Rise of “Homo Silicone”

Some reflections on ChatGPT and what it means

Imagine that you wake up in the morning, get dressed and ready for work, then step outside to get to your car when you stop. Everyone you see, all of your neighbors, strangers, are all looking up into the sky. So you look up to see what they are looking at. It’s a large, alien spaceship sitting in the clouds over your hometown.

Your life would be forever changed. One of those pivotal “before and after” moments that we as a society and even rarer, we as a species, reach and things are forever different. Seeing an actual UFO would count as one of those instances. Even if the UFO just sat there, doing nothing, for days, then weeks, then months, your life would pretty much go back to normal. You’d eat, go shopping, have to work, mow the lawn….

Everything would change knowing that we are not alone in the galaxy, that there is other life. Yet there would be no real change in your daily life.

One of those moments happened to me this week. Just the other day, actually. Like seeing that UFO, I can’t stop thinking about it. What it means and what will happen. Everything has changed.

And yet, everything has stayed the same.

I still have to go to work, eat, be with the family, go shopping, etc. All the while knowing that something else is going on. That the super intelligences have arrived.

OpenAI’s ChatGPT is the first publicly accessible.. oh, hell, I’ll let it tell you:

Prompt: What is ChatGPT?

Response: ChatGPT is a variant of the GPT (Generative Pre-training Transformer) language model that has been specifically designed for generating text in the style of a conversation or chat. It is trained on a large dataset of chat logs and is able to generate responses that are appropriate for a given conversation context.

The GPT model is a type of transformer-based language model that is trained to generate natural language text by predicting the next word in a sequence given the previous words. It is trained on a large dataset of human-generated text and is able to generate human-like text by learning the patterns and structures of language. ChatGPT is a variant of the GPT model that has been specifically trained on chat logs, allowing it to generate text that is appropriate for conversation contexts.

Some possible use cases for ChatGPT include generating responses for chatbots, generating conversation dialogues for chat-based applications, or generating text for chat-based games or simulations.

While that is a pretty bland sounding description, I’ve emphasises the relevant bit in bold:

ChatGPT is trained to generate natural language text by predicting the next word in a sequence given the previous words. It doesn’t know what it is writing, or why. It can’t tell a fact from a fiction nor can identify the letter “r” in a word. It is also subject to what I call the dad factor, in which the AI will just “make things up” if it doesn’t know the answer. And guestimate on things that it sort of knows the answer to. My experience has been there is a 20% dad factor in most responses. Still, that’s 80% right on.

I predict that everything has changed for humanity. Generative artificial intelligences (hereinafter “AI”) are everywhere. They can make images from a text prompt, virtual photographs so real they’ve been banned from photo sites. AI’s can look at your chest X-ray and tell you what meds you need to be on, or listen to an audio recording of someone’s voice and determine if they have Parkinson’s — and be used as a tool to modify the medication dosages to minimize it. Things are just going to increase in quality and quantity. While we aren’t being replaced, homo silicone is here to stay.

I’ve been interested in exploring the creative potential of ChatGPT 3.5, the first interactive text generator. By teaching it to write fiction — or compose fiction, as I put it — I’ve had some amazing results. Take, for example, the question that everyone everywhere has quickly asked themselves three times in a row:

How much wood would a woodchuck chuck if a woodchuck could chuck wood?

I put the above prompt into ChatGPT 3.5 and got an answer which was surprising to me because, well, I guess I didn’t know much about woodchucks:

It is a popular saying that a woodchuck, also known as a groundhog, would chuck as much wood as it could if it had the ability to chuck wood. However, woodchucks do not actually have the ability to chuck wood. They are burrowing animals that are more likely to dig tunnels in the ground than to chuck wood. They are primarily herbivorous and mainly eat grasses, fruits, and vegetables. So, in reality, a woodchuck would not chuck any wood at all.

So I then asked the AI to tell a short story about a wood chuck who could chuck wood and how much wood he could chuck. This turned out to be one of my favorite ChatGPT responses to a prompt of mine. This could definitely be a children’s book:

Once upon a time, in a forest far, far away, there lived a woodchuck named Chuck. Chuck was a bit different from all the other woodchucks in the forest. You see, Chuck had a special talent — he could chuck wood.

At first, Chuck didn’t realize he had this talent. He was just a young woodchuck, minding his own business, digging tunnels and eating grasses like any other woodchuck. But one day, while he was out foraging for food, he stumbled upon a fallen tree branch. Without thinking, Chuck grabbed the branch and chucked it as far as he could.

To Chuck’s surprise, the branch flew through the air and landed a good distance away. Chuck couldn’t believe his eyes. He had never seen anything like it.

Excited by his new discovery, Chuck started chucking more and more wood. He chucked branches and logs, big and small. He chucked so much wood that the other animals in the forest started to take notice.

“Look at Chuck, chucking all that wood!” they exclaimed. “He must be the strongest woodchuck in the forest!”

As word of Chuck’s wood-chucking abilities spread, more and more animals came to see him in action. Bears, rabbits, even the sly fox — all came to watch Chuck chuck wood.

But Chuck didn’t care about the attention. He was just happy to be able to use his special talent. And as it turns out, Chuck was a natural at chucking wood. He could chuck more wood in a day than any other woodchuck in the forest.

In fact, Chuck became so skilled at chucking wood that the other animals started to ask him for help. “Could you chuck this log over to my den?” they would ask. “Could you chuck this branch out of my way?”

Chuck was happy to oblige. He loved helping his friends and using his special talent.

As the years went by, Chuck became known as the Woodchuck Who Could Chuck Wood. And even though he was getting on in years, he never lost his love for chucking wood. He chucked wood every day, and he was still the strongest woodchuck in the forest.

So, if you ever find yourself in a forest and you need some wood chucked, just look for Chuck — the Woodchuck Who Could Chuck Wood.

That story was written in just under 5 seconds.

I’ll be the first to admit that not all of the fiction created by OpenGPT is at that level of storytelling. But take a look at some of my stories thus far and I think you’ll agree that it is not all that bad. And it is only going to get better. The current dataset upon which ChatGPT trained concluded at the end of 2020. So the system and its training data is basically two years old. The new system being trained, GPT4.0 has reportedly 500 times the amount of data. While that won’t make it 500 times more intelligent, it will likely make it at least twice as intelligent. Whatever intelligence means anymore.

That’s why I consider them to be essentially a new species: homo silicone.