Future of AI Meetup at the Asia School of Business!

In the past couple of weeks, I’ve had the chance to speak at a couple of events concerning generative AI, most recently the Future of AI meetup with NextUpAsia at the Asia School of Business!

As one of the invited speakers for this event, I had the chance to talk a lot about the different uses of AI in enterprise, drawing a distinction between generative AI and AI for process improvement, and also got the chance to highlight my thoughts about artificial intelligence in the context of business and in education, to demonstrate Midjourney for enterprises (and to create a t-shirt design for the Asia School of Business!), and to meet many new and interesting collaborators with whom I think there will be lots of unique opportunities to work together.

Some of these clips show you what happened at the session:

#1: Panel discussion about generative AI technologies.

During this part of the session, my fellow panelists Johnson Goh, Shahbaaz D’Ali, and Jason Sosa had a lively discussion with the audience about the present and future of AI technologies, touching upon the impact of generative AI on different industries, as well as some of the core limitations of generative AI.

Everyone came well-prepared with examples and topics to discuss, and it was mindblowing to watch the average level of discussion on the floor that night! My particular contribution to the session was to discuss the concept of the AI hallucination, which I’ll probably speak a little bit more about in another post later on, during which I observed that rather than replacing humans, it’s likely that generative AI will simply create an increased demand for humans who can exercise higher quality critical thinking and judgment in the future.

#2: Education in AI – A Discussion.

During this part of the session, I had the chance to highlight some of the key challenges and opportunities posed by Artificial Intelligence in education, and to also draw attention to the recent (and admirable!) actions of Singapore’s Minister Chan Chun Sing in highlighting an AI strategy for the Singaporean education system alongside speaking about some of the challenges and opportunities that students will face in the future as a consequence of the development of generative AI technologies.

Thoughts about the education system and AI preparedness.

#3: A Midjourney Enterprise demonstration.

This was rather spontaneous, but I had the chance to conduct a training about the ways that ChatGPT and Midjourney can integrate with one another in order to create something that is greater than the sum of their parts, by facilitating the process of image generation at scale.

Surprisingly, that’s not all as boring as it might initially sound, because we had the chance to create foods from a Ramadhan bazaar and to showcase these as proofs of concept to business owners along the way as well!

ChatGPT and Midjourney demonstration!


Overall, this talk was an incredible experience that I think has opened up a host of interesting new opportunities and a new frontier for me, as well as an enjoyable evening where I truly felt that I was living the life of the mind as I participated in a conversation that no doubt will continue to dominate the consciousness of people around the world in the days moving forward.

It was a huge privilege to be a part of the AI conversation and to begin talking about the ways in which AI can be used by businesses as part of their journey onward into the 21st century, and I’m thrilled to look at the opportunities ahead in the days to come 🙂

Thank you to NextUpAsia and the Asia School of Business established in collaboration with MIT for having me!

P.S. Work has been busy, but it’s beginning to dovetail more with writing and creating a lot more – I’ll try to write more regularly soon!

ELIZA – The Chatbot That Started It All.

I’ve been doing quite a bit of reading recently to prepare for BiZ Gear Up on the 24th, and part of that led me to read a bit more about the early history of chatbots – I hope you’ll enjoy this one!

We take a brief moment to move away from the hype that is OpenAI‘s ChatGPT, and take a brief intermission as we make a small trip back in time.

Picture this: it’s the year 1966, and a computer scientist at the Massachusetts Institute of Technology‘s Artificial Intelligence Laboratory named Joseph Weizenbaum has just created something remarkable – the world’s very first chatbot: ELIZA.

No alt text provided for this image
Image credit: Public domain via Wikimedia Commons

Just consider this example of a conversation from Norbert Landsteiner’s 2005 implementation of ELIZA, and you can see what it was capable of.

ELIZA was designed to simulate conversation by responding to typed text with pre-programmed phrases and questions.

But what made ELIZA so special was that it was programmed to mimic the conversational style of a therapist, in particular a Rogerian therapist.

Users could “talk” to ELIZA about their problems and concerns, and the chatbot would respond with empathetic and non-judgmental phrases like “Tell me more about that” or “How does that make you feel?”

It wasn’t just a simple question-and-answer program – it was designed to provide a sense of emotional support and understanding that reflects interestingly on the ways that people derive comfort from self-affirmation.

Weizenbaum didn’t intend for the chatbot to be taken very seriously, calling it a “parody” in his 1976 book “Computer Power and Human Reason”… But the way that the chatbot was received was far from just a parody.

The response to ELIZA was overwhelming.

People were fascinated by this new technology that could seemingly understand and respond to their thoughts and emotions, and the program quickly gained popularity as people tried the chatbot.

But perhaps what’s most remarkable about ELIZA is that it wasn’t just a novelty. Weizenbaum’s creation laid the foundation for decades of research in the field of natural language processing and artificial intelligence.

ELIZA was the first chatbot, but it certainly wouldn’t be the last – and its legacy lives on in the many conversational AI programs we use today, in our Bings, Bards, ChatGPTs, Claudes, and the many more that exist and will exist today.

Can’t wait to see what is to come 🙂

A Strange War: AI v. AI Detectors

“Upload your essay into Turnitin by 11:59pm on Thursday night?
You meant start the essay at 11:57 then submit it at 11:58, am I right?” — 
Gigachad ChatGPT student.

We begin our discussion by discussing the sweet smell of plagiarism.

It wafts in the air as educators run around like headless chickens, looking here, looking there as they flip through oddly good essays with panicked expressions.

“Was this AI-generated, Bobby?!” says a hapless teacher, staring at a piece of paper that seems curiously bereft of grammatical errors, suspecting that Bobby could never have created something of this caliber.

“No teacher, I just became smart!” Bobby cries, running off into the sunset because he is sad, he is going to become a member of an emo boyband, and he doesn’t want to admit that he generated his homework with ChatGPT.

generated by Midjourney, if that wasn’t obvious

This smell casts fear and trepidation over every single part of our education system, for it threatens to break it; after all, education is special and it is meant to be sacrosanct — after all, is it not the very same system that is designed to teach humans facts and knowledge and above all, to communicate and collaborate to solve the problems of our era with intelligence, initiative, and drive?

It’s unsurprising that the world of education has flipped out over ChatGPT, because artificial intelligence opens up the very real possibility that schools may be unable to detect it.

Fun and games, right? It’s just a bunch of kids cheating on assignments with artificial intelligence? It’s not going to affect the older generation?

As it turns out, no — that’s not the case. I’ll explain why later.

But before that, let’s talk a bit about the part of our education system that AI is threatening: Essay-writing.

If students simply choose to let their work be completed by artificial intelligence and forget all else, that just means that they’ve forgone the education that they’re supposed to have received, thereby crippling them by an act of personal choice, right…?

But each of us has been a student, and if we have children, our children either will be or have been students too; there is a deep emotional connection that stretches across the entire world when it comes to this.

Therefore, when Princeton University CS student Edward Tian swooped in to offer a solution,it’s not all that surprising that the world flipped.

Enter GPTZero.

Humans deserve the truth. A noble statement and a very bold one for a plagiarism detector, but something that’s a little deeper than most of us would probably imagine.

But consider this.

Not everyone who uses AI text is cheating in the sense of doing something that they are not supposed to and thereby violating rules, therefore the word ‘plagiarism detector’ doesn’t quite or always apply here.

This algorithm, as with other algorithms that attempt to detect AI-generated text, is not just a plagiarism detector that merely serves to catch students in petty acts of cheating —it is an AI detector.

An AI Detector At Work.

So how does it work?

GPTZero assigns a likelihood that a particular text is generated by AI by using two measures:

Perplexity, and Burstiness.

Essentially, in more human language than that which was presented on GPTZero’s website, GPTZero says that…

The less random the text (its ‘perplexity’), the more likely it was generated by an AI.

The less that randomness changes throughout time (its ‘burstiness’), the more likely that the text was generated by AI.

Anyway, GPTZero gives each text a score for perplexity and burstiness, and from there, outputs a probability that given sentences of a text were generated by AI, highlighting the relevant sentences, and easily displays the result to the user.

Alright, sounds great!

Does GPTZero deserve the hype, though?

…Does this actually work?

Let’s try it with this pleasant and AI-generated text that is exactly about the importance of hype (lol).

That’s 100% AI-generated and we know that as fact.

…Would we know if we didn’t see it in the ChatGPT terminal window, though?

…Okay, let’s not think about that.

Down the hatch…

…And boom.

As we can see, GPTZero, humanity’s champion, managed to identify that the text that we had generated was written by AI.



I proceeded to rewrite the essay with another AI software.

…After which GPTZero essentially declared:

So nope, GPTZero can’t detect rewritten texts that were generated with AI — which it should be able to if it truly is an *AI* detector in the best sense — and which in turn suggests that the way that it’s been operationalized has yet to allow it to be the bastion protecting humanity from the incursion of robots into our lives.

It’s not that GPTZero — or even OpenAI’s own AI Text Reviewer, amongst a whole panoply of different AI detectors – are bad or poorly operationalized, by any means. Rather, it’s that the operationalization is supremely difficult because the task is punishingly hard, and that we are unlikely to have a tool that can detect AI-generated text 100% unless we perform watermarking (MIT Technology Review) and we would have to use multiple algorithms to be able to detect text, or come up with alternate measures to do so.

An Arms Race between AI Large Language Models (LLMS) and AI Detectors — and why you should care (even if you’re not a student).

As I’ve mentioned, there is an arms race at hand between AI Large Language Models (LLMs) like ChatGPT, and AI detectors like GPTZero, the consequence of which is likely that the two will compete with one another and each will make progress in its own way, progressing the direction of both technologies forward.

Personally, I think that AI detectors are fighting a losing battle against LLMs for many reasons, but let me not put the cart before the horse — it is a battle to watch, not to predict the outcome of before it’s even begun.

Implications of this strange war:

But why should you care about any of this if you’re not a student? It’s not like you’re going to be looking at essays constantly, right?

Let’s take aside the fact that you’re reading a blog post right now, and let’s also move away purely from the plagiarized essay bit that we’ve been thinking about, as we gravitate towards thinking about how ChatGPT is a language model.

It’s a good bet that you use language everywhere in your life, business, and relationships with other people in order to communicate, coordinate, and everything else.

When we go around on the Internet, it’s not always immediately evident what was AI generated, what was generated by a human or, for that matter, what was inspired by an AI and later followed through by a human.

The whole reason we need something like a plagiarism detector is that we may not even be sure that a particular piece of language (which we most often experience in the form of text) is AI-generated with our own eyes and minds, to the point that we need to literally rely upon statistical patterns in order to evaluate some thing that we are looking at directly in front of us, thereby recruiting our brains as we evaluate the entirety of an output.

The problem is…

Language doesn’t just exist as text.

Language exists as text, yes, but also as speech. Moreover, speech and text are easily convertible to one another — and we know very well what ChatGPT is doing: Generating text.

We now know that there are Text To Speech (TTS) models that generate speech from text. They’re not necessarily all great, but that’s besides the point — it presages the translation from text into voice.

Think about it.

If the voices that are generated by AI become sufficiently realistic-sounding and their intonations (VALL-E, is that you?), how might you know that these voices aren’t real unless there are severe model safeguards that impede the models from functioning as they are supposed to?

Now combine that indistinguishable voice with sophisticated ChatGPT output that can evade any AI detector and in turn may, depending on the features that end up developing, evade your own capacity to tell whether you are even interacting with a human or not.

How would that play out in the metaverse?

How would that play out in the real world, over the phone?

How would you ever know whether anyone that you’re interacting with is real or not? Whether they are sentient?

The battle between AI and AI Detectors is not just a battle over the difference between an A grade and a C grade.

It’s a battle over a future where what’s at stake is identifying what even qualifies as human.

How AI Tech Will Disrupt Businesses (24th February)

Do you ever feel like you might have gotten yourself in something a little bigger than you’d imagined was possible?

Excited to announce that I’ll be speaking about AI for the “How AI Tech Will Disrupt Businesses” panel on the 24th of February! Thank you Vulcan Post for the feature and MrMoney TV x Entrepreneurs and Startups Malaysia for the invitation!

You’ll be able to meet me there directly and hear me talk about the ways AI is going to change businesses around the world alongside my fellow panelist, Richard Ker!

If you’ve not heard of Richard, the man is a legend at creating incredible infographics and marketing, and I respect both his trite observations and the value that he’s created for literally thousands of people throughout Malaysia and far beyond; the man is a true blue digital authority, If you’re looking for something specific, feel free to check out this article that he’s written on Facebook, amongst other things; the man is everywhere!

In other words, what does this mean?

It means I need to level up!

This conference is something that I’m truly honored to be a part of, and a wonderful opportunity to learn from many incredible minds that I won’t be missing by any stretch of the imagination.

As we speak, I’m preparing for with all my might at the moment even as I read and learn more about artificial intelligence, building up that reading habit again thoughtfully documented by my dear friend Sandy Clarke and that I’ll make sure to work towards in the days ahead as I build this platform.

Meanwhile, if you haven’t already, please feel free to join Artificial Intelligence Malaysia! I’ve had some pretty wild conversations in the past day or so, and it would be great to add a diversity of voices to the group especially if you’re really interested in AI and everything that it has to offer 🙂

In preparation for that, know that I’ve been reading extensively and creating lots of other content as well because I know that anything I have to make this worth your time, and will do my very best to do so.

Till we meet, then!

Quora’s Poe – A First Look.

Stop what you’re doing right now and download Poe!

…Unless you’re using an Android phone, in which case maybe you can drop what you’re doing right now, cry, buy an iPhone, then come back.

…OKAY NO DON’T KILL ME AAAAAAAAAAAAAAAAAnd now, dear readers, we talk about Poe! 

Generated with Midjourney!

If you don’t know what Poe is, Poe is not this Poe — it’s question and answer platform Quora’s brand new AI baby, now available on iPhone and iPad!

Initially, buying into the hype of the Microsoft and Google AI arms race, I thought that Poe was just a Chatbot that was trained on Quora data and by extension the millions upon millions of questions and answers that it contains, but I realized that it wasn’t (although that’d be cool, though uh… I’m not sure how that’d work considering that nowadays a ton of questions on Quora are kind of powered by people trying to copy-paste ChatGPT in order to rank?).

Anyway, Poe isn’t exactly a chatbot in and of itself – it is what I would describe as a Chatbot aggregator, which means that it collects several different Large Language Models (LLMs) into a single interface; no wonder, considering the fact that the project is called Poe because it’s short for “Project Open Exchange”, which I guess alludes to the fact that the premise is that you can ask questions to a variety of different AI chatbots and receive answers relatively quickly. Already on the platform you will see three main chatbots. The first in the lineup is Sage, the next is Claude, and the last of the bunch is Dragonfly; Sage and Dragonfly are powered by OpenAI, and Claude is powered by Anthropic P. B. C. and its Constitutional AI framework.  

Each has its own methods of going about generating conversations, with OpenAI going for RLHF and Claude through the channel of constitutional AI and harm reduction, but I think you should try these for yourself to see the differences, and perhaps also read this article from Scale to see a detailed comparison.

You’ll see each of these on the left end of the app and you can select them and start talking the way you can with ChatGPT.

Dragonfly is fast, but not significantly faster, I think, compared to Sage at the moment – although I’d probably appreciate that a bit more in the event that this app becomes super popular.

The question you might have is that, apart from the number of models available, how is any part of this experience different from ChatGPT or from Claude, though?

Let’s compare. 

So here, I ask ChatGPT why the sky is blue, and receive a pretty reasonable response. 

It takes about 10 seconds to complete. On the other hand, when we do the same thing with Sage, which is also an OpenAI model, we get the following in 4-5 seconds generation time – which is significantly faster than ChatGPT, but is not bound by the fact that ChatGPT has millions of users concurrently using it… But oh wait.

See the blue links?

When you hit these… 

…Sage begins to elaborate while providing further links as well.

To be exact, these aren’t exactly links – when you click them, they prompt the algorithm with a new text prompt that’s related to the words that you searched for, in turn providing more context and elaboration on what you asked about and helping you to fill up those knowledge gaps real quick.

I think that this is super cool and definitely a step in the direction of the future of search, because it does mean that you can go down a daisy chain of conversations, ask questions, have them answered, and be prompted to ask about the things that you don’t know about; I can totally imagine this as a question and answer service and can even imagine something like this replacing Quora, if not for the fact that subjective experiences and updated information were still relevant and important.

While at the moment this is constrained to material within the training set and by extension data limited to 2021, one can only imagine what might happen at a later point when or if these models receive internet access!

Apart from that though, a cool feature of Poe is…


One of the fun things about Poe is a whole social element that’s integrated into the app itself.

There’s a feature that allows you to share the things that you’re looking at on your feed so that people can see what you generate – essentially, whatever you ask, once you hit the Share icon and then “Share on Poe”…

…Which will let you create a little set of posts that will just randomly show up on people’s feeds, kind of like an implementation of a little TikTok-esque feed full of the prompts that people are publicly sharing around the world and that people can upvote and downvote at their leisure, along with little bubbles that show the kinds of prompts that people have shared at any given point.

I think it’s kind of cool that you get to see these questions, mainly cause you get to see how people around the world are choosing to interact with AI, which creates a (human) communal experience so we can see how people are choosing to prompt things and keeps things light and fun 😀

Here are a couple of examples:

It’s cool to see what people are thinking and writing about, isn’t it? Very much in the spirit of Quora, I think – it does make me wonder if that’s the next evolution of the platform, albeit I still imagine that it might be difficult for algorithms to source personal data or subjective opinions into their training data or make people willingly choose to submit it; perhaps the platforms will coexist? I don’t know.

Anyway, since the thing’s called Poe, I decided to ask Poe to go right ahead and role-play Poe and the Raven.

Uh, towards the end I went and created a bit of an Oxford Union style debate there.

Anyway, I found the chatbot aggregation, links, and social features to be pretty cool and solid features in the app at large, and these all make me really wonder how the platform’s going to evolve in the days ahead.

Some small concluding thoughts:

I guess that Poe’s trying to unite all the different AI models and chatbot applications in one space, and that does kind of make sense, but I would guess that some of the companies that are generating LLMs simply won’t feel the incentive to participate (or won’t have the capital x investment to afford the training costs), while the companies that have generated these APIs would be happy to charge Quora or perhaps at a later point the end users of Poe for using those APIs when they eventually monetize (it’s already happening with ChatGPT), they’ll still be keeping their latest and greatest models for their proprietary usage and for paying users so that these users can use their products beforehand.

Still, what we’ve got here is definitely pretty great already, and I look forward to seeing how this platform’s going to develop in the days ahead!

To end this little exploration, I couldn’t resist making a rap battle about sentient AI with a tiny bonus at the end.



And with that, the mic drops. Thanks for reading as always, and over and out!

ChatGPT in Teaching And Education: No Cheating Required (Part I – Students)

Victor Tan here in the house hitting you with yet another AI post! Today, we’re talking about everyone’s favorite AI text generator! In case you’ve not heard of ChatGPT just yet for some reason, it’s an AI tool that can generate human-like text based on a given prompt. It’s a variant of the well-known GPT (short for “Generative Pre-training Transformer”) created by OpenAI.

ChatGPT got pretty viral recently because outlets like Forbes and Wall Street Journal have been writing articles about how it’s been generating essays in mere minutes that, if actually submitted, would definitely count as cheating.

Here’s what ChatGPT says about that:

For this reason, ChatGPT’s received a fair bit of bad hype, and people seem confused about whether to accept, ignore, or vehemently reject it… It’s unclear that they know what to do about it.

WIth that in mind, it’s been fascinating to watch the different adaptation strategies of countries to the perceived challenge that ChatGPT has brought to the education system as well.

On one hand, some countries have responded with a strategy of mitigation. The state of New York banned ChatGPT (although how they could enforce it is questionable, considering that it’s possible to use ChatGPT on a home device), Australian universities have reverted to pen and paper exams.

That’s not all too surprising, especially since ChatGPT can definitely be used to cheat. It can write essays in mere seconds, craft grammatically well-structured summaries, and organize information to a dashingly effective degree. The craze has begun for AI writing detectors such as Edward Tian’s GPTZero that have yet to successfully and consistently identify AI generated text with a sufficient degree of accuracy to prevent false accusations: They are generally not very good yet, and an arms race is taking place between these detectors and AI text generators as we speak.

But mitigation is not the only strategy – and in an age where technology moves forward whether we like it or not, it seems to me only magical that is the approach we should pray for is one of adaptation. I believe that this is reflected in the strategy of Singapore, which has moved away from mitigation and more to adaptation, with specific allowances to learn how to ‘properly’ use tools such as ChatGPT.


More about this in my next post!

With that said, if you’re a student, how can ChatGPT save your grades and help you have an easier school life without potentially putting you on the line for an F grade for plagiarism, or on review by a disciplinary committee?

Well, even if you don’t cheat with it, ChatGPT is an incredible tool that will help you move forward with your education in leaps and bounds.

Let me show you how!

ChatGPT can help you ace your studies by helping you to…

  1. Provide explanations and examples:

Struggling with homework? ChatGPT can provide explanations and examples for various concepts, making it a great resource for completing those pesky assignments.

The reason that this is really helpful is that it helps you to contextualize the things that you’re learning rather than leaving them just as words, and to appreciate the connections between concepts and practicalities in a much more concrete way than you would otherwise experience if you were to just hear what the teacher is saying but not absorb it.

Let’s first start with a (very recent) historical example:

As you can see, the example here was well summarized, relatively balanced, and provides relatively factual information about what had happened albeit the matter remains controversial.

Next, here’s an example that might appeal to you future computer scientists, involving a cryptographic concept that I needed to brush up on:

Now that seems rather complicated, so let’s simplify it a bit.

That’s a bit better! You can do this with all sorts of things, so give it a try and see what you can do!

2. Help you to learn new things.

Want to learn more about a new subject? ChatGPT can provide a comprehensive overview, making it an excellent resource for expanding your knowledge.

Also, because it is conversational, you can directly ask ChatGPT to explain certain things that it has raised in previous conversations, which will allow you to naturally understand the context of what you’ve learned about and even expand your learning in these areas.

Here’s an example, featuring the English language 🙂

As you can see, I just had a conversation with ChatGPT, during which I learned a bit about verbs — ChatGPT was able to understand my requests for clarification and, when I asked for assistance in natural language, was able to extend my knowledge by providing me with even more information that I could in turn follow up on.

This is something that I would have found rather difficult to do with Google, as Google would have required me to make sense of the data that I find through the different links that I locate, and additionally impose more time costs on me in the form of time dedicated towards navigation — it is possible to learn and rather efficiently of course, but I would have to give ChatGPT the win in terms of ease of understanding and use here and hope that it shows you how efficiently you can learn with ChatGPT.

That being said, since it can help you learn, it’s only natural that ChatGPT can…

3. Help you to research things

Researching a paper or article? ChatGPT can generate summaries so you can get up to speed quickly and easily, which also means that you’ll be able to use it efficiently in connection with other tools such as search engines like Google in order to effectively research your tasks and plan out the things that you’d like to write for those otherwise arduous and pesky research essays.

Here’s an example, featuring the Napoleonic Wars:

But speaking of the Napoleonic Wars…

4. Providing practice questions:

Need to prepare for an exam? ChatGPT can generate practice questions and provide in-depth explanations for the answers.

Let’s get back to the Napoleonic Wars example for a bit, and you’ll see what I mean.

As you can see, this is tremendously powerful — it is something that you can do with any historical concept or idea, and if you try it out, you’ll understand the sheer power of what it can provide even if you don’t cheat with it.

5. Writing essays:

This is probably the most controversial matter of all, because there is the highest potential for cheating with ChatGPT here.

Still, ChatGPT can generate outlines, intro paragraphs, and body paragraphs, saving you time and effort in the process, by giving you a great starting point to begin your essay.

As you can see, ChatGPT can actually also write the essay for you.

The problem is, this works very well with factual essays, and if you do submit this as it is, it will definitely amount as cheating.

That said, there’s no harm in using AI to give you a sense of how to generate paragraphs, which in turn you can rewrite — I would observe, though, that the types of essays that you can generate well are many, and you can actually change the style of these essays in such a way that you may replicate the writing style of anyone with a significant body of work.

In order to use ChatGPT to improve your writing without cheating, you would have to have a sense of distinct voice and personality and also be able to add in some things to the essay that ChatGPT cannot actually execute on — that is especially relevant with things such as the college essay (I show this in my recent video, in which I wrote every single one of UChicago’s 2022–2023 essay prompts.)

For everything else, however, ChatGPT is generally capable of creating some pretty high quality output and proposing some pretty good essay structures, which can easily create the temptation to use that output vanilla — in other words, to cheat by having an algorithm do the work that you were assigned to do — when in reality, students would benefit more if they integrated their approach by not just relying on the outlines that they receive from this software, but instead also refining their thinking with the insights that arise from it.


As you can see, ChatGPT is tremendously powerful for learning, and it can be used in many ways to help you learn information at a rate that is far greater than that which you might have if you were simply to make use of textbooks or Google to proceed through the slog of learning in a (relatively) unstructured way.

I’d like to concede, as a matter of fact, this post was actually partly generated by AI — but the reason I say partly is that I edited it pretty heavily after making use of the initial framework that it had created in order to elaborate on the different examples and to participate in actually using the software in order to demonstrate what it could do while taking screenshots — something that the AI is incapable of doing at this point in time.

At the same time, though, I must acknowledge that as a language model, ChatGPT is tremendously competent at compiling together summaries, outlines, research, and even writing essays for its users in ways that naturally make it rather tempting for students to cheat with ChatGPT, for the simple reason that it is incredibly easy to do so in lieu of learning with it.


To conclude, I hope that you have enjoyed seeing some of the cool things that you can do with ChatGPT to extend your learning and the things that you can do with it, and that you will make use of it well to improve your life and knowledge.

That said, there is incredible potential within the ChatGPT technology and with AI at large to extend the capability of the human race, but there is equal potential to destroy it, subjugating our innate mental capacities and spirits to the idle temptations of creating and submitting a plagiarized AI essay for an A at the 11th hour and never actually doing the work.

Although cheating of this nature can seem harmless, my innocent musings lead me to wonder if cheating serves as a demonstration of how AI can essentially perform many of the tasks that human beings can do, and how some human beings will merely let them — thereby never ascending beyond their current level and merely allowing technology to resolve their problems either without asserting initiative or abiding poor planning and excuse-making in a realm where the tremendously sophisticated tools now available to us make such excuses effectively invalid.

Which is why, to me, AI seems to offer us two paths in the modern age, which in reality may well be the same path: that which leads to an era of greater learning and extension of our mental capabilities, or that which leads to our treating it merely as a tool to achieve our desired ends, thereby weakening ourselves in the process.

If you are a student, I would say this:

As human beings, I firmly believe we need to be able to double down, accepting what AI can do, and locating the gaps in between which we can find ourselves and locate the possibilities in which we are able to add value — a matter in which it is absolutely necessary to continue to develop ourselves by learning well, thinking critically, and making key decisions in terms of how to develop ourselves as the pace of technological innovation accelerates, and algorithms such as those that power ChatGPT only become increasingly advanced.

Even if there are solutions out there that enable you to pass off AI-generated essays as your own, do consider what you can do if you choose to let AI extend you rather than simply letting it be that which you owe credit to in the course of your academic career and by extension completely replace you in the thinking process; if you accept that without questioning it, fighting it, and growing rather than being subsumed by the tide that underpins it, then I guess you’d understand in that world, then, why I would think that while I feel that robots may not completely replace humans at large, the robots may at least replace you… Unless you let it reinforce your mind, rather than replace it.

As always, I wish for your best as a reader of this blog and as a fellow human being – thank you for reading, and we’ll talk more about the ways that AI can help education as a whole in the next post!

The Difference between AI Writing and Human Writing (A Demonstration with IGCSE English)

Now, there’s been a ton of drama recently about AI-driven writing. Influencer after influencer tells you that you can write blog posts and marketing copy and earn infinite amounts of money, telling you that lo and behold, the rapture is here and your AI overlords will now take you to an infinite space of profound wealth!

…But is it true though?

Totally reasonable to believe (because enough people are easily over-hyped and frankly, even if you don’t think you are subject to hype, you probably are)… But in my opinion inaccurate.

It’s true that AI can generate a lot of different articles and types of materials very, very quickly. That’s the whole idea behind my online course. (Welcome to this site if you’ve just found it, students!)

If you think that AI writing is going to replace human writing entirely though, I have an unfortunate truth for you though:

You’re probably not a very good writer.

Sorry to say that, but it’s probably true and that’s absolutely what I believe.

As I said in the previous post, I’m entirely prepared to eat my own words at a later point when our AI overlords become sufficiently advanced that they catch me in a prison of some sort or full-on write novels with incredible twists and planning with no prompting other than “Please write me a novel that will get to the New York Times Bestseller list and grant me a lifetime of drinking pina coladas in Uruguay”, but uh… I’m not convinced that that point is now.

That’s why in this post, we’re going to compare the process of writing an IGCSE English essay from two different perspectives: AI, and from a human perspective.

First of all though, some context:

I teach IGCSE English essay classes (and also IB English x Theory of Knowledge, A Levels, and IELTS classes) as part of my work with Ascendant Academy, and it’s a joy of a subject to teach because it unites two of my dearest passions – education and writing – into a single learning experience that I find tremendously valuable.

Second of all, here’s the context: This is a question from the Winter 2019 Question Paper 3 IGCSE English Language 0500 exam, and I was providing a live-writing exercise with one of my students, whereby I generated an essay in about 20 minutes without stopping (I might screen record one of these if I get permission one day).

Let’s start.

First of all, let’s talk about how I tried to do this with AI, specifically by logging in to ChatGPT with my OpenAI account and trying to get the universe’s favorite chatbot to give me what I wanted.

First, I tried to do this vanilla.

That was too short, so I figured that I should give ChatGPT a bit more context.

…Well, clearly that didn’t work. It gave me… A movie review?! It was time for more prompt engineering.

Okay, now we were getting somewhere.

The issue with this though, was that it was giving me a movie review and this was not something that I was vibing with, so I had to make some other adjustments. The result? I did a little bit more prompting based on the discussion that we had during the course of the lesson, during which I decided to write the essay about the experience of an unnamed scuba diver and his friend Jessica as they discovered a ship.

Here was the result:

Okay, this wasn’t bad!

…Did it mean that it was good, though? I wanted to know, so in the grand finale, I asked the AI for one final thing – to convert the entire thing into the same perspective that I used during my live-writing.

Here’s the result.

2 (a) Write a description with the title, ‘Underwater’. – Written by ChatGPT.


[Prompt]: Do that again, but this time write the description in first person perspective.

My Journey to Discover the Sunken Ship “The Indomitable”

As I descended into the depths of the ocean with my friend Jessica, I was transported to a world of stunning beauty and mystery. Schools of colorful fish swam by, while larger creatures glided gracefully through the water. However, the real treasure of our dive lay ahead – the sunken ship, “The Indomitable.”

The experience of diving into the underwater world was both exhilarating and surreal. With every passing moment, the world above grew more distant, and the world below came into sharper focus. The water shimmered, creating an ethereal aura, and the pressure change added to the sense of adventure.

As we approached the ship, our excitement grew. We were about to uncover the secrets of “The Indomitable,” a ship that had been lost for many years. The ship’s remains were covered in a layer of sea creatures and marine plants, creating a unique and beautiful sight. We explored the ship’s interior, discovering artifacts and uncovering the story of its final voyage.

However, our dive was not without its challenges. Visibility was limited, and we had to navigate through the tight and dark spaces of the ship with care. The danger of the unknown added to the thrill of the experience, but it also required us to be cautious and aware of our surroundings at all times.

In the end, our dive was a success. Jessica and I returned to the surface, exhilarated by our adventure and with a newfound appreciation for the underwater world. We left “The Indomitable” with memories that will last a lifetime, and with a newfound respect for the power and beauty of the ocean.

In conclusion, exploring the underwater world is a journey of discovery and adventure. Whether you are a seasoned diver or a newcomer, the experience of discovering a sunken ship like “The Indomitable” is a once-in-a-lifetime opportunity. So, grab your gear and dive into the unknown, and uncover the secrets that lie beneath the surface of the water.

2 (a) Write a description with the title, ‘Underwater’. – Written by Victor Tan.



The sound of Jessica falling into the water is a little less loud than I had imagined, considering that she was wearing a 30kg scuba tank and full waterproof gear. After a minute of trying to calm myself and failing, I join her in the water, falling in ungracefully with my fins over my head, eyes closed, feeling the cold rush of water: I am now underwater.

At first, I can see nothing, but it takes just a brief moment for my vision to resolve as I witness a side of the world that I had only seen in novels and Netflix shows. The water is a clear and pristine blue, almost like the color of sapphires polished to a brilliant gleam, and inside it I see an entire community – colorful fish swim and dance in complex arrangements, moving as if they are acrobats in the Cirque du Soleil around my awkward movements, as I try to adjust myself in a space that my body has precious few adaptations towards.

Below me, craggy gray rocks stretch out a canvas that extends into a deep and blue horizon down below, and as I move through the waters, I see that ahead of me, there is a darkness below – it is much deeper than I had imagined, and as I am thinking of what it would be like to visit, I feel a shaking on my left arm; it is Jessica signaling to me. 

She waves her arm in the water, pointing downwards, as bubbles stream through her mask and she begins to swim. Realizing that I will be left behind unless I follow suit, I quickly begin moving along with her as we course through the water, navigating this strange and beautiful underwater paradise together.

As we swim through the waters, the fish seem to either be celebrating our journey or mocking us, dancing around us at a speed that I could barely fathom; just before I finish my thought about how people can actually catch these creatures for a living, though, I see the sea turtle resting just above the pink coral formation that rests just at the base of one of the rocks, and as it moves away, perhaps having detected us, there I see the entirety of the coral formation – gigantic, almost as if it is a tremendous, crystalline tree that has ascended from the bottom of the sea floor.

We begin to move through it as we descend deeper, flashing our submersion-grade torchlights into the sea as the light bounces off the corals, subtly illuminating them in shades of pink as we make our journey even deeper as we pass by even more fish, abalone, and other strange creatures that I remind myself to read about in a Buzzfeed article when I get back to the surface. 

Just then, however, a clearing appears in the coral, and I bump into Jessica, who has stopped abruptly and turns to me with an excited expression through her mask. 

When I look where she is pointing, I see the ship.

It is grand, it is imposing, it is far larger than I ever imagined that a ship could be – a gigantic, hulking mass of rotting wood that sticks out of the rocky crevasse that it lies above, like a massive nail in the middle of a woodboard. As I look closer, I see the tattered sail flashing the remnants of a name for the ship:

“e Indomita…”

I guess that this ship was called “The Indomitable” at some point, but it certainly doesn’t look that way now, as seaweed seems to surround and entangle it, almost as if trying to reclaim one of the ocean’s wayward children back into her eternal embrace, mocking the name that the ship was called. 

Perhaps there is treasure here?

…Says my instinct, and it’s clear even in this world where words do not exist that Jessica shares this viewpoint.

Without needing to explain ourselves, we go deeper into the water, as we begin to explore the magnificent underwater wreckage.

And there we are!

That’s a comparison between AI writing and human-led writing.

Let’s look at what happened:

Initial output:

It’s clear to see that the initial output that was generated was relatively short and it also didn’t fit what we wanted – we had to adapt our strategy and therefore the problems that we use in order to get something that match a particular creative vision.

Still, the AI-written essay took a few promptings and took a very short while (10 minutes of prompting to get the result I described), while the essay I wrote took about 20 minutes to complete. Obviously they’re not directly comparable because the structuring is different, there are different turns of logic, different effects, and they have a different word count altogether.

I think it is clear that the AI generated output isn’t bad and if we think about what we took to get there, it’s certainly faster than writing things by hand, even considering my relatively quick writing speed – at the same time though, creating it does require some creative input and a sense of what you’d like to do, which means having a sense of story, development, and an overall creative vision that you like to implement through the AI, which isn’t something that you can get just from randomly prompting; that’s why I always observe (and those of you who have taken my online course may know this) that there is a strong element of what we call garbage in, garbage out.

If you have no idea what you want in the first place, there is no way that an AI, no matter how advanced, is going to be able to provide you with a meaningfully high-quality output; it’s very important to get a sense of what you want before you can let AI take the reins in any way!)

I would note from my own self evaluation though that there were certain executive decisions that I made during the writing process that made it so I could change up the imagery, and also know that there was a definite story that I wanted to tell through the essay, which in turn fed into the particular prompting strategy which I fed into ChatGPT.

I’ll note that if you were someone who wanted to create a piece of written work that fits your own individual specifications, it may also be faster to do so via the human route, particularly if you want to tailor things on the fly, improvise, or otherwise create certain things.

Of course, there’s a skill barrier that’s involved in this – if you don’t have the requisite mastery of language, grammar, logic, scenery, pacing, etcetera, you may find it a little more difficult to create as you wish when in your mind, it is difficult to express something of which you have no concept; language mastery influences your thoughts influences the pattern of the things that you can conceive of influences the actions that you take and the way you express yourself – therein lies the value of mastering language as a human, I think. (Not that I have mastered it entirely!)

Still, let’s not deny the value of AI. AI’s wonderful for conceptualizing ideas (and I definitely used ChatGPT while I was writing The Little Robot That Could Paint!), breaking through writer’s block, thinking through certain difficult concepts, and even revising your work, and it’s definitely here to stay. As you move forward though, I definitely encourage you to look at the opportunity that chatGPT he is giving to you not as something that will replace your mind and your decision-making, but instead something to accentuate it by helping you to much more rapidly at the rate, create, and test out ideas that time constraints may have made impractical for you in the past, thereby dramatically expanding the space of possibilities which you can meaningfully consider in your writing and in your work.

What did you think about this? I’ll let you come to your own conclusions. Do leave a comment if you wish to start a spirited discussion (does anyone even leave comments on blogs anymore?) or if you found this valuable 🙂

Thanks a ton!