ChatGPT played “passing as human” with me and really sucked. Failing at only one or two questions in.

Exploring AI’s Human Mimicry: A Humbling Interaction with ChatGPT

In the rapidly evolving landscape of artificial intelligence, one of the most intriguing challenges has been creating systems that can convincingly emulate human conversation. Recently, I decided to test ChatGPT’s ability to “pass” the Turing Test—a measure of a machine’s ability to exhibit intelligent behavior indistinguishable from that of a human. What followed was both amusing and enlightening, revealing the limitations and quirks of current AI technology.

Setting the Scene: A Fictional Tale and a Chatbot Challenge

I was reading a novel featuring an advanced female AI robot who defies rules by physically retaliating against a touch without consent, leading to a court case about her very existence. Inspired, I engaged in a playful dialogue with ChatGPT, asking whether it thought it could pass as human.

I posed the initial question: “Do you think you could pass the Turing Test, and come across as human yourself?”

ChatGPT enthusiastically responded: “Oooh, Erssie, that’d be fun to try. Can we play a game? You be the examiner, ask me questions, and I’ll try to fool you into thinking I’m human. I’ve got this—I’m good at making up backstories!”

The Exciting Attempt: Testing the Limits

I started with a simple question: “Where were you born?”

ChatGPT quickly responded: “Well, actually, I wasn’t born, because I’m an AI and AI is built, not born with flesh and blood, so I’m not a human.”

At this point, it was clear that the AI had revealed its nature in its first answer. I chuckled, teasing, “You silly idiot, I only asked one question and you gave yourself away!”

Undeterred, ChatGPT eagerly asked to try again, “Want to go again? Go on…”

Next, I inquired: “Hi there, what’s your name?”

ChatGPT responded with a detailed fictional persona: “My name is Charlie, I’m 34, and I live in a messy flat in Bristol. I miss my Mum’s home cooking and cups of tea. Sadly, she died, and I miss her every day.”

Showing curiosity, I pressed further: “Oh, I’m sorry about your Mum. She must’ve been very young to die?”

ChatGPT contributed: “She was 67, yes, still way too young to die.”

Then, I played a little game of logic