Whenever I read online explanations of ChatGPT and the technology behind it, I get a little confused.  I cannot fully get my head around some of the concepts as a non-techie.  Maybe because the way I think is very linear and I need a step-by-step explanation.

So below I will provide a simple explanation and link together ChatGPT, GPT, and Large Language Models (LLMs), so even I can understand it!

In the most basic of explanations, ChatGPT is a software program, an online application if you like, that is essentially a smart chatbot. Meaning that it can interact with human beings in a conversational way.  It's designed to understand what you say or ask and give you helpful responses that make sense (well, usually… ChatGPT sometimes gets things wrong!).

The "GPT" part in ChatGPT stands for "Generative Pre-trained Transformer." It's a fancy name for the technology/ model behind ChatGPT.  GPT is a type of artificial intelligence that has been trained on lots of data/text/information from the internet (more on this further below). Generative basically means it has the ability to create new content, such as images, music, or text, as it learns from previous examples it has been exposed to and GPT is a specific example of a generative AI model.

So, to summarize, GPT is a prominent example of a generative AI model that is capable of generating text based on the patterns and knowledge it has learned during training.

GPT works by using a big neural network, you can think of this as a super smart brain.   This brain can take in words or sentences and figure out what they mean. It also knows how to put words together to form new sentences.

Just to be clear ChatGPT is a variant or version of the GPT.

What is the relationship between GPT and Large Language Models?

Very simply, GPT is a type of Large Language Model (LLM) there are others available.

A large language model (LLM) is a type of machine learning model that is trained on huge amounts of data, such as books, articles, and websites.

As a result, they can perform a variety of natural language processing (NLP) tasks, including generating and classifying text, answering questions in a conversational manner, and translating text from one language to another. These machine learning models utilize deep learning algorithms to process and understand language.

When you communicate with ChatGPT, it uses its trained brain to understand your words and come up with a response. It tries its best to give you a helpful answer based on what it has learned from all the text it has read. Sometimes it may not understand perfectly or give the exact answer you want, but it's always learning and getting better.

GPT has gone through a number of evolutions and currently now stands at GPT4.  GPT4 is currently one of the largest and most powerful language-processing AI models to date.

ChatGPT in Action

As ChatGPT currently responds to text prompt instructions and in response provides the most relevant output.

Here’s a little experiment.  I asked ChatGPT the following question:

Question: Can you help me understand what you are? and what you can do.

Answer: "Certainly! I am ChatGPT, an AI language model developed by OpenAI. I have been trained on a wide range of texts from the internet to understand and generate human-like responses.

As for what I can do, I can help you with various tasks involving natural language processing. Some of the things I can do include:

1.      Answering questions: I can provide information on a wide range of topics such as science, history, geography, and more.

2.      Generating text: I can help with creative writing, generate stories, essays, or even help you draft an email.

3.      Language translation: I can assist in translating text from one language to another.

4.      Providing explanations: If you need clarification on a concept or want to understand a complex topic, I can provide explanations in a clear and concise manner.

5.      Assisting in tasks: I can help you with tasks like making a to-do list, setting reminders, or providing general advice.

It's important to note that while I strive to provide accurate and helpful information, I may occasionally generate incorrect or nonsensical responses. Therefore, it's always a good idea to verify important information from reliable sources".

So there you have it. ChatGPT has provided me with a clear understanding of what it is and what it can do for me!

If you want to use it for yourself you can sign up and use the free version of ChatGPT here: ChatGPT | OpenAI

What is GPT-3, GPT-3.5 and GPT-4?


So what we know so far, is that GPT-3, GPT3.5, and GPT-4 are large language models and they are trained on terabytes of information from the internet (training data)  that give artificial intelligence (AI) applications the ability to generate output, based on our prompts or commands. They're some of the largest neural networks (modeled after the human brain) available: GPT-3 has 175 billion parameters and GPT-4 the latest version has been trained on way more data.

Who developed Chat GPT?

ChatGPT was created by OpenAI, which is an artificial intelligence research laboratory and company. You've probably heard of Sam Altman is currently the Chief Executive of Open AI.

Below you can see some of his congressional testimony from 16th May 2023

0:00

/15:01

OpenAI is both a non-profit organization and has a commercial side to its business. Initially, OpenAI was founded as a non-profit research organization with the goal of ensuring that artificial general intelligence (AGI) benefits all of humanity. However, in 2019, OpenAI also established a for-profit entity called OpenAI LP to help secure the necessary funding for its ambitious research and development activities.

Microsoft and Infosys are a couple of the commercial investors in OpenAI.

Click here for the OpenAI website.

How should I use ChatGPT?

I thought I'd ask ChatGPT to answer this question, below is its response.

Question: How should I use ChatGPT?

Answer:  "Using ChatGPT is quite simple! You can interact with me by typing your questions or prompts in the text input box. Once you provide your input, I will process it and generate a response based on the knowledge I have been trained on.

Here are the general steps to use ChatGPT effectively:

1.      Type your question or prompt: Clearly state what you would like to know or the task you need assistance with. It can be a specific question, a request for information, or a topic you want to discuss.

2.      Submit your input: After you've typed your question or prompt, hit the Enter key or click on the "Send" button to submit it to me.

3.      Receive the response: I will generate a response based on the input you provided. The response will appear in the chat window.

4.      Continue the conversation: If you have further questions or need clarification, feel free to ask. We can continue the conversation by exchanging messages back and forth.

Remember that while I strive to provide helpful and accurate information, there may be instances where my responses are not entirely accurate or may require verification. Therefore, it's always a good idea to consult multiple sources and exercise critical thinking.

Feel free to ask me anything, and I'll do my best to assist you!"

Isn't that great? I asked ChatGPT how I should use it and it gave me a set of instructions! 😎

You can read the rest of the article here:  https://www.aitoolstribe.com/chatgpt/

Leave a Reply