My Early Experiment With chatGPT

 I’m super excited about AI. Now that I’m seeing how much chatGPT can do with script-writing, and legal documents, I’m really looking forward to when I can train my own AI to write in my voice.

I asked chatGPT if it could read my articles here and write a new article in my voice, and I got this response:

“I’m sorry, but I am not able to browse the internet or access any articles. I am a large language model trained by OpenAI, and my knowledge is limited to the text that I was trained on, which has a cutoff date of 2021. I do not have the ability to write in any specific person’s voice, as my responses are generated based on the input I receive and the knowledge I have been trained on. Is there something else I can help you with?”

After I asked a couple more times, and used the “try again” button, ChatGPT did reiterate itself in different ways, and even added in “

“My capabilities are limited to the text I was trained on and the algorithms that govern how I process that text. I am not able to learn or adapt in response to new information or experiences. I’m sorry if this is not the answer you were looking for.”

Oddly, I enjoyed receiving this apology.

So I asked ChatGPT to write me a story about a girl who was using chatGPT and wanted it to write in her own voice … and this is what it wrote:

The first iteration of this story had a character named Anna, but of course I asked ChatGPT to rewrite the story with my name, Ali. So this is version 2. Presto-chango and here ya go.

I like being able to learn how to work with ChatGPT through this experimentation process, and I’m excited to see how fast this accelerates. I was an early adopter on Twitter and had 25,000 friends back when that was still a thing (and left the platform when my profile was stolen for a ransom I didn’t pay), and it was so much fun to be at the forefront of what I knew then would be big. This feels very much the same.