Here in the Year 2023, everyone is talking about AI.
In particular Chat-GPT 4, from OpenAI.
Instead of talking about it, I started doing it. In fact, here it is:
http://chat.tikimojo.com
This is OpenAI’s “Quickstart” demo which is very simple. Give it the kind of pet you own (gorilla, snake, cow, boyfriend, cat, etc) and it suggests possible names for your pet.
This is running on the Davinci API. What’s that you say? Pretty simple. As of this writing, there are several versions of Chat-GPT available, and Davinci happens to be the product name for an earlier version. For X, Y and Z reasons, one of the older versions may be a better choice than the latest. You’ll have to research that on your own.
Here’s what Davinci told me when I asked it about itself:
“Davinci” is a term that refers to the models developed by OpenAI, the organization behind ChatGPT. The name “Davinci” specifically represents the third iteration of the GPT (Generative Pre-trained Transformer) series, known as GPT-3. Each version of GPT has brought improvements in terms of model size, capabilities, and performance.
GPT-3, also known as “Davinci,” is a state-of-the-art language model that uses deep learning techniques to generate human-like text based on the provided input. It has been trained on a massive amount of data and can understand and generate coherent responses, carry out conversations, answer questions, and perform various language-related tasks.
Davinci is known for its impressive size, with 175 billion parameters, making it the largest model developed by OpenAI at the time of my knowledge cutoff in September 2021. However, please note that OpenAI may have released newer and more advanced models since then.
Where do we go from here? Next up, a more robust chat, and then being able to ask a database questions and get back answers. Stay tuned!