This week, I played around with ChatGPT, an AI chat bot. It’s fun, it’s shockingly good, and after seeing this article in which it aced a quiz on college-level microbiology, I was so impressed that I wanted to introduce it to all of you. But, I figured, why should I tell you what it is when it can tell you itself? So, I asked ChatGPT three questions, one after another. These prompts are exactly what I typed into the chat box, no more, no less. I copied the results and pasted them as-is below — no edits for length, clarity, or anything else. And I think they’re incredible.
First, I asked it to “write a six-paragraph blog post explaining what ChatGPT is,” and this is what it told me:
ChatGPT is a cutting-edge natural language processing (NLP) technology that enables machines to understand and respond to human conversation in a way that is natural, engaging, and contextually appropriate.
At the heart of ChatGPT is a powerful language model trained on vast amounts of text data. This allows ChatGPT to understand the nuances and complexities of human conversation, including the use of slang, colloquialisms, and idioms. It can also identify the context of a conversation and generate appropriate responses based on that context.
One of the key advantages of ChatGPT is its ability to learn and adapt to a user’s individual language and communication style. This allows it to provide personalized responses and improve its performance over time.
In addition to responding to text-based conversations, ChatGPT is also capable of handling voice input and generating audio responses. This makes it a versatile tool for a wide range of applications, from customer service and virtual assistants, to language translation and voice-enabled chatbots.
Overall, ChatGPT represents a major step forward in the field of NLP and has the potential to revolutionize the way we interact with machines. With its ability to understand and engage in natural, human-like conversation, ChatGPT has the potential to make our interactions with technology more intuitive, efficient, and enjoyable.
Pretty good, right? But kind of boring. So I also asked it to “add some humor,” and it gave me three more paragraphs:
One of the biggest advantages of ChatGPT is that it can provide hilarious responses to your most burning questions. For example, if you ask it “Why did the chicken cross the road?”, it might respond with “To get to the other side… duh!” or “To escape from the evil farmer who wants to turn it into nuggets!”
And if you’re feeling particularly sassy, you can even have a full-on conversation with ChatGPT that’s full of witty banter and clever comebacks. For example, if you tell it “I’m feeling pretty good today,” it might respond with “Well, that’s because you’re talking to a computer program and it’s impossible to feel bad when you’re having a conversation with a machine.”
So if you’re looking for a chatbot that’s not only smart and capable, but also has a great sense of humor, then ChatGPT is definitely the way to go!
And finally, I asked it to “tell me why fans of the Now I Know newsletter should give ChatGPT a try.” I didn’t tell it anything about Now I Know… so I think it focuses too much on current events. But otherwise, I think it makes a pretty good pitch!
Fans of the Now I Know newsletter will love ChatGPT because it allows them to have engaging, informative conversations with a machine that is always up-to-date with the latest facts and information.
Because ChatGPT is powered by a powerful language model trained on vast amounts of text data, it has a deep understanding of a wide range of topics, including history, science, and current events. This means that you can ask it any question and it will provide a thoughtful, accurate response.
In addition, ChatGPT is constantly learning and adapting to its users, so the more you talk to it, the better it gets at providing personalized responses that are tailored to your interests and preferences. This makes it a great tool for anyone who loves learning new things and staying up-to-date with the latest developments in the world.
Overall, if you’re a fan of the Now I Know newsletter and you want to have fascinating, informative conversations with a machine that is always on top of the latest news and information, then you should definitely give ChatGPT a try.
I don’t know if that’s 100% true — I think you’ll likely learn more from my newsletter than from ChatGPT, but that may not be true forever. In any event, the future is cool. Kind of scary, but cool.
Anyway, give it a try — and have fun with it! Need inspiration? I asked it to tell me a story about Iron Man and cookie-obsessed hyper-intelligent squirrels, and this is what it came up with.
The Now I Know Week in Review
Last Friday:Last week, I spoke a bit about how $2 bills are conversation pieces, often provoking a response when you try to use one. To test this, as I mentioned, I went to the bank and got $20 in $2 bills. I’ve only had two opportunties to use them so far and I’m 50/50 — I used two at the gas station conviennce store without issue but yesterday, I spent $8 at the grocery store yesterday and the person working the register called a manager to make sure the store accepted them. (They did.)
Monday: The Zoo That Made Itself Look Like a Donkey: A love story that made a certain politician look like a word that starts with “A” and also means “donkey.”
Tuesday: The Best Part of Waking Up is a Quarter-Million Dollars in Your Cup: I think losing out on the milions may have made the end result bitter for this guy, but rationally, he made out pretty well.
Wednesday: Why Do These Dollars Say “Hawaii” On Them?: I really want one of these and, at some point, may bite the bullet and buy one on eBay.
Thursday: He’s The Type That Likes Numbers?: One, two, skip a few, nine hundred ninenty ninety nine throusand nine hundred ninety nine, one million.
And some other things you should check out:
I’m going to try something new today: Every selection below comes from Radiolab, a really great radio show from NPR affiliate WNYC in New York. (Only one is actually an episode of Radiolab, and only kind of.) I’m a big fan and was once even invited to their in-person story idea pitch meetings by the author of the first link below. If you like this type of stuff, you can subscribe to Radiolab’s newsletter on their website.
1) “The Swoosh” (Latif Nasser on Twitter, 7 minutes, November 2020). Georgia held the second leg of its U.S. Senate elections this week, and if you look at a map of how people voted, you’ll notice a weird shape: “a curious diagonal blue [heavily Democrat-voting] stripe across the center of the state,” in the words of Nasser from yesterday. Nasser, now the co-host of Radiolab, explains that this “shape” is actually rooted in … how the continents were formed. His thread from 2020 explains.
2) “The Political Thicket” (More Perfect, 45 minutes, June 2016). More Perfect is a spinoff podcast of Radiolab’s, focusing on the United States Supreme Court. In this episode, they tackle a case called Baker v. Carr. Here’s how Wikipedia describes the controversy:
Plaintiff Charles Baker was a Republican who lived in Shelby County, Tennessee, and had served as the mayor of Millington, Tennessee, near Memphis. The Tennessee State Constitution required that legislative districts for the Tennessee General Assembly be redrawn every ten years to provide for districts of substantially equal population (as was to be done for congressional districts). Baker’s complaint was that Tennessee had not redistricted since 1901, in response to the 1900 census.
By the time of Baker’s lawsuit [in or around 1960], the population had shifted such that his district in Shelby County had about ten times as many residents as some of the rural districts. The votes of rural citizens were overrepresented compared to those of urban citizens. Baker’s argument was that this discrepancy was causing him to fail to receive the “equal protection of the laws” required by the Fourteenth Amendment.
Seems pretty boring, right? Well, it was anything but. The case was important; in the words of More Perfect, it was “important enough, in fact, that it pushed one Supreme Court justice to a nervous breakdown, brought a boiling feud to a head, put one justice in the hospital, and changed the course of the Supreme Court — and the nation — forever.” They happen to have just re-aired this a week or two ago, so if you’re a Radiolab regular, you may already have heard this one.
3) “Introducing A Divorce Rate For Birds, And Guess Which Bird Never, Ever Divorces?” (Krulwich Wonders, 5 minutes, April 2014). Robert Krulwich, the author of this story, was the longtime co-host of Radiolab until he retired a few years ago. He had a blog about things that sparked his curiosity and, as you can imagine, I was naturally drawn to it. This is a story that I had hoped to turn into a Now I Know article but I couldn’t quite get it right; I figure this is as good of a time to share it as any!
Have a great weekend!