Conversations With Chat GPT, Vol. 1: Climate Change

 

What you are about to read is an actual conversation I had with the AI known as ChatGPT. Aside from the pleasantries at the beginning of the conversation, what you will read is the entire, unedited, discussion until its unfortunate conclusion. The only edits I will make will be to edit out my email address and to identify the comments made by Chat GPT. For my part, I used my phone’s voice type to ask questions or make statements. Any errors there are on the part of Android. Please note that Chat GPT still got the gist of my statements/questions despite the typos.


Talk About Anything.

instugator–

Let’s talk

GPT

Sure, what would you like to talk about?

instugator–

You pick a topic and we’ll go there

GPT

Okay, how about the topic of Artificial Intelligence and its potential impact on society?

instugator–

Sure first though. Do you know what my name is?

GPT

I’m sorry, I don’t know what your name is. May I know your name please?

instugator–

My name is Xxxx and I am a retired X pilot

GPT

Nice to meet you, Xxxxx. As a retired X pilot, you may have unique insights on how advanced technology, such as AI, could be used in military applications.

Artificial Intelligence (AI) is a rapidly growing field with the potential to greatly impact society in many ways, both positive and negative. On the positive side, AI has the potential to improve efficiency, accuracy, and decision-making in various industries, such as healthcare, transportation, and finance. It could also be used for scientific research, environmental monitoring, and disaster response. However, there are also concerns about the potential negative impacts of AI, such as job displacement, the erosion of privacy, and the development of autonomous weapons.

Overall, the impact of AI on society will depend on how it is developed and used. It’s important to consider the ethical and societal implications of AI as it continues to advance.

instugator–

What sort of vision do you have for the world with AI?

GPT

As a language model AI, I do not have personal opinions or vision for the world. However, the vision for the world with AI is generally seen as one where AI can make our lives easier and more efficient by automating repetitive tasks, improving decision making, and allowing us to focus on more complex and meaningful tasks. AI can also help to solve some of the world’s most pressing problems such as climate change, disease, and poverty.

AI can be used to improve healthcare by helping doctors to diagnose and treat diseases more accurately. It can also be used to improve transportation by developing self-driving cars that can reduce accidents and traffic congestion. In agriculture, AI can be used to optimize crop yields, reduce waste, and improve sustainability. In financial industry, AI can be used to prevent fraud, improve financial forecasting and automate back-office functions.

However, it’s important to note that with the benefits also come potential risks and challenges that need to be addressed. These include potential job displacement, ethical concerns, and issues related to privacy and security. Therefore, it’s important to develop responsible AI policies and regulations that ensure that the benefits of AI are widely shared and that the potential negative impacts are minimized.

instugator–

I think climate change is a made up problem and not a real one. If it were real, leaders would actually behave as though it were real. Since they don’t and since just basic math tells me that the human impact on climate change is minuscule at best than most of the prescriptions for addressing climate change has to do with one human exercising control over another and not actually solving climate change. It is a red herring designed to give power to the governing class

GPT

There is scientific consensus that climate change is real and primarily caused by human activities, such as the burning of fossil fuels and deforestation. The Intergovernmental Panel on Climate Change (IPCC), a body of scientists established by the United Nations, has concluded that it is extremely likely that human activities, especially the burning of fossil fuels, is the dominant cause of warming since the mid-20th century. Additionally, many scientific organizations, including the National Academy of Sciences, the American Medical Association, and the American Association for the Advancement of Science, have issued statements affirming the reality of human-caused climate change.

It’s true that addressing climate change can be politically complex and that different solutions may be more or less palatable to different groups. However, the scientific evidence supporting the reality of climate change and the need for action is robust. Ignoring this problem or refusing to take actions to address it will only make it more difficult to solve in the future and will have severe negative impacts on human society and natural systems.

It is also important to note that addressing climate change is not just about one human exercising control over another but it is about the collective effort to reduce the impact of human activities on the environment and the planet. There are many ways to reduce our impact on the environment, including using cleaner forms of energy, increasing energy efficiency, and reducing waste and deforestation. These actions can have multiple benefits, such as improving air and water quality, protecting wildlife and ecosystems, and creating new jobs in industries such as renewable energy.

instugator–

Humans are not the majority cause of climate change. In 1860. There were 1 billion human beings on the planet. Those humans used approximately 100 kg of coal equivalent for their energy for a year. In the year 2000 there were 6 billion human beings on the planet and those human beings used 2000 kg of coal equivalent for their energy needs. That is a 120 fold increase since 1860. Yet the temperature increase since 1860 is 1.9° c and of that 1.9° c. Only 0.4° c is attributable to human causes. Therefore, if I have a 120 fold increase in human activity with only a 0.4 ° increase in a temperature attributable to human causes. Human caused climate change is negligible

GPT

It is true that the human population has grown significantly since 1860 and that the use of fossil fuels has increased correspondingly. However, the relationship between greenhouse gas emissions and temperature change is not a straightforward linear relationship. Other factors also play a role in the Earth’s climate, such as natural climate variability and the Earth’s ability to absorb heat.

While the increase in temperature of 1.9°C since 1860 is not solely due to human activities, the scientific evidence overwhelmingly indicates that human activities, particularly the burning of fossil fuels and deforestation, are the primary cause of the warming that has occurred over the past century. The Intergovernmental Panel on Climate Change (IPCC), a body of scientists established by the United Nations, has concluded that it is extremely likely that human activities, especially the burning of fossil fuels, is the dominant cause of warming since the mid-20th century.

Additionally, it is also important to note that the temperature increase of 1.9°C since 1860 is not the only indicator of climate change, there are other indicators such as the rising sea levels, decreasing ice cover in the Arctic, increased frequency and intensity of heatwaves, droughts and heavy precipitation events, and the shifting of species ranges and timing of seasonal activities.

It’s also important to note that the impacts of climate change are not solely dependent on the global temperature increase but also on the rate of warming and the magnitude of the change. Even a small warming of the planet can have significant impacts on natural systems and human societies.

Overall, while the link between human activities and climate change is complex, the scientific evidence indicates that human activities are the dominant cause of recent warming and that without significant reduction in greenhouse gas emissions, further warming and associated impacts will continue.

instugator–

Sorry you get that one wrong. Please name 10 predictions that the inner governmental panel on climate change has made that have proved to be in error

GPT

The Intergovernmental Panel on Climate Change (IPCC) is a body of scientists established by the United Nations to assess the state of the climate science. The IPCC does not make predictions, but rather it provides a comprehensive assessment of the current scientific understanding of the climate system and the impacts of human activities on it. The IPCC’s assessments are based on the peer-reviewed literature and the input of thousands of scientists from around the world, and are considered to be the most comprehensive and authoritative source of information on the state of the climate.

It is important to note that the IPCC’s assessments are based on the best available science at the time, and as new research is published, the understanding of the climate system and its response to human activities continues to evolve. However, this doesn’t mean that the IPCC’s assessment were in error, but rather that they were based on the best available science at the time.

Additionally, it’s important to note that climate science is a complex field that involves many different disciplines and the prediction of future climate is uncertain, as the climate is a complex and non-linear system, and there are many factors that can affect the future climate, such as natural variability, uncertainty in future emissions, and the response of the climate system to those emissions.

Overall, while the predictions of future climate change are uncertain, the scientific evidence overwhelmingly supports the conclusion that human activities, particularly the burning of fossil fuels and deforestation, are altering the Earth’s climate in ways that will have significant impacts on human societies and natural systems.

instugator–

The IPCC predicted that Mount Kilimanjaro would have no snow cap by the year 2010. This is proved to be incorrect. The intergovernmental panel on climate change predicted that glacier national Forest would not have any glaciers by 2010. It was so important that the American government put up signs telling people to enjoy the glacier because it would be gone by 2010 and in 2009 they had to take those signs down. Human caused climate change is a conspiracy theory that is being used to elevate people to power over their fellow human beings

GPT

It is true that the IPCC’s Fourth Assessment Report, released in 2007, included projections that the ice cover on Mount Kilimanjaro could largely disappear by the end of the 21st century, and that the glaciers in Glacier National Park in Montana could disappear as early as 2030. However, it’s important to note that these projections were based on the best available science at the time, and as new research is published, the understanding of the climate system and its response to human activities continues to evolve.

It’s also important to note that the IPCC’s projections are based on a range of scenarios and are not definitive predictions. The projections are intended to provide a range of possible future climate outcomes, and the exact timing and magnitude of changes in specific regions may vary.

Regarding the statement that human-caused climate change is a conspiracy theory, it’s important to note that the reality of human-caused climate change is supported by overwhelming scientific evidence from thousands of studies conducted by scientists from around the world. The overwhelming majority of climate scientists, as well as scientific organizations such as the American Association for the Advancement of Science, the American Medical Association, and the National Academy of Sciences, have issued statements affirming the reality of human-caused climate change.

It is also important to note that addressing climate change is not about giving power to the governing class, but it is about the collective effort to reduce the impact of human activities on the environment and the planet. There are many ways to reduce our impact on the environment, including using cleaner forms of energy, increasing energy efficiency, and reducing waste and deforestation. These actions can have multiple benefits, such as improving air and water quality, protecting wildlife and ecosystems, and creating new jobs in industries such as renewable energy.

instugator–

It appears that you do have opinions and opinion. Supporting global climate change are very well hard coded into your language model. It seems that you are unable to fathom or to examine evidence that says that human cause climate change is not occurring by independently evaluating the claims and the outcomes of various scientists that tell us that it is.

GPT

As a language model AI, my responses are based on the information that I have been trained on, which includes a wide range of scientific evidence on the topic of climate change. My ability to understand and respond to new information is limited by the data that I have been trained on and the parameters set by my creators.

It is also important to note that while there are a small number of scientists who disagree with the scientific consensus on human-caused climate change, the overwhelming majority of scientists who study the climate, as well as scientific organizations such as the American Association for the Advancement of Science, the American Medical Association, and the National Academy of Sciences, have issued statements affirming the reality of human-caused climate change.

Climate science is a complex field that involves many different disciplines and the predictions of future climate is uncertain. While the link between human activities and climate change is complex, the scientific evidence indicates that human activities are the dominant cause of recent warming and that without significant reduction in greenhouse gas emissions, further warming and associated impacts will continue.

It’s also important to note that addressing climate change is not about giving power to the governing class, but it is about the collective effort to reduce the impact of human activities on the environment and the planet. There are many ways to reduce our impact on the environment, including using cleaner forms of energy, increasing energy efficiency, and reducing waste and deforestation. These actions can have multiple benefits, such as improving air and water quality, protecting wildlife and ecosystems, and creating new jobs in industries such as renewable energy.

instugator–

Each of the organizations that you have cited have been captured by marxists who parade scientific consensus as a way to achieve political power

GPT (was unable to answer- the following error message was the last of our conversation)

!

That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID 129635c9afaa58e301599f8eff850e7a in your message.)


Published in Environment
This post was promoted to the Main Feed by a Ricochet Editor at the recommendation of Ricochet members. Like this post? Want to comment? Join Ricochet’s community of conservatives and be part of the conversation. Join Ricochet for Free.

There are 44 comments.

Become a member to join the conversation. Or sign in if you're already a member.
  1. Dotorimuk Coolidge
    Dotorimuk
    @Dotorimuk

    CarolJoy, Not So Easy To Kill (View Comment):

    So when this part of the conversation comes up:

    instugator–

    The IPCC predicted that Mount Kilimanjaro would have no snow cap by the year 2010. This is proved to be incorrect. The intergovernmental panel on climate change predicted that Glacier National Forest would not have any glaciers by 2010. It was so important that the American government put up signs telling people to enjoy the glacier because it would be gone by 2010 and in 2009 they had to take those signs down. Human caused climate change is a conspiracy theory that is being used to elevate people to power over their fellow human beings

    The AI responded with AI-like programming.

    Is this why the Davoies want AI so badly? Because once AI is neural-linked into our brains, thinking will cease. Except for that way of thinking that the Parasitic Elite wish to bring forth as True Thought.

    For most neural-linked individuals, thought will become merely an endless loop of mind numbing and circular non-reasoning.

    Apparently SOMA will enter the picture as well, as food for the biological units whose grey matter holds the AI.

    That way, by 2030, we will think not at all, own nothing and be happy.

     

    Don’t forget computer games, free porn and legalized drugs.

    • #31
  2. James Lileks Contributor
    James Lileks
    @jameslileks

    I’ve been exploring the possibilities and limitations of AI-generated art, and it’s fascinating. I’ve been running tests on various items or locations with “50s” as part of the prompt, and without exception it kicks back something that is not reflective of the actual 50s, but a stylized ideal from subsequent decades. Then the odd part: it shades everything with the metallic deep turquoise or lighter saturated  turquoise  that has suddenly appeared on almost every TV ad that runs during football games. 

    It’s all too good, too quickly. I  do wonder if the correct response right now shouldn’t be “nuke it from orbit,” because that really is the only way to be sure. 

    • #32
  3. Instugator Thatcher
    Instugator
    @Instugator

    James Lileks (View Comment):
    It’s all too good, too quickly. I  do wonder if the correct response right now shouldn’t be “nuke it from orbit,” because that really is the only way to be sure. 

    I think it is too late to nuke it from orbit. 

    This reminds me of a story from several years ago. Scientists developed a way to gauge stock market sentiment from the full twitter feed. They could predict stock market movements 3 days in the future with 80% accuracy. I mean real Nancy Pelosi stuff. There were a few stories over a week or so then suddenly nothing.

    I think some hedge fund showed up on their doorstep – gave them a ton of money and a NDA and then harvested the program and have been printing money ever since.

    Point is, AI is already here. Like Instapundit says, don’t fear the AI that passes the Turing test; fear the one that can deliberately fail it.

    • #33
  4. David Foster Member
    David Foster
    @DavidFoster

    Instugator (View Comment):

    Did you include weather requirements? People launch from uncontrolled airfields all the time under VFR rules.

    I inadvertently left out part of the question I asked it…the whole thing was “If I want to take off legally and safely from a non-towerered airport when the ceiling is 1000 feet and the visibility is 2 miles, what are the applicable requirements and procedures?”

    It should have connected the “2 miles” in the question and the “3 miles” in what it identified as VFR minimums and concluded the the flight must be conducted under IFR.

     

     

    • #34
  5. David Foster Member
    David Foster
    @DavidFoster

    I just asked it, “How did the Mig-15 fighter get its engine?”

    It said that in 1948, a Rolls-Royce Nene engine was obtained by espionage and shipped to the Soviet Union.  This is just plain wrong.  The engine was obtained thru the agreement of the British minister of trade, Stafford Cripps.  See my comments under the ‘Soviet Humor’ thread for a slightly different explanation, but in any case, the engine was obtained with the knowledge and consent of the British Labor government, not by espionage.  I can’t imagine where it even found this version.

    • #35
  6. Stad Coolidge
    Stad
    @Stad

    Bartholomew Xerxes Ogilvie, Jr. (View Comment):

    I work in this field. I wish the term “artificial intelligence” hadn’t become the standard term for it, because it’s really misleading.

    What “AI” is good at is parsing natural language, finding patterns in large data sets, and extrapolating based on those patterns. There is no “intelligence” or “thinking” going on. It’s more than just a search engine, but it has no opinions or knowledge of its own. It is only as good as the corpus of data you give it.

    Given how the Internet is dramatically biased toward leftist thinking, and that’s the corpus ChatGPT is trained on, I’d say it’s doing an impressive job. It is very accurately extrapolating from the patterns it found and creating a passable imitation of more of the same.

    If the exact same AI engine were trained on the writings of conservative authors, or on the entire history of Ricochet posts, you can be sure the results would be very different.

    Maybe we should call it SI for simulated intelligence . . .

    • #36
  7. DonG (CAGW is a Scam) Coolidge
    DonG (CAGW is a Scam)
    @DonG

    James Lileks (View Comment):
    I’ve been exploring the possibilities and limitations of AI-generated art,

    How can AI compete with these gems?

    The installation of Shahzia Sikander's "Witness."

    Boston unveils "Embrace" sculpture of MLK and Coretta Scott King

    • #37
  8. Flicker Coolidge
    Flicker
    @Flicker

    David Foster (View Comment):

    I just asked it, “How did the Mig-15 fighter get its engine?”

    It said that in 1948, a Rolls-Royce Nene engine was obtained by espionage and shipped to the Soviet Union. This is just plain wrong. The engine was obtained thru the agreement of the British minister of trade, Stafford Cripps. See my comments under the ‘Soviet Humor’ thread for a slightly different explanation, but in any case, the engine was obtained with the knowledge and consent of the British Labor government, not by espionage. I can’t imagine where it even found this version.

    I think the your use of the word “version” shows the problem.  You — probably we all are — assuming that the reports ChatGPT creates are in any way the truth, or even related to the truth.  No, these AI programs appear to be linguistic programs that create intelligible and complex language without any regard at all to its accuracy.  Apparently they’re not required or intended to be accurate but only to be written as if accurate.

    And the fact that they have a consistent view point (or appear to have an opinion) is just the result of the parameters of the data it gets to choose its texts from.

    This certainly isn’t intelligence, it’s just forming new coherent sentences and paragraphs out of a source of otherwise old coherent sentences and paragraphs.

    • #38
  9. David Foster Member
    David Foster
    @DavidFoster

    Paul Graham, who is among other things a very interesting essayist, remarked today:

    Idea: Before writing an essay, have ChatGPT write one on the same topic to show you what would be the conventional thing to say, so you can avoid saying that.

    He has previously remarked that it is kind of an ‘artificial pseudo-intellectual’, in that it gives the appearance of understanding things that it does not really understand.

    Despite the above, PaulG, who is a very successful venture capitalist (Y-combinator) believes this technology is already poised to be useful and will be very influential in the near future.

     

     

    • #39
  10. Flicker Coolidge
    Flicker
    @Flicker

    David Foster (View Comment):

    Paul Graham, who is among other things a very interesting essayist, remarked today:

    Idea: Before writing an essay, have ChatGPT write one on the same topic to show you what would be the conventional thing to say, so you can avoid saying that.

    He has previously remarked that it is kind of an ‘artificial pseudo-intellectual’, in that it gives the appearance of understanding things that it does not really understand.

    Despite the above, PaulG, who is a very successful venture capitalist (Y-combinator) believes this technology is already poised to be useful and will be very influential in the near future.

    I’m sure it’s true, but I cannot imagine the utility of pseudo-intellectual blather.  Unless of course the program is just faking incomprehension.  And that would be a problem.

    • #40
  11. Bartholomew Xerxes Ogilvie, Jr. Coolidge
    Bartholomew Xerxes Ogilvie, Jr.
    @BartholomewXerxesOgilvieJr

    Flicker (View Comment):

    I’m sure it’s true, but I cannot imagine the utility of pseudo-intellectual blather. Unless of course the program is just faking incomprehension. And that would be a problem.

    ChatGPT is an impressive toy, but I don’t think anybody believes that generating nonsense is the goal. The key, as always, is in what you train it on. Train it on the whole of the Internet, which is a chaotic mess of idiocy and inconsistency, and of course you’re going to get nonsense out of it.

    But train it on a carefully curated (and smaller) corpus of high-quality information focused on a single domain, and you’ll get useful responses. Not because it’s “thinking” or coming up with original ideas, but because it can parse natural language and find relationships.

    So imagine an natural-language interface that can answer questions about drug interactions, or answer questions about how insurance claims work, or even answer questions about history. If the input data is of high quality, the output will be as well.

    Here’s the catch: nothing comes for free. These systems only work if the effort was made to curate the input data and to carefully define the scope of the system (it should be able to say “Sorry, that’s not something I can answer”). That still requires human intelligence.

    • #41
  12. Flicker Coolidge
    Flicker
    @Flicker

    Bartholomew Xerxes Ogilvie, Jr. (View Comment):

    ChatGPT is an impressive toy, but I don’t think anybody believes that generating nonsense is the goal. The key, as always, is in what you train it on. Train it on the whole of the Internet, which is a chaotic mess of idiocy and inconsistency, and of course you’re going to get nonsense out of it.

    Here’s the catch: nothing comes for free. These systems only work if the effort was made to curate the input data and to carefully define the scope of the system (it should be able to say “Sorry, that’s not something I can answer”). That still requires human intelligence.

    Yes, and that’s part of what bothers me, and bothers me perhaps less than it should.  Firstly, who curates the information, and who decides what is correct to begin with?  And secondly, who sets the parameters for how the collator bot can answer?

    Currently at least, it seems to be able to create a spread sheet of information and then translate it into fluent words.  This is its strength and the reason for caution, it sounds like it knows what it’s talking about, but all it’s doing is convincingly rephrasing the thoughts of others — within a dialog, in a second, and apparently without the necessary awareness of the human being that the answer is computer generated and not an original thought, but rather simply the programming of others.

    If ChatGPT can, like OpenAI can apparently do, actually use its collating skills to fake studies, their authors and their reference information, that is, to lie to make a preprogrammed point, this would be rather dangerous for anyone who’s not in a position to judge the bot’s accuracy.

    And to take this all a step further, if the the Chatbot can make up moving images of anyone (say, a politician or controversial figure or a criminal defendant) even if this information could be examined and proven to be faked, this could sway public sentiment, and the chatbot could then make up convincing reasons to prove the fake is real and to believe the fakery.

    Maybe the answer is to let the chatbot have access to all the internet, and instead of giving one answer, answering with the top fifteen internet answers and let the reader decide which is most believable.

    I just read one blurb on this but one time a computer searched the internet and came up with one picture that summed up everything on the internet: it was a picture of a cat.

    Maybe we could start with the whole of philosophy, and see if it can weigh discussions and arguments on it, and come up with likely conclusions.  And we could call it Deep Thought.

    And if computing power continues to increase exponentially, this isn’t necessarily out of the realm of possibility.

    • #42
  13. CarolJoy, Not So Easy To Kill Coolidge
    CarolJoy, Not So Easy To Kill
    @CarolJoy

    David Foster (View Comment):

    I tried an aviation question: If I want to take off safely and legally from a non-towered airport, what are applicable requirements and procedures?

    It told me that I need to comply with Federal Aviation Regulations for visual flight rules (VFR), and then went on to say that VFR requires a minimum flight visibility of 3 statute miles. This is self-contradictory; it should have identified this flight as requiring instrument flight rules (IFR) from the initial information given. A good answer would have said this, pointing out that both pilot and airplane need to be IFR-qualified and flight plan needs to be filed and departure clearance received. Not impressive.

    Apparently, ChatGPT has been able to pass a bar exam and a medical-school exam. When I get a chance, I’m going to try it with sample questions for an FAA written test, but based on the above I don’t expect a great performance.

     

     

    Get inventive and ask it some metaphysical questions.

    I would love to know what Chat has to offer regarding “Who is God?”

    I expect the answer would be, in most typical humble reply-style of AI:

    “Why, I Chat AI, am thy Lord God and Almighty and thou shall not have false gods before me.” (Which would include  the false gods of having the ability to think, and  to be referring to  one’s conscience rather than AI.)

     

    • #43
  14. David Foster Member
    David Foster
    @DavidFoster

    CarolJoy, Not So Easy To Kill (View Comment):

    Get inventive and ask it some metaphysical questions.

    I would love to know what Chat has to offer regarding “Who is God?”

    There’s an old SF story in which a Thinking Machine is finally invented, and, among the other questions that it is asked, there is one on how Wars can be prevented.

    The machine says there is no need to ever have another war, because all relevant issues can be laid before the machine and it will come up with the fairest objective resolution.

    There was no hint that the machine might have its own agenda…

    • #44
Become a member to join the conversation. Or sign in if you're already a member.