea doesn’t work) multiple times because they keep forgetting the details and going back to “But what if we just…!”
Had a prof who would let anyone bring in a single side of paper “cheat sheet” with anything on it. Same logic — if you write it down, you learn it. And the act of picking what goes on the limited sheet space teaches you what’s important. Etc.
All in all, I thought it was pretty cool.
And it’s realistic in jobs in many fields to refer to at least a cheat sheet worth of material from time to time, so in studying for any of those fields it makes sense to allow a small amount of the same. That way you’re able to focus on understanding instead of remembering equations or irrelevant precise facts.
The reason why you require people to remember is to make them remember that the fact exists even if they can’t remember what it was, so they know to look it up in the cheat sheet.
Looking back on teaching high school in the 2000’s, I recall only a few students who use cursive. I’m sure that producing their typical scratching works the same. I would not mind doing the writing in my notebooks.
Cursive only really works well with fountain pens. For ballpoints and mechanical pencils that need a certain amount of pressure, it’s more difficult to maintain a good continuous line.
True, it was developed for fountain pens and I much prefer them for writing of all sorts for the very low fatigue – if you know how to write with a relaxed hand and arm off the table. But todays kids, and the ones I was teaching in the 2000’s writing is torture. There were never taught to do it well and apparently all developed their own ball-of-knuckles death-grip auto-cramp methods. It was actually painfull to watch.
A good ballpoint is OK and some of the Pentel family have a fiber nib in the shape of a fountain pen nib and they work very well.
My handwriting is terrible and I get the “yips” often where I just randomly draw some extra curve and then have to go back and erase it, but give me a smooth piece of paper and a fine marker, and suddenly it just works.
I like fountain pens, especially as I can just refill them from an ink bottle, but there’s a massive difference in the cheap pens every business seems to buy and something like my 0.25mm pentel slicci, which takes very minimal force and controls its ink somewhat better. It helps a lot in trying to read my writing too, if the lines are suddenly possible to tell apart and I’m not fighting the pen.
The answer is to pay teachers more to teach concrete practical activities evaluated in class time with smaller class numbers. The financial savings model of mass “education ” by handing out creative /reflective writing challenges is what is going to be challenged. Why not now write an AI homework marking machine, and we call sit back and relax. The current lack of true educational values, ie a strong personal relationship of the teacher and student(s) together, leaves the current model exposed by AI. My first year Physics unit had 3 of 1 hr lectures and a 3hrs practical session each week. Our practical work was designed to be very educational and the work had to be completed and written up within the three hours. Our books never left the lab with us. This must have annoyed the hell off boarding college kids who had a network of wet jelly intelligence support in the form of off campus tutors to make sure the little darlings got through. It was a lot fairer to the poor kids who could not afford such live in advantages. It levelled the playing turf a good bit. The Physics lab was looking for gifted honest students, not cheats or fakes that did not do the hard yards themselves. By comparison Chemistry practicals were written up externally as was rife with “assisted” write ups.
The answer to AI distorting education? Plan better more meaningful education. The rote learning educator and the institutions that make vast sums of money from this brittle facade is what is being exposed here. I look forward to being able to pass off the onerous task of weeding out the bullshit in Hackaday replies by using AI, especially the replies written by AI. Now that would be handy.
In the US education is entirely in the hands of “Professional Educators” at the teacher’s colleges, and the unions. The last 20 years has been the disaster of “Group Cooperative Activities” and “circular curriculum” in which say a math book sparsely covers a lot of topics and comes full circle maybe later in the year and covers them a little more deeply. Then next year in “Math 2” you start the circle again, and again in “Math 3”. Basically most of the kids never figure out why they did that goofy matrix multiply thing in Math2 that somehow produced the answer to a bugs and frogs and trees question. Or the problem with which bicycle to make in your factory by drawing some lines on paper, or that it was a geometric approach to linear programming. The American student today is very ill served by the public schools.
Maybe this will force a change for the good but I will lay odds against.
Textbooks are a well known scam that’s been around forever; many university professors who don’t write their own or know of a good free reference will just specify something dated that looks useful while being more affordable. At the K12 level, I know the review process sucks and mostly the schools buy whatever’s available from the usual suspects whenever they get the money for a refresh. The individual teachers are basically herded into doing whatever new thing they are told they have to do if they’re going to keep trying to teach, sometimes. And sometimes, they don’t understand it either. :/
They buy whatever is being bought by the Texas schools. It drives the market. Home schoolers have much better choices, like Saxon for math.
There used to be teachers and researchers separately, but nowadays with the funding cuts there’s teacher-researchers and the teaching is allocated with just 20-30% of the total funds and about 10% of the total time because it’s the research that pulls in money from outside funding sources.
There are still tenure track research positions. They often require teaching one class for one semester a year. But the problem remains of the constant demand to find more grant money and employ more grad students with said grant money. Writing grant applications and papers to submit to publications leaves little time for research. The academic world is rather badly broken.
The problem isn’t new. In 1908 Felix Klein published a series of papers on elementary mathematics from an advanced standpoint. He wrote them for public school teachers. His concern was the extent to which new college students were both unprepared for the mathematics courses and unfamiliar with the notation and methods used by the experts. The teacher’s colleges and “professional educators” had gone off in their own direction using their own theories on how to teach the subject (highly influenced by the American John Dewey, whose ideas are still influential in US education departments). His goal in the ‘Erlangen Programme’ was to bring the teachers in line with the professional research mathematicians. There are excellent English language editions of the three volumes and well worth reading. “Elementary Mathematics from an Advanced Standpoint: Arithmetic, Algebra, Analysis”, “Elementary Mathematics from an Advanced Standpoint: Geometry”, “Elementary Mathematics from a Higher Standpoint: Volume III: Precision Mathematics and Approximation Mathematics”
The engineering industries could stand to teach a few engineering schools and especially the K12 schools the same lesson. And the field of business would love if K12 taught how to use a typical office suite on a desktop computer (at minimum).
im sure pearson is already drooling at the idea of having AI write the problems and answers for their online homework systems. then they will charge more money for the access because “AI powered”.
I remember a short story that focused on a teenager, morose because her father wouldn’t spring for the Latest Greatest Font upgrade for her “writer”, a dictation machine that transcribed her words into written form.
when I can buy it on aliexpress on tinde?
I’m a teacher, and I have taught in both the US and the UK.
I absolutely love and appreciate this as an artful response to the education system. I don’t think it’s likely to be terribly practical for anyone other than the inventor to use, but that’s not the point. This is a piece of mechanical rhetoric and performance art. It would have been way less work to just write the damn homework but this guy would rather do weeks of meaningful creative work than a few hours of rote copying. I love it.
One interesting thing — In the comments above, there seems to be a cultural disconnect happening due to the different approaches to homework between the US and the UK. In US secondary education (AKA high school) a percentage of your grade typically comes directly from completing homework assignments, often weekly. The exact details of this are left up to the teacher. In UK secondary education (GCSEs, A levels), homework pretty much only exists to help you prepare for an exam, and your final grade will be at least 70% from a standardized final exam. So cheating on homework, whether you approve of it or not, means very different things for the student in these different systems. (Don’t know about other countries. I think the UK approach is the more common one around the world?)
Unfortunately, I don’t think that innovations like AI chatbots or this homework writing machine are likely to make the education system in any country see the error of their ways and replace memorisation with authentic tasks and constructivist approaches. What is far more likely is that we will see even more reliance on timed exams under strict conditions. Timed exams are a great way to measure memorized knowledge and a very particular type of writing skill. Their other strength is that you can call them absolutely ‘fair’ in that everyone can be sitting the same exam with the same resources at the same exact time across the whole country. Unfortunately it is absolutely terrible at measuring problem solving, creativity, or research skills.
I don’t care how creative or good at problem solving and research you are if you lack the basic knowledge and even terminology of the subject because you’ve never memorized it. Thou shall not pass.
Re-inventing the wheel creatively is still wasted effort.
Comment glitched, but I think as bad as homework is, even timed exams are better. #345453534 has my full reply.
Even when homework (and quizzes, which are often similar) are a smaller fraction of your grade, things like chegg, tutors, and study groups regularly boost the final grades of those who use them above almost all of those classmates who don’t. The students who use such strategies have effectively seen their assignments completed before they’ve started it, along with a full explanation of the work, except that hopefully the specifics aren’t available and they can’t just copy the answers verbatim. It’s basically like having an older sibling who’s taken every class you take and gave you all their work, but they can’t take your test for you. Even then, if your test depends on a lot of cramming right before, well, if you had help you probably have more free time to study for the test.
Projects (even individual projects) tend to have grades that aren’t as skewed by the use of such strategies, but instead they are skewed by the fact that as a rigidly graded assignment, there are things you can’t do that you’d do if it was a project for a non-academic purpose. So if you can’t approach the end goal the way the instructor intended, you have to go above and beyond to figure out not only the lesson you were supposed to learn, but what it is that they intended you to do to get there, why it doesn’t work, and what to do instead that they will hopefully accept. If they instead set problems for you to try and address in a more-than-sufficient timeframe where everyone’s equally prepared and supplied, the fairness is a relief.
Multiple choice and such has its downsides, but just taking a timed exam is pretty good, and I think well designed questions can actually address creativity and problem solving, if there’s room for that in the topic under test. For example, you can definitely solve a programming puzzle like the ones on codingbat in a creative way. I used to often see how few lines I could use, or I’d use recursion for fun. Of course, it’s hard to test research like this. But you could provide a standard reference book for a few problems and make some of the problems be a short answer where the student says what the first few things they would look for in order to research X would be, or what sort of a question they could ask in order to get the answer. The instructor would have to grade how good of a question the student could formulate, though, using judgement.
Ugh, got the comment glitch again. #345453534
Leave a Reply Cancel reply
Please be kind and respectful to help make the comments section excellent. ( Comment Policy )
This site uses Akismet to reduce spam. Learn how your comment data is processed .
Never miss a hack
If you missed it.
Australia’s Second Largest Telco Went Dark, And Chaos Reigned
How To Talk To Your Scope
2023 Halloween Hackfest: This Year’s Spooky Winners
The Case For A Technology Aware Lobby Correspondent
A Look At All The Badge Hacks Of Supercon 2023
Fail Of The Week: This Flash Drive Will NOT Self-Destruct In Five Seconds
Thanks For Hacking
Hackaday Podcast 245: The Silver Swan, ET’s Umbrella Antenna, Model Tanks Vs Space Shuttle Tires
Linux Fu: Easy Kernel Debugging
Keebin’ With Kristina: The One With The Duplex Typewriter
By using our website and services, you expressly agree to the placement of our performance, functionality and advertising cookies. Learn more
- Español NEW
Danny Dunn and the Homework Machine facts for kids
Danny Dunn and the Homework Machine is the third novel in the Danny Dunn series of juvenile science fiction/adventure books written by Raymond Abrashkin and Jay Williams . The book is "about a boy who invents a machine to do his homework for him only to be tricked into doing more with his spare time".
The book was first published in 1958 and originally illustrated by Ezra Jack Keats . This is the first novel in the series to feature Irene.
Danny uses a computer that Professor Bullfinch has created for NASA to prepare his homework, despite Professor Bullfinch's warning that Danny is to leave the machine alone. With his friend Joe Pearson and his new neighbor, Irene Miller, Danny has some success with the machine before it is sabotaged. Danny figures out what is wrong with the machine and corrects the problem. Danny's teacher also learns about the machine, and has her ideas for the Homework Champions. Once she finds out, she thinks of a way to trick the kids.
The "homework machine" is in the style of the large mainframe computers of the 1950s, and one that uses paper punched cards . The concept of students using computers for research is common today; however, this computer was not merely a machine via which the drudgery of solving many three or four digit long division problems could be offloaded; it was also somehow able to accept "programming" of students' text books that enabled it to write reports on topics that were covered by the text books.
Amateur radio is used for the first (and possibly only) time in the series, with Danny and Irene attempting to get a homework question answered. The callsigns used would have been accurate for mid-western operators in that era but not for the mode used (shortwave). In any event, there was too much static and the kids resorted to opening the windows and talking across the alley.
- Paperback, 1958, illustrated by Ezra Jack Keats
- Hardback, 1958, illustrated by Ezra Jack Keats
- Hardback, 1960, illustrated by Ezra Jack Keats
MacDonald and Jane's
- Hardback, 1977, illustrated by Anne Mieke
- Paperback, 1979, #5 in their series
- Paperback, 1983 reissue, illustrated by Ezra Jack Keats
Danny Dunn and the Homework Machine was turned into a musical children's album on both Golden Records (Golden LP 239) and Wonderland Records (WLP-338), with music composed by Julie Mandel.
- This page was last modified on 6 November 2023, at 08:14. Suggest an edit .
- Log In / Register
- My Library Dashboard
- My Borrowing
- Checked Out
- Borrowing History
- ILL Requests
- My Collections
- For Later Shelf
- Completed Shelf
- In Progress Shelf
- My Settings
The Homework Machine The Homework Machine
- [S.l.] : Simon & Schuster Books for Young Readers, 2009.
From the community
More from the community, community lists featuring this title, community contributions.
Powered by BiblioCommons.
NERF: nerf04 Version 9.18.0@b5f06b4 Last updated 2023/10/31 13:30 Built 2023/10/23 17:15