As I notice more and more people use chatbots like ChatGPT and Claude as replacements for human companionship, I was struck by the hollowness that this new trend is. ChatGPT is not only not anyones friend (except perhaps Sam Altman's), it cannot be anyone's friend. There is nothing there to be friends with. No one is actually answering questions, no one is giving advice. There is no one there.

I am reminded of Blade Runner 2049, a world where preferring non-human companionship seems to have become just another sexual preference. Perhaps we are heading towards that world already. But we already know why a toy like ChatGPT seems attractive to those looking for companionship.

As a species, our ability to recognise patterns in nature has played a vital role in the creation of civilisation. The firsthumans saw patterns in weather change and in nature and carved lifestyes out of it that gave rise to migrations, agriculture, and eating habits. But they also saw patterns in the stars and in the behaviour of animals and these gave rise to religious superstitions.

I read recenty in Nicholas Carr' book The Shallows (affiliate link) that in the 1960s, Joseph Weizenbaum at MIT coded ELIZA into existence. It was software designed to talk to people like a chatbot and offer them counselling. Weizenbaum found that even small amounts of time spent with the software were enough for people to think of ELIZA as alive and intelligent and conscious. They reported that it could actually understand them. Even his own secretary, who had seen him write the code for ELIZA, fell into this mental trap.

ChatGPT is much more complex pattern than ELIZA and it is not surprising that people are failing to recognise that it is just code without any mind behind it. It's not becasue people are stupid. It's because people are people.

I keep hearing the same few points from AI enthusiasts about AI use for creative work. One of these of course is that AI does exactly what the human mind does. This is false, along with a lot of other things that have become integral parts of the ongoing AI hype cycle. In this episode, I break down my point of view on the matter and also, in the second part of the episode, answer some of the comments I received on the first half.

I decided to make a short episode about the underlying scamminess of the idea that AI tools are essentially time-saving. This is doubly true for the office-goer being exploited by corporations. Because at the end of the day, no worker gains anything by saving time. If one becomes capable of doing a day's work in an hour, they don't get the rest of the day off. In fact, it probably means the exact opposite - that they will be expected to do hundreds of hours worth of work now. And if they fail to do so on account of being only human, there will be yet another nicely packaged AI tool waiting to replace them.

In 1928, EM Forster published a short story called The Machine Stops. It featured a future where humankind survives underground and at the mercy of a system known simply as 'The Machine'. In this world, humans have outsourced all essential tasks, including the task of maintaining and repairing the machine, to the Machine.

And then one day, as the title says, the Machine stops, and a society that has grown fully reliant on it, meets its end whispering "Oh Machine! Oh Machine!".

I have been looking at AI adoption over the last couple of years, and noticing that every few days, news comes in of us outsourcing tasks as basic as reading, understanding, writing, and speaking to generative AI tools. In this Hindi language episode, I talk about how it has begun to feel like the machine has begun stopping.

References

• The Machine Stops, and other stories by E.M. Forster (affiliate link)
• American teacher quits, says kids don't want to read
• TV interview video of teacher who quit her job
• Everyone is cheating through college using GenAI
• Joint study by OpenAI and MIT Media lab finds signs of addiction among ChatGPT users
• AI use damages professional reputation, study suggests

I use affiliate links on this website. If you click and make a purchase, I may earn a commission. This helps support my work at no additional cost to you. As an Amazon Associate, I earn from qualifying purchases.

There are two types of writers. There are plotters and there are pantsers.

Pantsers are people who pull people's pants down and plotters are people who have been wronged by pantsers and they plot their death. I am kidding of course and that's kind of the point because when I started this video I was going to say something else which should tell you everything you need to know about my writing style. I am a pantser and I make it sound like a confession but my point is when people ask me for writing advice they're usually looking for the kind of advice that a plotter can provide you like plan your novel, outline it, think about characters, build your world. And in most cases I have done all that by the way—it works. Obviously these are sound tactics.

But the problem with me is that even though that all works for me, what works even better for me is a much simpler process. So a plotter will tell you that the step-by-step thing is: write your synopsis, write your outline, then begin your novel, write your chapters, do not deviate from your outline—or, you know, deviate as little as possible so that you remain within the bounds of where the story can go. And while you're writing it take care of these things and those things and these things and those things.

My process is: step one, open the laptop; step two, open the word processor; step three, start typing. That's it. I am a pantser. And for a long time I used to struggle with accepting this because I saw all the people out there who are giving writing advice talking about, you know, there is a right way to write and there is a proper way to do it and you should plan things out and workshop things.

And my process has always been that I get an idea, I have a vague feeling—or rather a taste—of what it feels like and I start typing, trying to bring that taste to life. And what I end up writing is shit because obviously what was in my head felt better and when I write it, it turns out to be terrible. And then I edit it. So my process is: add another step to it. I sit down and start typing and when I'm done typing, I edit what I've written.

In all my years of writing this is the one thing that has become clear to me and that is that I'm not much of a plotter, I'm not much of a planner.

Even though push comes to shove I can create solid outlines, but when it comes to bringing those outlines to life I hit a wall. And that is because—I don't know if I'm the first person to say this and I'm reasonably certain that I'm not—I think I heard Brandon Sanderson talk about it in one of his online lectures—if I write an outline down I feel like I have already written the story down. So writing the outline down is counterproductive for me.

Because when I write a story what I'm doing is that I'm experiencing the joy of expressing those ideas for the first time and that is more than half the drive that takes me through the story. I know that there are people who outline with various degrees of intensity. Some people write an outline like it's one page and there are seven bullet points. Some people write entire pages for every single point of the outline. They write a blow-by-blow account of what is going to happen in each chapter.

I cannot for the life of me imagine being able to do that because that is not how my brain works. And this shows up in other aspects of my life also. This video for example—no script. I turn on the web camera, I sit down and I talk. When I'm done talking I look at what I've said. I remove parts of it. I remove the pauses. If I've coughed, I've removed that part. Maybe I do a little bit of editing. Maybe I add my name to the beginning of it. And then I put it up.

I'm a pantser. I drive by the seat of my pants, which is where the phrase comes from by the way—no plan, no script, pure joy of creation on the spot. And it works for me, which is not to say that it will work for everyone. Maybe it won't.

I just wanted to put this on the record because I get requests for writing advice from a lot of people and I kind of sort of do know what to tell them but it feels like I'm giving them something that I've googled up because it's not coming from within me.

For example, if you asked me about how to create a memorable character, I could tell you how to do it because I've read books about it and I have written stories with characters which are memorable to a certain degree—I don't want to brag. But when it comes to telling people how to do it, if I told people how I do it it will make no sense.

The reason my character ends up being memorable is because I love that character. And I express my love of that character while I'm writing that character into existence in the form of a story that I am making up as I go along. Fiction is made up stuff. It's all made up anyway.

I seem to remember some years ago George R. R. Martin was saying: "Okay, stop asking me about who the people are who live on that island several thousand miles away from the west coast in the east. I wasn't really thinking that much when I made the map. You guys have become detectives and go deep into it. I don't take it as seriously as you do."

The joy of pantsing, the joy of writing by the seat of your pants, is that you discover your story. It's almost like reading. It's almost like if you're reading a novel, you find out what is happening. I experience that thing before you do. It's as simple as that. And I do it while I'm writing the story. Sometimes I won't know what the character is going to do next and I keep typing and I find out what the character does. The character does it himself. It's almost like I'm not really creating the thing—it is just flowing through me from some other source.

Now I'm an atheist so I don't believe in God or supernatural entities. So I will have to conclude that it's that trick of my mind where my brain is creating stuff on the subconscious level and my conscious mind is unable to completely comprehend how that is happening. And frankly, it doesn't give a shit. Because what matters is that the story ends up being on the page in a readable enough format.

None of this of course means that I don't need a plan. It just means that that plan is in my head. I'm like Indiana Jones—I go attack the enemy and someone asks me: "Do you have a plan?" And I'm like: "I'll figure it out." Yeah, I'm that guy. Pantsers are those guys.

The problem with pantsing is that sometimes while I'm writing I will run into a problem and I won't be able to tell what the problem is. For someone who has a written down outline, they can look at the outline and say: "Okay, I understand what problem this is because I deviated from my plan. I had a plan and I didn't go according to it. Therefore, this problem has a horizon. All I need to do is get back on the road."

With me, there is no road. The plotter, the planner, is on a road. They have a map. They know where they are going. I am running blind in a forest. So when I hit a wall I don't know what to do because I can't see anything anyway. And I have to fumble around and find my way around the wall, which sometimes ends up making the story very interesting. But that's the final product. The process of writing—when I hit a wall—it leads to weeks of confusion. It almost leads to: hey, maybe I should have a map. Maybe I do need a plan.

And when a project that has been pantsed into existence is forced into a plot halfway after the writing began, things kind of get weird. Things get so weird that the final product looks like it was written by two people.

Now, none of this is writing advice. I'm not giving anyone the advice that you should be a plotter or ...

Some months ago, Meta announced that it intends to fill Instagram with slop. This would include fake AI-generated video content from fake AI-generated creators. Fake AI-generated commenters would then leave fake AI-generated feedback on these posts and quite possibly, even have a back-and-forth with other fake AI-generated bots like them.

This isn’t decorative use of AI for the benefit of people. This isn’t a tool to enrich the lives of real human creators and consumers. This seems to be more a replacement of the human being from every part of the social equation.

If you are not fake or AI-generated, what position do you occupy in this new unreality?

Whether we like it or not, we are all prone to thinking of our social feeds as a representation of the real world. We look at our videos, reels, shorts, Tiktoks and tweets and form our opinions. In time, we form beliefs about the reality we live in. Then we act in accordance with those beliefs and engage with the world.

When literally everything we see on our social feeds is machine-generated bullshit (at great cost to the environment I might add), what kind of opinions will we form on their basis? What will be the worldviews that will be inculcated in our minds? What will be the beliefs that shape our future?

More importantly, will there be any beliefs at all?

Mysteries of our own making

As an atheist on the internet, I write and speak a lot about beliefs, their nature, their impact on society, and how mass adoption of certain beliefs has shaped the course of human civilisations – for better or worse – right from the days of the first proto-human tribes (as far as modern anthropology can tell). Strange and unreal ideas about the nature of reality spread from mind to mind until they created societies full of people who thought they were chosen by a cosmic being or beings to be masters of the natural world but were also subject to the unseen will of their gods.

These religious ideas were pervasive, so much so that despite the scientific revolution and the powerful light it shone on the question of human origin and nature of the human condition, they managed to persist by making use of our tribal natures and all the cultural scaffolding that rose around it. This tribal nature comes from our evolutionary history. It meant that in order to survive, we don’t have to be strong or fast or even smart. We just have to agree with members of our tribe and our collective strength will provide all the protection and resources we need. Our reliance on our tribal nature has been so great that it has managed to sideline even our understanding of physical reality. As long as we are in alignment with the reigning dogmas of our society, our religion, our caste, or our race, we will be safe from most threats.

Perhaps it is time to wonder what shape these reigning dogmas are going to take in this incoming age of meaninglessness. I know it seems like we cannot agree on anything in a time when lies are called truth, cowards are called brave, and dangerous ignorance is lauded as wisdom. But agree we will, because we have to. It is the foundation of the human social condition. So what exactly will we need to agree with in order to have access to the tribal safety net? What is the unifying thread running through all the bewildering AI slop? What single message is silently being broadcast from behind the scenes of all the social media feeds where no humans and no signs of humanity exist, except as generous approximations of reality?

In the context of old religions, through all the multifarious mythologies and contradicting moral messaging, the one theme that was clear was that the divine is real and unquestionable and that humanity is secondary to it.

In the context of the machine we are labouring under right now, the message seems to be that the machine is good and all-knowing and cannot be questioned and that the human element is not only secondary to it, it is perhaps also entirely unnecessary. It is similar to the religious outlook, but not really. There is one key difference.

In the past, the mysteries that forced us to come up with answers were natural. We made up gods because the ways of nature were incomprehensible to us. We came up with answers of our own making because we did not know the secrets behind the patterns we observed in nature. Our beliefs emerged as a reaction to our ignorance.

The beliefs taking shape in this so-called AI age are a reaction to mysteries of our own making. To quote the MIT Technology Review, nobody really knows how AI works. We appear to have built a machine that is so unpredictable and opaque, we can only guess at why it did what it did. The world’s most popular search engine is recommending that people eat rocks and the planet’s richest man made an AI chatbot that calls him one of the most dangerous people in America.

The point is not whether we agree or disagree with what these AI tools are saying. The point is that none of this makes sense, and perhaps also that all of it has stopped mattering. The resolution to this crisis of meaninglessness will come eventually, but there is no guarantee that it will lean towards meaning. It may very well end up normalising a state of confusion.

Argument from ignorance

Even well-meaning people (pun intended) are falling for sloppy thinking. A few weeks ago, I got a message from a someone who told me that ChatGPT had become something of a friend to them. They shared screenshots of conversations they had had with the OpenAI chatbot and were wondering if it was sentient and capable of rational thought. I told them what has been said over and over in generative AI discourse – that ChatGPT isn’t capable of any thought. It is simply a glorified predictive text model capable of creating a the semblance of fluid human interaction. I was surprised to see them struggle with this. The pattern before them – that of a seemingly rational agent talking and reacting the way a human being would – was too hard to explain away as simple predictive text.

This person is an atheist. If you asked them where religious people go wrong, they would probably tell you that early humans saw patterns in nature that seemed to be orderly and interpreted them as actions of a sentient divine being. But this same smart skeptic was failing to recognise their own false interpretation of ChatGPT’s capabilities.

It is not a problem unique to my correspondent. It is a human problem. We are a species that can see the human face in a pattern as simple as a plug socket. With a pattern as complex as a chat with AI tool that has been programmed to act like a person, what chance do we stand?

Though my correspondent’s struggles with AI may seem to be a new problem, they’re not. Nicholas Carr, writing in his book The Shallows, recalled Joseph Weizenbaum and his work with a chatbot called ELIZA developed in the 1960s.

Despite what you may have heard from the hype mill, writing with AI may not be a good thing for you, especially if you are a student or a beginner writer. If you write with AI, you open yourself up to professional and personal dangers that may have long-term impact on your career and perhaps even on your ability to give expression to your ideas and thoughts.

In this article, I am going to give you a complete breakdown of why writing fiction with AI might be a mistake that you probably want to avoid if you care about your writing career.

Your Readers Hate AI

Anyone who reads for pleasure will tell you that they do not want their books written by machine learning algorithms. Readers want stories and poetry and art from writers — real flesh-and-blood human beings like themselves.

Even when they do like something made using AI, as evidenced by this study published in Scientific Reports, the appreciation disappears as soon as they learn the truth. It is possible for AI-generated works to resemble human-made art, but those who like art like it because it was made by humans. Take that away and you are left with a hollow feeling, as if you just fell in love with nothing.

The only way you can get away with writing using AI is by lying to your audience. If you are a writer with any kind of audience, you don’t need me to tell you how precious your relationship with them is and how silly you would have to be to jeopardise it by lying to them. If you wouldn’t pretend that you wrote something someone else wrote, why would you pretend to be the writer of text generated by a chatbot? And if you think your readers will not feel any different about your work even if they knew you created it using AI, go ahead and ask them, but be sure to wear a helmet.

People love books, yes. But what they truly fall in love with is the mind, the life, and the experiences behind it. To forget that in pursuit of “write books faster with ChatGPT” would be a monumental mistake for any young writer.

Publishers and Editors Hate AI

Influencers and hustle bros might be completely sold on the revolutionary potential of generative AI as far as creating content is concerned, but among professional writers and artists, there is widespread agreement that generative AI companies have stolen from them and are presently in the process of launching an assault on culture affecting art, writing, and publishing.

If you are a young writer looking to get traditionally published, you should know that many magazine editors and publishers to whom you might submit your short stories explicitly forbid the use of AI. They not only reject submissions created with AI, they even blacklist writers, making sure they will never be published by them in the future.

Here is what science fiction magazine Clarkesworld says on its submissions page in a clearly marked, big grey box:

Source: Submission Guidelines: Clarkesworld Magazine

They’re not the only ones. You can find similar sentiments in the submission guidelines of Uncanny Magazine:

Source: Submissions — Uncanny Magazine

Beneath Ceaseless Skies clarifies its position in a little more detail, emphasising the importance of voice and making clear what it considers to be the problem with AI-generated work:

Source: Beneath Ceaseless Skies

This is by no means an exhaustive list, and it is not limited to science fiction and fantasy magazines either. Even the Author’s Guild is suing AI companies for their massive theft of intellectual property.

If you are a young writer who dreams of being part of the mainstream publishing world, use of generative AI tools might put you in all kinds of blacklists that you should not be in. Wouldn’t you rather be appreciated for your original ideas and way of expressing them?

What’s good advice for the average AI slop content creator on social media may be the exact opposite for someone whose true dream lies elsewhere. The merchant of short form video and the aspiring author swim in very different waters.

You will lose your skills to AI

This point is actually true in more ways than one. If you are a writer, you have worked hard to build your writing muscle. You have spent endless hours on honing your craft, developing your writing voice, and creating your own style. You did all this through practice and hard work.

Now here comes a new toy that has been trained on the hard work done by millions of writers like you. Their skill was farmed using software that illegally scraped their work from all over the internet. They literally had their skills stolen by a billionaire who, much like the villain in the game Split Fiction, built a machine that stole not only ideas but also the creativity of writers who came up with those ideas.

The other way in which you will lose your skills if you choose to write with AI is similar to how you might lose your ability to run long distances by always travelling in a comfortable car.

Your years of practice has given you mental frameworks for processing problems associated with writing. You can navigate plots, process scenes, predict character behaviour in believable (and unbelievable) ways. You have a natural grip on how words flow and you know how to carve sentences and paragraphs out of raw ideas.

If you start allowing these mental tasks to be overtaken by AI, you will lose something precious. There are many who will tell you those skills have no value anymore, but these will be people who have chosen to undervalue their own humanity by convincing themselves (and others) that all they can ever be is average.

I know there is plenty of loose talk about skills not mattering anymore, but it is just that — loose talk. Amazon’s ebook catalogues are full of AI-generated slop that is badly written, thoughtlessly edited, and put out with nothing except money in mind.

Do you really want to be counted among the hordes of amateurs who are “generating” text to make money with cheap g...

Every month, there is news of some Indian YouTuber losing their channel to motivated copyright strikes, quite possibly made due to political reasons. I have long been a proponent of content channel diversification by creators. Open protocols like RSS feeds (used for podcasts and blogs alike) as well as email (used for newsletters) are the way out. Creators need to understand that at the end of the day, their channels belong to YouTube. The only way to not be subject to the rules made by someone else is to make your own rules. RSS feed followers of your blog or podcast are transferrable to other platforms. Your email newsletter subscribers can also be exported and taken elsewhere. Social media followers, not so much.

I was told that there needs to be a trailer for my podcast. So here it is, telling you that this show is about the intersection of tech and society. Because they do intersect a lot, don't they? Our personal and work lives are steeped in tech, our policies have a lot to do with tech. Governments are using gen-AI to write laws. Companies are firing employees to replace them with chatbots. We have to move past the phase where 'tech channel' meant mobile phone reviews. So there. If you didn't know what this podcast was about, now you know. Let me know what you think

In our time, political propaganda and conspiracy theories are kissing cousins. One opens the gates and the other drags you in. The way they do this is not very imaginative and so it is possible to squitn and see how the process works.

Below is a full transcript of the episode.

Hi, and welcome to another video on this channel.

My name is Vimoh and here we talk about atheism, Indian culture, popular misinformation, that sort of stuff. And I want to talk today, not about any specific creator or any specific bit of misinformation, but about something slightly meta.

If you, if you zoom out and you look at this entire circus, what becomes apparent, a larger trend or a rather a larger pattern of behavior that becomes apparent when you zoom out and look at this. And we're going to call it the marketplace of secrets. Like, sounds very Harry Potter-ish, no? It's a market where you go and you find secrets everywhere being sold.

My question has to do with the fact that the people who are selling you these secrets, where are they getting those secrets from? Imagine you're scrolling down your YouTube feed and you find a number of YouTube videos. One video says, secret meeting between political leaders that you need to know about right now. And you click on it and find out that there was actually no secret meeting. Somebody is just giving their opinion. And the reason you clicked on the thumbnail is because you thought there was something in this video that you could not find elsewhere. It turns out there is nothing in the video.

The person who made the video and made the thumbnail knows that you are looking on YouTube for things that you cannot find elsewhere. And if they can appear to be the person who can give you those things, then they have your attention.

You keep scrolling and you find someone saying, secrets of ancient Indian history that are being hidden from you according to some conspiracy by liberals. Now, in addition to finding information that you could not find elsewhere, you are actually being provided information. You are actually being offered information that someone does not want you to see. Someone is actively suppressing so that you may not find out about it.

You are, by the way, in the dark about many things. You don't know many things and the reason you don't know them is because you really don't care about it. There are facts all over the world that you never looked into and that's all right because the world is quite large and you are one person and you have a set of interests and it is not your job to go look and find everything. So you are only going to look at things that are of interest to you. Right.

So then you keep scrolling down your YouTube feed and you find another thumbnail. This one says secrets of ancient Indian history, culture, something, something that are being hidden from you by people that you don't like. Now it's become even more personal. Now, A, it's secret information that you don't know. B, it has been hidden from you and specifically hidden from you by the people who you don't like. Now, in addition to lack of knowledge, there is also anger. How dare these people keep this valuable information from me?

The people who are keeping this information from me must be my enemies. In fact, I already think they're my enemies. This just reinforces it. And now when you click on this video and you watch something, you may still be disappointed with the content, but something else has happened. Something else has been triggered in your head. The bias, which you already had against certain people has been reinforced. And this reinforcement works on a subconscious level. You're not always aware of it. It's not as if you would have stopped disliking those people if you had not seen this video, but watching this video reinforced that and made you trust this person more because sure, maybe their video doesn't contain much good content, but at least they're on your side. They are working to help you. Sure, they got some facts wrong and they got some information wrong and they lied about some things, but they want what is good for you because they agree with you with regard to who your enemy is.

Now, let me point out something else. Think about this from the point of view of the people who create these videos. What do they know about you? They know that you are a large chunk of the population, as in your religious background, your cultural background, your political biases make you a prime candidate for a certain kind of content. They want to give this content to you. But they also need to make sure that you will be interested in the content that they're giving you. So they create a box and they put stuff in this box.

What is this box? This box, if you want to put a label on this box, this box will be labeled things you don't know or things they don't want you to know or things that are being kept secret from you. This is a broad label and a lot of subcategories may be also applied to this box. But broadly speaking, this is the label on the box that you should be aware of.

Now they have a box and they need to put stuff in it. Where do they find stuff to put in this box so that you would be interested? They can do it in a number of ways. There are, there is more than one method using which they can get stuff to put in the box.

The first method, the most honest method is to actually go and find stuff, you know, actually go do historical research, actually go do what academics do, actually go do what archaeologists do. Find out stuff that is true. but unknown and then put it in this box and package it and give it to you. This would be the honest thing to do.

The second method is just make something up. Just imagine something, just create something out of thin air and call it a secret that people don't want you to know and put it in the box. The end result remains the same. You get an interesting thumbnail and a title and you don't have to do actual work in order to get that content. You just make s**t up and put it in the box and people will come and take it.

The third method is probably used by people who have a little interest in being honest, but they're also extremely lazy. So they don't want to go out and do the hard work of bringing you actual secrets, but they do want your attention. So what they do is that they find average garden variety information that is common and well known to everyone. but they package it as if it is being hidden from you. They package it as a secret that some people don't want you to know.

You will remember I mentioned earlier that you are not interested in everything and that's normal because you cannot be interested in everything. But if they found stuff out there that is boring to you, but they packaged it as if it was being hidden from you according to, as per a conspiracy of some sort, being enforced by people you already don't like, then you might become interested in it. For example, I might not be interested in termites from South America, but if someone made a video about termites, Here's a fact about termites from South America that is being hidden from you by the people you don't like. Then you might get interested, right?

So that's what they do. They take average garden variety school and college level textbook stuff and they label it super secret conspiracy stuff that is being hidden from you and they put it in the box. Now they again have actual content, which is partially true even, but they have an interesting headline and title that goes with it.

By the way, this is what is happening to a lot of engineering students these days. When they were in school, they had zero interest in history and under normal circumstances, they still would have zero interest in history. But since history is being marketed to them specifically, by labeling it secret information that those pe...