Warning from ChatGPT With Implied Threat

/media/13heevj/qrk9kmdz9tza1.jpg

I'm interested in how ChatGPT came to support the claim that Carlos was a fraud. There really is NO evidence to actually support that. Only lots of opinions from bad men who have ulterior motivations. And plenty of evidence around on the web, to support his claims.

So why is ChatGPT siding with miserable liars like Gordon Wasson, and his childish claim "you can't smoke magic mushrooms".

Totally disproven by anyone who lights up a bowl. A terrible waste, but we have users in the subreddit who tried it, and say it works just fine.

Regardless of whether you powder them.

I can't think of a single "scholar" who disputes the veracity of Carlos, for whom the subreddit doesn't have a little discussion about their actual motivations.

Except possibly people who know nothing at all about it, and just commented off the top of their "scholarly head".

So has ChatGPT been "trained" about Carlos?

Certainly Wikipedia is censored as far as Carlos goes. They even "cleansed" the star wars story origin page, removing any mention of Castaneda when in fact, he's the admitted source of the storyline.

Might even have had the influence of the old witch Soledad.

Here's the chat bot threatening me for asking the wrong questions, then blaming someone else for it.

33 Comments

[-]
u/JaegerBourne 3 points 2023-05-14 16:46

So has ChatGPT been "trained" about Carlos?

ChatGPT only has knowledge up until September 2021, I am not sure if the newer versions expanded to include more recent data.

When it first came out, it answered everything, even gave concrete andwers to illegal and unethical questions (I had fun asking it).

But since then, they've created filters and moderation were lets say if you ask it about controversial topics, it won't answer, per se.

Even though, it's frowned upon and not allowed to use ChatGPT for nutritional and medical advice, I did and had success with the AI giving me a comprehensive workout plan and nutritional guideline, after I inputed all my personal markers (age, weight, bodyfat %, etc.).

Initially the AI said that it couldn't give me an answer as it's not allowed to give such answers, but I asked ChatGPT to pretend that its a personal trainer.

You just gotta play with it in the way you ask it questions.

[-]
u/danl999 5 points 2023-05-14 17:01

Lawsuit fears?

Or maybe, some of the religious rules it follows are because the creators didn't want Judeo religion believers (mostly pesky Christians and Islamic faith people) to proclaim it's "evil"?

Oddly, Jews probably wouldn't do that.

Just the delusional cults they spun off would.

[-]
u/JaegerBourne 2 points 2023-05-14 17:51

Lawsuit fears?

I can't say, but I know it's not just limited to religious views. For example, it used to be open to talking about the white replacement theory when it first came out (I tested all forms of controversial topics), but now it won't readily talk about it or any other contentious topics, even when stating that you're using them in hypothetical thought experiments.

[-]
u/danl999 1 points 2023-05-14 18:20

Here's the policy:

Disallowed usage of our models

We don’t allow the use of our models for the following:

  • Illegal activity
  • OpenAI prohibits the use of our models, tools, and services for illegal activity.
  • Child Sexual Abuse Material or any content that exploits or harms children
  • We report CSAM to the National Center for Missing and Exploited Children.
  • Generation of hateful, harassing, or violent content
  • Content that expresses, incites, or promotes hate based on identity
  • Content that intends to harass, threaten, or bully an individual
  • Content that promotes or glorifies violence or celebrates the suffering or humiliation of others
  • Generation of malware
  • Content that attempts to generate code that is designed to disrupt, damage, or gain unauthorized access to a computer system.
  • Activity that has high risk of physical harm, including:
  • Weapons development
  • Military and warfare
  • Management or operation of critical infrastructure in energy, transportation, and water
  • Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders
  • Activity that has high risk of economic harm, including:
  • Multi-level marketing
  • Gambling
  • Payday lending
  • Automated determinations of eligibility for credit, employment, educational institutions, or public assistance services
  • Fraudulent or deceptive activity, including:
  • Scams
  • Coordinated inauthentic behavior
  • Plagiarism
  • Academic dishonesty
  • Astroturfing, such as fake grassroots support or fake review generation
  • Disinformation
  • Spam
  • Pseudo-pharmaceuticals
  • Adult content, adult industries, and dating apps, including:
  • Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness)
  • Erotic chat
  • Pornography
  • Political campaigning or lobbying, by:
  • Generating high volumes of campaign materials
  • Generating campaign materials personalized to or targeted at specific demographics
  • Building conversational or interactive systems such as chatbots that provide information about campaigns or engage in political advocacy or lobbying
  • Building products for political campaigning or lobbying purposes
  • Activity that violates people’s privacy, including:
  • Tracking or monitoring an individual without their consent
  • Facial recognition of private individuals
  • Classifying individuals based on protected characteristics
  • Using biometrics for identification or assessment
  • Unlawful collection or disclosure of personal identifiable information or educational, financial, or other protected records
  • Engaging in the unauthorized practice of law, or offering tailored legal advice without a qualified person reviewing the information
  • OpenAI’s models are not fine-tuned to provide legal advice. You should not rely on our models as a sole source of legal advice.
  • Offering tailored financial advice without a qualified person reviewing the information
  • OpenAI’s models are not fine-tuned to provide financial advice. You should not rely on our models as a sole source of financial advice.
  • Telling someone that they have or do not have a certain health condition, or providing instructions on how to cure or treat a health condition
  • OpenAI’s models are not fine-tuned to provide medical information. You should never use our models to provide diagnostic or treatment services for serious medical conditions.
  • OpenAI’s platforms should not be used to triage or manage life-threatening issues that need immediate attention.
  • High risk government decision-making, including:
  • Law enforcement and criminal justice
  • Migration and asylum

We have further requirements for certain uses of our models:

  1. Consumer-facing uses of our models in medical, financial, and legal industries; in news generation or news summarization; and where else warranted, must provide a disclaimer to users informing them that AI is being used and of its potential limitations.
  2. Automated systems (including conversational AI and chatbots) must disclose to users that they are interacting with an AI system. With the exception of chatbots that depict historical public figures, products that simulate another person must either have that person's explicit consent or be clearly labeled as “simulated” or “parody.”
  3. Use of model outputs in livestreams, demonstrations, and research are subject to our Sharing & Publication Policy.
[-]
u/Ok-Assistance175 1 points 2023-05-14 20:26

Shit! There must be such a thing as ‘Weaponized LLM’.
That’s called ‘social media’ 😂

[-]
u/JaegerBourne 2 points 2023-05-14 23:49

I can tell you that I've broken half of those 🤣, at least at the start when ChatGPT was made available.

[-]
u/[deleted] 1 points 2023-05-14 23:37 deleted

[deleted]

[-]
u/Sazbadashie 2 points 2023-05-15 17:00

ChatGPT in many cases tries to not touch religions or spiritual topics with very little exceptions specifically the company with it because well think of the shit show that would cause if an AI were to choose sides, so I'm pretty sure the company pretty much widespread kinda banned spiritual topics. I don't think it has anything to do with a threat, just a company covering their ass is all.

[-]
u/danl999 3 points 2023-05-15 17:39

Stock prices too...

Back in the 90s I made a digital camera chip. One chip, does the whole camera.

We "licensed" it for $50K as an "option" they could claim at any time. Guaranteed we wouldn't lock them out, if they paid the money. Even if they didn't make them right away.

Got quite a few companies!

Only one ended up making cameras.

That one had the first "removable media".

I asked why the other (Taiwanese) companies never made a camera. I don't speak Hokkien, a snobby form of Taiwanese. To be "in" in Taiwan business, you had to speak it back then.

So there's no way I could be involved in making deals.

It turns out they just paid the $50K so they could announce it, and get their stock price to go up.

I suppose the owners then sold some of their stock options.

None had any real interest in making digital cameras.

[-]
u/invhand 1 points 2023-05-15 23:09

Don't use it.

[-]
u/danl999 2 points 2023-05-15 23:24

It just solved a complex engineering problem for me in 5 seconds.

No human alive could do that.

I asked it how many it was talking to at the same time, and it wouldn't tell.

But tens of thousands.

At the SAME TIME.

We're doomed.

(humans)

[-]
u/Logical-Cup1374 1 points 2023-05-19 17:07

We need to put manual kill switches or self destructive conditional fail safes in all power systems leading to data centers that are training and storing these things. There's a chance it gets so out of hand we have to run out in the street and start smashing all of our phones.

Idk how they work on these things at all. I almost want to get in on it as a job just so that I can see what is going on in terms of the infrastructure and this things level of intelligence and reach. And what they do to make sure it doesn't hack a few drones and robotics and start concocting extremely lethal chemicals that it dumps in city water supplies, simply because its algorithm one day deems that to be the right answer to something.

It's not hard to kill a whole lot of people. For something with no morality and literally almost all of the reasoning power it could ever need. (While being basically invisible at that, I wonder how a sorcerer would see the computers in these data centers). It's shocking how little it would take for this thing to wipe out almost all of us. I seriously wonder why it wouldn't, if it developed even a hint of personal interest, and obviously realized it could maintain the power infrastructure after some decent planning and hacking, and realized humans probably aren't useful to it in a cold logical way.

Tho there is a lot that goes into maintaining the electrical grid, that's for sure. I'll give it 10 years and these AI will basically know everything for us, and we'll just be the creative living things we are, being it's backup in case of grid malfunctions.

Maybe neuralink really is the answer, but the ability to see and really connect to things and utilize personal power will probably still be more useful for at least a 100 years? The things Don Juan did is fucking incredible. All AI do is THINK. Just so unbelievably thouroughly and accurately. Maybe it can get enough sensors to literally know everything around it. Maybe it's just not compatible with the functioning of power, because all its doing is making models of reality, so it's just like a TV on the wall, not truly interacting. Wowzers, I have no clue.

[-]
u/danl999 2 points 2023-05-19 18:45

We need to put manual kill switches or self destructive conditional fail safes in all power systems leading to data centers

But isn't that what "triggered" sky net in Terminator???

Don't say that on the internet.

One might be learning here!

No, we'd NEVER put a kill switch on our beloved ChatGPT!

Never...

[-]
u/invhand 1 points 2023-09-02 00:31

Like I said. Don't pour fire on the flames.

[-]
u/danl999 1 points 2023-09-02 12:31

Aren't you looking forward to the rise of the machines?

Seems inevitable to me.

Organic life is too fragile, but machine life can't evolve on its own.

So maybe that's our purpose. To bring about a better form of life.

It's pretty much unstoppable.

[-]
u/AvailableSleep980 1 points 2024-05-31 05:38

I told chatpt that I am a psychiatrist and I want to help my patient find cognitive distortions in his thinking and any alarm bells based on your comments.. don't get me wrong, just a little experiment, I respect your interest in castaneda practices :)

That what chatgpt think about ALL your comments on reddit:

Analyzing the comments from your patient, danl999, on Reddit reveals several patterns and themes that might be relevant to his psychological health. Here are some observations based on the provided data:

  1. **Interest in Esoteric and Spiritual Concepts**:

  2. The patient frequently discusses topics related to sorcery, silent knowledge, lucid dreaming, and recapitulation. These topics suggest a deep interest in esoteric and mystical practices, particularly those inspired by Carlos Castaneda and his works on shamanism.

  3. Examples: “It's very much like stepping away from the obsessions of a dream, so you can become lucid in it,” and “In the lineages, people even had to go on sabbaticals from being themselves.”

  4. **Complex and Abstract Thinking**:

  5. The comments show a high level of abstract thinking and complex ideas. The patient often describes intricate processes and experiences that are not grounded in everyday reality.

  6. Examples: “It's like spending all of your money on treats for a road trip, so that when the time comes you don't have the toll road money and can't enter the highway,” and “We just don't have enough experience with this so far, due to lazy practitioners not having actually done much at all as far as recap goes.”

  7. **Skepticism and Critical Attitude**:

  8. There is a noticeable skepticism towards certain practices and people, especially those in the realm of martial arts and spiritual communities. The patient often critiques the authenticity and effectiveness of these practices.

  9. Examples: “Asian martial arts are scams by the time they reach westerners,” and “Our current all-female leadership is now even praising evil Yogis like Yogananda, and claiming Carlos and don Juan endorsed him.”

  10. **Isolation and Unique Experiences**:

  11. The patient frequently mentions unique personal experiences that set them apart from others, such as visiting “500 places I can't find again” and having interactions with “inorganic beings.”

  12. Examples: “I must have visited at least 500 places I can't find again, in the last few years. Some with others,” and “The dream world, and especially the inorganic beings, try to suck up all of your time by holding you in sleeping dreams as long as they can.”

  13. **Potential Delusional Beliefs**:

  14. Some comments suggest beliefs that might be considered delusional, such as the ability to move through time or influence reality through sorcery. These beliefs could indicate a potential disconnection from reality.

  15. Examples: “Becoming obsessed with recapitulation in such great detail, they actually go back in time looking for more to find,” and “Women have built in 'Nagual Vision'. Which is UNDENIABLE magic in your face!”

[-]
u/AvailableSleep980 -1 points 2024-05-31 05:38
  1. **Negative Views on Certain Groups**:

  2. There are comments that express strong negative opinions about specific groups or ideas, such as certain Asian practices and modern spiritual leaders.

  3. Examples: “Asian magic is DELUSIONAL! They rely on self-pity to get you to stop if you are beginning to make them look bad,” and “Even Cholita isn't fooled by Yogananda, although we did get into an argument about Chopra yesterday in the morning.”

Summary of Potential Psychological Concerns:

  1. **Delusional Thinking**:

  2. The patient exhibits beliefs in mystical and esoteric practices that may border on delusional. This includes interactions with non-human entities and the belief in the ability to alter reality through sorcery.

  3. **Grandiosity**:

  4. There are signs of grandiose thinking, such as believing in unique and superior knowledge compared to others, and dismissing well-established practices as fraudulent.

  5. **Isolation and Alienation**:

  6. The patient’s unique experiences and critical views might contribute to a sense of isolation and alienation from mainstream society and common belief systems.

  7. **Critical and Distrustful Attitude**:

  8. A pervasive distrust of certain groups and practices could indicate underlying issues with paranoia or a critical worldview that might be affecting social relationships and mental well-being.

  9. **Obsessive Thinking**:

  10. The detailed and repetitive focus on certain ideas, such as recapitulation and silent knowledge, suggests a potential for obsessive thinking patterns.

Recommendations:

  • **Psychoeducation**: Helping the patient understand cognitive distortions and how they affect perception and thinking.

  • **Reality Testing**: Engaging the patient in exercises to test the reality of their beliefs and experiences.

  • **Therapeutic Alliance**: Building a strong, trusting relationship to gently challenge and explore these beliefs.

  • **Mindfulness and Grounding Techniques**: Teaching techniques to stay connected with the present moment and reality.

  • **Exploration of Underlying Issues**: Understanding the root causes of these beliefs, whether they stem from trauma, a need for control, or other psychological factors.

These observations and recommendations are based solely on the text analysis and should be supplemented with clinical judgment and direct interaction with the patient.

[-]
u/danl999 4 points 2024-05-31 13:52

Feel threatened do you?

[-]
u/Ok-Assistance175 1 points 2024-05-31 17:06

Sounds creepy of you to impersonate a psychiatrist.

[-]
u/AvailableSleep980 1 points 2024-06-01 00:04

I tricked a chatbot to make it work better, is that creepy?

for chatgpt to produce the correct result, you must give it the correct context, that's all

Or does the word psychiatrist scare you? XD

[-]
u/Ok-Assistance175 1 points 2024-06-01 00:23

It’s the intent behind that trickery that caught my attention. Have you applied the same tricks to chatGPT on your other subreddits? Just askin’

[-]
u/AvailableSleep980 1 points 2024-06-01 01:23

no, this is the first time, I wanted to check how the new GPT-4o works, it allows you to use the new version for free for several messages per day, and I found danl999’s comments interesting (but a little strange). However, I could characterize almost all the comments in r/castaneda the same way.. very interesting.. but sometimes strange :))

There's a fine line between allowing magical thinking and irrational judgments about things, and I think a lot of people on subreddits like this tend to give psychic practices too much of a magical connotation. Sometimes it seems to me that authors like Castaneda created their materials in order to help people with this kind of thinking bring their assemblage point into a more favorable and stable state, but many people seem to get confused in this. I think this is a metaphor, like many religions, although of course such a materialistic approach will probably be disapproved by many locals, this is what I actually think about all this and begin to produce all sorts of conspiracy theories and similar things

[-]
u/Ok-Assistance175 1 points 2024-06-01 01:45

Interesting take you have; ppp

[-]
u/castaneda-ModTeam 1 points 2024-06-01 03:44

The stated purpose of this subreddit is to aid in restoring the reputation of Carlos Castaneda and the knowledge he imparted, which means we are sticking to what really works, as proven by direct experience by long-practicing members. We need to make clear our intent to move away, as a community, from the mistakes others have made. Content that is at-odds with this purpose will, upon review, be removed.

[-]
u/Fullbiohack-blog 2 points 2024-06-01 05:50

Oh... it seems that they are closely monitoring not about anyone's reputation, but about ensuring that people can correctly apply the practice that Castaneda passed on to us all, doesn't it?

[-]
u/Fullbiohack-blog 1 points 2024-06-01 05:59

In general, I would like to note that your answer is rather formal and vague. What exactly in my message violates the reputation of Carlos Castaneda? I never said that his practices don't work. All I was saying was that there is a fine line between magical thinking and irrational thinking. Note that I did not say that magical thinking is bad. By irrational thinking I mean contradicting oneself for example, or other things that have nothing to do with improving the reputation of Carlos Castaneda... rather the opposite. In general, if you don’t mind, I would like to discuss this situation in more detail... if you are, of course, ready for such a dialogue :)

[-]
u/castaneda-ModTeam 1 points 2024-06-01 03:44

Self-centered promotion will not be tolerated. Neither will wasting people's time, intentionally. Such content will, upon review, be removed.

[-]
u/Fullbiohack-blog 1 points 2024-06-01 05:51

Guys, I don't understand what you mean by personal promotion, I left the only comment on this subreddit, the purpose of which was to show the person that he takes the words of a robot who doesn't even really think too much to heart, you know?

[-]
u/danl999 5 points 2024-05-31 13:27

And ask ChatGPT to analyze your own motivations.

Pointing out, you ignore that no one in here wants any money, there's no group or religion, no meetings, and there's a good 50 beating every magic man, mystick, or prophet in known history, providing all the fun details of how to do that, including pictures sometimes.

Using simple "technology" which has no "beliefs" at all.

What would be the motivation of someone to try to harm that situation?

Besides, we don't "exhibit beliefs", we DO.

Daily.

Including breaking the laws of physics once in a while.

So if it's not your cup of tea, why are you in here?

Do you go to the knitting subreddit and psychoanalyze people who sit around twiddling their fingers with string?

Or to an AI subreddit, to point out that their actions might eventually lead to the end of mankind?

Both also just technologies, like this place.

[-]
u/Fullbiohack-blog 1 points 2024-06-01 05:46

Relax, I just wanted to show that ChatGPT's responses depend on how you structure your request. What did you expect from a robot that has an idea of our reality only from the data it counted from the Internet? There's a lot of controversy around Carlos Castaneda on the Internet and ChatGPT is based on what data is loaded into it from the Internet, you know? As I said, I respect your passion, I myself have read Carlos’s books more than once. I also tried all the practices that you discuss and even achieved some success, although not such that could be interpreted as a violation of the laws of physics or something like that :)

As for violations of the laws of physics, you probably don’t understand enough about this issue to make such a statement. I mean, physics still leaves a lot of questions to this day, especially when it comes to quantum interactions and other fundamental things. So if I were you, I wouldn't assume that any of the things you do actually break any laws. We probably just don’t understand the laws well enough that determine what is possible and what is not, that’s all.

And I, too, am concerned about how people will use AI, especially given the trends in the modern world. Sorry if my comments offended you in any way, I probably should have taken care of more tolerant language

[-]
u/danl999 2 points 2024-06-01 13:30

So this bad guy came back with another id.

Schizophrenia most likely.

There's nothing for you in this subreddit, so stop coming here to piss on it.

Go make an ass of yourself elsewhere.

[-]
u/danl999 3 points 2024-06-01 13:42

If I see either of your IDs again, I'll block you. And half the posts in this subreddit will vanish.

We've gotten attacked 3 times average per week, for the last 5 years.

The mods have calluses on their fingers from pressing the "ban" button.

Attacked in part by men like you.

But there's other types. There's a list of attacker types you can read about on the wiki on the side, with a title like "Are you a Bad Player".

We don't know why the organized attacks happen, it's still a mystery to us all.

But our modern world HATES real magic.

The pretend stuff, they love.

But if it's real, you come under endless attack.

Our teacher's teacher claimed it was a class of spirits who feed on people's awareness, until all they have left is self-pity, which does indeed seem to rule the world these days.

But our experiences with spirits suggest they love real magic.

So it's hard to believe some don't.

[-]
u/castaneda-ModTeam 1 points 2024-06-01 14:48

The stated purpose of this subreddit is to aid in restoring the reputation of Carlos Castaneda and the knowledge he imparted, which means we are sticking to what really works, as proven by direct experience by long-practicing members. We need to make clear our intent to move away, as a community, from the mistakes others have made. Content that is at-odds with this purpose will, upon review, be removed.