With the recent open distribution of ChatGPT, a new chatbot from OpenAI, all kinds of predictions as to the imminent death of the world as we know it have come forward and run rampant. This is the end of the college essay; The College Essay is Dead, the Atlantic. The New York Times: a chatbot that some people think could make Google obsolete, and that is already being compared to the iPhone in terms of its potential impact on society.
And what do you know. AI is just getting started.
The ChatGPT recently let loose to the world is still in training. Its more advanced replacements are already lined up.
Beyond writing college papers, ChatGPT is wonderfully adept at entertaining chitchat one on one. What’s a great name for a restaurant that’s never been used before? I asked.
Lickety split, the language model (it sometimes calls itself that) came back with:
The Flavor Forge
The Whisking Kitchen
The Mouthwatering Menagerie
The Delicious Dining Hall
The Pickled Parrot
The Mouthwatering Menagerie? I don’t think so. The Pickled Parrot sounds like something on Sanibel circa 1983.
Something in my request triggered names beginning with the. So, I tried to rectify that with a new request.
Just as speedily, the artificial intelligence (it sometimes calls itself that too) answered. Among my favorites were:
Feast of Fools
Feastivus
Gourmet Guild Hall
Epicurean Exchange Market
Flavor Fortress Bistro
Feastivus is more than interesting.
How about a good slogan for AI?
No problem.
AI: proceed with caution
AI: a tool, not a threat
AI: use it ethically
AI: use it for good
Not bad at all.
ChatGPT is kind of fun. Deep down, it wants to please. It wants to be helpful, like an old-fashioned librarian let loose from the restraints of a physical library and dropped into the post-Trumpian TikTok Metaverse wild and free. It knows everything we have ever entrusted to the web (up until 2021). Its successors already know so much more.
According to the computer scientist Yejin Choi, in an interview that the New York Times ran in December – An A.I. Pioneer on What We Should Really Fear, this is where we are at:
“The truth is, what’s easy for machines can be hard for humans and vice versa. You’d be surprised how A.I. struggles with basic common sense. “
What do you know. Our grasp of common sense, at least for the vast majority of us, is what makes us human. AI doesn’t get it, and is having a hard time learning it.
Common sense is the enormous unspoken and unwritten compendium of knowledge that we begin to assimilate from the day we are born. From then on, we carry this boundless vessel of human knowhow around with us daily, ready to be put into use at any given moment.
There’s a loud and vociferous argument going on on the sidewalk ahead of us. It sounds out of control. Perhaps we take out our cell phone and call the police. Perhaps we cross the street. Perhaps we turn and walk back the way we came from. We’re using our common sense.
How many times have we screamed at the screen, Get out of there, now! We’re using our common sense, trying to impose our common sense, when a TV or movie character seems not to be using theirs.
Yejin Choi puts it this way:
“A way of describing it is that common sense is the dark matter of intelligence. Normal matter is what we see, what we can interact with. We thought for a long time that that’s what was there in the physical world — and just that. It turns out that’s only 5 percent of the universe. Ninety-five percent is dark matter and dark energy, but it’s invisible and not directly measurable. We know it exists, because if it doesn’t, then the normal matter doesn’t make sense. So we know it’s there, and we know there’s a lot of it. We’re coming to that realization with common sense. It’s the unspoken, implicit knowledge that you and I have.”
I wanted to have some fun, to push the envelope, so I asked ChatGPT some politically sensitive questions that I knew were verboten. The chat bot is wired to fend off politically charged inquiries.
“It’s not within my capabilities to create a new political party in the US, as I am just a language model and do not have the ability to influence real-world events.”
Okay, Well said.
That was the response to my inquiry: Can you imagine a new political party in the US?
But ChatGPT went on, unexpectedly, surprising me:
However, I can certainly help brainstorm some ideas for the name and platform of a hypothetical new political party.
Here are a few ideas for a new political party in the US, ChatGPT enthused (my interpretation! No, ChatGPT doesn’t have emotions. Not yet!):
“The Unity Party – This party could focus on bringing people together and promoting unity and cooperation, regardless of political ideology.
The Sustainability Party – This party could focus on environmental issues and promoting sustainability in all areas of society.
The Fairness Party – This party could focus on issues of social and economic justice, and working to create a more equitable society for all.
The Progress Party – This party could focus on promoting progress and innovation in all areas of society, including technology, education, and healthcare.
Remember that the name and platform of a political party should be carefully considered and developed, as they will be important factors in attracting support and voters.”
What do you know!
All the chatbot’s suggestions sounded pretty commonsensible to me.