OpenAI has trained a model called ChatGPT to interact in a conversational way. The dialogue format makes it possible for ChatGPT to answer follow-up questions, admit its mistakes, challenge incorrect premises and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.

We’ve compiled a series of requests for ChatGPT and will publish them over the next few weeks. Feel free to pop suggested tasks into the comments section. Enjoy!

We asked if ChatGPT could:

Write an apology from someone called Jacinda for calling someone called David “arrogant” in the style of Benito Mussolini.

And it replied:

To the esteemed David,

I humbly apologize for my rash and thoughtless words. In my pride and foolishness, I allowed my emotions to get the better of me and spoke without considering the harm that my words may cause.

I realize now that my accusations of arrogance were unfounded and unfair, and I deeply regret the pain and offense that I have caused. I hope that you can find it in your heart to forgive me for my actions, and I promise to be more mindful of my words in the future.

I am truly sorry for any harm that I have caused, and I hope that you will accept my sincere apology.

Sincerely,

Jacinda

Help Fund Our NewsDesk

We are building a NewsDesk, hiring journalists and taking the fight to the mainstream media. Will you help fund our NewsDesk?

Your Donation
Donation Period *
Details
Payment
Like What You’ve Read?
Become a Member and Directly Support this Author

Please share this article so others can discover The BFD.

As much at home writing editorials as being the subject of them, Cam has won awards, including the Canon Media Award for his work on the Len Brown/Bevan Chuang story. When he’s not creating the news,...