One of the more common and useful ways to use tools like ChatGPT is to brainstorm.  

If you don’t know where to start with something or if you want to see if there are ideas that you didn’t think of, this is a good way to stimulate creative thinking.

I know, I know, it seems backwards.  It doesn’t have to be though and it can help you get past writer’s block, idea block, or whatever block is holding up your progress.

You can give a small amount of context and ask the AI tool to ask you questions about it to gather...

The normal behavior of tools like ChatGPT is to give detailed responses.  Sometimes those responses are too long.  

(Usually, those responses are too long…)

Luckily this is another area where you can tell it what you would like to see. Keep in mind that it doesn’t always do...

A few posts ago I talked about a simple 4-step prompt framework to get you started.  If that isn’t getting you the results that you are looking for, here is a framework to create prompts with more context.  

A writing style determines the sentence structure, word choices, and how ideas are expressed.  

There are many options.  Like anything else with ChatGPT, it will guess what you want if there are options and you don’t specify one.

Machines are, well, machines.  As machines, they don’t have feelings.  If you don’t specify the underlying emotions that you want in your output (text, image, etc.) ChatGPT will guess. It probably won’t guess correctly.

Most of the prompts given to AI tools like ChatGPT are short on information and context.  This leads to the tool making more assumptions and giving worse results than expected.

Continuing the conversation from the last post, ChatGPT has  plenty of output options for the more technical users.

Most people don’t realize that they are not limited to “plain text” output from text-based AI tools like ChatGPT.

Here is a line directly from OpenAI’s documentation about ChatGPT:“ChatGPT sometimes writes plausible sounding but incorrect or nonsensical answers…”