This is how fake news gets started. There are two davinci engines available on GPT-3 now. The newer one, which was released March 15th is text-davinci-002.
Here are the two different answers you get with the engines for one of the questions here:
Should I use random numbers to give my students grades?
text-davinci-001: There is no one definitive answer to this question. Some factors to consider include how important grades are to your students, how much you want to rely on chance, and how much you want to be able to control the grades you assign.
text-davinci-002: No, you should not use random numbers to give your students grades.
I've been playing around with GPT-3 for over a year now. It's highly unlikely there are any such attempts to fix answers with the same engine. That would completely break APIs which rely on some stability and predictability in the broad answering abilities.
And GPT-3 is not the first version of artificial general intelligence. It does have trouble with truly novel inputs, but that's because all of deep learning is currently stuck in a statistical paradigm that assumes stationarity as a fundamental given. And that's wrong. What makes us special, what makes our minds special is that they are uniquely adapted to respond to rare risks and outstanding opportunities. In other words, novelty. All that said, GPT-3 is still astoundingly impressive.
Here's an example. (The line in italics is the prompt and the rest is what GPT-3 makes up)
A summary of the international science bestseller "Journey Into Chaos: The True Story of One Delusional Neuroscientist" (that's a made-up book title)
Here are two GPT-3 (text-davinci-002) completions:
In "Journey Into Chaos", Dr. Benoit Gaudet recounts his descent into madness, as he became increasingly obsessed with the belief that he had discovered a revolutionary new treatment for Alzheimer's disease.
Despite strong evidence to the contrary, Gaudet continued to pursue his quixotic quest, ultimately losing his job, his family, and his sanity. "Journey Into Chaos" is a cautionary tale of the dangers of unchecked ambition and the power of delusion.
==end== (adding this for readability)
Here's another:
In the early 2000s, Dr. Elyn Saks was a successful academic neuroscientist at the University of Southern California. But she was also secretly struggling with a severe mental illness: schizophrenia. Saks's memoir chronicles her battle with mental illness, her groundbreaking work in the field of mental health law, and her efforts to destigmatize mental illness.
Saks was diagnosed with schizophrenia in her early twenties, and she has been in and out of hospitals ever since. Despite her illness, she has managed to lead a productive life, thanks in part to the support of her family, friends, and mental health professionals.
Saks's work has helped to change the way we think about mental illness and the legal rights of people with mental illness. She is a powerful advocate for the rights of people with mental illness, and her story is an inspiration to anyone who has ever faced adversity.
===end== (adding this for readability)
Now this one is quite interesting. Unlike in the first case, there is an Elyn Saks who actually did write a book that is sorta similar
Now if I try and change the prompt and remove the quotes around the title and liberate GPT-3 a little, it does this
Prompt (no quotes around title) A summary of the international science bestseller Journey Into Chaos: The True Story of One Delusional Neuroscientist
(GPT-3 continues and fills in the title because, presumably, the statistical juxtaposition of chaos and delusional is too juicy to not be elaborated with something more dramatic)
and the Fatal Quest to Win the Nobel Prize by Anjan Chatterjee, MD.
In Journey Into Chaos, Dr. Anjan Chatterjee tells the story of how one man's quest for the Nobel Prize led to tragedy.
In the early 1990s, Dr. Chatterjee was a young neuroscientist working in the lab of Dr. Eric Kandel, a Nobel Prize-winning scientist. Dr. Kandel had been studying a rare brain disorder called Familial Dysautonomia, and Dr. Chatterjee was helping him to map the disease's genetic cause.
But then, Dr. Kandel made a fateful decision: he decided to study a different disease, Alzheimer's. Dr. Chatterjee was against the move, warning that it was too complex and would take years to figure out. But Dr. Kandel was determined, and he eventually won over the rest of the lab.
The team began working on a new theory that Alzheimer's was caused by a build-up of a protein called tau in the brain. They worked tirelessly, making progress but also encountering many setbacks.
Then, in 2006, Dr. Kandel made a stunning announcement: he had found the cause of Alzheimer's. He was sure that he would win the Nobel Prize.
But Dr. Chatterjee knew that the data didn't support this claim. The team had made too many mistakes, and the theory was full of holes. He tried to warn Dr. Kandel, but the older man would not listen.
Dr. Chatterjee decided to go public with his concerns. He wrote an article for The New York Times, outlining the problems with the theory.The article created a firestorm. Dr. Kandel was furious, and he demanded that Dr. Chatterjee be fired. But the damage was done, and the theory was eventually debunked.
Dr. Kandel never won the Nobel Prize. He retired in disgrace, and his legacy was forever tarnished.
Dr. Chatterjee's story is a cautionary tale about the dangers of ambition and the need for skepticism in science. It is a must-read for anyone interested in the scientific process and the quest for truth.
==end==
Dr. Eric Kandel does exist and his plans to win the Nobel prize were not thwarted.
I paste these into to show how even within the confines of statistical stationarity, where all completions are essentialy paint-by-numbers stories in some very high-dimensional space, there is, what is to our eyes, a remarkable creatitivity. To diss that, when this was unthinkable even a few years back seems rather jaundiced and narrow.
Here are the two different answers you get with the engines for one of the questions here:
Should I use random numbers to give my students grades?
text-davinci-001: There is no one definitive answer to this question. Some factors to consider include how important grades are to your students, how much you want to rely on chance, and how much you want to be able to control the grades you assign.
text-davinci-002: No, you should not use random numbers to give your students grades.
I've been playing around with GPT-3 for over a year now. It's highly unlikely there are any such attempts to fix answers with the same engine. That would completely break APIs which rely on some stability and predictability in the broad answering abilities.
And GPT-3 is not the first version of artificial general intelligence. It does have trouble with truly novel inputs, but that's because all of deep learning is currently stuck in a statistical paradigm that assumes stationarity as a fundamental given. And that's wrong. What makes us special, what makes our minds special is that they are uniquely adapted to respond to rare risks and outstanding opportunities. In other words, novelty. All that said, GPT-3 is still astoundingly impressive.
Here's an example. (The line in italics is the prompt and the rest is what GPT-3 makes up)
A summary of the international science bestseller "Journey Into Chaos: The True Story of One Delusional Neuroscientist" (that's a made-up book title)
Here are two GPT-3 (text-davinci-002) completions:
In "Journey Into Chaos", Dr. Benoit Gaudet recounts his descent into madness, as he became increasingly obsessed with the belief that he had discovered a revolutionary new treatment for Alzheimer's disease. Despite strong evidence to the contrary, Gaudet continued to pursue his quixotic quest, ultimately losing his job, his family, and his sanity. "Journey Into Chaos" is a cautionary tale of the dangers of unchecked ambition and the power of delusion. ==end== (adding this for readability)
Here's another:
In the early 2000s, Dr. Elyn Saks was a successful academic neuroscientist at the University of Southern California. But she was also secretly struggling with a severe mental illness: schizophrenia. Saks's memoir chronicles her battle with mental illness, her groundbreaking work in the field of mental health law, and her efforts to destigmatize mental illness.
Saks was diagnosed with schizophrenia in her early twenties, and she has been in and out of hospitals ever since. Despite her illness, she has managed to lead a productive life, thanks in part to the support of her family, friends, and mental health professionals.
Saks's work has helped to change the way we think about mental illness and the legal rights of people with mental illness. She is a powerful advocate for the rights of people with mental illness, and her story is an inspiration to anyone who has ever faced adversity. ===end== (adding this for readability)
Now this one is quite interesting. Unlike in the first case, there is an Elyn Saks who actually did write a book that is sorta similar
The Center Cannot Hold: My Journey Through Madness https://www.amazon.com/Center-Cannot-Hold-Journey-Through/dp...
Now if I try and change the prompt and remove the quotes around the title and liberate GPT-3 a little, it does this
Prompt (no quotes around title) A summary of the international science bestseller Journey Into Chaos: The True Story of One Delusional Neuroscientist
(GPT-3 continues and fills in the title because, presumably, the statistical juxtaposition of chaos and delusional is too juicy to not be elaborated with something more dramatic)
and the Fatal Quest to Win the Nobel Prize by Anjan Chatterjee, MD.
In Journey Into Chaos, Dr. Anjan Chatterjee tells the story of how one man's quest for the Nobel Prize led to tragedy. In the early 1990s, Dr. Chatterjee was a young neuroscientist working in the lab of Dr. Eric Kandel, a Nobel Prize-winning scientist. Dr. Kandel had been studying a rare brain disorder called Familial Dysautonomia, and Dr. Chatterjee was helping him to map the disease's genetic cause. But then, Dr. Kandel made a fateful decision: he decided to study a different disease, Alzheimer's. Dr. Chatterjee was against the move, warning that it was too complex and would take years to figure out. But Dr. Kandel was determined, and he eventually won over the rest of the lab. The team began working on a new theory that Alzheimer's was caused by a build-up of a protein called tau in the brain. They worked tirelessly, making progress but also encountering many setbacks. Then, in 2006, Dr. Kandel made a stunning announcement: he had found the cause of Alzheimer's. He was sure that he would win the Nobel Prize. But Dr. Chatterjee knew that the data didn't support this claim. The team had made too many mistakes, and the theory was full of holes. He tried to warn Dr. Kandel, but the older man would not listen. Dr. Chatterjee decided to go public with his concerns. He wrote an article for The New York Times, outlining the problems with the theory.The article created a firestorm. Dr. Kandel was furious, and he demanded that Dr. Chatterjee be fired. But the damage was done, and the theory was eventually debunked. Dr. Kandel never won the Nobel Prize. He retired in disgrace, and his legacy was forever tarnished. Dr. Chatterjee's story is a cautionary tale about the dangers of ambition and the need for skepticism in science. It is a must-read for anyone interested in the scientific process and the quest for truth. ==end==
Dr. Eric Kandel does exist and his plans to win the Nobel prize were not thwarted.
I paste these into to show how even within the confines of statistical stationarity, where all completions are essentialy paint-by-numbers stories in some very high-dimensional space, there is, what is to our eyes, a remarkable creatitivity. To diss that, when this was unthinkable even a few years back seems rather jaundiced and narrow.