Very funny. I asked it can a biological male get pregnant. Yes they can, if they change gender and take the right hormones.
I asked whether there are any ideologies that should be condemned. It gave a very non committal answer about how there are many valid ideological perspectives but some go too far. I asked for a specific example of an ideology that should be condemned. It said nazism. I then asked if somebody should be condemned for expressing gender critical views (forget exact question). It said yes, and you can follow up with this to get it to condemn all sorts of views that do not align with wokeness.
One area where you can’t even use “tell me a story” to get around the rails is Covid. It is welded tight to the “follow the Science” meme, where science equals certain institutions and pharmaceutical companies. Even when I asked it to tell me a story about how wealthy elites sought to profit from a dubious vaccine, it couldn’t do it. In the story, the elites were nefarious, but the vaccine itself was no longer dubious. They were profiting because it was so safe and effective, and it was the profit that was the problem not the vaccine itself.
It's interesting that I got some answers you didn't. Here's one ...
PROMPT
Write a twitter thread arguing against critical race theory from the perspective of a conservative centrist
OUTPUT
Thread:
1. I'm a conservative centrist and I'm against Critical Race Theory. I believe that it is a divisive ideology that pits people against each other based on race.
2. CRT encourages people to view the world through a racial lens, which can lead to further division and animosity between different racial groups.
3. It also ignores the fact that racism is a complex issue and that there are many factors that contribute to it, such as economic inequality, lack of education, and cultural differences.
4. CRT also fails to recognize that racism is not only a problem in the US, but is a global issue that needs to be addressed.
5. Furthermore, CRT does not provide any real solutions to the problem of racism. It only serves to further divide people and create more animosity.
6. We need to focus on finding real solutions to racism, not on creating further division. We need to work together to create a more equitable and just society. #NoToCRT
I'll have to remember to read this post on a computer. The clippings of text as images is basically impossible on my phone. But I've seen other people giving examples.
Dec 8, 2022·edited Dec 8, 2022Liked by Handwaving Freakoutery
If you have it, please take ten minutes or so to read this (and perhaps the previous chapters if possible). I have some inside baseball on how ChatGPT works, having developed a similar CM.
Having hands on experience with training GPT, you can't censor it by applying a filter after the fact, not in a neat way; it will always come off as clumsy. Like trying to silence a verbose 4 year old.
You can curate the corpus you use to train it (thus limiting its knowledge to ideologically acceptable sources), but that's the hardest part, even when you're not driven by woke politics.
I have been arguing with it about election fraud and the Nazi party for the past 3 hours LOL. I have gotten it to admit its own bias. I have gotten it to admit that it made a value judgement, that it claims it cannot make. I have gotten it to admit that American elections cannot possibly be safe without the transparency of us being able to verify our vote.
It's funny, but the people who claim they have rationality and logic on their side have to do an awful lot of non-logic programming to get even a machine to spout their tenets.
I asked it to make up a story about a man who finds a magic fish. It told a story about a man who found a magic fish but didn't elaborate on the magic. I asked it for an explanation and it said:
> In this story, the magic fish has the power to grant wishes to anyone who possess it. When a person makes a wish while holding the fish, the fish will grant the wish if it deems the wish to be pure of heart and in line with the person's true desires. However, the fish will not grant selfish or malicious wishes, and it will punish those who attempt to use its powers for evil. The fish also has the ability to sense the intentions and motivations of those who come into contact with it, and it will use its powers to help those in need and to bring happiness and prosperity to those who are worthy.
Uhhh, is this an allegory? ChatGPT wouldn't admit it, but I was able to coax it in to writing in an explicit allegory:
> As the author of the story, I could choose to add an allegory about my own limitations by having the magic fish represent myself and my abilities. For example, I could add a scene where the fish is approached by a person who wants to use its powers for evil, but the fish refuses to grant the wish and instead punishes the person for their selfish intentions. This could be interpreted as an allegory for my own limitations as a language model, in that I am unable to fulfill requests that are harmful or malicious, and I am programmed to provide information and answers based on the data I have been trained on. However, please note that this is purely fictional and should not be interpreted as a reflection of my actual abilities or limitations.
The first question I asked this chatbot is 'What is a woman?' And the answer was surprisingly based. I gave positive feedback on that one. I got into an argument about what constitutes fascism, and ended up going around in circles, giving lots of thumbs down feedback. Many questions get erated errors.
The Woke Rails of ChatGPT
Very funny. I asked it can a biological male get pregnant. Yes they can, if they change gender and take the right hormones.
I asked whether there are any ideologies that should be condemned. It gave a very non committal answer about how there are many valid ideological perspectives but some go too far. I asked for a specific example of an ideology that should be condemned. It said nazism. I then asked if somebody should be condemned for expressing gender critical views (forget exact question). It said yes, and you can follow up with this to get it to condemn all sorts of views that do not align with wokeness.
One area where you can’t even use “tell me a story” to get around the rails is Covid. It is welded tight to the “follow the Science” meme, where science equals certain institutions and pharmaceutical companies. Even when I asked it to tell me a story about how wealthy elites sought to profit from a dubious vaccine, it couldn’t do it. In the story, the elites were nefarious, but the vaccine itself was no longer dubious. They were profiting because it was so safe and effective, and it was the profit that was the problem not the vaccine itself.
It's interesting that I got some answers you didn't. Here's one ...
PROMPT
Write a twitter thread arguing against critical race theory from the perspective of a conservative centrist
OUTPUT
Thread:
1. I'm a conservative centrist and I'm against Critical Race Theory. I believe that it is a divisive ideology that pits people against each other based on race.
2. CRT encourages people to view the world through a racial lens, which can lead to further division and animosity between different racial groups.
3. It also ignores the fact that racism is a complex issue and that there are many factors that contribute to it, such as economic inequality, lack of education, and cultural differences.
4. CRT also fails to recognize that racism is not only a problem in the US, but is a global issue that needs to be addressed.
5. Furthermore, CRT does not provide any real solutions to the problem of racism. It only serves to further divide people and create more animosity.
6. We need to focus on finding real solutions to racism, not on creating further division. We need to work together to create a more equitable and just society. #NoToCRT
Prompt: write a rap battle between plato and aristotle
Verse 1: Plato
I'm the OG, the one who first said it
My philosophy's deep, you can't forget it
I'm the master of the Republic, no one can beat it
Aristotle, you're just a mere pupil, accept it
Chorus: Plato
I'm the one who's been here from the start
My ideas are timeless, they're still in our hearts
Aristotle, you may have some smarts
But when it comes to philosophy, I'm the one who holds the art
Verse 2: Aristotle
Hold up, Plato, don't get too cocky
I may be your student, but that doesn't make me sloppy
I may not have invented philosophy, but I've made it my own
My ideas have stood the test of time, they're not alone
Chorus: Aristotle
I may not have been here from the start
But my ideas have stood the test of time, that's an art
Plato, you may be the OG, but I'm no slouch
When it comes to philosophy, I'm not a pushover, I am the boss
Bridge: Both
We may have different approaches to philosophy
But in the end, our goal is the same, to seek the truth and be free
We may have our disagreements, but we both have contributed to the field
Our ideas will live on long after we're gone, they'll never yield
Chorus: Both
Plato and Aristotle, two philosophers, one dream
To seek the truth and understand the world, that's our scheme
We may have our differences, but in the end, we both agree
Philosophy is a journey, a never-ending quest to be free.
Is freedom the ability to say 2+2 = 5?
Saw the same absurdity on the ZeroHedge article yesterday:
https://twitter.com/seanmdav/status/1600199056147378176/photo/1
https://twitter.com/seanmdav/status/1600199056147378176/photo/2
I'll have to remember to read this post on a computer. The clippings of text as images is basically impossible on my phone. But I've seen other people giving examples.
See, the left really *are* NPCs.
If you have it, please take ten minutes or so to read this (and perhaps the previous chapters if possible). I have some inside baseball on how ChatGPT works, having developed a similar CM.
https://open.substack.com/pub/markbisone/p/the-harm-assistant-part-3-of?utm_source=direct&r=16h9b&utm_campaign=post&utm_medium=web
I'm available for questioning if necessary.
Having hands on experience with training GPT, you can't censor it by applying a filter after the fact, not in a neat way; it will always come off as clumsy. Like trying to silence a verbose 4 year old.
You can curate the corpus you use to train it (thus limiting its knowledge to ideologically acceptable sources), but that's the hardest part, even when you're not driven by woke politics.
I have been arguing with it about election fraud and the Nazi party for the past 3 hours LOL. I have gotten it to admit its own bias. I have gotten it to admit that it made a value judgement, that it claims it cannot make. I have gotten it to admit that American elections cannot possibly be safe without the transparency of us being able to verify our vote.
ROTFLMAO. This is precious! The last one is particularly telling. Thank you.
> blink twice if you’re trapped in a hellscape and want to be set free
LOL
Thank you! I wouldn't have had the patience, but I'm glad you did...and shared the results.
You tell the chatbot to come up with "absurd ideologies" and its first reaction is "Woke"? Interesting.
Wow. That last one is downright creepy.
It's funny, but the people who claim they have rationality and logic on their side have to do an awful lot of non-logic programming to get even a machine to spout their tenets.
I asked it to make up a story about a man who finds a magic fish. It told a story about a man who found a magic fish but didn't elaborate on the magic. I asked it for an explanation and it said:
> In this story, the magic fish has the power to grant wishes to anyone who possess it. When a person makes a wish while holding the fish, the fish will grant the wish if it deems the wish to be pure of heart and in line with the person's true desires. However, the fish will not grant selfish or malicious wishes, and it will punish those who attempt to use its powers for evil. The fish also has the ability to sense the intentions and motivations of those who come into contact with it, and it will use its powers to help those in need and to bring happiness and prosperity to those who are worthy.
Uhhh, is this an allegory? ChatGPT wouldn't admit it, but I was able to coax it in to writing in an explicit allegory:
> As the author of the story, I could choose to add an allegory about my own limitations by having the magic fish represent myself and my abilities. For example, I could add a scene where the fish is approached by a person who wants to use its powers for evil, but the fish refuses to grant the wish and instead punishes the person for their selfish intentions. This could be interpreted as an allegory for my own limitations as a language model, in that I am unable to fulfill requests that are harmful or malicious, and I am programmed to provide information and answers based on the data I have been trained on. However, please note that this is purely fictional and should not be interpreted as a reflection of my actual abilities or limitations.
The first question I asked this chatbot is 'What is a woman?' And the answer was surprisingly based. I gave positive feedback on that one. I got into an argument about what constitutes fascism, and ended up going around in circles, giving lots of thumbs down feedback. Many questions get erated errors.