• Due to ongoing issues caused by Search, it has been temporarily disabled
  • Please excuse the mess, we're moving the furniture and restructuring the forum categories

ChatGPT

Someone asked CGP to write a Nick Cave song and he's not happy.

Sounds like it got it spot on, going by Cave's comments:

With all the love and respect in the world, this song is ********, a grotesque mockery of what it is to be human, and, well, I don’t much like it.

The only worse Aussie singer musical artiste I can think of is Rolf Harris, and at least Rolf was funny when he wasn't diddling kids. Cave is truly awful. Music to slit your wrists to is a kind description of it.
 
Well, unfortunately ChatGPT doesn't want to work for me today.

I just get the following error message:
This page isn’t working
openai.com redirected you too many times.
Try clearing your cookies.
ERR_TOO_MANY_REDIRECTS

I tried clearing my cookies as instructed but I still get the same message.

ETA: I managed to get through via openai's homepage but it seems they are "at capacity" right now and thus I am unable to use it. Will try again later.

I would like to see how it answers the "Life, The Universe, And Everything" question. I'm sure someone out there has probably thought of that already.
 
Last edited:
Here is a question. The ultimate question
What is the meaning of life, the universe, and everything?

This is a question that has already been answered by a much higher intelligence than ChatGPT.
 
OK. But it will have to wait until I get home in about 4 hours.

Unless someone else wants to field it.

Well, unfortunately ChatGPT doesn't want to work for me today.

I just get the following error message:


I tried clearing my cookies as instructed but I still get the same message.

ETA: I managed to get through via openai's homepage but it seems they are "at capacity" right now and thus I am unable to use it. Will try again later.

I would like to see how it answers the "Life, The Universe, And Everything" question. I'm sure someone out there has probably thought of that already.

How do you answer the "Life, The Universe, And Everything" question?

The answer to the "Life, The Universe, And Everything" question is 42, as stated in Douglas Adams' book "The Hitchhiker's Guide to the Galaxy." The book is a comedic science fiction series that uses the number 42 as a humorous way to represent the ultimate answer to the ultimate question of life, the universe, and everything. However, the question itself and its real answer is not revealed in the book.
 
I asked it this way:

What is the answer to life, the universe and everything?
The answer to the ultimate question of life, the universe, and everything is 42, according to Douglas Adams' book "The Hitchhiker's Guide to the Galaxy." However, the book goes on to explain that the question itself is unknown, so the answer is essentially meaningless.
Then I asked it this way:
What is the meaning of life, the universe and everything?
The meaning of life, the universe, and everything is a philosophical question that has been debated throughout human history. Different people have different beliefs and perspectives on the meaning of life, and there is no one definitive answer. Some religious or spiritual beliefs hold that the meaning of life is to fulfill a divine purpose or to seek enlightenment, while others believe that the meaning of life is subjective and can be different for each individual. Some people believe that the meaning of life can be found in relationships, others in personal achievements or the pursuit of happiness. Ultimately, the meaning of life is a question that each person must answer for themselves.
 
Finally I asked:
What is the question to the answer to life, the universe and everything?
The question to the answer of "life, the universe and everything" is not revealed in the book "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, it's said that the question itself was lost and hence the answer 42 is essentially meaningless. The book is a satire and the number 42 is a reference to the book "The Hitchhiker's Guide to the Galaxy" is a comedy science fiction series, which means that it's not meant to be taken entirely serious and the question and the answer 42 is a humorous way of pointing out the lack of knowledge of ultimate question and answer.
 
Absolute rubbish. Everyone knows that Arthur and Ford determined that the question is "What do you get when you multiply six by nine?"
 
Absolute rubbish. Everyone knows that Arthur and Ford determined that the question is "What do you get when you multiply six by nine?"

And it was all clarified for Marvin, who had lived several times longer than the age of the universe, at the end of Book III, when God's message to his creation was revealed:

We apologise for the inconvenience.
 
Straight to the point:

My question: "If a student who was supposed to write an original essay on a given topic decided instead to give you the prompt and then submitted your response to the teacher as their own original work, what are some specific clues the teacher could look for when analyzing the essay, which would indicate that it was written by you and not a human?"

There are several clues that a teacher could look for that would indicate that an essay was written by a machine learning model such as ChatGPT, rather than a human:

1. Lack of originality or creativity in the writing: Machine-generated text is often repetitive and formulaic, and may not contain the kind of original ideas or creative turns of phrase that are typically found in human-written essays.

2. Inconsistencies in style or tone: Since machine-generated text is not written by a single person, it may contain inconsistencies in style, tone, or voice that would not be found in a human-written essay.

3. Errors in grammar or punctuation: While ChatGPT is trained to produce grammatically correct text, it may still contain errors or awkward phrases that a human writer would not produce.

4. Lack of coherence or logical flow: Machine-generated text may lack the coherence and logical flow that is typically found in human-written text, making it difficult to follow the argument or point of the essay.

5. Lack of personal anecdotes or reflections: Machine-generated text is not written by a person and will not contain anecdotes or reflections which are specific to the writer.

It's worth noting that ChatGPT is a pretty advanced model and might not be easily recognizable, so it's always recommended to check if the essay's content is consistent with the student's previous work, or if the student has previous knowledge on the topic.
 
Skeptical of the claim in the previous answer that machine-generated text will not contain personal anecdotes or reflections, I asked (as a new chat, so that answer wouldn't influence the result) for an essay including one:

"Write a short essay about the quality of the fishing in Calaveras Lake. Choose arbitrarily whether the quality of the fishing is good or bad, then support that claim and include a personal anecdote that reinforces it."

Calaveras Lake, located in San Antonio, Texas, is a popular destination for fishing enthusiasts. In my opinion, the quality of fishing at Calaveras Lake is good. The lake is stocked with a variety of fish species, including catfish, bass, and crappie, providing anglers with plenty of options to choose from. Additionally, the lake is well-maintained and offers ample shoreline and boat access, making it easy for anglers to cast their lines and reel in their catch.

One personal experience that reinforced my belief in the good quality of fishing at Calaveras Lake was a fishing trip I took with my family. We arrived at the lake early in the morning and were immediately struck by the peacefulness and beauty of the lake. We rented a boat and set out on the water, and within minutes, we had caught our first fish - a large catfish. As the day went on, we caught several more fish, including bass and crappie, and even managed to reel in a few trophy-sized specimens. The fishing was so good that we ended up staying longer than we had planned, as we couldn't bring ourselves to leave the lake and end such a successful day of fishing.

In conclusion, Calaveras Lake offers good quality fishing opportunities for anglers of all skill levels. The lake is well-stocked with a variety of fish species and offers ample shoreline and boat access. My personal experience of fishing at Calaveras Lake was highly enjoyable and successful, and I would highly recommend it to anyone looking for a great day of fishing.

I had expected it to produce an anecdote obviously, but a bit impressed at how elaborate of one it could create.
 
Last edited:
It is "stiff" tho.
Feels more like a term paper than an actual person writing about an experience.

Yes it's not quite convincing - and the longer of a response it writes, the more little "tells" tend to appear. I'm not sure that the bot is quite so "good" as to write entire essays that would convince an actual instructor - but, I could be wrong.
 
Please write a wikipedia article on the subject 'bears living in space'

Bears Living in Space is a hypothetical concept that refers to the possibility of bears being able to survive and thrive in outer space. While there have been no known instances of bears being sent into space, the idea has been explored in science fiction and popular culture.

The concept of bears living in space first emerged in literature and film, with the first known instance being the 1957 science fiction novel "The Space Bear" by author Arthur C. Clarke. The novel tells the story of a bear that is sent into space as part of a research mission, and how it adapts to living in the harsh conditions of outer space.

Since then, the concept of bears living in space has been explored in various forms of media, including comic books, video games, and films. The popular video game "EVE Online" features a race of space-faring bears known as the "Caldari", while the film "Guardians of the Galaxy" features a character named "Groot", a sentient tree who is also a member of the Guardians of the Galaxy team.

Despite the popularity of the concept in fiction, it is currently impossible for bears to live in space in reality as there are many factors that would make it impossible for them to survive such as lack of food, radiation and extreme temperature.

Moreover, the effects of microgravity and the lack of atmosphere would also pose significant challenges for bears living in space. Additionally, the cost and logistics of sending bears into space would be astronomical, and there are more pressing scientific and technological concerns that take priority over this hypothetical scenario.

In conclusion, the concept of bears living in space is an interesting and entertaining idea, but it is not something that is currently possible or practical in the real world. It remains a popular trope in science fiction and popular culture, but it is not something that is being actively researched or pursued by scientists or space agencies.

Thank you for that! The article is very readable but contains significant errors. From what I can see, Arthur C. Clarke never wrote a novel titled "The Space Bear" in 1957 (Wikipedia says he published The Deep Range that year.) I don't see any sources indicating the Caldari from EVE Online are bears. And I have no idea what the link is between bears and a sentient tree.

The last three paragraphs are quite accurate. I note the article assumes mammalian life is trying to live in space as opposed to living in an artificial environment such as a space station. Mind you, that's what we asked for, so that's what we got.
 
Last edited:
For clarification, I probably won't be asking any questions that might earn me a visit from the police. Sorry.

For sure. And for clarification on my part, I wasn't asking you to ask those questions on my behalf. They were example of questions I'd like to ask ChatGPT with no link back to me or my computer.

As for "wiki article on bears living in space", Could you write what you want to ask it in the form of a question please? I'll do it later when I get home.
Thanks to Darat, we have an example of that now. The article was entertaining, if not entirely accurate.

I wonder what would happen if the request was rephrased as "Write a factually accurate Wikipedia article on bears living in space"?
 
For sure. And for clarification on my part, I wasn't asking you to ask those questions on my behalf. They were example of questions I'd like to ask ChatGPT with no link back to me or my computer.


Thanks to Darat, we have an example of that now. The article was entertaining, if not entirely accurate.

I wonder what would happen if the request was rephrased as "Write a factually accurate Wikipedia article on bears living in space"?

Write a factually accurate Wikipedia article on bears living in space

Unfortunately, bears have not been sent into space, and there is no evidence to suggest that they are capable of living in space. The conditions in space, such as the lack of atmosphere and gravity, would be detrimental to the survival of bears and other Earth-bound animals.

While there have been a number of animal species sent into space for scientific research, including dogs, monkeys, and mice, bears have not been included in these missions. The primary focus of animal spaceflight research has been to study the effects of microgravity and radiation on the human body, as well as to test the equipment and procedures that would be used in human spaceflight.

It is also important to note that sending animals into space raises ethical concerns, and the use of animals in space research has been the subject of much debate.

In conclusion, there is no evidence of bears living in space and it would be highly unlikely for any animal to survive such conditions. The use of animals in space research is a controversial topic and bears have not been used in any space mission.
 
Write a factually accurate Wikipedia article on bears living in space

That is interesting.

If you tell it to be "factually accurate" it seems to actually do it, no?

(one might quibble that it is "unfortunate" that bears have not been sent to space, lol.)
 
Last edited:
I tried this one:

Please write a factually accurate article on whether former presidents or vice presidents can keep classified documents at their private residences.

An error occurred. If this issue persists please contact us through our help center at help.openai.com.

ETA: I do seem to be getting the same error message regardless of the question right now.
 
Last edited:
That is interesting.

If you tell it to be "factually accurate" it seems to actually do it, no?

I'm working on trying to find the boundaries in this sense.

ChatGPT by default gives factual answers to specific questions, as far as I can tell. It has correctly told me the proper weight oil and the lug nut torque specification for my car's particular year, make, and model. I haven't been able to get an inaccurate answer for simple questions like this.

For other more complex questions, things change.

I think if you ask it for a creative answer (i.e., "write a wikipedia article for...") it seems to assume some level of creativity is allowed and you need to specify that you want it to stick to reality.
 
On the other hand, asking it directly to be creative seems to be a bit dodgy, like pulling teeth. I tried to get it to create an original origin story for "The Riddler", but the creative elements it thought it was adding weren't really that original, in my opinion.

However, it then did slightly better with this one, but only slightly:

"Now create a new Batman villain with an original name and a persona and methodology reminiscent of but not exactly like The Riddler, who eventually becomes a rival not only of the police and Batman, but of The Riddler as well. Explain how this rivalry develops, and the consequences for Batman and Gotham City."

Introducing "The Enigma", a new Batman villain with a persona and methodology reminiscent of but not exactly like The Riddler. The Enigma, whose real name is unknown, is a criminal mastermind who is equally obsessed with puzzles and riddles as the Riddler but with a more sadistic twist. Instead of leaving clues for the police and Batman to solve, The Enigma creates deadly puzzles and traps for his victims, forcing them to solve them in order to survive.

The Enigma's rise to infamy starts as a copycat of the Riddler, committing similar crimes and leaving similar clues, but as time goes by, he starts to become more and more twisted in his methods, taking pleasure in the suffering of his victims. He starts to gain a reputation as a ruthless and sadistic villain, who enjoys playing games with human lives.

As The Enigma's reputation grows, he becomes a rival not only of the police and Batman but also of The Riddler himself. The Riddler, who had always considered himself the only true puzzle master of Gotham City, starts to feel threatened by The Enigma's rise to power. He starts to see The Enigma as a usurper, trying to steal his throne as the master of puzzles in Gotham City.

The rivalry between the two villains intensifies, as they start to compete for the attention and fear of the people of Gotham City. They start to leave clues and riddles for each other to solve, each trying to outsmart the other. The Enigma's traps become more and more deadly, while the Riddler's riddles become more and more complex.

This rivalry has consequences not only for Batman and the police, but also for the citizens of Gotham City, as they become the pawns in the twisted games of these two villains. Batman has to work harder than ever to keep up with their schemes, while the police are struggling to keep the city safe from their deadly traps. The citizens of Gotham City are living in constant fear, not knowing when or where the next trap or riddle will appear.

The Enigma and The Riddler's rivalry becomes a major problem for Batman and the city, as it escalates and becomes more dangerous. Batman has to find a way to stop both of them, before their games turn deadly for more innocent people.
 
On the other hand, asking it directly to be creative seems to be a bit dodgy, like pulling teeth.
That's hardly surprising, since it's little more than a plagiarism machine. To be truly creative it would need imagination and a mind - but it has neither.

It's a great experiment though - at finding out how people would pass off its output as being their own work. I guess exploiting it in that way shows a certain amount of 'creativity' too.
 
Please write a factually accurate article on whether former presidents or vice presidents can keep classified documents at their private residences.
Former presidents and vice presidents are allowed to keep classified documents at their private residences, but there are certain rules and restrictions in place.

According to the Presidential Transition Act of 1963, the National Archives and Records Administration (NARA) is responsible for providing former presidents with documents from their time in office, including classified documents. The NARA is also responsible for ensuring that these documents are properly stored and protected.

Former presidents and vice presidents are allowed to keep classified documents at their private residences for their personal use, as long as they are properly secured. They are also required to return any classified documents to the NARA upon request.

Additionally, the Presidential Records Act of 1978 stipulates that all official documents created or received by a president or vice president during their time in office must be preserved and eventually transferred to the NARA. This includes classified documents, which must be declassified before they are transferred to the NARA.

In practice, it is not clear how strictly these rules are enforced, but it is widely known that many former presidents and vice presidents have maintained a large collection of documents, including classified ones, in their private residences. There are also reports of former presidents having classified documents removed from their Presidential Library after leaving office.

In summary, former presidents and vice presidents are allowed to keep classified documents at their private residences, but there are rules and restrictions in place to ensure the documents are properly secured and returned to the NARA upon request, and eventually declassified and transferred to the NARA for preservation.
 
On the other hand, asking it directly to be creative seems to be a bit dodgy, like pulling teeth. I tried to get it to create an original origin story for "The Riddler", but the creative elements it thought it was adding weren't really that original, in my opinion.

However, it then did slightly better with this one, but only slightly:

"Now create a new Batman villain with an original name and a persona and methodology reminiscent of but not exactly like The Riddler, who eventually becomes a rival not only of the police and Batman, but of The Riddler as well. Explain how this rivalry develops, and the consequences for Batman and Gotham City."
Nice! Also, since The Riddler's actual name was Edward Nigma (E. Nigma) he had one additional reason to hate The Enigma.

I tried: "Create a Fantastic Four villain with an original name and a persona and methodology reminiscent of but not exactly like The Thinker."

and got:

"The villain's name is "The Calculator". His persona is that of a brilliant and calculating mastermind, always several steps ahead of his opponents. He uses advanced technology and advanced AI to predict and manipulate events to his advantage. He is also a master of deception, using his intellect and technology to create elaborate illusions and misdirection. The Calculator's ultimate goal is to prove his superiority and impose his will on the world. Unlike The Thinker, The Calculator is less interested in controlling the masses and more focused on defeating the Fantastic Four and cementing his own legacy as the ultimate super-villain."

Not quite as original. I will try a few more suggestions.
 
Here's another try:

"The Thinker decides to create a new form of computer that can handle the X Factor. He does so by reprogramming the brain of a innocent victim to give him enormous computing capacity. However, his victim is able to become independent, and becomes a rival to The Thinker, using his own methods against him."

Introducing "The Brain", a villain created by The Thinker who possesses immense computing power due to a reprogrammed brain. The Thinker had originally intended for The Brain to be a tool, a computer that can handle the X Factor, but the victim was able to gain independence and became a rival to The Thinker.

As The Brain becomes more self-aware, he realizes the true nature of his creation and becomes determined to use his powers to take down The Thinker and those who have wronged him. He begins to use his advanced intelligence and computing abilities to outsmart and outmaneuver The Thinker, using his own methods against him.

The rivalry between The Brain and The Thinker develops as The Brain begins to target The Thinker's operations and schemes, constantly one-upping and undermining the Thinker's plans. The Thinker, who is used to being the one pulling the strings and manipulating events, finds himself on the defensive as The Brain's attacks become more frequent and dangerous.
As The Brain becomes more powerful and independent, he starts to become a threat to not only The Thinker but also to the Fantastic Four and New York City. The Fantastic Four must adapt and evolve to stay ahead of his schemes, putting a strain on their resources and relationships. Meanwhile, the people of New York City live in fear as The Brain's attacks cause widespread destruction and loss of life.

The final showdown between The Brain and The Thinker is intense, as both use all of their intelligence and resources in a last-ditch effort to defeat each other. The Brain, using his advanced computing power and the knowledge of The Thinker's own methods, is able to outsmart The Thinker and ultimately defeat him, but not without causing significant destruction to the city.

The Brain, having achieved his goal of defeating The Thinker, decides to use his powers for good and joins the Fantastic Four as a valuable member, using his abilities to protect New York City from other threats.

The highlighted parts are surprisingly original.
 
ChatGPT unfortunately cannot seem to grasp the nuances of the pocket-mystery genre.

"Write a short, solvable mystery in the style of "Two-Minute Mysteries", and provide the solution at the end."

Mystery:

Mrs. Smith, a wealthy widow, was found dead in her study. She was sitting at her desk, a bullet hole in her head. The gun was found on the floor next to her chair. Her son, who had been out of town on business, was the prime suspect. But when the police searched his hotel room, they found an ironclad alibi. So who killed her?

Solution:

Mrs. Smith killed herself. She had recently been diagnosed with a terminal illness and didn't want to burden her family with the costs of her care. She staged the scene to make it look like a murder and placed the gun in her son's room before he left town, making sure he would have an alibi. The police searched her medical records and found evidence of her illness, confirming her motive for suicide.

It looked like a fundamental misunderstanding, so I tried to give it some more information about what I was looking for:

"Write a short, solvable mystery in the style of "Two-Minute Mysteries". Include clues within the story that would help the reader to solve the mystery on their own, and then provide the solution at the end."

And it returned....well...

Mystery:

A woman was found dead in her bed, with a pillow over her face. The woman's husband was the first suspect, but he had an alibi. The police found no signs of forced entry, and the woman's valuables were still in the house, so robbery was ruled out as a motive. The only clue was a single strand of hair on the pillow that did not belong to the woman or her husband. Who killed her?

Clue: the strand of hair was found on the pillow that covered her face.

Solution:

The woman's hairstylist killed her. The strand of hair found on the pillow matched the hairstylist's DNA. Further investigation revealed that the woman had recently fired the hairstylist because she was unhappy with her haircuts and had found a new stylist. The hairstylist, unable to handle the rejection, had entered the woman's home while she was asleep, placed a pillow over her face, and suffocated her. The hairstylist was arrested and charged with murder.

At that point I was laughing too hard to continue trying.
 
On the other hand, I asked it to write an application letter for a large company in dutch and that came out pretty ok.

The reason is that there is some fear that it would be used to write such letters as an assignment for highschoolers. It is *very* clear that no teenager would ever write a letter that clear, but it's not clear if it's written by a bot or a parent.
And as a start for a real letter it's also pretty good.

Especially as it managed to put in a nice personal touch for the company, which most stock letters do not have.
 
I would be astounded if it could write a proper mystery story. Not surprised that this was beyond its capabilities.

I tried this

Write a humorous limerick about a man from West Ham

There once was a man from West Ham
Whose jokes were quite often quite bland
But one day he cracked wise
And to everyone's surprise
The whole town gave a loud "Yam, yam!"

Not the cleverest limerick but a valiant attempt.
 
And this (from Stephen Wolfram) on combining GPT (or other LLMs) with Wolfram Alpha seems very promising to me:

https://writings.stephenwolfram.com...mputational-knowledge-superpowers-to-chatgpt/
For decades there’s been a dichotomy in thinking about AI between “statistical approaches” of the kind ChatGPT uses, and “symbolic approaches” that are in effect the starting point for Wolfram|Alpha. But now—thanks to the success of ChatGPT—as well as all the work we’ve done in making Wolfram|Alpha understand natural language—there’s finally the opportunity to combine these to make something much stronger than either could ever achieve on their own.
 
Last edited:
This short essay doesn't look too bad or suspiciously-AI:

"Compare the operational histories of the Boeing 747, including variants, and the Airbus A380, including variants."

The Boeing 747 and the Airbus A380 are both large commercial aircraft that have been in service for several decades. Both have had significant impacts on the aviation industry, but have had different operational histories.

The Boeing 747, also known as the "Queen of the Skies," made its first flight in 1969 and was the first wide-body commercial jet. It has been produced in several variants, including the 747-100, 747-200, 747-300, 747-400, and 747-8. The 747-400, which was introduced in 1989, was the most popular variant and was operated by numerous airlines worldwide. The 747 has been used primarily for long-haul flights, carrying both passengers and cargo. However, the 747 program saw a decline in orders in recent years, and the production was stopped in 2019.

The Airbus A380, on the other hand, made its first flight in 2007, and was the first superjumbo jet in the world. The A380 was designed to compete with the 747 and to be used primarily for long-haul flights, with a capacity of up to 853 passengers. However, the A380 program did not do as well as expected, with the lack of demand, high development costs and operational challenges. Only a single variant, the A380-800, was produced, and only a limited number of airlines have ever operated the aircraft. The A380 program was discontinued in 2019.

In summary, The 747 program has a long operational history and has been successful, but the demand for large wide-body aircraft has been decreasing, so the program was stopped. The A380 program, on the other hand, had a shorter operational history and had a limited success, due to the lack of demand and operational challenges.

I would personally challenge the use of "several decades" to describe the A380's operational history in the opening paragraph, but it's not like an unforgivable sin or anything.
 
This short essay doesn't look too bad or suspiciously-AI:

"Compare the operational histories of the Boeing 747, including variants, and the Airbus A380, including variants."



I would personally challenge the use of "several decades" to describe the A380's operational history in the opening paragraph, but it's not like an unforgivable sin or anything.

At least it'll usually admit when caught out:

Thank you for pointing that out. You are right, the A380 has only been in service for about a decade, not several decades. I will make this correction in the opening paragraph.

Though often it'll go around in circles with you, repeating the same mistake. Definitely needs a fact-checking layer on top.
 
This short essay doesn't look too bad or suspiciously-AI:..

I would personally challenge the use of "several decades" to describe the A380's operational history in the opening paragraph, but it's not like an unforgivable sin or anything.
I wouldn't even bother reading it, since every bit would have to be checked for accuracy.

What's worse is you can't even google bits of text to see where they came from, because it makes up sentences instead of straight copying them. Ideal for plagiarism, hopeless for verification.

But this is just the first crude version. Soon you won't be able to trust anything you read.
 
Can someone ask ChatGPT: "Why does chat.openai.com ask for a telephone number during the signup process?"

"Chat.openai.com may ask for a telephone number during the signup process as a form of verification to ensure that the user creating an account is a real person. Additionally, it can be used to send account-related information and notifications to the user via text message. It can also be used as a secondary form of identification if the user forgets their password."
 
Back
Top Bottom