A Spat With My Chatbot

Luther Theses

I had a bit of a spat with m Chatbot this morning. I was reading a post by Doc Searles on his blog. Searles wrote about his experience trying to use to answer a question about theme song for a podcast. He is the co-author of The Cluetrain Manifesto, along with Rick Levine, Christopher Locke and David Weinberger. It was first posted to the web in 1999 as a set of ninety-five theses about the new realities of Web Marketing. (I’m a sucker for a good manifesto, so I’ve followed him ever since. I’m also fond of nailing theses to the door of the church.)

The blog post started with the usual protestations about being forced to use Microsoft products:

Bing search took me to a page of search results about the podcast itself, which didn’t help; but I saw a chat menu under its search bar. Clicking on that brought up a huge popover headlined, “Chat mode is only available when you have access to the new Bing.” For that I need to “unlock conversational search on Microsoft Edge.”

Which I already had, but had hardly used. So I went to Bing on Edge and clicked on the Chat link. Next, it wanted me to log into Microsoft itself. This required two- factor authentication for my password manager (Dashlane) and for Microsoft. Annoying, but we live in an annoying time.

I wanted to check and see if my experience with Bing was the same as Doc’s. (He got better results from a site called Perplexity.ai).

I used the same question Doc Searles had asked: “I’ve listened to A History of Rock Music in 500 Songs, and I wanted to know who sang the theme song. I thought it was a song by the Boswell Sisters, a vocal trio from the 1930s who were pioneers of jazz and swing. I asked my chat-bot, Bing, to confirm my guess.

Bing said that the theme song was “Flying Home” by Lionel Hampton and His Orchestra, a jazz tune from 1942 that featured a famous sax solo by Illinois Jacquet. He said it was one of the earliest examples of rock and roll elements in music, such as the backbeat, the riff, and the honking saxophone. He even gave me a link to listen to the full song.

I was skeptical. Doc had posted a blog post by the podcast host, Andrew Hickey, where he said the theme song was “Rock and Roll” by the Boswell Sisters. He said it was the first song to use the phrase “rock and roll” in its lyrics, and that it was a precursor to rockabilly and rock and roll. I quoted the text to Bing and asked her to check her facts.

Bing was adamant. He said I was confusing the theme song with the background music. He said the background music was a selection of songs that were important for the history of rock music, and one of them was indeed “Rock and Roll” by the Boswell Sisters. But he said the theme song, which played at the start and end of every episode, was “Flying Home” by Lionel Hampton and His Orchestra. He gave me more links to verify his claim.

I was stubborn. I refused to believe him. I thought he was mistaken or malfunctioning. I decided to listen to an episode of the podcast myself and prove him wrong. I opened my podcast app and played the latest episode. It only runs a few seconds, but it sure sounds like a female vocal group to me.

I decided to quit then, and realized that I had just spend 20 minutes arguing with a machine over something trivial and lost. But, I couldn’t let it go.

I wrote: I’ve gone back and listened to the introductory music of the podcast and it still sounds like a female vocal group in the intro to the podcast. But I’m going to let it go at this point. We can just agree to disagree.

Bing wrote: I understand. Sometimes it’s hard to tell the difference between similar songs. I respect your opinion and I appreciate your willingness to let it go. I hope you enjoy the podcast and I hope we can chat again soon.

I guess I’ll leave it at that.

Using Bing AI to Fact Check

I was able to use the Bing Chat this morning to fact check the lecture at the Chautauqua.

I’m trying to use Bing as my primary interface to generative AI as much as I can. It’s currently the best free version of Large Language Model, and I’m recommending for anyone who wants to learn more about the current state of generative AI.

Note: You’ll need to use the Microsoft Edge Browser and login to a Microsoft account to get the most out of the Bing Chat feature.

Mike Huckabee spoke this morning at Chautauqua as part of the weekly theme of “Infrastructure: Building and Maintaining the Physical, Social and Civic Underpinnings of Society”.  Huckabee’s introduction portrayed him as much more accomplished than I had thought. The Institution has made a substantial effort to bring more conservative speakers to balance what some see as a progressive bias.

The reason for the invitation was the fact that he was known as the “highway governor,” when he led the campaign for a 1999 bond issue to rehabilitate the state’s system of crumbling interstate highways. The bond issue was funded by increasing the gas tax by 4-5 cents a gallon.

He’s a fairly engaging speaker–he was a preacher after all. But the substance of the lecture was pretty much what I expected–including a long rant on an imaginary town called Huckville, where everyone lived according to the Golden Rule, businesses functioned with no regulations and a mythical flat tax provided all the money the society could need.

The biggest collective sigh from the audience came when he said that that that the science on climate change has not been established. To prove his point, he claimed that in the 1970’s the world was preparing for a new ice-age, which never never happened. If the scientists were wrong then, why should we believe them now?

I asked Bing for a response. Is it true that in the 1970’s scientists predicted a period of global cooling ending with a new ice age?

Bing responded.

There is a common misconception that scientists in the 1970s widely predicted a new ice age was coming. However, this is not true. According to a review of the scientific literature from 1965 to 1979, only 7% of the papers suggested global cooling, while 44% suggested global warming and 49% had no explicit opinion 1. The majority of the papers that predicted cooling were based on the effects of aerosols or orbital forcing, which are natural factors that can temporarily lower the global temperature. However, these factors were outweighed by the effects of greenhouse gases, which cause long-term warming.

The idea of a new ice age was mostly propagated by the media, which often sensationalized or misinterpreted the scientific findings. For example, in 1974, Time magazine published an article titled “Another Ice Age?” that claimed “scientists have found new evidence that another ice age is on the way” 2. However, this article did not reflect the consensus of the scientific community at the time, and it was based on a few isolated studies that were later shown to be flawed or incomplete. In fact, Time magazine later corrected its mistake and published an article in 2006 titled “Be Worried. Be Very Worried.” that warned about the dangers of global warming 3.

Therefore, it is inaccurate to say that there was a period in the 1970s when scientists believed that we were entering a new ice age. The evidence for global warming was already stronger than the evidence for global cooling, and it has only become more conclusive since then.  

I could have done much deeper research on this subject using more traditional search, but it would have taken a while to produce the clear text that Bing and the LLM produced in about a minute. It was worth a minute to fact check, but not much more.

References

1. [https://globalwarmingbasics.org/2016/07/02/an-ice-age-was-predicted-in-the-1970s/](https://globalwarmingbasics.org/2016/07/02/an-ice-age-was-predicted-in-the-1970s/)
2. [https://scienceblogs.com/gregladen/2013/06/04/the-1970s-ice-age-myth-and-time-magazine-covers-by-david-kirtley](https://scienceblogs.com/gregladen/2013/06/04/the-1970s-ice-age-myth-and-time-magazine-covers-by-david-kirtley)
3. [https://content.time.com/time/covers/0,16641,20060403,00.html](https://content.time.com/time/covers/0,16641,20060403,00.html)

Chautauqua Themes

– Week One (June 24–July 1): **On Friendship**
– Week Two (July 1–8): **Games: A Celebration of Our Most Human Pastimes**
– Week Three (July 8–15): **Can the Center Hold? — A Question for Our Moment**
– Week Four (July 15–22): **The State of Believing**
– Week Five (July 22–29): **Infrastructure: Building and Maintaining the Physical, Social and Civic Underpinnings of Society**
– Week Six (July 29–August 5): **A Life of Literature**
– Week Seven (August 5–12): **The National Parks: How America’s ‘Best Idea’ is Meeting 21st-Century Challenges**
– Week Eight (August 12–19): **Freedom of Expression, Imagination, and the Resilience of Democracy**
– Week Nine (August 19–27): **The Global South: Expanding the Scope of Geopolitical Understanding**

css.php