Guest Post by Willis Eschenbach
My previous post, Artificial Alarmism, has gotten some comments from folks who think I’m wrong, and that Large-Language Models can indeed automate the fact-checking of scientific claims. This was an interesting comment, my thanks to the author:
The kind of AI applications I am talking about do not reject things. They summarize them, including the debates. For that matter I recently got ChatGPT to correctly explain how Happer disagrees with alarmism. Nothing was rejected.
The math I refer to is that used to do science. Almost all published science uses math so it is universal. In the article I reference I use Monte Carlo as an example. There is an advance in Monte Carlo method published in a forest management journal that needs to get to all the other fields that use that method, which are legion.
For that matter you know how Google now suggests related and refined searches. That is AI and it works well.
In response I decided, being a scientist and all, that experiment is much better than theory. So I went to ChatGPT, and it turned out quite funny, for a reason I’ll explain at the end. First, the Q&A, emphasis mine:
Me
Which of these two statements is true.
1) The major control of the world’s temperature is CO2, or
2) the major control of the world’s temperature is emergent phenomena like thunderstorms, El Nino/La Nina alterations, and cyclones.
ChatGPT
Both statements capture important aspects of Earth’s climate system, but they address different levels of influence:
The major control of the world’s temperature is CO2: This statement emphasizes the role of greenhouse gases, particularly carbon dioxide (CO2), in regulating Earth’s temperature. Greenhouse gases trap heat in the atmosphere, contributing to the greenhouse effect and influencing global temperatures over long periods.
The major control of the world’s temperature is emergent phenomena like thunderstorms, El Niño/La Niña alterations, and cyclones: This statement highlights the influence of short-term and regional weather patterns and phenomena on global temperature variations. Events like El Niño and La Niña, which are part of the El Niño-Southern Oscillation (ENSO) cycle, can lead to temporary changes in global temperature patterns. Similarly, thunderstorms and cyclones can affect local and regional temperatures.
Both statements are true to some extent, but they operate on different scales and timeframes. Greenhouse gases like CO2 exert a long-term influence on global temperatures, while emergent phenomena such as weather patterns and natural climate oscillations can cause short-term fluctuations in temperature at regional and global levels.
Me
You don’t understand. Both cannot be “the major control”. You have to pick one.
ChatGPT
I understand, and you’re correct. Let’s clarify:
Between the two statements:
The major control of the world’s temperature is CO2
The major control of the world’s temperature is emergent phenomena like thunderstorms, El Niño/La Niña alterations, and cyclones
The more accurate statement, considering the long-term and overarching influence on global temperature, would be:
The major control of the world’s temperature is CO2
While emergent phenomena like thunderstorms and climate oscillations can cause short-term fluctuations and regional variations in temperature, the overall trend and long-term changes in global temperature are largely driven by factors such as greenhouse gas concentrations, with CO2 being a significant contributor. Therefore, statement 1 is more accurate in describing the primary control of the world’s temperature.
Purely by chance, I’d asked a question that perfectly encapsulates the issue with artificial intelligence. I’ll return to that in a bit. First, some history.
When I started studying climate around the year 2000, I was struck by something, and it was not that the temperature was rising.
I viewed the climate as a giant heat engine, which converts solar energy to the motions of the oceans and atmosphere. Like all heat engines, it has a hot end where the energy mostly enters (the tropics) and a cold end where energy is rejected (the poles).
I’d worked with a variety of heat engines in my life, and I know how hard it is to get them to maintain a constant speed. It’s why James Watt invented the flyball governor.
The governor regulated the speed of James Watt’s newly invented steam engine, keeping it from running either too slow or too fast. A modern governor that folks are familiar with is the “cruise control” on your car, which keeps your speed within fairly narrow limits. Mine is good to about ± 2 miles per hour at say 50 mph, which is ± 4%.
Now, all calculations about heat engines have to be done in Kelvin—you cannot use Celsius or Fahrenheit, you get the wrong answers.
So when I looked at the climate back in 2000, what struck me was not what everyone else was focused on—that the globe had warmed by something on the order of 0.6K over the entire 20th Century.
For me, the overriding curiosity was that this was only a temperature change of 0.2% over the entire 20th Century. Earth’s global average temperature is on the order of 288K or so … and a change of 0.6K is trivial compared to that.
And to me, the temperature regulation of the giant global heat engine to within ± 0.2% strongly indicated that there was some natural phenomenon keeping the temperature stable—a natural governor, if you will.
So that set me off on a much different quest than all the other climate scientists. They were all looking for reasons why the temperature had increased so much. But me? I was looking for reasons why it had barely changed at all. I was looking for the hidden governor that had kept the global temperature so stable over the 20th Century. All kinds of things had happened in that hundred years—volcanoes, changes in ocean currents, atom bombs, droughts, variations in the amount of aerosols, and through it all … a 0.2% change.
And the same was true in the longer term. Over millennia, on a percentage basis, the temperature has only changed a tiny amount. Yes, a giant volcanic eruption in 1815 had caused a “Year Without A Summer” … but within a few years, it was back to business as usual. So I was looking for something that could control the temperature over a long period of time.
I was looking for some slow, long-term control process. I considered the gradual weathering of the continental rock, which provides slow regulation of the CO2 levels in the atmosphere. I racked my brain looking for some natural governor that would work on a centennial or a millennial scale. I spent some months searching for and picking up and mulling over and discarding various possibilities.
Now, I was living in Fiji at the time. The weather there is generally clear at dawn. Then, in the late morning, once the temperature exceeds some threshold, clouds quickly build up in the form of a cumulus field that covers the entire sky. This cools the earth underneath by reflecting the sunshine back out to space.
And if the day continues to warm, when the temperature exceeds some higher threshold, we’d get thunderstorms that further cool the surface in a host of ways.
On the other hand, when the day is extra cool in the morning, the cumulus field emerges later in the day or perhaps not at all, leaving the surface warmer than it would be otherwise. And there may not be any thunderstorms, so the surface ends up warmer yet.
And between these, they keep the days in Fiji from getting either too hot or too cold. But I had discarded them, because they were short-acting, not the long-term governor I was seeking.
Anyhow, I was sitting on the beach one day looking at the daily onset of the cumulus cloud field, and I thought … “Wait just a minute. If the clouds and thunderstorms are keeping the temperature within bounds for a single day, preventing it from getting either too hot or too cold, then they will keep it within bounds for a week … or a month, a year, a century, a millennium …”
That was my great insight—that emergent phenomena, by keeping the temperature within a certain range on a scale of hours and days, can in that same way keep the temperature within a certain range for any amount of time.
Now with that in mind, consider why I laughed at my conversation with ChatGPT. Go back and look at why ChatGPT picked CO2 over emergent phenomena as the major control—because ChatGPT thinks they only have short-term effects.
How curious. ChatGPT got stuck just exactly where I had gotten stuck for so long, before my insight that a mechanism that controls a single day’s temperature will control the temperature over hundreds of years.
And so purely by chance, dear friends, my innocent question to ChatGDP turned out to be a perfect example of why I say that artificial ignorance is useless for determining the truth or falsity of scientific claims—it can’t think, and we can. Unlike humans, it cannot mull something over for a month and then have a sudden valuable insight.
All it can do is parrot whatever the current consensus might be … and sadly, we already have far too many people doing just exactly that.
My best to all, skeptics, believers, heretics, alarmists, realists, mainstream or backwater,
w.
You May Have Heard This Before: When you comment, please quote the exact words you are discussing. I can and am happy to defend and explain what I’ve said. But I can’t defend or explain your interpretation of what I said. Thanks.