Employing Generative Artificial Intelligence with Responsibility

Introduction

I wrote the following delightful chronicle when I was studying Graduate Research Methods during the programme of Master of Business Administration (which I concluded in April 2026). The chronicle, though, was written between August and September 2025, and our instructor had prompted us to explain how we made use of Generative Artificial Intelligence tools. Happy reading!

Artificial Intelligence Report

The employment of artificial intelligence in educational settings can have a broad sense. ChatGPT, Perplexity, Google and Microsoft Translators, and Office 365 use certains types of artificial intelligence. Some use predictive analytics, others use machine learning, while alternate models use natural language processors. Artificial intelligence techniques should not be employed as a substitutor of knowledge, but as an enhancer of the practice of studying.

First parameter: Microsoft Translator

When I am stuck with a complex word or idea, I go to the translator hosted by Microsoft, which is similar to Google's, but this one has three options of translations: Standard, Casual, and Formal, and I can manipulate the translation to my liking.

Furthermore, if I translate a word, let's say, the connector "whereas", from detect language to English, and then set the translation to Casual, Microsoft Translation, which can be accessed from any browser, will explain what the vernacular stands for, or in the present case, give me an alternate way to convey "whereas". I have also included a screenshot concerning Google Translate to see if I get similar results. (See below images for reference. Data is from June 5, 2026.)

Sample of Microsoft Translation collected on June 5, 2026. It translates "whereas" from "detect langauage" to English, where it returns "while". Translation mode is set to "Casual".

Sample of Google Translation collected on June 5, 2026. It translates "whereas" from "detect lanaguage" to English, where it returns "whereas". Translation mode is not available for Google Translator, but it does have a dictionary included.

This experiment provides us information that Microsoft Translator can be useful for paraphrasing, and that Google Translator can be useful for semantics akin to an alternate dictionary, for example, a searcher not satisfied with a definition of a word on Merriam-Webster, then goes to Google Translate to get a second opinion.

Second parameter: AI Overview as a scoping review (Google and Bing, basically)

Whenever I want to understand more of a concept that I am not sure what its definition is, I go to a search engine akin to Microsoft Bing and type just the word related to my query. Searchers on the internet tend to make conversational queries, like instead of searching "watermelon", searchers look for "where can I buy watermelon near me". What I prefer doing is to search a broad term and narrow it down as I read through most of the links displayed on the search engine results page. Now that the two most popular search engines akin to Google and Bing have so-called "AI overviews" in their results page, scoping a concept gets to a different level, because the robot will scan the webpages related to the query and summarize the principal results.

In the following images, I queried "covalent bonds" in Microsoft Bing and in Alphabet Google and these are the results. (See images for reference. Data is from June 5, 2026.)

Sample of a search on Microsoft Bing for "covalent bonds" colected on June 5, 2026.

Sample of Google search for "covalent bonds" depicting an AI Overview section. Data collected on June 5, 2026.

Notice that the search engine results page shows the AI overview statement and beside (in case of Bing) and below (in case of Google) a link directing to Wikipedia. This indicates a strong domain authority concerning Wikipedia, which does not mean Wikipedia is a good source, though.

Third parameter: Conversational AI as scoping reviews (OpenAI ChatGPT, Perplexity AI)

This idea is similar to the second parameter, but it requires more critical reasoning, because conversational artificial intelligence mechanisms do not always display their sources.

In the following cases, I queried "friday, june 5, 2026: hegemony" in Perplexity AI, OpenAI's ChatGPT, and xAI's Grok large language models to see what they return. (See images for reference. Data collected dates from June 5, 2026.)

Sample of a search on Perplexity for "friday, june 5, 2026: hegemony". I personally like to add dates in my conversations with robots, so that I know exactly when I did such observation, like a researcher from the eighteenth or nineteenth century would write a journal entry with his observations.

Sample of a search on ChatGPT for "saturday, june 6, 2026: hegemony".

With this simple, yet powerful example, I demonstrate that both Perplexity AI and Grok tend to be more explainable than OpenAI's ChatGPT, because it actually shows its thought process in clear steps, thus making them better for academic research; at least the groundwork, not the full research.

Fourth parameter: Employment of conversational artificial intelligence mechanisms for role playing

I have tried this scenario with several natural language processors (NLPs), that is, mechanisms that convert text into more text based on the initial text. My portfolio of NLPs include ChatGPT, Google Gemini (that I use on my smartphone for quick responses), and Microsoft's Copilot. On rare occasions I found myself having a conversation with Deepseek and Anthropic's Claude. When I utilise X (formerly Twitter), I like to have xAI's Grok large language model to interpret my own posts and some posts that appear on my news feed.

For the next case, I will employ the following prompt: "Hi, buddy! I live on Planet Earth and I am an explorer who happens to be a K-12 student. I would like to know if I can trust natural language processors and large language processors akin to you for school assignments. Thanks in advance!".

Response provided by ChatGPT on Saturday, June 6, 2026. (Note that ChatGPT calls me "Otto" because I previously told it to do so):

Hi, Otto.

You can trust large language models like me for some parts of schoolwork, but not for all parts.

A useful way to think about it is that an AI is more like a very knowledgeable assistant than an infallible expert. It can:

• Explain concepts.
• Summarize texts.
• Suggest ideas for projects.
• Help organize research.
• Check grammar and clarity.
• Generate practice questions.
• Show different perspectives on a topic.

However, it can also:

• Make factual mistakes.
• Invent sources, quotations, or references.
• Misinterpret questions.
• Present uncertain information with confidence.
• Miss recent developments if not connected to current sources.

For school assignments, a good approach is:

1. Use AI to understand the topic and generate ideas.
2. Consult textbooks, class materials, and reliable sources.
3. Verify important facts independently.
4. Write the final work in your own words.
5. Follow your school's rules regarding AI use.

As an explorer, you might appreciate this comparison: a language model is a bit like a compass. A compass can help you navigate, but it is not the territory itself. You still need maps, observations, and judgment to complete the journey.

In short: trust AI as a helpful tool, but not as the sole authority for your assignments. The more important the assignment, the more carefully you should verify what the AI tells you.

The following link redirects to what Microsoft's Copilot large language model returned: https://copilot.microsoft.com/shares/8Ezri9hSZviuWeuVqaPHV

This exchange happened on Saturday, June 6, 2026. Note that, while OpenAI's ChatGPT compared itself to a compass, Microsoft's Copilot described itself as a guide, only because I said in the beginning of the conversation that I was "an explorer".

Conclusion

With these simple, yet replicable experiments, I tried to demonstrate that any form of artificial intelligence akin to machine learning, predictive analytics, or natural language processors, can be employed to conduct preliminary, scoping research of a broad topic. Artificial intelligence should not be employed as a shortcut in education, but as an enhancing tool, just like Google introduced itself back in the late 1990s, early 2000s.

I grew up with Wikipedia and I had a strong urge to copy, paste information from there to complete my school assignments. Instead, I actually took the time to read and critically evaluate what was written on Wikipedia, because it tends to contradict itself most of the time.

I have studied a lot of topics when I was a secondary school student through Wikipedia articles, including the English revolutions of 1649, 1688, and the eventual bankruptcy filing of the city of Detroit in 2013.

Wikipedia is not perfect, but it helped me understand school subjects, just like artificial intelligence tools can be helpful for students in every level of education, especially beyond secondary school. The limitation in this case is to resist the urge to copy, paste information you receive as an output from artificial intelligence, just like I resisted copying, pasting data from Wikipedia. And if you inspect some outputs provided by generative artificial intelligence models, you will notice that they really are or may be direct reproductions from Wikipedia!