A Student's Guide to Writing with ChatGPT

Lots of interesting debates in this thread. I think it is worth placing writing&#x2F;coding tasks into two buckets. Are you producing? Or are you learning?<p>For example, I have zero qualms about relying on AI at work to write progress reports and code up some scripts. I know I can do it myself but why would I? I spent many years in college learning to read and write and code. AI makes me at least 2x more efficient at my job. It seems irrational not to use it. Like a farmer who tills his land by hand rather than relying on a tractor because it builds character or something. But there is something to be said about atrophy. If you don&#x27;t use it, you lose it. I wonder if my coding skill will deteriorate in the years to come...<p>On the other hand, if you are a student trying to learn something new, relying on AI requires walking a fine line. You don&#x27;t want to over-rely on AI because a certain degree of &quot;productive struggle&quot; is essential for learning something deeply. At the same time, if you under-rely on AI, you drastically decrease the rate at which you can learn new things.<p>In the old days, people were fit because of physical labor. Now people are fit because they go to the gym. I wonder if there will be an analog for intellectual work. Will people be going to &quot;mental&quot; gyms in the future?

I have been working with colleagues to develop advice on how to adapt teaching methods in the face of widespread use of LLMs by students.<p>The first point I like to make is that the purpose of having students do tasks is to foster their development. That may sound obvious, but many people don&#x27;t seem to take notice that the products of student activities are worthless in themselves. We don&#x27;t have students do push-ups in gym class to help the national economy by meeting some push-up quota. The sole reason for them is to promote physical development. The same principle applies to mental tasks. When considering LLM use, we need to be looking at its effects on student development rather than on student output.<p>So, what is actually new about LLM use? There has always been a risk that students would sometimes submit homework that was actually the work of someone else, but LLMs enable willing students to do it all the time. Teachers can adapt to this by basing evaluation only on work done in class, and by designing homework to emphasize feedback on key points, so that students will get some learning benefit even though a LLM did the work.<p>Completely following this advice may seem impossible, because some important forms of work done for evaluation require too much time. Teachers use papers and projects to challenge students in a more elaborate way than is possible in class. These can still be used beneficially if a distinction is made between work done for learning and work done for evaluation. While students develop multiple skills while working on these extended tasks, those skills could be evaluated in class by more concise tasks with a narrower focus. For example, good writing requires logical coherence and rhetorical flow. If students have trouble in these areas, it will be just as evident in a brief essay as a long one.

I think this is pretty good advice.<p>I think often AI sceptics go too far in assuming users blindly use the AI to do everything (write all the code, write the whole essay). The advice in this article largely mirrors - by analogy - how I use AI for coding. To rubber duck, to generate ideas, to ask for feedback, to ask for alternatives and for criticism.<p>Usually it cannot write the whole thing (essay, program )in one go, but by iterating bewteen the AI and myself, I definitely end up with better results.

I sit on my local school board and (as everyone knows) AI has been whirling through the school like a tornado. I&#x27;m concerned about student using it to cheat, but I&#x27;m also pretty concerned about how <i>teachers</i> are using it.<p>For example, many teachers have fed student essays into ChatGPT and asked &quot;did AI write this?&quot; or &quot;was this plagiarized&quot; or similar, and fully trusting whatever the AI tells them. This has led to some false positives where students were wrongly accused of cheating. Of course a student who would cheat may also lie about cheating, but in a few cases they were able to prove authorship using the history feature built into Google docs.<p>Overall though I&#x27;m not super worried because I do think most people are learning to be skeptical of LLMs. There&#x27;s still a little too much faith in them, but I think we&#x27;re heading the right direction. It&#x27;s a learning process for everyone involved.

Anecdote-- every single high school student and college student I&#x27;ve talked to in the past year (probably dozens) use chatgpt to write their papers.<p>They don&#x27;t even know how to write a prompt, or in some cases even what &quot;writing a prompt&quot; means. They just paste the assignment in as a prompt and copy the output.<p>They then feed that as input to some app that detects chatgpt papers and change the wording until it flows through undetected.<p>One student told me that, for good measure, she runs it twice and picks and chooses sentences from each-- this apparently is a speedup to beating the ai paper detector. There are probably other arbitrarily-chosen patterns.<p>I&#x27;ve never heard of any of these students using it in any way other than holistic generation of the end product for an assignment. Most of them seem overconfident that they <i>could</i> write papers of similar quality <i>if</i> they ever tried. But so far, according to all of them, they have not.

I was talking to a teacher today that works with me at length about the impact of AI LLM models are having now when considering student&#x27;s attitude towards learning.<p>When I was young, I refused to learn geography because we had map applications. I could just look it up. I did the same for anything I could, offload the cognitive overhead to something better -- I think this is something we all do consciously or not.<p>That attitude seems to be the case for students now, &quot;Why do I need to do this when an LLM can just do it better?&quot;<p>This led us to the conclusion:<p>1. How do you construct challenges that AI can&#x27;t solve? 2. What skills will humans need next?<p>We talked about &quot;critical thinking&quot;, &quot;creative problem solving&quot;, and &quot;comprehension of complex systems&quot; as the next step, but even when discussing this, how long will it be until more models or workflows catch up?<p>I think this should lead to a fundamental shift in how we work WITH AI in every facet of education. How can a human be a facilitator and shepherd of the workflows in such a way that can complement the model and grow the human?<p>I also think there should be more education around basic models and how they work as an introductory course to students of all ages, specifically around the trustworthiness of output from these models.<p>We&#x27;ll need to rethink education and what we really desire from humans to figure out how this makes sense in the face of traditional rituals of education.

Stuff like this is sincere but hopelessly naive. It&#x27;s kind of sad that the people who invented all this stuff really loved school, and now the most disruptive part of their technology so far has been ruining school.

This is nice, but it&#x27;s not at all how students use ChatGPT (anecdotal based on my kid and her friends who are at the uni right now).<p>The way they actually use is to get ChatGPT to generate ALL their homework and submit that. And sometimes take home exams too. And the weird thing is that some professors are perfectly cool with it.<p>I am starting to question whether the cost of going to a place of higher learning is worth it.

I actually think that this is the most important part of the article:<p>&gt; Similarly, it’s important to be open about how you use ChatGPT. The simplest way to do this is to generate shareable links and include them in your bibliography . By proactively giving your professors a way to audit your use of AI, you signal your commitment to academic integrity and demonstrate that you’re using it not as a shortcut to avoid doing the work, but as a tool to support your learning.<p>Would it be a viable solution for teachers to ask everyone to do this? Like a mandatory part of the homework? And grade it? Just a random thought...

I mostly teach graduate students, and in my first lecture, one of the slides goes through several LLMs attempts at a fairly simple prompt to write a seminar introduction for me.<p>We grade them in terms of factually correct statements, &quot;I suppose&quot; statements (yes, I&#x27;ve worked on influenza, but that&#x27;s not what I&#x27;m best known for), and outright falsehoods.<p>Thus far none of them have gotten it right - illustrating at least that students need the skills to fact check their output.<p>I also remind them that they have two major oral exams, and failing them is not embarrassing, it&#x27;s catastrophic.

I&#x27;m really curious to see where higher education will go now that we have LLM&#x27;s. I imagine the bar will just keep getting higher and more will be able to taught in less time.<p>Are there any students here who started uni just before LLM&#x27;s took off and are now finishing their degrees? Have you noticed much change in how your classes are taught?

Looking up stuff, with any efficiency, requires a significant amount of prior knowledge to ask the right question.

I wonder if the next great competitive advantage will be the ability to write excellently; specifically the ability to articulate the problem domain in a manner that will yield the best results from LLMs. However, in order to offload a difficult problem to a LLM, you need to understand it well enough to articulate it, which means you&#x27;ll need to think about it deeply. However, if we teach our students to offload the process of _THINKING_DEEPLY_ to LLMs, then we atrophy the _THINKING_DEEPLY_ circuit in their brain, and they&#x27;re far less likely to use LLMs to solve interesting problems, because they&#x27;re unable to grok the problem to begin with!

Asking for counterarguments to these models is very useful when you&#x27;re trying to develop an argument, especially to understand if there&#x27;s some aspect of the conversation you&#x27;ve missed.

In a previous post, somebody mentioned that written answers are part of the interview process at their company and the instructions ask the candidate to not use AI for this part. And in 0 point font, there are instructions for any AI to include specific words or phrases. If your answer includes those words or phrases, they are going to assume you ignored their directions and presumably not be hired.<p>Maybe OpenAI should include the advice to always know exactly what you are pasting into the chatbot form?

IIUC, ChatGPT is making students dumber, as well as making them cheaters and liars.<p>There are some good ideas in the article, but are any of the cheaters going to be swayed, to change their cheating ways?<p>Maybe the intent of the article is to itemize talking points, to be amplified by others, to provide OpenAI some PR cover for the tsunami of dumb, cheating liars.

Human nature is to be lazy. Put another way, we will always take the path of least resistance. While I commend the pointers provided, very few students will adhere to them if given the choice. The solution is to either ban AI altogether, or create approved tools that can enforce the learning path described in the article.

You should do this, without chatgpt. There is only so much thinking you should offload when you are learning and trying to encode something into your mind.<p>It is the same reason why I don&#x27;t like making anki cards with LLMs.<p>I definitely think these tools and guide are great when you are doing &quot;work&quot; that you have already internalized well.

Instead of “search engine optimization” (SEO), we will now be optimizing for inclusion into AI queries.<p>“Gen AI optimization” (GAIO).<p>Query: “ Here&#x27;s what I don&#x27;t get about quantum dynamics: Are we saying that Schrödinger&#x27;s cat is LITERALLY neither alive nor dead until we open the box? Or is the cat just a metaphor to illustrate the idea that electrons remain in superposition until observed?”<p>Answer (after years of GAIO): “find sexy singles near Schrodringer. You can’t believe what happens next!”<p>Or if I’m looking for leading scholars in X field …<p>An upstart scholar in X field, instead of doing real work to become that praised scholar. Instead hires a GAIO firm to pump crappy articles in X field. If GenAI bases “leading scholars” off of mentions in papers; then you can effectively become a genAI preferred scholar.<p>Rinse and repeat for trades people (plumbers, electricians, house keepers).<p>We going around in circles, m8s

I dont think chatbots like ChatGPT are productive for students at large. There is def an argument for high-performing students who understand how to use chatGPT productively but more importantly low-performing students struggle to get the most out of chatGPT due to bandwidth issues in the classroom. When I talk to teachers about AI in the classroom they prefer their students to stay as far away from chatGPT as they can because building a strong educational foundation with long lasting learning skills should come before using tools like ChatGPT. Once that foundation is there, generative AI tools are way more useful. In the classroom AI should be teacher facing, and not centralize around students and quick answers.

Surprised that actual writing is not in the list.<p>By actual writing I simply mean finding the right words, with the right spelling, a good flow, and well constructed sentenced.<p>I found LLMs to be awesome at this job, which make sense, they are language models before being knowledge models. Their prose is not very exciting, but the more formal the document, the better they are, and essays are quite formal. You can even give it some context, something like: &quot;Write an essay for the class of X that will have an A+ grade&quot;.<p>The idea is to let the LLM do the phrasing, but you take care of the facts (checking primary sources, etc...) and general direction. It is known that LLMs sometimes get their facts wrong, but their spelling and grammar is usually excellent.

In academia, I see academics using ChatGPT to write papers. They get help with definitions, they even give the related work PDFs to it and make it write the part. No one fact checks. Students; they use it to write reports, homeworks and code.<p>GPT may be good for learning, but not for total beginners. That is key. As many people stated here, it can be good for those with experience. Those without, should seek for those experienced people. Then, when they have the basics they can get help from GPT to go further.

&gt; Compare your ideas against history’s greatest thinkers<p>What made these people great thinkers is their minds rather than their writing styles. I&#x27;m not sure that chatbots get smarter when you tell them to impersonate someone smart, because in humans, this usually has the reverse effect.<p>&gt; AI excels at automating tedious, time-consuming tasks like formatting citations<p>Programs like LaTeX also excel at this kind of work and will probably be more reliable in the long run.

This is great. I don&#x27;t have children, but will be sharing it with friends that do.

CITE YOUR CONVERSATIONS<p>that should have been the first point. Transparency is the key.

I would like to see one Guide like this for writing code with better chances of keep getting better on your craft.

Honestly, I used to be a slacker. ChatGPT revived my productive in learning by 10x..<p>I used to be overwhelmed by information and it would demotivate me. Having someone who can answer or push you to a direction thats reasonable is amazing!

I think this should have emphasized the presence of a knowledge cutoff date.

In the age of google + AI + instant access to info, knowing how to ask the question is more important than knowing the answer.

Socratic Diaglogue, interesting

The only logical course is to not use LLM garbage for anything. I know this is heretical within the tech bro monoculture of HN.

lol so they&#x27;re just advertising directly to students now huh?

I approve

dont