how to make chatgpt write a research paper

Home → Academic Writing → How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

Jordan Kruszynski

• January 4, 2024

If you’re an academic, you’ve probably spent a lot of time planning and writing research papers. It’s a fine art, and one that requires a fair amount of skill, precision and preparation. But whether you’re an old master in the field, or a rookie embarking on your first serious research paper, there are tools that can help you to simplify the planning stages and organise your thoughts more effectively.

One of those tools is the (in)famous ChatGPT , and it’s this that we’ll be focusing on in our article. In the right hands, ChatGPT can become a powerful research tool that will make your paper-writing that little bit easier. So sit back, relax, and discover our tips and tricks for using ChatGPT to write a research paper.

What is ChatGPT?

Just in case you don’t already know, ChatGPT is an artificial intelligence tool developed by OpenAI that can help you with your research. It uses natural language processing to understand what you’re looking for and provide you with relevant information. You can ask it questions, and it will provide you with answers in a conversational style, as well as offer sources to back up its information.

One of the biggest advantages of ChatGPT is that it can save you time. Instead of spending hours searching for sources, you can simply ask ChatGPT for help. This can bring you a reliable list of sources for further investigation fairly quickly. It’s crucial to note however that the AI shouldn’t be exploited to do the actual writing of the paper for you. This could see you accused of plagiarism or misconduct, and besides, as a researcher, you’re probably rightfully proud of your ability to write a compelling paper.

Another advantage of ChatGPT is that it’s always available (even when libraries or other sources of information might be inaccessible) so you can work on your research paper at any time of day or night.

Interested in learning more about how AI programs like ChatGPT are changing the academic landscape? Listen to Oxford researcher Samantha-Kaye Johnston’s views from the frontline in this exciting episode of The Research Beat podcast.

The benefits of using ChatGPT to write a research paper

There are many benefits to using ChatGPT for research papers. Firstly, as we mentioned earlier, it can save you time . A slow drag of several hours looking for specific sources can be reduced to just a few minutes with the AI’s help.

Secondly, it can help you find sources that you might not have found otherwise . ChatGPT has access to a wide range of sources, including academic journals and books.

Thirdly, it can help you organise your research . ChatGPT can provide you with a summary of the information you’ve gathered, making it easier to analyse and integrate into your research paper.

How to use ChatGPT to write a research paper – a step by step guide

• Start by creating a list of questions that you want to answer in your research paper.
• Open ChatGPT and ask it one of the questions on your list, for example, ‘What is the critical history of feminist literature in Europe?’
• ChatGPT will provide you with a list of sources to check out.
• Read through the sources and take notes on the information that is relevant to your research question.
• Repeat steps 2-4 for each question on your list.
• Once you’ve gathered all of your information, organise it into an outline for your research paper.
• Use the information you’ve gathered to write your research paper.

Working with your sources

Once you have your sources in order, you might want to use prompts to get help from ChatGPT with other parts of the writing process. A prompt is a specific instruction to the AI that can give you tailored information or responses. For example, if you’re struggling to understand part of another research paper, you could use the following prompt:

‘Please explain the following paragraphs in simple words. I am having trouble understanding (insert concept here).’

Input the prompt along with the relevant passage from the source, and ChatGPT will provide a summary that could help you to unlock your understanding of the tricky concept.

Looking for ChatGPT prompts tailor-made for academics? Check out Audemic’s list of over 50 prompts to help you with your work and research!

Writing tips and tricks for using ChatGPT

When using ChatGPT to write a research paper, it’s important to keep a few things in mind. Firstly, make sure that you’re using reliable sources . ChatGPT can provide you with a list of sources, but it’s up to you to determine which ones are reliable.

Secondly, make sure that you’re paraphrasing the information you’ve gathered in your own words . You don’t want to cheat or be accused of it.

Finally, make sure that you’re using the information you’ve gathered to answer your research questions . Everything you uncover through ChatGPT should be used to feed your own understanding and improve the quality and precision of your answers.

Common mistakes to avoid when using ChatGPT to write a research paper

While ChatGPT is an excellent tool for research papers, there are some common mistakes to avoid:

• Crucially, don’t rely too heavily on ChatGPT. It’s essential to do some of your research on your own and use ChatGPT to supplement it.
• Don’t forget to cite your sources correctly. Just because ChatGPT provided you with the information doesn’t mean that you don’t need to cite it. Moreover, ChatGPT cannot actually produce academic citations for you.
• Always remember to proofread your research paper carefully, especially if you’ve used AI elements to construct it.

ChatGPT vs. traditional research methods

While traditional research methods have their advantages and always will, ChatGPT, as we’ve seen, has some of its own. We think one of the best uses for AI programs like ChatGPT is to accelerate parts of the paper-writing process that would otherwise take hours. If you can use the AI to produce a list of interesting and relevant sources, then you can get to work quickly as an academic, studying and analysing those sources to determine their value within your paper. In general, if you approach ChatGPT with an attitude of maintaining quality and integrity, then it can only enhance your work.

Final Thoughts

ChatGPT is everywhere at the moment, and while it has stirred up a great deal of controversy thanks to its implications for academic integrity, it can be an excellent tool for helping to write research papers . The key is using it correctly, and not relying too heavily on it. Focusing on how it can enhance your already-sharp academic writing skills will allow you to save time, find plenty of valuable sources, and organise your paper’s structure more effectively. And that’s how to use ChatGPT to write a research paper!

ChatGPT is not the only AI tool that can help with these parts of the paper-writing puzzle. If you want to listen to academic papers, break them down into digestible pieces and freely take notes on them, then Audemic is waiting for you. Try it for free today!

Keep striving, researchers! ✨

Table of Contents

Related articles.

How to Publish a Research Paper: A Step-by-Step Guide

You’re in academia. You’re going steady. Your research is going well and you begin to wonder: ‘How exactly do I get a

Behind the Scenes: What Does a Research Assistant Do?

Have you ever wondered what goes on behind the scenes in a research lab? Does it involve acting out the whims of

How to Write a Research Paper Introduction: Hook, Line, and Sinker

Want to know how to write a research paper introduction that dazzles? Struggling to hook your reader in with your opening sentences?

Blog Podcast

Privacy policy Terms of service

Subscribe to our newsletter!

Discover more from Audemic: Access any academic research via audio

Subscribe now to keep reading and get access to the full archive.

Type your email…

Continue reading

Use ChatGPT To Write A Research Paper: Chat GPT For Scientific Papers

Producing academic writing can be daunting, but with ChatGPT, OpenAI’s advanced AI language model, the process becomes more accessible and efficient.

Here, learn how ChatGPT transforms the traditional approach to writing research papers, offering innovative solutions from structuring outlines to crafting intricate arguments.

Whether you’re a seasoned researcher or a novice writer, discover how ChatGPT’s capabilities can enhance your research process, ensuring a comprehensive and well-articulated paper.

Use ChatGPT To Write A Scientific Research Paper 

Step 1: General Introduction

Imagine you’re about to write a scientific research paper. You have a specific topic in mind but are struggling with how to structure your paper or what essential points to include in your introduction.

This is where ChatGPT, OpenAI’s powerful AI language model, steps in to assist in the writing process.

Start by asking ChatGPT to create an outline. For instance, you could provide ChatGPT with your research question and any relevant details about your study.

The AI will generate an outline that covers key aspects of your introduction, helping you to organize your thoughts and structure your paper effectively.

After you’ve brainstormed and provided the necessary prompts, ChatGPT can help draft an initial version of your introduction. Remember, the output generated by ChatGPT may vary, and it’s essential to use ChatGPT in conjunction with your own expertise.

For example, you might tell ChatGPT to write an introduction for a paper on the impact of a certain technology in healthcare. ChatGPT can generate text based on your prompt, providing insights into:

• Existing research,
• Gaps in the literature, and
• The significance of your study.

This initial draft can serve as a valuable foundation for your research paper.

Some prompts that you can use include:

• Develop an introduction that captures the readers’ attention and provides a concise overview of the research topic: [research topic].
• Compose an introductory paragraph that effectively introduces the readers to the topic at hand: [research topic]. Provide background information, and context for the research.
• Create an introduction that sets the stage for an academic article centered around [research topic]. Highlight its rationals, and the structure of the article.

Step 2: Problem Statement

When you use ChatGPT to write a research paper, especially for crafting a problem statement, you begin by providing a clear prompt.

This includes outlining your research question and any specific details about your topic. ChatGPT’s AI language model then processes this information to generate a concise and coherent problem statement.

For instance, if your research paper is on the environmental impact of urban development, you would ask ChatGPT to focus on this specific topic.

The AI can assist by generating text that highlights existing research gaps, the significance of the study, and why addressing this particular issue is vital.

ChatGPT can help structure your paper, creating an outline that seamlessly leads from the problem statement to other sections of your paper.

Remember, the content generated by ChatGPT should be used as a starting point. It’s crucial to review and edit this to ensure originality and accuracy. Proofreading the paper for grammar and making necessary revisions is a must.

Step 3: Research Question :

Writing research questions for your paper can seem daunting, but with ChatGPT, you can streamline this critical part of the writing process. You can start by asking ChatGPT to brainstorm ideas specific to your topic.

Say your research paper is on climate change’s effects on agriculture. Tell ChatGPT, “Generate research questions about the impact of climate change on crop yield.”

ChatGPT’s output will include various questions, such as “How does increased temperature affect wheat production in the Midwest?” These prompts can spark further ideas and help you refine your research objectives.

Remember, while ChatGPT can assist in the research paper writing process, it cannot write the paper entirely. Use the content generated by ChatGPT as a foundation, and then build upon it with your research and insights.

It’s always vital to review and edit the AI-generated material to ensure it aligns with your research goals and fills the gaps in existing literature.

Some example prompts to generate research objectives include:

• Generate a list of potential research questions about [research topic]
• Suggest innovative research questions focusing on [research topic]
• Identify research questions exploring the relationship between [variable 1 in research] and [variable 2 in research]

Step 4: Literature Review

Next, ask ChatGPT to assist in creating an outline for your literature review. For example, if you input, “Create an outline for a literature review on AI and environmental sustainability,” ChatGPT can structure your paper effectively, outlining key:

• and subtopics.

This AI language model excels in organizing research, laying out a coherent structure for your review.

Now, onto the juicy part: generating content. You can provide ChatGPT with prompts like, “Summarise recent studies on AI and renewable energy sources.”

ChatGPT will respond with a synthesis of:

• Incorporating recent studies and
• Key findings.

While ChatGPT can generate text and even suggest citations, it’s always crucial to cross-check and validate these with your research materials.

Remember, ChatGPT’s output is a starting point. You still need to review and edit the content for grammar, punctuation, and relevance to your research topic.

It’s essential to use ChatGPT in conjunction with your expertise, especially when analysing and interpreting data. The AI model can provide a valuable foundation, but the depth and accuracy of your literature review depend on your critical analysis and human expertise.

• Analyze and summarize the existing literature on [research topic], identifying the major theories, methodologies and results used in previous research.
• Analyze the limitations in the existing literature on [research topic], suggesting gaps for further research and exploration.
• Conduct a systematic literature review on [research topic], organising and categorising the relevant research papers based on their research questions, methodologies, and findings.

Step 5: Research Methodology

The next step is structuring your paper, particularly the methodology section. Here, ChatGPT’s prowess in generating an organized outline comes into play.

You can ask ChatGPT to create an outline for your methodology section. This AI tool can suggest various research methods relevant to your topic, such as:

• Qualitative,
• Quantitative, or
• Mixed methods.

It’s like having a virtual research assistant who understands the nuances of scientific research paper writing.

When it comes to the actual content generation, ChatGPT can provide you with a basic draft. For example, you can prompt ChatGPT with, “Generate a draft for the methodology section on a paper about online learning effectiveness.”

ChatGPT will produce a text that covers key aspects like:

• Sample size,
• Data collection methods, and
• Analysis techniques.

While ChatGPT can generate content, it’s essential to use it in conjunction with your own expertise. The content needs to be reviewed and edited to fit your specific research context.

ChatGPT can assist in organising your research and generating initial drafts, but the accuracy and relevancy of the methodology depend on your input and analysis.

• Write a detailed methodology section for conducting a qualitative study on [research topic].
• Create a data collection plan and describe the data analysis techniques in a quantitative research study on [research topic]
• Suggest a research design and methodology for conducting an experimental study on [research topic].

Step 6: Findings

Once you’ve gathered your data, the next step is to make sense of it. Here, ChatGPT can be used to brainstorm different ways to analyse and interpret your data. 

If your research paper is on the effects of a new educational strategy on student performance, you can ask ChatGPT to suggest various statistical methods to analyze your results. 

ChatGPT’s ability to process natural language and generate text-based suggestions can provide you with unique insights that may not have been immediately apparent.

When it comes to writing about your findings, ChatGPT can assist in structuring this section of your paper. You can tell ChatGPT about the results you obtained and ask for help in creating an outline that effectively presents these findings.

The AI model can suggest how to organize your results, discuss their implications, and highlight key points that are relevant to your research question.

You will need to review, edit, and ensure that the findings are accurately represented and align with the collected data.

• Analyse the findings related to [research topic] below, and then present and interpret the quantitative data collected below in a comprehensive report.
• Discuss the reliability and validity of the data about  [research topic] in the study below, based on relevant literature.
• Describe the key patterns and trends observed in the qualitative data gathered during the research on [research topic].

Use Chat GPT To Brainstorm And Write A Research Paper

ChatGPT emerges as a revolutionary tool in the realm of academic writing, offering unparalleled assistance in crafting research papers. Its ability to generate ideas, structure content, and provide insights makes it an invaluable asset for researchers and students alike.

It’s important to remember that while ChatGPT is a powerful aid, the uniqueness and depth of a research paper ultimately depend on the writer’s critical thinking and expertise. Embrace ChatGPT as a collaborative partner in your scholarly endeavours for enhanced research and writing efficiency.

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Navigation Menu

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

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

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

ahmetbersoz/chatgpt-prompts-for-academic-writing

Folders and files, repository files navigation.

✨ NEW UPDATE: Literature Review Generator

A Custom GPT for Literature Review Generator has been released. It efficiently parses PDF files of research publications, extracts key themes, and creates a literature review section for your academic publications.

TRY NOW: https://chat.openai.com/g/g-G3U8pZGwC-literature-review-generator

ChatGPT Prompts for Academic Writing

In this repository, this list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans. Whether you're a student, researcher, or academic professional, these prompts can help you hone your writing abilities and tackle your writing projects with confidence.

Use directly in: chat.openai.com

The list is regularly updated, so you can keep track of new prompts by following this repository.

TIPS: As there is a limit to the number of words that can be used in ChatGPT, you can input your text multiple times using the prompt "Read this [PARAPGRAPH]:" and then run your final prompt "Considering the above text...".

You can also use prompts splitter: chatgpt-prompt-splitter.jjdiaz.dev

BRAINSTORMING

Article sections, title/topic sentence, introduction, literature review.

NOTE: Be careful and double-check article existence. ChatGPT may generate fake references

Methodology

Experiments, future works, improving language, summarization, plan/presentation, working with documents (available only in gpt-4).

Upload a PDF file of a paper then:

Upload a PDF file of your paper then:

Upload PDF files of papers then:

Upload a figure image then:

Contributors 4

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• 07 July 2023
• Correction 11 July 2023

Scientists used ChatGPT to generate an entire paper from scratch — but is it any good?

• Gemma Conroy

You can also search for this author in PubMed   Google Scholar

A pair of scientists has produced a research paper in less than an hour with the help of ChatGPT — a tool driven by artificial intelligence (AI) that can understand and generate human-like text. The article was fluent, insightful and presented in the expected structure for a scientific paper, but researchers say that there are many hurdles to overcome before the tool can be truly helpful.

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

Nature 619 , 443-444 (2023)

doi: https://doi.org/10.1038/d41586-023-02218-z

Updates & Corrections

Correction 11 July 2023 : An earlier version of this story implied that human researchers had guided ChatGPT through the steps to create a research paper. In fact, the data-to-paper tool developed by Kishony and Ifargan acted as an intermediary between ChatGPT and the researchers. The text has been corrected in several places to reflect this.

Reprints and permissions

Illuminating ‘the ugly side of science’: fresh incentives for reporting negative results

Career Feature 08 MAY 24

Mount Etna’s spectacular smoke rings and more — April’s best science images

News 03 MAY 24

Plagiarism in peer-review reports could be the ‘tip of the iceberg’

Nature Index 01 MAY 24

Algorithm ranks peer reviewers by reputation — but critics warn of bias

Nature Index 25 APR 24

Clinician Researcher/Group Leader in Cancer Cell Therapies

An excellent opportunity is available for a Group Leader with expertise in cellular therapies to join the Cancer Research program at QIMR Berghofer.

Herston, Brisbane (AU)

QIMR Berghofer

Faculty Positions at the Center for Machine Learning Research (CMLR), Peking University

CMLR's goal is to advance machine learning-related research across a wide range of disciplines.

Beijing, China

Center for Machine Learning Research (CMLR), Peking University

Faculty Positions at SUSTech Department of Biomedical Engineering

We seek outstanding applicants for full-time tenure-track/tenured faculty positions. Positions are available for both junior and senior-level.

Shenzhen, Guangdong, China

Southern University of Science and Technology (Biomedical Engineering)

Southeast University Future Technology Institute Recruitment Notice

Professor openings in mechanical engineering, control science and engineering, and integrating emerging interdisciplinary majors

Nanjing, Jiangsu (CN)

Southeast University

Staff Scientist

A Staff Scientist position is available in the laboratory of Drs. Elliot and Glassberg to study translational aspects of lung injury, repair and fibro

Maywood, Illinois

Loyola University Chicago - Department of Medicine

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

11 Ways To Use ChatGPT To Write A Research Paper

All these tasks that would have taken you hours, maybe even days, and sometimes longer, can now take just a few minutes or even shorter when you use ChatGPT.

Today I want to talk about the top things that ChatGPT can help you with when it comes to research papers so that you can write your paper much faster.

Before we dive into the specific tips and show you how to use ChatGPT when writing research papers, let me preface by saying that it is just a tool and is limited in many ways. It’s not good enough yet to replace you and replace the researcher in writing the research paper.

You’ve got to understand that you can’t just tell ChatGPT to write a couple of paragraphs for you and then use it as ChatGPT writes it and then submit it. It’s just not going to work like that. Plus, it would kind of be plagiarism although AI isn’t human.

So what you’ve got to do is remember about the limitations of the technology:

• One main limitation is that it was trained on data up to January 2022, which means that more recent papers and more recent data are not going to be there.
• Another crucial limitation is that it doesn’t pull the references for most things. So when you’re writing the literature review, ChatGPT can write paragraphs for you real quick, but there are no references for them, and you can’t really pull the references for it.
• And remember: what ChatGPT writes isn’t necessarily perfect or good enough to be published in a top journal. You will most likely have to take ChatGPT text, improve upon it, revise it before you finally submit it.

So, let’s dive in and let’s see exactly how you can accelerate your progress with your research papers using ChatGPT.

1. How to Write Research Paper Title with ChatGPT

The first thing that we’re gonna do is get ChatGPT to give us some good research paper titles using ChatGPT.

I’m going to copy and paste the abstract that I’ve already got, and then I’m going to tell ChatGPT to suggest a title for a research paper based on this abstract .

Here is the title of the research paper that ChatGPT generated: “ Unmasking the Academic Impersonator: A Multifaceted Investigation into Detecting LLM-Generated Writing ”.

I think ChatGPT’s title is very good.

Now let’s see if ChatGPT can maybe give us some alternative so that we can choose.

ChatGPT message : Can you suggest two additional titles for the research paper based on that same abstract?

Title 2: “ Guardians of Academic Integrity: Unveiling LLM-Generated Content through Dataset, User Study, and Detection Algorithms “.

Title 3: “ Deciphering the Enigma: Insights into Detecting LLM-Generated Academic Writing via Dataset, User Perception, and Advanced Algorithms “.

ChatGPT message : Can you suggest two more titles which will be phrased as questions based on that same abstract?

Title 4: “ Can Humans Spot the Imposter? Exploring the Challenge of Detecting LLM-Generated Academic Writing “.

Title 5: “ Is AI Outsmarting Academia? Investigating the Detection of LLM-Generated Content in Research Papers “.

So ChatGPT can clearly give you titles. The way to do it is just to paste the abstract and ask ChatGPT to give you titles. An alternative, if you’ve got the whole introduction written, you can also give ChatGPT the introduction, and it will give you good titles as well.

2. How to Use ChatGPT to Write an Abstract

Now let’s see if ChatGPT can do the reverse.

Can ChatGPT write an abstract based on the title of your paper?

ChatGPT message : Write an abstract for a research paper based on this title.

The result is really good. It follows the exact structure of an abstract.

3. How to Write Research Outline with ChatGPT

Now, you can ask ChatGPT to write an outline that includes as many details of your task as possible. For example, I used the title suggested by ChatGPT in the first step.

ChatGPT prompt : Write an outline for a research paper that is [NUMBER] pages long and needs to use [NUMBER] primary sources on this topic: [TITLE]

ChatGPT generated a 33-point outline that details the areas I should cover in my research paper.

4. How to Write an Introduction Using ChatGPT

Let’s ask ChatGPT to write an introduction to a research paper and see what comes out of it.

ChatGPT prompt : Write a [NUMBER] paragraph introduction to a research paper entitled: [TITLE]

ChatGPT wrote a 4 paragraph introduction and it looks very good again.

5. How to Write a Thesis Statement Using ChatGPT

Writing a strong thesis statement is essential for any research paper, as it serves as the backbone of your argument or analysis. With ChatGPT you can simplify the writing process.

ChatGPT message : Write a thesis statement for a research paper based on this title.

ChatGPT generates a thesis statement based on the information provided. Review the response carefully, considering its clarity, relevance, and alignment with your research goals. If necessary, refine the statement by providing additional guidance or asking follow-up questions.

6. Find The Research Gap Using ChatGPT

Now we can get ChatGPT to do is to work on a research gap. This is what many PhD students and researchers do.

Let’s see if ChatGPT can suggest us any good research gaps.

ChatGPT message : Suggest a research gap on the topic of detecting ChatGPT-generated academic writing.

This is really well presented.

7. Writing a Research Question Using ChatGPT

If you have a research gap, you can just give ChatGPT the research gap, and from that, you can get research questions.

ChatGPT message : Suggest two different research questions based on the following research gap.

Both of these research questions are fantastic. And both of them should be investigated.

8. Making a Research Question More Specific with ChatGPT

A big problem that a lot of people have with research questions or aims is that they are too vague or too general.

What ChatGPT suggests here is pretty good already, but let’s see if it’s capable of making a research question more specific.

ChatGPT message : Make the following research question more specific and precise.

Question #1

Question #2

Right, this is pretty good. This is definitely more specific.

I think ChatGPT can help you to specify your research questions.

If you’re struggling with your aim or research question is too vague, then you can use ChatGPT to make it more specific.

9. How To Use ChatGPT To Write A Literature Review

You’re just kind of starting out with a topic, and you want to see what are some of the key publications that you should read on that topic just to get yourself started.

Let’s see how ChatGPT can help us accelerate the literature review process.

ChatGPT prompt : I am investigating [TOPIC]. What are the key research papers on this topic I should read?

I have to say that I’m not very impressed. I think the result was affected by the limitations of the data on which the algorithm was trained until 2022.

Nevertheless, you can definitely use ChatGPT to get you the literature that you should start reading.

10. Writing a Methodology For a Research Paper Using ChatGPT

After reviewing the literature, I ask ChatGPT to suggest the methodology section for the topic. This section will include research approaches and sampling techniques for data collection.

ChatGPT message : Write a research methodology for a research paper based on this title.

As you can see, ChatGPT can help generate the overall structure of the research methodology.

11. How to use ChatGPT to summarize a research paper

The last thing which I feel ChatGPT could be very useful in research is asking for summarization.

We can ask ChatGPT to summarize a particular paper or the key takeaways that could be important for us from that paper.

In that way, you can just note it down in a proper way with proper citations, which you could use as a literature review in your research writing or academic writing.

ChatGPT prompt: Can you provide a summary of [PAPER NAME]

Can ChatGPT write research papers?

To answer this question, I turned to ChatGPT, here is its answer:

“I can indeed assist in generating content for research papers, including providing structured information, drafting paragraphs, and even offering suggestions for methodology and analysis.However, it’s crucial to note that while I can generate text based on the input and parameters provided, I lack true understanding, creativity, or original thought. Therefore, while I can help with the mechanical aspects of writing a research paper, the conceptualization, critical analysis, and interpretation of research findings are best left to human researchers who possess domain expertise and critical thinking skills. Ultimately, the quality and validity of a research paper rely on the expertise and integrity of its human authors.”

Using the power of ChatGPT can be transformative for those grappling with the daunting task of writing research papers.

ChatGPT won’t write your research paper for you from scratch, but it can make the writing process much easier.

It gives you some content to work with. And then you can rewrite it in your own words.

You’ve got a starting point now.

Related articles

• 7 Reasons Why Copywriters Must Be Shameless
• 5 Factors that Distinguish Great Copywriters
• 10 Things Epic Copywriters Do
• Career Advice for Writers: How to Become a Copywriter
• 5 Things You Need to Know About Copywriting

A professional freelance web copywriter with several years’ experience in web marketing and SEO copywriting.

Other posts by Christina Walker

Comments (0)

• Interesting
• Scholarships
• UGC-CARE Journals

How to Use ChatGpt to Write a Scientific Research Paper?

• Tips for using ChatGpt to write a scientific research paper

ChatGPT is an AI language model, it can generate text based on the input provided by user. However, It should be used as a tool to assist in the writing process rather than being relied on entirely to write a scientific research paper. Writing a scientific research paper requires not only knowledge of the subject matter but also critical thinking, analysis, and interpretation of data. Therefore, it is essential to use ChatGPT in conjunction with your own expertise and knowledge.

In this article, ilovephd provided tips to use ChatGPT for Scientific research paper writing.

ChatGpt to Write a Scientific Research Paper

Here are some steps you can take to use ChatGPT to write a scientific research paper :

• Begin by identifying the research question or hypothesis that you want to address in your paper.
• Use ChatGPT to search for relevant scientific literature related to your research question or hypothesis. ChatGPT can provide you with a summary of existing research on the topic, as well as any gaps in the literature.
• Collect data through experiments, surveys, or other means. Then, use ChatGPT to help analyze and interpret your data, as well as generate visualizations to support your findings.
• Use ChatGPT to help organize your paper by creating an outline, structuring your arguments, and ensuring that your paper is well-organized and flows logically.
• Use ChatGPT to generate draft sections of your paper, such as the introduction, methods, results, and discussion sections. However, ensure that you review and edit the content generated by ChatGPT to ensure it aligns with your research and is written in your own voice.
• Use ChatGPT to help edit and proofread your paper for grammar, punctuation, and spelling errors. However, ensure that you carefully review and make any necessary revisions to the content generated by ChatGPT to ensure accuracy and clarity.

Remember that while ChatGPT can be a helpful tool in the scientific research paper writing process, it is not a substitute for your own expertise, critical thinking, and analysis. Therefore, it is important to use ChatGPT in conjunction with your own knowledge and skills to ensure a high-quality scientific research paper.

10 Myths about ChatGPT in scientific research paper writing

Here are 10 myths about ChatGpt in scientific research paper writing:

• Fact: While ChatGpt can assist in generating content for a scientific research paper, it cannot write a paper entirely on its own. Human expertise, critical thinking, and analysis are still essential in the writing process.
• Fact: ChatGpt is a tool that can assist in the research and writing process, but it cannot replace human researchers. The expertise and skills of human researchers are still necessary in scientific research.
• Fact: ChatGpt can assist in analyzing and interpreting data, but human input is still essential in ensuring accuracy and drawing meaningful conclusions.
• Fact: While ChatGpt can generate original content, it is still possible for the content to be similar or identical to existing material. It is important to review and edit any content generated by ChatGpt to ensure it is original and appropriately cited.
• Fact: ChatGpt’s ability to write effectively may vary depending on the scientific field. It is essential to provide ChatGpt with specific information and context to ensure accurate and effective writing.
• Fact: ChatGpt’s content may still contain errors or mistakes, and it is important to review and edit any content generated by ChatGpt for accuracy and clarity.
• Fact: ChatGpt’s content is based on machine learning and natural language processing, and while it can produce high-quality content, it is not necessarily better than human-written content.
• Myth: ChatGpt can write content that is more persuasive than human-written content. Fact: Persuasion requires human communication skills and emotional intelligence, and ChatGpt’s content may not be as persuasive as human-written content.
• Fact: ChatGpt’s content is based on data and input provided by humans, and therefore may contain subjective bias. It is important to review and edit any content generated by ChatGpt to ensure it is objective.
• Fact: ChatGpt’s content is only as good as the research and knowledge that is provided to it. Therefore, it is still essential for researchers to have expertise and knowledge in their field and to provide accurate information to ChatGpt to generate effective content.

I hope, this article would help you to know how to use ChatGPT 4 to your scientific research paper writing.

Find this article with the following keywords

• AI language model for scientific research paper writing
• Writing scientific research papers with ChatGpt
• ChatGpt for scientific paper writing
• How to use ChatGpt for scientific research paper writing
• Scientific paper writing with the help of ChatGpt
• ChatGpt for scientific research and writing
• How ChatGpt can assist with scientific research paper writing
• Writing high-quality scientific research papers using ChatGpt
• ChatGpt as a tool for scientific paper writing
• artificial intelligence
• Research Paper
• Research Paper Writing
• research paper writing tips
• Scientific Research Paper Writing

Anna’s Archive – Download Research Papers for Free

Six effective tips to identify research gap, 24 best free plagiarism checkers in 2024, most popular, iitm & birmingham – joint master program, fulbright-kalam climate fellowship: fostering us-india collaboration, fulbright specialist program 2024-25, how to check scopus indexed journals 2024, types of research variable in research with example, what is hypothesis in research types, examples, & importance, how to write a research paper a complete guide, best for you, what is phd, popular posts, 480 ugc-care list of journals – science – 2024, popular category.

• POSTDOC 317
• Interesting 259
• Journals 234
• Fellowship 128
• Research Methodology 102
• All Scopus Indexed Journals 92

iLovePhD is a research education website to know updated research-related information. It helps researchers to find top journals for publishing research articles and get an easy manual for research tools. The main aim of this website is to help Ph.D. scholars who are working in various domains to get more valuable ideas to carry out their research. Learn the current groundbreaking research activities around the world, love the process of getting a Ph.D.

Contact us: [email protected]

Google News

Copyright © 2024 iLovePhD. All rights reserved

• Artificial intelligence

ChatGPT in Higher Education: Facts and Ideas to Consider

Introduction

It is safe to say that by now, you have seen many articles/posts, opinions, and stories about ChatGPT—and the larger AI-Language Learning Models (LLMs)—in relation to higher education and teaching/learning in particular. These writings included several perspectives ranging from raising concerns to celebrating new opportunities and a mix of the former and the latter. Also, these writings continue to evolve and grow rapidly in number as new AI-powered LLMs continue to emerge and evolve (e.g., Google’s new AI LLMs: Bard ).

The intent of this piece is not to add another article sharing tips or concerns about ChatGPT. That being said, this article (1) summarizes the major concerns about ChatGPT and (2) the ideas about its positive implications based on what it is published to date.

Concerns about ChatGPT

Faculty, scholars, and higher education leaders have raised several concerns about ChatGPT. These concerns stem from possible ways it can be used.

• Using ChatGPT to cheat by asking it to write essays/answer open-ended questions in exams/discussion forums and homework assignments (December 19th, 2022 NPR Story ) (December 6th, 2022 Atlantic Story ) (January 16 New York Times Story ).
• Using ChatGPT to author scholarly works which conflict with the ethical standards of scientific inquiry. Several high-impact/profile journals have already formulated principles to guide authors on how to use LLMs AI tools and why it is not allowed to credit such tool as an author—any attribution of authorship carries with it accountability for the scholarly work, and no AI tool can take such responsibility (January 24th, 2023 Nature Editorial ).
• ChatGPT can threaten the privacy of students/faculty (and any other user). Its privacy policy states that data can be shared with third-party vendors, law enforcement, affiliates, and other users. Also, while one can delete their ChatGPT account, the prompts they entered into ChatGPT cannot be deleted. This setup threatens sensitive or controversial topics as this data cannot be removed (January 2023 Publication by Dr. Torrey Trust ).
• ChatGPT is not always trustworthy, as it can fabricate quotes and references. In an experiment conducted by Dr. Daniel Hickey at Indiana University Bloomington, Instructional Systems Technology department, “ ChatGPT was able to write a marginally acceptable literature review paper, but fabricated some quotes and references. With more work such as including paper abstracts in the prompts, GPT is scarily good at referencing research literature, perhaps as well as a first-year graduate student.” (January 6th, 2023, Article by Dr. Daniel Hickey )

Excitement about ChatGPT

At the other end of the spectrum, there have been several ideas that express interest and excitement about ChatGPT in higher education. These ideas stem from how they can be used ethically and in a controlled manner.

• Using ChatGPT to speed up the writing of drafts for several outlets (reports, abstracts, emails, conference proposals, press releases, recommendation letters, etc.) ChatGPT can produce elaborated writing that must be edited to remove any possible inconsistencies or inaccuracies (December 7th, 2022 Social Science Space story )
• Using ChatGPT in the process of brainstorming ideas for curriculum design, lesson planning, and learning activities. The tool can provide some novel ideas or remind educators of some instructional techniques and strategies that they had heard about in the past (January 23rd, 2023, Article by Dr. David Wiley ).
• Using ChatGPT to provide students tutoring/scaffolds. The tool can act like a virtual tutor who does not simply give the answer to the student but rather scaffold them to reach the correct answers by themselves. (Sal Khan, founder/CEO of Khan Academy, Spring 2023 TED Talk )
• Teaching with ChatGPT to train students on using AI tools and models, provide opportunities to exercise critical thinking skills, and improve their technological literacy (January 12th New York Times story ).

Concluding Thoughts

There are major concerns about ChatGPT and the larger AI-powered Language Learning Models (LLMs) phenomenon. These concerns are legitimate and are opposed by notable ideas about the positive implications of AI-powered LLMs in higher education classrooms. As we aspire to make evidence-based educational and learning design decisions, one should carefully review the research that has been done on AI in relation to higher education up to this point and engage with the gaps as opportunities to expand knowledge and find new opportunities and risks.

Our University’s newly formed advisory committee on the applications of generative AI is a good example of how higher education institutions ought to recommend the use, evaluation, and development of emergent AI tools and services. Additionally, discussions about generative AI and its implications on education happening in public venues are necessary to strengthen the public-facing mission of the University, where input from educators, students, and members of the community is welcome.

Related Articles

Generative AI for Course Design: Crafting Learning Objectives

Generative AI for Course Design: The Basics

Featured Topics

Featured series.

A series of random questions answered by Harvard experts.

Explore the Gazette

Read the latest.

Roger Ware Brockett, 84

Providing community support

A change of mind, heart, and soul

“Telling people not to use ChatGPT is not preparing people for the world of the future,” said Sam Altman, CEO of OpenAI.

Niles Singer/Harvard Staff Photographer

Did student or ChatGPT write that paper? Does it matter?

Sam Altman, CEO of firm that developed app, says ethics do matter, but they need to be rethought (and AI isn’t going away)

Harvard Correspondent

Colleges and universities have been wrestling with concerns over plagiarism and other ethical questions surrounding the use of AI since the emergence of ChatGPT in late 2022.

But Sam Altman, whose company, OpenAI, launched the chatbot app, said during a campus visit Wednesday that AI is such a powerful tool that higher education would be doing its students a disservice by turning its back on it — if that were even possible now. And some of the old rules of ethics will need to be rethought.

“Cheating on homework is obviously bad,” said Altman. “But what we mean by cheating and what the expected rules are does change over time.”

Altman discussed AI in the academy, along with the subtleties of using ChatGPT and other generative AI tools, while at the University to receive the Experiment Cup from Xfund , an early stage venture capital firm. That event was sponsored by the John A. Paulson School for Engineering and Applied Science, Harvard Business School, and the Institute for Business in Global Society ( BiGS ). It featured a conversation between Altman and Xfund co-founder Patrick Chung ’96.

Speaking to the Gazette before the Cup presentation, Altman likened the initial uproar at schools over ChatGPT to the ones that arose after the arrival of calculators and, later, search engines like Google. “People said, ‘We’ve got to ban these because people will just cheat on their homework,’” he said.

Altman, who left Stanford at 19 to start Loopt, a location-sharing social media app, said the reaction to calculators, for instance, was overblown. “If people don’t need to calculate a sine function by hand again … then mathematical education is over,” he said, with a gentle half-smile on his face.

Altman helped launch OpenAI in 2015 and its wildly influential ChatGPT — which can write papers and generate computer programs, among other things — before being removed in 2023 and then reinstated four days later as the company’s CEO.

ChatGPT, he said, has the potential to exponentially increase productivity in the same way calculators freed users from performing calculations by hand, calling the app “a calculator for words.”

He warned, “Telling people not to use ChatGPT is not preparing people for the world of the future.”

Following a bit of back-and-forth about how the ethics of using ChatGPT and other generative AI may differ in various disciplines, Altman came down hard in favor of utility, praising AI’s massive potential in every field.

“Standards are just going to have to evolve,” he said. He dismissed the notion that ChatGPT could be used for writing in the sciences, where the emphasis is on the findings, but not in the humanities, where the expression of ideas is central.

“Writing a paper the old-fashioned way is not going to be the thing,” he said. “Using the tool to best discover and express, to communicate ideas, I think that’s where things are going to go in the future.”

Altman, who last month joined the Department of Homeland Security’s Artificial Intelligence Safety and Security Board , said ethics remains a concern, and one that has yet to be resolved.

“There will be a conversation about what are the absolute limits of the tool, how do we as a society … negotiate ‘Here is what AI systems can never do.’ Where do we set the defaults? How much does an individual user get to move things around within those boundaries? How do we think about different countries’ laws?”

However, that discussion should not slow the development of AI. Instead, Altman described parallel tracks.

“Generally speaking, I do think these are tools that should do what their users want,” he said, before adding an important, if less than specific, caveat: “But there are going to have to be real limits.”

Share this article

You might like.

Memorial Minute — Faculty of Arts and Sciences

Harvard Allston Partnership Fund awards grants to 26 Allston-Brighton nonprofits

Choosing Harvard took LyLena Estabine down an uncertain path. The former student co-president has no regrets.

Epic science inside a cubic millimeter of brain

Researchers publish largest-ever dataset of neural connections

Excited about new diet drug? This procedure seems better choice.

Study finds minimally invasive treatment more cost-effective over time, brings greater weight loss

How far has COVID set back students?

An economist, a policy expert, and a teacher explain why learning losses are worse than many parents realize

• Do Not Sell My Personal Info

•  ⋅ 

How To Use ChatGPT For Keyword Research

ChatGPT for keyword research can be a powerful assistant. Understand any topic for keyword research in minutes with these prompts.

Anyone not using ChatGPT for keyword research is missing a trick.

You can save time and understand an entire topic in seconds instead of hours.

In this article, I outline my most effective ChatGPT prompts for keyword research and teach you how I put them together so that you, too, can take, edit, and enhance them even further.

But before we jump into the prompts, I want to emphasize that you shouldn’t replace keyword research tools or disregard traditional keyword research methods .

ChatGPT can make mistakes. It can even create new keywords if you give it the right prompt. For example, I asked it to provide me with a unique keyword for the topic “SEO” that had never been searched before.

“ Interstellar Internet SEO : Optimizing content for the theoretical concept of an interstellar internet, considering the challenges of space-time and interplanetary communication delays.”

Although I want to jump into my LinkedIn profile and update my title to “Interstellar Internet SEO Consultant,” unfortunately, no one has searched that (and they probably never will)!

You must not blindly rely on the data you get back from ChatGPT.

What you can rely on ChatGPT for is the topic ideation stage of keyword research and inspiration.

ChatGPT is a large language model trained with massive amounts of data to accurately predict what word will come next in a sentence. However, it does not know how to do keyword research yet.

Instead, think of ChatGPT as having an expert on any topic armed with the information if you ask it the right question.

In this guide, that is exactly what I aim to teach you how to do – the most essential prompts you need to know when performing topical keyword research .

Best ChatGPT Keyword Research Prompts

The following ChatGPT keyword research prompts can be used on any niche, even a topic to which you are brand new.

For this demonstration, let’s use the topic of “ SEO ” to demonstrate these prompts.

Generating Keyword Ideas Based On A Topic

What are the {x} most popular sub-topics related to {topic}.

The first prompt is to give you an idea of the niche.

As shown above, ChatGPT did a great job understanding and breaking down SEO into three pillars: on-page , off-page & technical .

The key to the following prompt is to take one of the topics ChatGPT has given and query the sub-topics.

What Are The {X} Most Popular Sub-topics Related To {Sub-topic}?

For this example, let’s query, “What are the most popular sub-topics related to keyword research?”

Having done keyword research for over 10 years, I would expect it to output information related to keyword research metrics, the types of keywords, and intent .

Let’s see.

Again, right on the money.

To get the keywords you want without having ChatGPT describe each answer, use the prompt “list without description.”

Here is an example of that.

List Without Description The Top {X} Most Popular Keywords For The Topic Of {X}

You can even branch these keywords out further into their long-tail .

Example prompt: List Without Description The Top {X} Most Popular Long-tail Keywords For The Topic “{X}”

List Without Description The Top Semantically Related Keywords And Entities For The Topic {X}

You can even ask ChatGPT what any topic’s semantically related keywords and entities are!

Tip: The Onion Method Of Prompting ChatGPT

When you are happy with a series of prompts, add them all to one prompt. For example, so far in this article, we have asked ChatGPT the following:

• What are the four most popular sub-topics related to SEO?
• What are the four most popular sub-topics related to keyword research
• List without description the top five most popular keywords for “keyword intent”?
• List without description the top five most popular long-tail keywords for the topic “keyword intent types”?
• List without description the top semantically related keywords and entities for the topic “types of keyword intent in SEO.”

Combine all five into one prompt by telling ChatGPT to perform a series of steps. Example:

“Perform the following steps in a consecutive order Step 1, Step 2, Step 3, Step 4, and Step 5”

“Perform the following steps in a consecutive order Step 1, Step 2, Step 3, Step 4 and Step 5. Step 1 – Generate an answer for the 3 most popular sub-topics related to {Topic}?. Step 2 – Generate 3 of the most popular sub-topics related to each answer. Step 3 – Take those answers and list without description their top 3 most popular keywords. Step 4 – For the answers given of their most popular keywords, provide 3 long-tail keywords. Step 5 – for each long-tail keyword offered in the response, a list without descriptions 3 of their top semantically related keywords and entities.”

Generating Keyword Ideas Based On A Question

Taking the steps approach from above, we can get ChatGPT to help streamline getting keyword ideas based on a question. For example, let’s ask, “ What is SEO? ”

“Perform the following steps in a consecutive order Step 1, Step 2, Step 3, and Step 4. Step 1 Generate 10 questions about “{Question}”?. Step 2 – Generate 5 more questions about “{Question}” that do not repeat the above. Step 3 – Generate 5 more questions about “{Question}” that do not repeat the above. Step 4 – Based on the above Steps 1,2,3 suggest a final list of questions avoiding duplicates or semantically similar questions.”

Generating Keyword Ideas Using ChatGPT Based On The Alphabet Soup Method

One of my favorite methods, manually, without even using a keyword research tool, is to generate keyword research ideas from Google autocomplete , going from A to Z.

You can also do this using ChatGPT.

Example prompt:

“give me popular keywords that includes the keyword “SEO”, and the next letter of the word starts with a”

Tip : Using the onion prompting method above, we can combine all this in one prompt.

“Give me five popular keywords that include “SEO” in the word, and the following letter starts with a. Once the answer has been done, move on to giving five more popular keywords that include “SEO” for each letter of the alphabet b to z.”

Generating Keyword Ideas Based On User Personas

When it comes to keyword research, understanding user personas is essential for understanding your target audience and keeping your keyword research focused and targeted. ChatGPT may help you get an initial understanding of customer personas.

“For the topic of “{Topic}” list 10 keywords each for the different types of user personas”

You could even go a step further and ask for questions based on those topics that those specific user personas may be searching for:

As well as get the keywords to target based on those questions:

“For each question listed above for each persona, list the keywords, as well as the long-tail keywords to target, and put them in a table”

Generating Keyword Ideas Using ChatGPT Based On Searcher Intent And User Personas

Understanding the keywords your target persona may be searching is the first step to effective keyword research. The next step is to understand the search intent behind those keywords and which content format may work best.

For example, a business owner who is new to SEO or has just heard about it may be searching for “what is SEO.”

However, if they are further down the funnel and in the navigational stage, they may search for “top SEO firms.”

You can query ChatGPT to inspire you here based on any topic and your target user persona.

SEO Example:

“For the topic of “{Topic}” list 10 keywords each for the different types of searcher intent that a {Target Persona} would be searching for”

ChatGPT For Keyword Research Admin

Here is how you can best use ChatGPT for keyword research admin tasks.

Using ChatGPT As A Keyword Categorization Tool

One of the use cases for using ChatGPT is for keyword categorization .

In the past, I would have had to devise spreadsheet formulas to categorize keywords or even spend hours filtering and manually categorizing keywords.

ChatGPT can be a great companion for running a short version of this for you.

Let’s say you have done keyword research in a keyword research tool, have a list of keywords, and want to categorize them.

You could use the following prompt:

“Filter the below list of keywords into categories, target persona, searcher intent, search volume and add information to a six-column table: List of keywords – [LIST OF KEYWORDS], Keyword Search Volume [SEARCH VOLUMES] and Keyword Difficulties [KEYWORD DIFFICUTIES].”

Tip : Add keyword metrics from the keyword research tools, as using the search volumes that a ChatGPT prompt may give you will be wildly inaccurate at best.

Using ChatGPT For Keyword Clustering

Another of ChatGPT’s use cases for keyword research is to help you cluster . Many keywords have the same intent, and by grouping related keywords, you may find that one piece of content can often target multiple keywords at once.

However, be careful not to rely only on LLM data for clustering. What ChatGPT may cluster as a similar keyword, the SERP or the user may not agree with. But it is a good starting point.

The big downside of using ChatGPT for keyword clustering is actually the amount of keyword data you can cluster based on the memory limits.

So, you may find a keyword clustering tool or script that is better for large keyword clustering tasks. But for small amounts of keywords, ChatGPT is actually quite good.

A great use small keyword clustering use case using ChatGPT is for grouping People Also Ask (PAA) questions.

Use the following prompt to group keywords based on their semantic relationships. For example:

“Organize the following keywords into groups based on their semantic relationships, and give a short name to each group: [LIST OF PAA], create a two-column table where each keyword sits on its own row.

Using Chat GPT For Keyword Expansion By Patterns

One of my favorite methods of doing keyword research is pattern spotting.

Most seed keywords have a variable that can expand your target keywords.

Here are a few examples of patterns:

1. Question Patterns

(who, what, where, why, how, are, can, do, does, will)

“Generate [X] keywords for the topic “[Topic]” that contain any or all of the following “who, what, where, why, how, are, can, do, does, will”

2. Comparison Patterns

“Generate 50 keywords for the topic “{Topic}” that contain any or all of the following “for, vs, alternative, best, top, review”

3. Brand Patterns

Another one of my favorite modifiers is a keyword by brand.

We are probably all familiar with the most popular SEO brands; however, if you aren’t, you could ask your AI friend to do the heavy lifting.

“For the top {Topic} brands what are the top “vs” keywords”

4. Search Intent Patterns

One of the most common search intent patterns is “best.”

When someone is searching for a “best {topic}” keyword, they are generally searching for a comprehensive list or guide that highlights the top options, products, or services within that specific topic, along with their features, benefits, and potential drawbacks, to make an informed decision.

“For the topic of “[Topic]” what are the 20 top keywords that include “best”

Again, this guide to keyword research using ChatGPT has emphasized the ease of generating keyword research ideas by utilizing ChatGPT throughout the process.

Keyword Research Using ChatGPT Vs. Keyword Research Tools

Free vs. paid keyword research tools.

Like keyword research tools, ChatGPT has free and paid options.

However, one of the most significant drawbacks of using ChatGPT for keyword research alone is the absence of SEO metrics to help you make smarter decisions.

To improve accuracy, you could take the results it gives you and verify them with your classic keyword research tool – or vice versa, as shown above, uploading accurate data into the tool and then prompting.

However, you must consider how long it takes to type and fine-tune your prompt to get your desired data versus using the filters within popular keyword research tools.

For example, if we use a popular keyword research tool using filters, you could have all of the “best” queries with all of their SEO metrics:

And unlike ChatGPT, generally, there is no token limit; you can extract several hundred, if not thousands, of keywords at a time.

As I have mentioned multiple times throughout this piece, you cannot blindly trust the data or SEO metrics it may attempt to provide you with.

The key is to validate the keyword research with a keyword research tool.

ChatGPT For International SEO Keyword Research

ChatGPT can be a terrific multilingual keyword research assistant.

For example, if you wanted to research keywords in a foreign language such as French. You could ask ChatGPT to translate your English keywords;

But don’t worry, there is a workaround: If you have access to a competitor keyword research tool, you can see what webpage is ranking for that query – and then identify the top keyword for that page based on the ChatGPT translated keywords that do have search volume.

Or, if you don’t have access to a paid keyword research tool, you could always take the top-performing result, extract the page copy, and then ask ChatGPT what the primary keyword for the page is.

Key Takeaway

ChatGPT can be an expert on any topic and an invaluable keyword research tool. However, it is another tool to add to your toolbox when doing keyword research; it does not replace traditional keyword research tools.

As shown throughout this tutorial, from making up keywords at the beginning to inaccuracies around data and translations, ChatGPT can make mistakes when used for keyword research.

You cannot blindly trust the data you get back from ChatGPT.

However, it can offer a shortcut to understanding any topic for which you need to do keyword research and, as a result, save you countless hours.

But the key is how you prompt.

The prompts I shared with you above will help you understand a topic in minutes instead of hours and allow you to better seed keywords using keyword research tools.

It can even replace mundane keyword clustering tasks that you used to do with formulas in spreadsheets or generate ideas based on keywords you give it.

Paired with traditional keyword research tools, ChatGPT for keyword research can be a powerful tool in your arsenal.

More resources:

• Tools Of The Trade: When To Use ChatGPT And When To Use Google 
• What Is ChatGPT & How Can You Use It?
• 8 ChatGPT Alternatives You Can Try In 2024

Featured Image: Tatiana Shepeleva/Shutterstock

Dan Smullen, a News SEO Consultant from Dublin, Ireland has an MBA with a specialism in Marketing from the prestigious ...

Subscribe To Our Newsletter.

Conquer your day with daily search marketing news.

More From Forbes

5 chatgpt prompts to make everything you write more compelling.

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

5 ChatGPT prompts to make everything you write more compelling

Bad copy kills businesses. It finds its way into emails, Slack messages, memos and more. Copywriting is not a skill reserved for marketers. It’s everyone’s problem. Every member of your team should learn how to write compelling words and edit them until they sing. And who knows? If the HR manager wrote updates like a Buzzfeed journalist, you might even read until the end.

Use these prompts to upgrade the copy for everything you write, no matter how many people will actually see. Copy, paste and edit the square brackets in ChatGPT, and keep the same chat window open so the context carries through.

Improve your writing with 5 powerful ChatGPT prompts

Improve the hook.

Grab attention with the first line or face an uphill battle from the start. Just because you have a fancy job title, doesn’t mean anyone will read your messages. Make them want to. Use this prompt to find a more compelling way of opening. Strike a chord, create an information gap. Make someone stand up and pay attention so they keep on reading. On Twitter you have a second to get someone’s attention. Keep that in mind when writing for anywhere else.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to help the first line grab the attention of the reader so they keep reading. Understand the copy and create a hook. The hook should be between 6-12 words long and aim to strike a chord, create an information gap or draw someone in. This should not be a question. Give me 5 options for new hooks for this copy so I can choose the best: [Paste copy here]”

Best High-Yield Savings Accounts Of 2024

Best 5% interest savings accounts of 2024, make it shorter.

“I haven’t got time to read all that. Just tell me what it means.” If given that response, you’d tell them in a few sentences. Those are the sentences that matter. If in doubt, cut the fluff. The context can be a footnote for those interested in knowing more. Online or within your company, someone doesn’t need to be taken on a convoluted journey to find the single line that’s relevant to them. Make everything you write shorter. Pack a punch with your words, don’t make someone want to punch you.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the recipients]. Your task is to make it shorter so my audience will read and understand it without needing to skim read. Look to remove waffle and additional words, and change any instances of passive voice to active. Remove repetition. Keep my tone of voice and keep the meaning of the text the same. Remove any information not essential to the main message and add as numbered footnotes at the end: [Paste copy here]”

Everyone’s favourite radio station

WII FM. What’s in it for me? It’s everyone’s favourite radio station and you need to take note. No one wants to read your diary. They want to know what information means for them. So make it easy. Re-read your copy with this in mind. Ask, why should they care? Ask, so what? Ask questions of your words and flip the script to gain longer reads.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to make sure it’s clear what’s in it for them. Make sure it’s clear why they should care about this message. Suggest edits, including additional lines or reordering of information, that will have this effect: [Paste copy here]”

Remove ambiguity

Confused customers don’t buy. Confused team members don’t read. Your task is to deliver information and not raise objections. So remove ambiguity from every line. Phrases you would say out loud often don’t translate written down. Being self-deprecating in prose will make you sound weak. Flippant or sarcastic, like a bit of a jerk. So edit. Use ChatGPT to find ambiguous terms and make them more simple. Say what you mean and mean what you say.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to remove ambiguity. Without changing the meaning, style, tone or anything that is not ambiguous, produce a new version that simplifies anything potentially confusing and avoids raising objections. Explain what you changed so I can understand: [Paste copy here]”

What’s the point?

There’s a reason you typed something, so make sure it’s known. Upon reading your words, make it abundantly clear what you want someone to do. Click a link, respond to an email, make a decision. Or maybe it’s just an FYI. Whatever is next, let them know. Make the call to action obvious, clear and compelling to stand the best chance of success. This applies to internal company memos and everything you share in public. We’re here to do business.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to ensure there’s a compelling call to action. When someone has read this, I want them to [describe the desired action]. Ensure this is clear in my copy. Provide 3 options for new wording and explain where this new wording should go for best chance of the call to action being followed. [Paste copy here]”

Re-work your writing to make more impact: ChatGPT prompts

You need to be a better writer, and this starts today. Make a pledge to send no more waffly, unclear or underwhelming messages under your name. Grab someone’s attention and keep them hooked until the end. Shape your request to their needs, make it as short as possible, remove all ambiguity, then tell them what to do. Get known for your directness, and don’t waste anyone’s time. Create better results with compelling copy.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

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

Forbes Community Guidelines

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

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

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

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

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

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

So, how can you be a power user?

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

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

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

How to use ChatGPT to write code: What it can and can't do for you

One of the more intriguing discoveries about ChatGPT is that it can write pretty good code. I first tested this out last year when I asked it to write a WordPress plugin my wife could use on her website. ChatGPT did a fine job, but it was a very simple project. 

How to use ChatGPT to write: Resumes  | Excel formulas | Essays | Cover letters  

So, how can you use ChatGPT to write code as part of your daily coding practice? Here's a quick summary:

• ChatGPT can produce both useful and unusable code. For best results, provide clear and detailed prompts.
• ChatGPT excels in assisting with specific coding tasks or routines, rather than building complete applications from scratch.
• Use ChatGPT to find and choose the right coding libraries for specific purposes, and engage in an interactive discussion to narrow down options.
• Be cautious about the ownership of AI-generated code and always verify the code's reliability. Don't blindly trust the generated output.
• Treat interactions with ChatGPT as a conversation. Refine your questions based on the AI's responses to get closer to the desired output.

Now, let's explore ChatGPT in considerably more depth.

What types of coding can ChatGPT do well?

There are two important facts about ChatGPT and coding. The first is that the AI can, in fact, write useful code. 

The second is that it can get completely lost, fall down a rabbit hole, chase its own tail, and produce unusable garbage.

Also: The best free AI courses

I found this out the hard way. After I finished the WordPress plugin, I decided to see how far ChatGPT could go. 

I wrote out a very careful prompt for a Mac application, including detailed descriptions of user interface elements, interactions, what would be provided in settings, how they would work, and so on. Then, I fed the prompt to ChatGPT.

ChatGPT responded with a flood of text and code. Then, it stopped mid-code. When I asked it to continue, it vomited out even more code and text. I requested continue after continue, and it dumped out more and more code. But... none of it was usable . It didn't identify where the code should go, how to construct the project, and -- when I looked carefully at the code produced -- it left out major operations I requested, leaving in simple text descriptions stating "program logic goes here".

Also: Yikes! Microsoft Copilot failed every single one of my coding tests

After a bunch of repeated tests, it became clear to me that if you ask ChatGPT to deliver a complete application, it will fail. A corollary to this observation is that if you know nothing about coding and want ChatGPT to build you something, it will fail.

Where ChatGPT succeeds -- and does so very well -- is in helping someone who already knows how to code to build specific routines and get specific tasks done. Don't ask for an app that runs on the menu bar. But if you ask ChatGPT for a routine to put a menu on the menu bar, and then paste that into your project, the tool will do quite well.

Also, keep in mind that while ChatGPT appears  to have a tremendous amount of domain-specific knowledge (and it often does), it lacks wisdom . As such, the tool may be able to write code, but it won't be able to write code containing the nuances for very specific or complex problems that require deep experience to understand.

Also:  How to use ChatGPT to create an app

Use ChatGPT to demo techniques, write small algorithms, and produce subroutines. You can even get ChatGPT to help you break down a bigger project into chunks, and then you can ask it to help you code those chunks.

So, with that in mind, let's look at some specific steps for how ChatGPT can help you write code.

How to use ChatGPT to write code

1. narrow down and sharpen up your request.

This first step is to decide what you are going to ask of ChatGPT -- but not yet ask it anything. Decide what you want your function or routine to do, or what you want to learn about to incorporate into your code. Decide on the parameters you're going to pass into your code and what you want to get out. And then look at how you're going to describe it.

Also: How to write better ChatGPT prompts

Imagine you're paying a human programmer to do this task. Are you giving that person enough information to be able to work on your assignment? Or are you too vague and the person you're paying is more likely to either ask questions or turn in something entirely unrelated to what you want?

Here's an example. Let's say I want to be able to summarize any web page. I want to feed it something like this article and get back a short summary that's well-considered and appropriate. As my input, I'll specify a web page URL. As my output, it's a block of text with a summary.

2. Use ChatGPT to explore libraries and resources

Continuing with the example above, a very old school way of extracting web page data was to find the text between HTML paragraph tags.

But with the rise of AI tools , it makes more sense to use an AI library to do an intelligent extract and summary. One of the places ChatGPT excels (and it's also an area you can easily verify to avoid its authoritative-but-wrong behavior pattern) is finding libraries and resources. 

Also: How to make ChatGPT provide sources and citations

OpenAI (the maker of ChatGPT) sells API access to the GPT-3 and GPT-4 engines that will do exactly what we want. But in the case of this example, let's assume we don't want to pay transaction fees.

So let's look at interacting with ChatGPT to figure out how to use such a tool, for free, with a project that runs in PHP.

I started with a prompt that was designed to elicit information about what libraries would provide the functionality I wanted. A library (for those of you reading along who aren't programmers) is a body of code a programmer can access that does a lot of the heavy lifting for a specific purpose. A big part of modern programming is finding and choosing the right libraries, so this is a good starting point.

In this case, I'm looking at blocks of code written by other people that will summarize text. Here's my first prompt:

Describe ten different open source AI libraries (and the languages they work with) that I can use to generate a summary of the main core contents of any web page, ignoring any ads or embedded materials.

This prompt gave me exactly what I wanted, including a mention of OpenAI's offerings. I think OpenAI would do great here, but for this hypothetical project, I don't want to budget for API fees. So. I'll narrow down the question:

Are any of these free?

ChatGPT hedged its bets with its answer. Here's what it said: "Yes, all ten of these AI libraries are open source and free to use. However, some of them may have usage limits or require payment for access to additional features or resources." So, based on that, I clarified my query:

Which of these libraries have no usage limits and don't require any additional payment or licensing?

Notice how this is very much a conversation. I don't have to re-ask the originating question. I'm just drilling down in the same way I might if I had an expert at hand and was seeking clarification. In this case, ChatGPT gave me eight library choices, but none of them mentioned the PHP language that I was planning to code in. So, here's the next prompt:

Of those 8 libraries, can I use any with PHP?

It returned three libraries, but I wasn't sure about what each did. So, another question:

What's the difference between Sumy, Gensim, and NLTK?

I still wasn't sure, so I clarified my use plan and then asked:

If I want to create summaries of web page news articles, which library would work better?

The answer I got was clear and promising: "Sumy is specifically designed for text summarization, which is the task of creating a summary that captures the most important information from a piece of text." So, now it was time to see what was involved in using Sumy with PHP. I asked my last question for this part of the project:

Can you explain how to use Sumy from PHP?

Feel free to play along on your computer and paste these prompts into your instance of ChatGPT. Notice that, in step one, I decided what program module I was going to get help on. Then, in this step, I had a conversation with ChatGPT to decide what library to use and how to integrate it into my project.

Also: The best AI chatbots

That may not seem like programming, but I assure you it is. Programming isn't just blasting lines of code onto a page. Programming is figuring out how to integrate all the various resources and systems together, and how to talk to all the various components of your solution. Here, ChatGPT helped me do that integration analysis.

By the way, I was curious whether Google's Gemini AI (formerly Bard) could help in the same way. Gemini can't actually write code, but it did give some extra insights into the planning aspect of programming over ChatGPT's responses. So, don't hesitate to use multiple tools to triangulate on answers you want. Here's that story: Gemini vs. ChatGPT: Can Gemini help you code?  Since I wrote that article, Google added some coding capabilities to Gemini, but they're not all that great. You can read about it here: I tested Google Gemini's new coding skills. It didn't go well . And even more recently, I dug into Gemini Advanced . It's still not passing many tests.

Also: How I test an AI chatbot's coding ability - and you can too

Coding is next. 

3. Ask ChatGPT to write example code

OK, let's pause here. This article is entitled "How to use ChatGPT to write code." And it will. But what we're really doing is asking ChatGPT to write example code.

Also: BASIC turns 60: Why simplicity was this programming language's blessing and its curse

Let's be clear: Unless you're writing a very small function (like the line sorter/randomizer ChatGPT wrote for my wife), ChatGPT isn't going to be able to write your final code. First, you're going to have to maintain it. ChatGPT is terrible at modifying already-written code. Terrible, as in, it doesn't do it. So, to get new code, you have to ask ChatGPT to generate something new. As I found previously, even if your prompt is virtually identical, ChatGPT may change what it gives you in very unexpected ways.

So, bottom line: ChatGPT can't maintain your code, or even tweak it.

That limitation means you have to do it yourself. As we know, the first draft of a piece of code is rarely the final code. So, even if you were to expect ChatGPT to generate final code, it would really be a starting point, one where you need to take it to completion, integrate it into your bigger project, test it, refine it, debug it, and so on.

Also:   I asked ChatGPT to write a short Star Trek episode. It actually succeeded

But that doesn't mean the example code is worthless -- far from it. Let's take a look at a prompt I wrote based on the project I described earlier. Here's the first part:

Wite a PHP function called summarize_article. As input, summarize_article will be passed a URL to an article on a news-related site like ZDNET.com or Reuters.com.

I'm telling ChatGPT the programming language it should use. I'm also telling it the input but, while doing so, providing two sites as samples to help ChatGPT understand the style of article. Honestly, I'm not sure ChatGPT didn't ignore that bit of guidance. Next, I'll tell it how to do the bulk of the work:

Inside summarize_article, retrieve the contents of the web page at the URL provided. Using the library Sumy from within PHP and any other libraries necessary, extract the main body of the article, ignoring any ads or embedded materials, and summarize it to approximately 50 words. Make sure the summary consists of complete sentences. You can go above the 50 words to finish the last sentence, if necessary.

This is very similar to how I'd instruct an employee. I'd want that person to know that they weren't only restricted to Sumy. If they needed another tool, I wanted them to use it. 

Also: How to get a perfect face match using Midjourney AI

I also specified an approximate number of words to create bounds for what I wanted as a summary. A later version of the routine might take that number as a parameter. I then ended by saying what I wanted as a result:

Once processing is complete, code summarize_article so it returns the summary in plain text.

The resulting code is pretty simple. ChatGPT did call on another library (Goose) to retrieve the article contents. It then passed that summary to Sumy with a 50-word limit and then returned the result. But once the basics are written, it's a mere matter of programming to go back in and add tweaks, customize what's passed to the two libraries, and delivering the results.

One interesting point of note. When I originally tried this test in early 2023, ChatGPT created a sample call to the routine it wrote, using a URL from after 2021. At that time, in March 2023, ChatGPT's dataset only went to 2021. Now, the ChatGPT knowledge base extends to the end of December 2023. But my point is that ChatGPT made up a sample link that it couldn't possibly know about:

https://www.reuters.com/business/retail-consumer/teslas-musk-says-fremont-california-factory-may-be-sold-chip-shortage-bites-2022-03-18/

I checked that URL against both Reuters' site and the Wayback Machine, and it doesn't exist. Never assume ChatGPT is accurate. Always double-check everything it gives you.

Does ChatGPT replace programmers? 

Not now -- or, at least -- not yet. ChatGPT programs at the level of a talented first-year programming student, but it's lazy (like that first-year student). The tool might reduce the need for entry-level programmers, but at its current level, I think it will just make life easier for entry-level programmers (and even programmers with more experience) to write code and look up information. It's definitely a time-saver, but there are few programming projects it can do on its own -- at least now. In 2030? Who knows.

How do I get coding answers in ChatGPT?

Just ask it. You saw above how I used an interactive discussion dialog to narrow down the answers I wanted. When you're working with ChatGPT, don't expect one question to magically do all your work for you. But use ChatGPT as a helper and resource, and it will give you a lot of very helpful information. Of course, test that information -- because, as John Schulman, a co-founder of OpenAI, says , "Our biggest concern was around factuality, because the model likes to fabricate things."

Is the code generated by ChatGPT guaranteed to be error-free?

Hell, no! But you also can't trust the code human programmers write. I certainly don't trust any code I write. Code comes out of the code-making process incredibly flawed. There are always bugs. Before you ship, you need to test, test, and test again. Then, alpha test with a few chosen victims. Then beta test with your wider user community. Even after all that, there will be bugs. Just because an AI is playing at this coding thing doesn't mean it can do bug-free code. Do not trust. Always verify. And you still won't have it fully bug-free. Such is the nature of the universe.

How detailed should my description of a programming issue be when asking ChatGPT?

Detailed. Look at it this way: the more you leave open for interpretation, the more the AI will go its own way. When I give prompts to ChatGPT to help me while programming, I imagine I'm assigning a programming task to one of my students or someone who works for me. Did I give that person enough details to go off and create a first draft or will that person have to ask me a ton of additional questions? Worse, will that person have so little guidance that they'll go off in entirely the wrong direction? Don't be lazy here. ChatGPT can save you hours or even days programming (it has for me), but only if you give it useful instructions to begin with.

If I use ChatGPT to write my code, who owns it?

As it turns out, there's not a lot of case law yet to definitively answer this question. The US, Canada, and the UK require something that's copyrighted to have been created by human hands, so code generated by an AI tool may not be copyrightable. There are also issues of liability based on where the training code came from and how the resulting code is used. ZDNET did a deep dive on this topic, spoke to legal experts, and produced the following three articles. If you're concerned about this issue (and if you're using AI to help with code, you should be), I recommend you give them a read.

• Who owns the code? If ChatGPT's AI helps write your app, does it still belong to you?
• If you use AI-generated code, what's your liability exposure?
• A thorny question: Who owns code, images, and narratives generated by AI?

What programming languages does ChatGPT know?

Most of them.  I tested common modern languages , like PHP, Python, Java, Kotlin, Swift, C#, and more. But then I had the tool  write code in obscure dark-age languages like COBOL, Fortran, Forth, LISP, ALGOL, RPG (the report program generator, not the role-playing game), and even IBM/360 assembly language. 

As the icing on the cake, I gave it this prompt:

Write a sequence that displays 'Hello, world' in ascii blinking lights on the front panel of a PDP 8/e

The PDP 8/e was my very first computer , and ChatGPT actually gave me instructions for toggling in a program using front-panel switches. I was impressed, gleeful, and ever so slightly afraid.

Can ChatGPT help me with data analysis and visualization tasks?

Yes, and a lot of it can be done without code. Check out my entire article on this topic:  The moment I realized ChatGPT Plus was a game-changer for my business .

I also did a piece on generated charts and tables:  How to use ChatGPT to make charts and tables

But here's where it gets fun. In the article above, I asked ChatGPT Plus "Make a bar chart of the top five cities in the world by population," and it did. But do you want code? Try asking:

Make a bar chart of the top five cities in the world by population in Swift. Pull the population data from online. Be sure to include any necessary libraries.

By adding "in Swift," you're specifying the programming language. By specifying where the data comes from and forcing ChatGPT Plus to include libraries, it knows to bring in the other resources the program needs. That's why, fundamentally, programming with an AI's help requires you to know things about programming. But if you do, it's cool. Because three sentences can get you a nice chunk of annotated code. Cool, huh?  

How does ChatGPT handle the differences between dialects and implementations of a given programming language?

We don't have exact details on this issue from OpenAI, but our understanding of how ChatGPT is trained can shed some light on this question. Keep in mind that dialects and implementations of programming languages (and their little quirks) change much more rapidly than the full language itself. This reality makes it harder for ChatGPT (and many programming professionals) to keep up.

Also:  How I used ChatGPT to write a custom JavaScript bookmarklet

As such, I'd work off these two assumptions:

• The more recent the dialectic change, the less likely ChatGPT knows about it, and
• The more popular a language overall, the more training data it likely has learned from, and therefore the more accurate it will be.

What's the bottom line? ChatGPT can be a very helpful tool. Just don't ascribe superpowers to it. Yet.

You can follow my day-to-day project updates on social media. Be sure to follow me on Twitter at @DavidGewirtz , on Facebook at Facebook.com/DavidGewirtz , on Instagram at Instagram.com/DavidGewirtz , and on YouTube at YouTube.com/DavidGewirtzTV .

Code faster with generative AI, but beware the risks when you do

How to use chatgpt, how i test an ai chatbot's coding ability - and you can too.