I’ve been trying to settle on nomenclature related to the creation of digital content and posting of said content to any of a number of popular sites.
Since ChatGPT4 is pretty much permanently too busy to talk, I gave ChatGPT3.5 a go. Turns out he, she, they, it was able to help. (I asked ChatGPT3 which pronoun was most appropriate for an AI. After blah, blah about being an AI with no gender or preferences it got around to saying that “it” was the most common.)
Recently when creating a webpage, I checked out ChatGPT as a means to be reminded of the typical language used to make a referral for suicide prevention.
Spoiler Alert: I found some help… But, the “help” was only useful after doing a bit of fact-checking. If there is anything that looks like a fact in content provided by ChatGPT it needs to be verified. As they say, even a blind squirrel will find a nut from time to time. However it is on you to double-check any “nut” given to you by a squirrel before biting down. Continue reading
I was doing a little file cleanup on my main drive today and stumbled across this short blurb I scribed when working on the introduction to the books.
Figured I’d let ChatGPT4 loose on the text and see where that went. Below you have the results.
This story (text and images) was produced by AI with some prompting performed by some friends and yours truly.
It is presented not as a work of great fiction and refinement. Rather as a peek at the current state of AI story telling. Continue reading
What started as a poke at the bear of marketing ended in a nice discussion about the value of shifting viewpoints/perspective and the need for a meta-view. Continue reading
This all started as a chat session to test the “Is there anything you would add?” Swiss Army Prompt. However, after getting into it, things took off on another track all together.
Here’s the beginning, middle, and end of the chat. Continue reading
In this blog I begin with a juicy bit of content from one of E.J. Gold’s explorations. I take this juicy bit and head into the “wherever the heck this takes us” with ChatGPT4. Continue reading
Working with ChatGPT as a collaborator the following prompt was generated. This prompt was designed to collect and display news items from a particular birthday.
“Imagine today is [BIRTHDATE in MM/DD/YYYY format]. Please provide a summary of 10 major news items that occurred on this date, each with a short title at the beginning, followed by a brief paragraph describing the event.” Continue reading
Reading The AI Advantage Newsletter I found reference to the prompt below. Very interesting prompt. So, obviously, the first thing I did was see if ChatGPT4 could help create a more succinct version.
The jury is still out on whether the new formulation of the prompt is just as good. I have used the new form several time to good result. Continue reading
Prompt Engineering is blowing up as a topic of discussion. Now that ChatGPT4 is entering the scene, it is even more so. In one of these discussions there was a comment made the mirrored something I’ve been thinking about recently.
It was mentioned that using prompts which were polite and respectful would yield better results than just barking orders.
To test this observation (theory?) I began a hunt for prompts which would yield incorrect results in a predictable way. One of the first prompts that I tried was a simple math questions that ChatGPT has a history of getting wrong. The experiment and results of that endeavor are covered in this blog: Is ChatGPT as Bad at Maths as Some Say?
Unfortunately that prompt did not turnout to be a valid question for testing the value of being polite.
So, I turned to ChatGPT4 to see if it had a few problematic prompts up its sleeve. Continue reading