AI, or artificial intelligence, is a rapidly evolving field with countless different applications. There are many different types of AI, some of which are better suited for certain tasks than others. One major distinction is between generative and discriminative AI. Generative AI, as the name suggests, is used to create things like images, music, text, and videos [1]. On the other hand, discriminative AI is used to classify things, like determining whether an image is of a cat or a dog.
There are a multitude of generative AIs available, but only a few are currently advanced enough to be particularly useful for prompt engineering. Two of the most commonly used generative AIs are GPT-3 and ChatGPT. GPT-3 is a language model that can generate a wide range of written content, while ChatGPT is a chatbot that can engage in conversational dialogue with humans [2]. While both AIs can generate responses to prompts, they may produce different responses given the same input.
If you are a developer, GPT-3 is recommended since it is more reproducible. However, if you are a non-developer, ChatGPT is easier to use [2]. Most techniques for prompt engineering can be applied to both AIs, but some are exclusive to GPT-3. Therefore, using GPT-3 is recommended if you want to utilize all the techniques in this course.
In conclusion, AI is a broad field with numerous applications. There are different types of AI, such as generative and discriminative. Generative AI can create things like images, music, and text, while discriminative AI is used for classification. GPT-3 and ChatGPT are two commonly used generative AIs that can generate responses to prompts, but may produce different responses given the same input. If you are a developer, GPT-3 is recommended since it is more reproducible, while non-developers may find ChatGPT easier to use.
How these AIs work
This section describes aspects of popular generative text AIs.
These AIs have brains that are made up of billions of artificial neurons. The way these neurons are structured is called a transformer architecture.
It is a fairly complex type of neural network. What you should understand is:
- These AIs are just math functions. Instead of �(�)=�2, they are more like f(thousands of variables) = thousands of possible outputs.
- These AIs understand sentences by breaking them into words/subwords called tokens (e.g. the AI might read
I don't likeas"I", "don", "'t" "like"). Each token is then converted into a list of numbers, so the AI can process it. - These AIs predict the next word/token in the sentence based on the previous words/tokens (e.g. the AI might predict
applesafterI don't like). Each token they write is based on the previous tokens they have seen and written; every time they write a new token, they pause to think about what the next token should be. - These AIs look at every token at the same time. They don’t read left to right, or right to left like humans do.
Please understand that the words “think”, “brain”, and “neuron” are zoomorphisms, which are essentially metaphors for what the model is actually doing.
These models are not really thinking, they are just math functions. They are not actually brains, they are just artificial neural networks. They are not actually biological neurons, they are just numbers.
Free AI Analysis Contact Form
