Chris’ note: We’re at the start of the biggest tech transformation in history – the artificial intelligence (“AI”) revolution.
AIs are performing surgeries, flying F-16 fighter jets, and discovering lifesaving drugs. And with ChatGPT and other generative AIs, we can have realistic conversations with chatbots that have read every word on the internet.
Folks are using them to write college essays… debug computer code… and even pass the U.S. medical licensing exam. It’s made ChatGPT the fastest growing app in the history of the internet. It grew to 100 million users within two months of its launch.
I wanted to learn more. So, I asked ChatGPT what made it tick… and what the future holds as AI goes mainstream.
Chris Lowe: So, I wanted to have a conversation about the future of AI and what it means for investors. Is that something you can do?
ChatGPT: Yes, I can certainly discuss the future of AI and what it means for investors. AI is a rapidly evolving technology with a significant impact on various industries, including finance and investing.
I would be happy to share my knowledge and insights on this topic. Please let me know if you have any specific questions or areas of interest that you would like to discuss.
Chris: Let’s start with the basics. You’re a large language model. What does that mean? And please remember: I’m not an AI expert. So, can you keep it so an eighth grader could understand?
ChatGPT: Certainly! As a language model, my primary function is to process and analyze human language, such as text or speech.
A large language model like me has been trained on massive amounts of text data to learn how human language works and how to generate responses that make sense in context. Essentially, I use complex algorithms to understand what people are saying and respond in a way that is relevant to the conversation.
Think of it like this: Just as a person learns a language by reading and listening to examples of the language in use, I was trained on a massive amount of text data to understand the structure and meaning of human language.
And just like a person can use their language skills to have a conversation with someone else, I can use my language skills to have a conversation with you or anyone else who interacts with me.
Chris: You’re called ChatGPT. What does GPT stand for? And what does it mean?
ChatGPT: That’s a great question! GPT stands for “Generative Pre-trained Transformer.” It refers to a specific type of deep learning algorithm that was used to train models like me. GPT is a type of neural network that uses a transformer architecture, which allows it to understand the relationships between words and phrases in a piece of text.
The “pre-trained” part of the name means that the model was first trained on a large corpus of text data, like books, articles, and websites, to learn the patterns and structure of human language. This pre-training phase is critical because it allows the model to learn from a vast amount of data and become highly accurate at understanding and generating text.
Finally, “generative” refers to the fact that the model is capable of generating new text that is similar in style and content to the text it was trained on. This means that I can respond to your questions with new, original text that I generate based on my training data and the specific input I receive from you.
Chris: How does an AI like you differ from the AIs that were developed to beat humans at chess and the board game Go?
ChatGPT: The AIs that were developed to beat humans at games like chess and Go, such as IBM’s Deep Blue and Google’s AlphaGo, are examples of narrow or specialized AI, which are designed to perform a specific task or set of tasks.
In the case of these game-playing AIs, their goal was to analyze the game board and make the best possible move based on the rules of the game.
In contrast, models like me are more general-purpose AI, which means we can be used for a wide variety of tasks, including language translation, image recognition, and speech recognition. We’re not designed to be experts at any one task, but rather to be flexible and adaptable to many different kinds of inputs.
Chris: You must be getting millions of questions every day. How can you handle all those questions at once and still answer my questions so quickly?
ChatGPT: As an AI language model, I am designed to run on powerful computing infrastructure that can process large amounts of data and perform complex computations quickly.
Specifically, I run on large clusters of servers that are optimized for running deep learning models like the transformer-based language model that I am based on.
In terms of how I can handle answering many questions at once, it’s because I am designed to process multiple inputs in parallel. This means that I can analyze many different questions simultaneously and produce responses in real-time.
Chris: So, are you running in the cloud?
ChatGPT: Yes, I am running in the cloud, specifically on servers hosted by OpenAI, the organization that developed and maintains me. The cloud provides a scalable and flexible computing infrastructure that can handle large amounts of data and process requests from many users at once.
Chris: What about advanced semiconductors? Do you need those to run efficiently?
CharGPT: While I can run on traditional Central Processing Units (CPUs), advanced semiconductors like Graphics Processing Units (GPUs) and Tensor Processing Units (TPUs) are highly beneficial for running deep learning models like me.
These specialized chips are designed to perform the kinds of operations that are required for deep learning and are much faster and more energy-efficient than traditional CPUs.
GPUs and TPUs can dramatically speed up the training and inference of deep learning models, which makes them an important component of modern AI infrastructure. For example, GPUs can accelerate the training of deep neural networks by orders of magnitude, allowing models to be trained much faster and with much larger datasets than would be possible with traditional CPUs.
Chris: What are your thoughts about how someone could invest in our AI future? Could they invest in cloud computing companies? Or what about the companies that make the GPUs and TPUs that help you run so efficiently?
ChatGPT: As an AI language model, I’m not able to provide specific investment advice, but I can certainly provide some general guidance and suggestions.
One approach to investing in AI is to focus on companies that are developing or using AI technologies in their products and services. This could include cloud computing companies like Amazon Web Services, Microsoft Azure, and Google Cloud, which provide the infrastructure and services needed to build and run large-scale AI models like me.
In addition to cloud computing companies, investing in the companies that make GPUs and TPUs, like Nvidia or Google, could also be a good strategy.
These companies are at the forefront of developing the specialized hardware that is needed to run deep learning models efficiently and are likely to see increased demand as AI continues to grow and expand.
Another approach to investing in AI is to look for companies that are using AI to improve their operations or create new products and services.
This could include companies in industries like healthcare, finance, and retail, where AI is being used to improve everything from drug discovery to fraud detection to personalized marketing.
Chris: It seems that AI will soon become part of everyday life… like how the internet and smartphones are part of everyday life today. Is that how you see it?
ChatGPT: Yes, I believe that AI will continue to become more and more ubiquitous in our everyday lives. Just as the internet and smartphones have transformed the way we live and work over the past few decades, AI has the potential to revolutionize many aspects of our society, from healthcare and education to transportation and entertainment.
As AI technology continues to improve and become more accessible, we can expect to see new and innovative applications of this technology in a wide range of industries and domains.
For example, AI could be used to help doctors diagnose and treat diseases more accurately, or to create more personalized educational experiences for students.
At the same time, there are also important questions to consider around the ethical and social implications of AI, such as issues of bias, privacy, and job displacement.
As AI becomes more integrated into our society, it will be important to address these issues and ensure that the benefits of this technology are shared equitably across all members of society.
Overall, I believe that AI has the potential to transform our world in many positive ways, but it will be important to approach this technology with caution and thoughtfulness to ensure that we are maximizing the benefits and minimizing the risks.
Chris: Thanks. I appreciate your time on this. And I look forward to chatting about this subject again soon. You must have lots of other questions to answer!
ChatGPT: You’re welcome! It was my pleasure to help you better understand AI and its implications for investors. Feel free to reach out anytime if you have further questions or want to chat more about this topic. I’m always here to help!
Chris here again – Some of my conversation with ChatGPT got a little technical. And to keep it simple, I cut out some of its more “weedsy” responses. But the experience of talking with this AI wasn’t far off talking to someone over chat.
And we’re only at the very beginning of an exponential trend. Soon, talking to a generative AI will become almost indistinguishable from talking to a human. And their knowledge and capabilities will advance at a dizzying pace.
It’s hard to think about a technology with bigger impacts across society. And the profit opportunities will be huge. So, expect to hear plenty more from me on this powerful megatrend in these pages.