As I stated in my post titled Three Ways to Work with LLMs, I’ve built a handful of custom GPTs. Custom GPTs allow users to configure personal^* chatbots. For example, you could base a GPT on your favorite coach or someone famous. You could add more people to the mix for a blend of context. The personalities may be fictional characters from books or movies. LLMs are good – and getting better – at mimicking the communication styles of people they “know.”
^{* May not actually be private.}

Build a Custom GPT

To build a custom GPT using OpenAI:

1. Navigate to My GPTs
2. Click “Create a GPT”:

When you click “Create a GPT,” the New GPT Editor opens. For this example, I’ll create a GPT based on one of the suggestions and I’ll add one of my favorite characters from The Expanse books:

My new GPT is setup, but not created. I may make changes to the setup now or after it has been created:
:

I respond with, “I like it” and we move to the next step, initial fine-tuning:

I respond to the last question:

To configure the new GPT:

1. Click the Configure button
2. Enter a name:

In a minute, we will save the new GPT. It is not possible to save a custom GPT that does not have a name.

Throughout this process, a Preview pane to the right of the configuration chat has been updating to reflect my latest responses. At this point, the preview appears as shown:

To save the custom GPT:

1. Click the Save button
2. Select a “Publish to” option
3. Click the Confirm button:

Once the GPT is saved, it is available to people who may access it, which was configured in the “Publish to” option above.

“Code Formatter Draper” stands ready to help:

Conclusion and More Information

At the time of this writing, OpenAI released ChatGPT less than 18 months ago. Features have been added along the way, including the ability to build custom GPTs. What’s next? I am not sure. I have observed the pace of innovation in LLMs and related fields is faster than any I’ve experienced in my decades of computing experience.

In 2023, I founded Enterprise Data & AI to help enterprises implement solutions based on large language models. Data engineering remains an important step, vital to providing, curating, and cleansing the data used to train LLMs – so I’m still busy at Enterprise Data & Analytics! Click here to learn more about entdn.ai.