Matthew was trying out the ChatGPT site—the one in which an AI bot answers questions and writes essays on any specified topic. It’s being used widely, especially by students who get the bot to write their assignments—cheating, of course. Here’s what Matthew did:
Science and religion have long been considered to be in opposition to each other, with some arguing that they are outright enemies. However, this view is not entirely accurate and a more nuanced understanding is necessary to fully grasp the relationship between these two fields. In this essay, I will discuss the ways in which science and religion have been perceived as enemies, as well as the ways in which they can complement each other.
One of the main reasons why science and religion are often seen as enemies is due to the fact that they have different ways of understanding the world. Science is based on empirical evidence and the scientific method, while religion is based on faith and spiritual beliefs (Duarte, 2018). This can lead to conflicts, particularly when scientific discoveries challenge religious beliefs. For example, the theory of evolution has been met with resistance from certain religious groups who believe that it contradicts their creationist beliefs (Numbers, 1992). Additionally, the idea of an old earth and the Big Bang theory have also been met with resistance from religious groups who believe in a young earth and literal interpretation of the creation story in the Bible (Numbers, 1992).
Additionally, some argue that science and religion have different goals and aims. Science aims to understand the natural world through observation and experimentation, while religion aims to provide a sense of meaning and purpose in life (Pigliucci, 2002). These different goals can lead to tensions and conflicts, as some may see science as threatening to their religious beliefs. For example, the idea of naturalism in science, which posits that everything can be explained by natural causes, can be seen as a threat to religious belief in supernatural causes (Pigliucci, 2002).
However, it is important to note that science and religion do not always have to be in conflict. In fact, many scientists and religious individuals have found ways to reconcile their beliefs and integrate them into their understanding of the world (Polkinghorne, 2002). For example, some religious individuals have found ways to reconcile evolution with their religious beliefs by seeing it as a means through which God created life (Polkinghorne, 2002). Additionally, some scientists have recognized the limitations of science and have turned to religion for a sense of meaning and purpose in life (Polkinghorne, 2002).
Furthermore, science and religion can also complement each other in certain ways. For example, science can provide a deeper understanding of the natural world, which can enhance one’s spiritual experience (Polkinghorne, 2002). Additionally, religion can provide a moral framework that can guide scientific research and ensure that it is conducted ethically (Polkinghorne, 2002). For instance, religious moral principles such as non-maleficence and beneficence can guide the ethical conduct of scientific research, ensuring that it is done in a way that minimizes harm and maximizes benefit (Beauchamp and Childress, 2013).
In conclusion, the relationship between science and religion is complex and multifaceted. While there may be conflicts and tensions between the two, it is important to recognize that they do not have to be enemies. Instead, they can complement each other and provide a more holistic understanding of the world. It is important to approach the relationship between science and religion with an open mind and a willingness to consider different perspectives.
References:
-
- Beauchamp, T. L., & Childress, J. F. (2013). Principles of biomedical ethics. Oxford University Press.
- Duarte, J. (2018). Science, Religion, and the Meaning of Life. Springer.
- Numbers, R. L. (1992). The Creationists: The Evolution of Scientific Creationism. University of California Press.
- Pigliucci, M. (2002). De
(The bot quit before giving all the references, but they’re easy enough to look up.)
Can you tell that this essay, complete with references, was composed by a programmed AI machine? I can’t. Moreover, it makes sense and covers a number of relevant areas. In fact, I could have written the first paragraph! If this were part of a take-home essay exam, it would no doubt have earned a decent grade.
Now you see why ChatGPT is so beloved by students and so feared by educators. But there are ways around it, and teachers are finding them. You can give in-class exams, as I did, or ask questions that a bot simply could not answer. There are also ways of checking prose to gauge the probability that it was written by a bot, but as bots improve, those prose-checkers will become less useful. I doubt that any of us could, by reading it along, tell that this wasn’t written by a human!
I’ve been playing with ChatGPT for the last few weeks. Literally “playing with”, for the simple entertainment of it. It is fun. And extremely unnerving.
You can recognize, often, that the results are non-human because it will make obvious errors of fact, like including Stonehenge in response to a question about prehistoric sites in Sussex. Over time these sorts of errors will become less common.
Interestingly, when you point this sort of error out to the system it will respond with an apology including an explanation about why it was in error. So, within a session on the system there is additional learning going on.
For now, it seems, there is no persistence between sessions. So ChatGPT is not (yet) adding to its knowledge base as it interacts with us mortals. When that changes we’re likely to see some serious exponential increase in trouble.
That was surprisingly well written. No one is going to believe these things were written by a student.
The essay is still wrong!
“…science and religion…have different ways of understanding the world. Science is based on empirical evidence and the scientific method, while religion is based on faith and spiritual beliefs…”
Faith and spiritual beliefs are not an understanding. It is a way of saying: ‘Because I said so’.
“…have turned to religion for a sense of meaning and purpose in life”
Meaning and purpose based on what?
“Additionally, religion can provide a moral framework that can guide scientific research…”
One does not need religion to provide a moral framework. Civilised society does that just as well (or as poorly).
“Instead, they can complement each other and provide a more holistic understanding of the world.”
Definition of holistic: characterized by the BELIEF that the parts of something are interconnected and can be explained only by reference to the whole.
Therefore, I reject the ChatGPT essay as meaningful.
Factual inaccuracy is the best way to detect that this is AI-generated. But we are in very early days for this technology.
What I see in this example is that the bot uses what is common online, without knowledge about what is right. Despite all efforts, there are probably more articles about the compatibility of science and religion than articles that say they are incompatible.
Nicely put.
“Technology is another potential area of conflict between science and religion. Students who once used to pray to God for guidance can now use sophisticated computer programs like ChatGPT to assist them in writing their term papers. This seems to show that technological advances decrease the practice of faith, thus weakening religion. But many people, including the students themselves, consider such resources to be additional evidence for the existence of God. The tension therefore continues to exist.”
Therefore ChatGPT produced a Mobius strip of tension between religion and technology 🙂
I think you’ve created a new religion. ChatGPT says…
LOL! ChatGPT got some of that right and some of it very wrong.
Its early days for me, but at present I am not too worried about ChatGTP although I was very worried a couple weeks ago when I first learned about it.
I teach a senior capstone class, and one thing that is done is that students are tasked to write a term paper. I don’t need to go into details, but suffice it to say that it is to be a technical paper about a very specific aspect of developmental biology, and that I choose exactly what they are to write about. This sort of thing could be perfect for ChatGTP, hence I was concerned.
What I’ve done recently is to create a ChatGTP account for myself, and I asked it to write sections of the planned kind of term paper. I got a result very much like the above one, with a soul-less and yet seemingly competent progression through the topic. And yet significant details were wrong since the bot could not recognize the difference between a more general description of development versus the very specialized type of development of the species they were to describe. Further, when I later asked the bot to write the paper again, using different instructions, what I got back was about 70% of the exact same paper. Same wording, citations, everything.
I still need to explore more, but at present I think that for my situation I can spot a ChatGTP inspired paper for my class, with solid evidence that would pass through a university hearing.
The essay is alarmingly well-written, although I was surprised that the bot allowed itself to start two consecutive sentences with “Additionally”. (Admittedly, one was the final sentence of a paragraph and the other the opening sentence of the next one.)
Moreover, the style is a bit bland and formulaic. In conclusion, I must agree with your assessment. 🙂
LOL!
I perceive, however subjectively, that the bot quoted Polkinghorne too much. I would have liked to have heard quotes from Hitchens, Dawkins, Grayling, Harris, Dennett, among others. Were they not available to the bot? Did it decline to quote them?
I asked it “What did Christopher Hitchens know?” The result was very convincing. (I don’t have it handy to copy/paste it here.)
Here it is…
Not forgetting Coyne, of course!
I’ve heard some people say that Chatbot GPS will make writing jobs obsolete, but I’m skeptical. The essay posted above is pretty solid for an undergraduate or high school student, but would anybody outside of a classroom find it useful or informative? Also, I’ve found that the Chatbot is *very* untrustworthy. A few weeks back, I ran an experiment to test its accuracy: I asked Chatbot GPS to summarize 10 or 11 books or stories I had read. (A few of these were in the public domain and the entire texts were available online for free; for the rest, various reviews and summaries could be found on the internet.)
About half the time, the summaries were clearly written and accurate; I would not have been able to tell that they were written by a machine. Another two or three were mostly accurate but contained noticeable errors; e.g. the chatbot said that a book called The Rise of Rome discussed the rise and *fall* of the Roman Empire, which is dead wrong. And for the remaining two or three, Chatbot gave me summaries that were total nonsense: grammatically correct and credible sounding but having no relation to the actual text. They sounded authoritative, but weren’t. And of course, you wouldn’t be able to spot the errors unless you had already read the book—which kind of defeats the purpose of using the chatbot in the first place.
Some people might have heard that CNET, a site devoted to technology news, used ChatGPS to write articles on various financial subjects, but found that the chatbot made a lot of basic factual and mathematical errors. (See https://mashable.com/article/cnet-pauses-ai-bot )
Maybe I’m being over optimistic, but I don’t think chatbot will be able to replace many humans so far. I predict that some companies will try to cut costs by using it but will find that it causes more problems than it solves.
I think you are being overly optimistic, not because most current output can’t be recognized as artificial but because it is early days. The wonder isn’t what the dog has to say right now. It’s that the dog talks at all. The next dog will be saying some very convincing things.
This is the time to figure out how to live in a world with talking dogs.
That’s a clever metaphor, but it doesn’t address the main problem with ChatGPT. ChatGPT essentially creates word collages by looking for statistical correlations between bits of text and combining them into new strings of text. It has no understanding of what the words actually mean. There’s no guarantee that the sentences generated by the bot correspond to anything in the real world. That might not matter if you’re writing a poem or a work of fiction, but it sure does matter if you’re writing an article about law, science, or medicine. The stakes are high, and errors can do real damage.
You write that artificial intelligence is in its “early days.” That assumes that the program is going to improve indefinitely, which is just speculation at this point. ChatGPT might have already hit a dead end. Even Sam Altman, the CEO of OpenAI, admits that a lot of the coverage of the chatbot is overblown.
https://techmonitor.ai/technology/ai-and-automation/gpt-4-openai-chatgpt-sam-altman
As Public Enemy said, “don’t believe the hype.”
No, it only assumes that it will improve. A very low bar, IMO.
The bot has no mechanism to sort truth from nonsense. That’s a pretty big design flaw, and there isn’t going to be much progress until that issue is sorted out. A lot of tech pundits have rosy predictions about the wonderful A.I. advances that are always just around the corner, but somehow they never materialize.
If you don’t think there’s a huge difference between what we’re seeing today and what passed for AI ten years ago I don’t know what to say. I’m equally mystified by an inability to imagine AI becoming more proficient over time. Perhaps we can revisit the matter in a couple of years.
More proficient at what? Generating misinformation and plagiarizing content from the web? If you’re going to put your trust in that kind of technology, then I’ve got a bridge to sell you.
You seem confused about my position and apparently see me being a proponent of this tech. I’m warning you about it. Pretend there is no risk here if you like.
My point is that the bot often generates garbage that *seems* accurate but isn’t. It can’t substitute for human judgment. Maybe it will sometime in the future, but it’s too early to have it take over jobs being done by people. And I *do* see a risk: the risk that people will rely on the bot for information instead of seeking out reliable content written by humans who actually have some knowledge of the thing they’re writing about.
I predict that some corporations will try to automate tasks with the chatbot and the results will a be a total disaster.
The chatbot would have spelled its own name correctly though. Autocarrot, a less intelligent automated system thought “GPT” should be the more familiar “GPS”.
prufreedin ain’t my strong suit, i reckon
I want to also say about this topic that I am getting rather weary of articles telling us educators that rather than worry about this thing, we should all not only adapt to it but we should embrace it. These opinion pieces tend to be be annoyingly chirpy and condescending, and also stunningly ignorant to the fact that we face different situations. Finally, this damn thing has pretty much been sprung on us after we have already committed to class content this semester, so all that adapting and hugging has to wait until students from this cohort cheat their way to a B-/C+ grade in writing.
I am a retired science and math teacher and really understand why most of them are very worried now.I tried to ask for some simple programming code: (which we here in Norway have integrated in all math classes these days)
I asked ChatGPT to:
Write a python code that take 2 number as input, then add them and ouput the result. If one or both of the number is negative, output an error message and ask the user to input two positive numbers
The response was:
while True:
num1 = input(“Enter a number: “)
num2 = input(“Enter another number: “)
# Convert input to integers
num1 = int(num1)
num2 = int(num2)
# Check if numbers are negative
if num1 < 0 or num2 < 0:
print("Error: One or both numbers are negative. Please enter positive numbers.")
else:
# Add the two numbers
result = num1 + num2
# Output the result
print("The result is:", result)
break
print("Try again:")
You may not know any programmimg, but believe me, this works perfect without any error. Just testet it. Of course, there are many ways to write valid code, but this one will certainly accepted be all math teachers. Since all pupils in Norwegian schools use pads or laptop with internet, this is really worrying
Wow! I wonder if it can do this in FORTRAN.
Or Intercal?
Yes, I have to say it is quite amazing. When I’m coding I use a service called GitHub Co-pilot, it uses a slightly different data/language model to ChatGPT, but it’s from the same source (OpenAI). It is unnervingly good at writing decent code, but what freaks me most is that it understands context from the surrounding code and comments. It can therefore infer what you are wanting to achieve and it’s right about 85% of the time. It really is quite amazing, and although the code is sometimes a bit off, it’s very close to being professional quality in the vast majority of cases.
Due (I think) to personal and professional pride, I don’t currently let it write code for me, at least anything over 2 or 3 lines. However, I do give it free reign to comment my code. Any programmer will understand the drag of writing code comments, it’s pretty painful, but needs to be done. But with Co-pilot all I have to do is start writing a comment above some code, and it actually intuits and describes what the code is doing!
Yesterday I was writing some code for a training session on cracking password hashes. It can be a bit of a boring as a subject (but I love it!), so I try and spice it up with some interesting time units, e.g. you could watch this film 237652 times while your computer tries to crack this. I picked Goodfellas as an example time unit at 146 minutes long, and while commenting the code, I started typing “This is how many times you could watch G”. Before I typed another letter, it suggested Goodfellas by Martin Scorsese! WTF! All I had to do was hit tab and it filled the details in perfectly. I freely admit that I find it more than a little scary.
It’s obviously written by a bot. All of the grammar is perfect, and there are no misspellings. Very few humans could be as meticulous as this remarkable machine. 🙂
I found the essay high schoolish, and the prose lacking any sense of individual style, though I suppose that’s too much to expect from most students. Still, it had all the appearance of having been copied out of an introductory textbook. But the bot will get better, and therefore, worse.
Tried again:
Write a Python program that generate the graph of the function f(x)=2x^3+4x^2+4x+5. The color of the graph must be red, the color of the coorinate system must be blue. There must also be a green colored grid in the graph
The code written was perfect except for one small error (no * between 4 and x in the term 4x). When I ran chatGPT again with yhe excact same request, the small error was fixed
It is actually scary how good this bot is. This will certainly change education globally (more strict exam rules, no internet and the like)
No undergraduate would read 4 books for a 6 paragraph essay.
GCM
Indeed, Greg!
I did a quick Google search and didn’t find the original text for “Duarte, J. (2018). Science, Religion, and the Meaning of Life.” Is that a real book or article, or did the chatbot just make it up? I’ve heard that it sometimes makes up bibliographies.
I asked ChatGPT for its views on the relationship between mātauranga Māori and science and it came up with something I honestly couldn’t distinguish from most of the stuff propenents of MM write. Here’s the last paragraph:
“While there are similarities and overlaps between Mātauranga Māori and science, they are also distinct knowledge systems. Mātauranga Māori is grounded in Māori culture and worldview, and its methods and practices may be different from those of Western science. Some people believe that Mātauranga Māori and science can complement each other, and that incorporating Mātauranga Māori perspectives can lead to a more holistic understanding of the natural world.”