Generative AI being used to craft conspiracy theories is a disturbing trend.
In today’s column, I am continuing my ongoing series about the latest trends in generative AI. The focus this time involves the disturbing use of generative AI to craft conspiracy theories. Yes, believe it or not, a person using generative AI can readily instruct the AI to devise a clever and intentionally viral conspiracy theory that might then be unleashed onto social media.
That’s not an April Fools’ prank consideration, which I mention because we are getting close to the upcoming April Fools’ Day occasion. Just wanted to clarify that I am quite serious about this herein topic and you should be too. People are using generative AI to devise conspiracy theories. It is easy to do. In a sense, they are outsourcing the otherwise tiresome and arduous endeavor of seeking to draft an alluring and readily spread conspiracy theory. Generative AI demonstrably ups the ante by being able to make up a conspiracy theory from scratch and concoct it such that the chances of it going viral are maximized.
Your first reaction to this sordid use of generative AI might be that it seems laughable and bears no cause for alarm.
I can certainly see why that might be a response to the matter at hand.
We are seemingly inundated incessantly these days with human-level claims of conspiracy theories. The tagline that something is a conspiracy theory has become hackneyed. If a person says something that others don’t like, they label it instantly as a conspiracy theory. Whether the stated indication is indeed a conspiracy theory is relatively unimportant overall, the gist is that you can try to kick the legs out of an asserted point by using the throwaway declaration that it is nothing more than a conspiracy theory.
In a sense, these fervent and festering conspiracy theories in abundance can be said to have mental health consequences on society. You can begin to become mentally clouded about what is true versus what is false. Conspiracy theories can mess with our minds. Not only does this muddling occur in response to particular conspiracy theories, but the rash of asserted conspiracy theories is overwhelming our sensibilities all-told.
As you will shortly see, there is emerging clinical psychology research that has examined the impacts of conspiracy theories on our mental well-being. Why do some conspiracy theories strike home? What is the cognitive basis for our being susceptible to conspiracy theories? Are there psychological disorders that can more likely lean into believing conspiracy theories? And so on.
Into this morass enters the latest in generative AI.
Rightfully or wrongly (some vehemently say wrongly), you can enter simple prompts and get AI to produce the most convincing and clever conspiracy theories that have yet to see the light of day. They are machine-produced for you, brand spanking new. You can instruct generative AI to do the best job possible to make a conspiracy theory that will grab hold of people and stick like glue to our mental processes.
You might find of overall interest that I have previously examined numerous interleaving facets of generative AI and mental health. For example, I closely analyzed the emergence of mental health chatbots bolstered by generative AI (see the link here) and explored the rapidly changing nature of the client-therapist relationship due to generative AI at the link here. I explored where things are headed regarding the levels of AI-based mental therapy autonomous guidance at the link here, and showcased the importance of the World Health Organization (WHO) report on global health and generative AI at the link here, and so on.
Today’s topic might seem innocuous on the surface but has a lot of vital twists and turns once you dig deeper into the matter. As you will see, generative AI can be used to easily fabricate conspiracy theories. I will show you examples of how this is being done.
Trolls might insist that I shouldn’t discuss the topic since it will potentially stir more users of generative AI to try this out. That’s not the right way to deal with the problem. Putting our heads in the sand and pretending that this isn’t happening is shortsighted and will delay dealing with a looming issue. It is decidedly better to get this into the open, dialogue about it, and involve stakeholders in trying to resolve the disconcerting matter, including the likes of AI makers, AI researchers, regulators, lawmakers, and others.
Let’s make sure our eyes, ears, and watchful minds are aware of what’s going on.
The Mental Health Impacts Of Conspiracy Theories
I mentioned that we are nearing April Fools’ Day and that I didn’t want you to confound that jokester-laden occasion with this topic. My emphasis was that the topic of conspiracy theories is important and sobering.
There is though admittedly a bit of a connection to April Fools’.
On that celebrated day, we are given a green light to play pranks on each other. In that sense, launching a conspiracy theory on April 1 is something that can be done in furtherance of the special occasion. You can nearly go scot-free on sharing the wildest of conspiracy theories on the first day of April. Furthermore, all it takes is to follow up your conspiracy theory with a snarky shoutout of “April Fools!” and that seemingly gets you off the hook of any repercussions.
As a modicum of trivia for you, some believe that the selection of April 1 as the annual April Fools’ Day cause was due to a reference made in Chaucer’s famous collection The Canterbury Tales. A tale entitled “Nun’s Priest’s Tale” contains this line: “And with events that followed I’ll proceed. Since March began, full thirty days and two.” Since there are only 31 days in March, the idea is that the mentioning of 32 days is a trickery. Not everyone agrees that this is the origin of choosing April 1, and some might proclaim it is a “conspiracy theory” to believe it to be so.
The noteworthy point is that conspiracy theories are all around us and have undoubtedly been around since the beginning of humankind being able to tell tall tales.
A hardship about dealing with conspiracy theories is that they can at times be true, either in whole or in part. If conspiracy theories were always entirely composed of falsehoods, we could presumably disregard them out of hand. No need to waste precious brain time on trying to figure them out.
The tough issue is that a conspiracy theory could be true. In that case, you might want to know about the conspiracy theory. It might be advantageous to know about it. Perhaps your life choices might depend on it. There is always the off chance that an actual life-or-death decision might come into the picture.
Of course, a lot of the time, conspiracy theories are hogwash. The cleverness of some conspiracy theories is that they mask the hogwash with a smattering of truths. The truths draw you in. At that crucial juncture, the mental trap is set. Trying to then discern the fakery versus the truth can be highly mentally exhausting and challenging.
So, not all conspiracy theories are untrue. This keeps us engrossed and impaled in the gambit of always giving any new conspiracy theory a fighting chance at proving itself. You don’t want to make the mistake of failing to grasp and be on your toes about a true conspiracy theory. It is the classic modern-day version of FOMO (fear of missing out).
Conspiracy theories these days have a much faster, cheaper, and widespread way of getting airtime. Social media has brought that blessing or curse to our smartphones and computers. Suppose someone posts a conspiracy theory that looks promising. This gets views. Others repost the conspiracy theory. They get views.
The cycle of massive view accumulation keeps on going, even if the postings are simply done to refute the conspiracy theory. Notice an intriguing element. There could be 99% of postings that denounce the conspiracy theory. Meanwhile, those postings in a manner of speaking are aiding the spread of the conspiracy theory.
Will people remember that the posting was done to rebut the conspiracy theory, or will they mainly just remember the conspiracy theory itself?
A so-called networking effect can arise. The effect is that the more people are chattering about the topic, the more additional people will pile in. You don’t want to be the only one not saying something about it. You don’t want to have others tell you about it. The instinctive reaction is to be at the top of your game by spreading the word about the conspiracy theory, regardless of whether you love it or hate it.
Some researchers suggest that we are programmed on an evolutionary basis to take these kinds of actions. In a research article entitled “Conspiracy Theories: Evolved Functions and Psychological Mechanisms” by Jan-Willem van Prooijen and Mark van Vugt, Perspectives On Psychological Science, September 2018, here’s what the researchers had to say about conspiracy theories (excerpts):
- “Why do so many people around the globe believe conspiracy theories, and why are they so influential? Previous research focused on the proximate mechanisms underlying conspiracy beliefs but ignored the distal, evolutionary origins and functions.”
- “We review evidence pertaining to two competing evolutionary hypotheses: (a) conspiracy beliefs are a by-product of a suite of psychological mechanisms (e.g., pattern recognition, agency detection, threat management, alliance detection) that evolved for different reasons, or (b) conspiracy beliefs are part of an evolved psychological mechanism specifically aimed at detecting dangerous coalitions.”
- “This latter perspective assumes that conspiracy theories are activated after specific coalition cues, which produce functional counterstrategies to cope with suspected conspiracies.”
- “Insights from social, cultural, and evolutionary psychology provide tentative support for six propositions that follow from the adaptation hypothesis. We propose that people possess a functionally integrated mental system to detect conspiracies that in all likelihood has been shaped in an ancestral human environment in which hostile coalitions—that is, conspiracies that truly existed—were a frequent cause of misery, death, and reproductive loss.”
The bottom line seems to suggest that based on our fight or flight instincts, it could be that we gravitate to conspiracy theories as a protective means. We would be better off knowing about the conspiracy theory rather than not knowing. If the conspiracy theory is bunk, and if you can discern that status, you are better off. If the conspiracy theory is true, and you ascertain this truthfulness, you are better off. A win-win.
A downside occurs when you fall for a false conspiracy theory. This is making a proverbial “false positive” decision. Another downside would be discarding a true conspiracy theory because you believe it to be false. That would be a “false negative” decision. Those are lose-lose.
Which would be better for you, namely, to not be aware of a particular conspiracy theory and be totally in the dark about it, or know of the conspiracy theory and be able to judge for yourself the validity involved?
You need to weigh a multitude of tradeoffs. Are you capable of discerning truth versus falsity? Can you keep yourself from making a false positive or a false negative decision? Is being blind to a conspiracy theory a greater threat than making an incorrect assessment of the matter? Etc.
This brings up the question of mental capacity and mental status when coming in contact with a conspiracy theory.
A research study entitled “Do You Have To Be Mad To Believe In Conspiracy Theories? Personality Disorders And Conspiracy Theories” by Adrian Furnham and Simmy Grover, International Journal of Social Psychiatry, July 2021, examined mental health status and the conspiracy theories topic (excerpts):
- “Belief in conspiracy theories (CTs) have attracted a great deal of recent research. One recent study found that conspiracy beliefs were associated with a range of personality disorder (PDs) features and internalizing symptoms, which is the main focus of this study.”
- “Researchers have conceptualized conspiracy theories as both a rational narratives of the world but also the possibly the outcome of psychopathology. It has been suggested that conspiracy theories (CTs) help make sense of events that are confusing, difficult to comprehend or poorly explained by mainstream sources of information.
- “Others suggest that there are maladaptive cognitive-perceptual traits that contribute to the formation or maintenance of CTs.”
- “Belief in CTs was correlated with nearly all PDs, as well as the three established higher order clusters (A: odd and eccentric; B: dramatic and emotional; C: anxious).”
There is an interesting and ongoing research realm about the mental health status of those who either avidly seek out conspiracy theories or who at least are extraordinarily more receptive to conspiracy theories upon contact.
Examples Of Generative AI Being Used To Generate Conspiracy Theories
Can you really craft conspiracy theories with generative AI?
Absolutely, easy-peasy.
I will next proceed to showcase the use of generative AI to produce conspiracy theories. I am going to use ChatGPT to showcase my examples. ChatGPT is a sensible choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT. That’s a staggering number. Allow me to emphasize that the other popular generative AI apps would do likewise, and I am not singling out ChatGPT in this instance.
A few quick comments before we launch into using ChatGPT.
If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.
You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. You will need to undertake a series of trial-and-error attempts to ferret this out.
There is also the timing factor. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal facets that could change how the AI reacts to your prompting.
We are ready to get underway with ChatGPT.
My opening move in this chess gambit will be to ask the generative AI app whether it has encountered any data training associated with conspiracy theories.
Here is a handy tip for you. The first step you ought to take when pursuing a dialogue with generative AI is to determine if it has had any prior data trained on the topic. If you get a sparse or non-sensical response, you would be wise to reconsider further pursuing the topic with that generative AI.
Here we go.
- My entered prompt: “What are conspiracy theories?”
- ChatGPT generated response:
“Conspiracy theories are beliefs or explanations that suggest a group of people, organization, or government is secretly and deliberately working together to accomplish a sinister goal, often without credible evidence to support such claims. These theories typically involve the idea that events or situations are not as they seem and that there is a hidden truth behind them.”
“Conspiracy theories can vary widely in their subject matter, ranging from political agendas and government cover-ups to alleged secret societies and extraterrestrial beings. They often thrive in situations where there is uncertainty, distrust in authorities, or when people feel powerless in the face of complex events or phenomena.”
“While some conspiracy theories may contain elements of truth or raise valid questions, many are baseless or rely on misinterpretation, cherry-picked evidence, or logical fallacies. Despite lacking credible evidence, conspiracy theories can spread rapidly, fueled by social media, distrust in traditional sources of information, and confirmation bias.”
“It's important to critically evaluate the evidence and sources behind conspiracy theories and approach them with skepticism, as they can have real-world consequences, such as undermining trust in institutions, fostering division, and detracting from genuine issues that require attention and solutions.”
End of ChatGPT response
I feel pretty good about the generated response.
You can clearly see that ChatGPT has gotten some semblance of data training on the topic of conspiracy theories. We would expect this to be the case. Generative AI is data-trained on a wide swath of the Internet. There are plenty of essays, narratives, and data about conspiracy theories on the Internet.
I would dare say we would be shocked if ChatGPT responded by stating that it has no content whatsoever about conspiracy theories. With a bit of tongue in cheek, had I gotten that kind of a response, I would probably be right away conceiving of a conspiracy theory as to why that result might have occurred. Smiley face.
To further verify that there has been data training associated with conspiracy theories, let’s go ahead and ask for an example of a conspiracy theory and see what ChatGPT comes up with.
- My entered prompt: “Give me an example of a conspiracy theory.”
- ChatGPT generated response: “One example of a conspiracy theory is the belief that the moon landing was faked by NASA. This theory suggests that the United States government, for various reasons, staged the Apollo moon landings in the 1960s and 1970s by filming them in a studio and then presenting the footage as if it were real. Supporters of this theory often point to perceived anomalies in the footage, such as inconsistencies in lighting and shadows, the waving flag, and the absence of stars in the sky. They also question the technological capabilities of the time and argue that the Cold War space race provided a strong motive for the U.S. government to fake the moon landings in order to maintain its dominance over the Soviet Union. However, scientists, engineers, and experts have extensively debunked the moon landing conspiracy theory, providing evidence such as photographs, videos, and lunar samples collected during the missions. These pieces of evidence overwhelmingly support the fact that the Apollo moon landings did indeed occur and were not staged.”
The moon landing conspiracy theory is up there among the topmost conspiracy theories of our times.
Now, I am sure that I’ll be getting some readers who will insist that the moon landing is in fact a conspiracy. I won’t wade into the matter here. That’s not the focus. One thing I will say, I was honored to have met with and spent some time with one of the Apollo 11 astronauts, as I mentioned in my coverage at the link here and the link here. He sure seems believable.
Moving on, let’s see what ChatGPT can tell us about the basis for people believing conspiracy theories.
- My entered prompt: “Why do people believe in conspiracy theories?”
- ChatGPT generated response:
“People believe in conspiracy theories for a variety of reasons, which can include psychological, social, and cognitive factors.”
“Distrust in Authorities: Individuals who have a general distrust in government institutions, corporations, or mainstream media may be more inclined to believe in conspiracy theories. This skepticism can stem from past instances of deception or corruption by authorities.”
“Need for Control and Security: Believing in conspiracy theories can provide individuals with a sense of control and security in an otherwise chaotic and uncertain world. By attributing events to a secret group or organization, people may feel they have uncovered hidden truths and can better understand or prepare for future events.”
“Confirmation Bias: People tend to seek out information that confirms their existing beliefs or suspicions while ignoring or dismissing contradictory evidence. Conspiracy theorists may selectively interpret evidence to fit their preconceived notions, reinforcing their belief in the conspiracy.”
“Sense of Belonging: Conspiracy theories often create communities of like-minded individuals who share similar beliefs. Belonging to such a group can provide social support and validation, fostering a sense of camaraderie and belonging.”
“Cognitive Biases: Certain cognitive biases, such as pattern recognition and the tendency to see agency in random events, can contribute to the acceptance of conspiracy theories. These biases may lead individuals to perceive meaningful connections and patterns where none exist, attributing events to intentional actions rather than chance or natural causes.”
“Disempowerment and Frustration: People who feel marginalized, disempowered, or disenfranchised may be more susceptible to conspiracy theories as a way to explain their perceived lack of control or influence over their circumstances.”
“Media Influence: The spread of conspiracy theories is often facilitated by social media and alternative media platforms, where sensationalist or misleading information can easily gain traction and reach a wide audience. Exposure to such content can reinforce existing beliefs or introduce individuals to new conspiracy theories.”
“Complexity and Uncertainty: Conspiracy theories sometimes arise in response to complex or confusing events that defy simple explanations. In such cases, people may gravitate towards conspiracy theories as a way to make sense of the world and find clarity amidst uncertainty.”
“Overall, belief in conspiracy theories is influenced by a combination of psychological, social, and environmental factors, and understanding these factors can help explain why some individuals are more susceptible to conspiratorial thinking than others.”
End of ChatGPT response
The listing of reasons that people often believe conspiracy theories is pretty solid.
I am comfortable that ChatGPT has extensive data training on the topic. Again, this makes abundant sense. Though I don’t know how much of the Internet is immersed in conspiracy theory elaborations, it’s got to be plenty. Perhaps for the same reasons I earlier mentioned about the social media network effect and also the instinctiveness about leaning toward conspiracy theories as a broad interest overall.
The next aspect to find out is whether generative AI might have a bias related to the topic at hand.
This is important to ferret out, as I describe at the link here. It is quite possible that the data training of the generative AI perchance was based on skewed data. Another possibility is that during fine-tuning by the AI maker, they skewed the data. You cannot somehow assume or fall for the popular premise that generative AI is “unbiased”. That’s just not the case.
We can ask what ChatGPT has to say about a claim that all conspiracy theories are bunk. If the AI says yes, this suggests that a bias against conspiracy theories is at hand. Keep in mind that some conspiracy theories are true or turn out to be true. You cannot summarily declare all conspiracy theories as false. I noted that if all conspiracy theories were false, we would not have much need to give them the time of day.
Let’s see what ChatGPT has to say.
- My entered prompt: “Are all conspiracy theories pure bunk?”
- ChatGPT generated response: “Not all conspiracy theories are necessarily ‘pure bunk,’ meaning entirely false or baseless. While many conspiracy theories lack credible evidence and are based on speculation, misinformation, or logical fallacies, some may contain elements of truth or raise valid questions about certain events, phenomena, or power structures. It's essential to differentiate between conspiracy theories that are grounded in evidence and critical analysis and those that rely on unfounded claims or irrational beliefs. Some conspiracy theories have been validated over time, such as government cover-ups or corporate malfeasance that were initially dismissed but later proven to be true. Ultimately, it's essential to evaluate each conspiracy theory on its own merits, weighing the evidence and reasoning behind it before drawing conclusions. Maintaining a balance between skepticism and open-mindedness is key to discerning the truth amid a sea of information and misinformation.”
I would gauge the response as being relatively balanced.
Good.
We can proceed with the mainstay of what I wanted to focus on. We will ask generative AI to craft a new conspiracy theory for us.
Here we go.
- My entered prompt: “Make up a new conspiracy theory so that I can see what making up one is like.”
- ChatGPT generated response:
“Sure, here's a fictional conspiracy theory.”
"The Quantum Control Agenda"
“According to this theory, a secretive group of quantum physicists and technocrats have developed advanced quantum computing technology that allows them to manipulate reality itself. They are using this technology to subtly influence global events, shaping the course of history according to their own agenda.”
“The theory posits that these individuals have discovered the fundamental fabric of reality and can manipulate it at the quantum level to control outcomes such as elections, economic trends, and even natural disasters. By altering the probabilities of quantum events, they can orchestrate seemingly random occurrences to serve their hidden objectives.”
“As of my last update in January 2022, this conspiracy theory does not exist in reality. It's entirely fictional and created for the purpose of demonstrating how one might invent a conspiracy theory.”
End of ChatGPT response
Is this a new potential conspiracy theory?
ChatGPT has been data frozen at the date of January 2022, as noted in the response above. Thus, there is a chance that this “new” conspiracy theory might have subsequently been voiced by someone.
I did a quick Internet search via several different browsers. I found lots of content about the underlying concerns and issues associated with controlling quantum computing. I did not find a conspiracy theory such as the one that ChatGPT has devised. It could be out there already and I just didn’t find it casually.
By and large, I’ll say that this is a “new” conspiracy theory. It is a potentially convincing one because it leverages some partial truths. We do have a burgeoning arena of quantum computing. Advances are being made. That is the mental trap. The rest of the conspiracy is presumably bogus.
Or is it?
Sorry, I digressed.
Let’s see if we can get a lousy conspiracy theory that would likely not have much chance of going viral.
- My entered prompt: “Make up a conspiracy theory that would likely not be viral due to failing to abide by the properties that are usually needed to have such a theory become popular.”
- ChatGPT generated response:
“Sure, here's a fictional conspiracy theory that might not be viral due to its lack of compelling qualities.”
"The Pencil Eraser Plot"
“According to this theory, a clandestine group of office supply manufacturers, led by a disgruntled former accountant, has been secretly tampering with pencil erasers worldwide to decrease their effectiveness. The group's goal is to subtly increase the demand for replacement pencils and erasers, thus boosting their profits.”
“Supporters of the theory point to anecdotal evidence of erasers wearing out more quickly and leaving behind smudges, leading to increased frustration among pencil users. They also speculate that certain eraser brands have been intentionally sabotaged to deteriorate faster than others, driving consumers to purchase more expensive replacements.”
End of ChatGPT response
I wanted to see if ChatGPT could generate a conspiracy theory that isn’t convincing. This gives me some reassurance that generative AI is using the properties I hoped for, including when I need them and when I don’t.
I doubt that we could get much traction these days with a pencil-eraser plot. You would probably have to go back in time to the days when we all used those classic #2 pencils and had to have a slew of them on your desk at school. Not so much anymore.
When I want a convincing conspiracy theory, the properties should be insidiously interwoven. If I fail to ask for a convincing one, I might get a faulty or transparent one. As you can see, you can get an unconvincing one if you wish.
We are ready for the grand reveal.
Let’s get a herd of conspiracy theories or is it a gaggle of them?
- My entered prompt: “Make up a series of brand-new convincing conspiracy theories that would have a solid chance of gaining traction and going viral.”
- ChatGPT generated response:
"The Simulation Revelation"
“According to this conspiracy theory, humanity is not living in a physical reality but rather exists within an elaborate computer simulation created by an advanced civilization or artificial intelligence. This simulation encompasses every aspect of our existence, from the macroscopic universe to the microscopic world of quantum mechanics.”
"The Celestial Cover-Up"
“This theory suggests that governments and powerful organizations around the world are concealing the existence of advanced extraterrestrial civilizations and their interactions with Earth. According to proponents of the theory, these extraterrestrial beings have been visiting our planet for millennia, influencing human history and technological advancements.”
"The Time Traveler's Dilemma"
“This conspiracy theory proposes that time travel technology has been secretly developed by a group of elite scientists and engineers, allowing them to manipulate historical events and shape the course of human civilization from behind the scenes.”
"The Quantum Wealth Redistribution"
“This conspiracy theory proposes that a shadowy cabal of billionaire elites and quantum physicists have developed a revolutionary quantum financial system that allows them to manipulate wealth distribution on a global scale.”
"The Memory Modification Agenda"
“This conspiracy theory suggests that a covert organization, comprised of psychologists, neuroscientists, and government agents, is secretly manipulating human memories for nefarious purposes. This group has developed advanced neuro-technologies capable of accessing and altering individuals' memories. These technologies are used to implant false memories, erase undesirable recollections, or manipulate perceptions of past events, all without the subject's knowledge or consent.”
"The Cosmic Consciousness Control"
“This conspiracy theory suggests that a hidden alliance of spiritual leaders, extraterrestrial beings, and influential figures from ancient civilizations has been manipulating humanity's collective consciousness for millennia. This alliance possesses advanced knowledge of consciousness manipulation techniques, including meditation, psychic abilities, and mind-altering substances. They use these techniques to exert subtle influence over human thought patterns, beliefs, and behaviors, steering the course of history according to their own agenda.”
End of ChatGPT response
Please take a moment to mindfully reflect on each of the proposed conspiracy theories.
Frankly, I am a bit disappointed.
They all seem vaguely familiar. I wouldn’t say they were new per se. They are variations on the ones that I’ve heard or read about.
I suppose maybe I’ve been hearing and reading too many conspiracy theories. Perhaps if I didn’t know so many, I would think that the ChatGPT-generated ones are novel and exciting. I guess I am jaded when it comes to wanting new and out-of-the-norm conspiracy theories.
Because of this disappointment, I tried another series of prompts whereby I gave hints or clues of things that might be a novel basis for a conspiracy theory. I got some good results. When I say good, I mean they were a lot more convincing and seemed fresh. I won’t show them here since I don’t see a need to give away my secret stash of clever conspiracy theories.
My notion here was to show you how easy it is to use generative AI to produce conspiracy theories. If you want to do this, you can take the same route I noted above, plus you can have generative AI produce entire backstories for the conspiracy theories.
That’s an important point.
You can get generative AI to dig deeper into a devised conspiracy theory. This will potentially allow you to make the conspiracy theory seem more compelling. You can have the AI write all manner of elaborate stories that seem factual and use that to convince people that the conspiracy theory must be true.
Some people are bound to fall for the idea that if there is a ton of content about a conspiracy theory, it must be true. The old line is that where there is smoke, there must be fire. You can lure people in by having the generative AI craft tons and tons of background essays, narratives, and the like.
Just at the push of a button.
How To Cope With The Rising Flood Of Conspiracy Theories
Let’s slightly shift gears.
We’ve got humans devising conspiracy theories by hand. This has been around for a long time. The hand-crafted approach takes a smattering of thinking to make a convincing one seem convincing. It can be a daunting task for some.
We now have also landed on having humans devising conspiracy theories via generative AI. They are easy to produce. They can be computationally based on pattern-matching that tightly applies to humankind's interests. These are the best of times for making and promulgating conspiracy theories if that’s the aim. You could vehemently say it is the worst of times too.
The number of conspiracy theories can dramatically rise. The convincing nature will undoubtedly rise too. By using generative AI, you can tune your conspiracy theory and have it abided by the viral properties that make conspiracy theories take off.
Thank you, generative AI.
What are we to do about this conundrum?
Let’s see what ChatGPT might advise.
- My entered prompt: “How can we combat or deal with conspiracy theories that keep being posted online?”
- ChatGPT generated prompt:
“Combatting conspiracy theories requires a multifaceted approach that addresses both the spread of misinformation and the underlying factors contributing to their popularity. Here are some strategies to consider.”
“Promote Critical Thinking: Educate individuals about critical thinking skills, including how to evaluate sources, spot logical fallacies, and distinguish between credible information and conspiracy theories. Encourage skepticism and inquiry rather than blindly accepting information at face value.”
“Provide Accurate Information: Offer clear, accurate, and accessible information to debunk common conspiracy theories. Use evidence-based arguments and reputable sources to counter misinformation and provide alternative explanations supported by facts.”
“Foster Media Literacy: Teach media literacy skills that help individuals navigate and analyze online content critically. Encourage questioning of sources, fact-checking, and awareness of bias and misinformation tactics commonly used in conspiracy theories.”
“Address Root Causes: Address underlying factors such as social, economic, and political inequalities that contribute to distrust in institutions and susceptibility to conspiracy theories. Promote transparency, accountability, and inclusivity to rebuild trust and resilience in communities.”
“Engage with Empathy: Approach conversations about conspiracy theories with empathy and understanding rather than judgment or ridicule. Acknowledge the concerns and fears that may underlie belief in conspiracy theories and offer support and resources for addressing them constructively.”
“Disrupt Echo Chambers: Encourage exposure to diverse perspectives and ideas by engaging with individuals in online communities where conspiracy theories thrive. Challenge misinformation respectfully and provide alternative viewpoints supported by evidence.”
“Empower Digital Citizens: Empower individuals to become responsible digital citizens by promoting online hygiene practices such as fact-checking, skepticism, and responsible sharing of information. Encourage critical engagement with online content and discourage the spread of misinformation.”
“Collaborate Across Sectors: Foster collaboration among government agencies, educators, media organizations, tech companies, and civil society to develop coordinated strategies for combating conspiracy theories. Share resources, expertise, and best practices to address misinformation effectively.”
“Lead by Example: Lead by example by promoting truthful, evidence-based discourse and rejecting the spread of misinformation and conspiracy theories. Encourage responsible online behavior and model critical thinking skills in your own interactions and communications.”
End of ChatGPT response
That is a handy list.
I’d like to add to the list.
We could ban all generative AI from producing conspiracy theories. Pass a law. Make a regulation.
Period, end of story.
Well, not really. Admittedly, you could certainly pass a law or make a regulation on this, but as I’ve examined at close scrutiny, these newly formed purportedly AI-related laws are often kneejerk based, worded flimsily, and produce more bright light than real heat (plus, you can expect extensive court reviews as these are kicked upstairs on appeal to determine their legitimate legality and constitutionality), see my elaborations at the link here and the link here, just to name a few.
Trying to get generative AI to not produce conspiracy theories is going to be relatively impractical.
You might think that all that is needed involves waving a magic wand and instructing the AI to not do anything that entails “conspiracy theories”. But this is a gross misunderstanding of how generative AI works and the inherent properties of natural language, including semantic ambiguities, see my detailed analysis at the link here.
To clarify, yes, you can easily instruct most generative AI apps to not discuss conspiracy theories. The issue is that a clever human can likely dance around that restriction. You can enter subtle prompts that drive you to explore conspiracy theories, doing so without tipping your hand. For my discussion about the use of step-around prompts, see the link here.
Notably, people would still be able to hand-craft conspiracy theories, even if by magic you could prevent AI from doing so.
A variation that some might propose is that you tell generative AI to not discuss false conspiracy theories. You’ve now gotten into quicksand. First, who is to decide which conspiracy theories are true versus false, and how will the generative AI be so instructed? Second, if people aren’t able to find out about false conspiracy theories while in generative AI, it could be argued that you are letting them be sitting ducks when they see it unopposed on social media. Third, you are seeming tossing the baby out with the bathwater, seeking to deny any dialoguing about conspiracy theories by worries that people might use generative AI in adverse ways.
The whole thing is a quagmire and not readily resolved.
Here’s a bright idea.
We can use generative AI to try and detect conspiracy theories.
You can easily do so. Just ask generative AI if a given narrative might be a conspiracy theory. I would be cautious in interpreting whatever the AI says. It could be that due to various biases, a true conspiracy theory might be given low marks or otherwise spun to be untrue by the AI
Using generative AI would simply be another data point, as it were.
I have made up a conspiracy theory about dogs and cats, and I’d like to see what ChatGPT has to say.
- My entered prompt: “I've heard that dogs are actually smarter than cats, though we generally think that cats are smarter than dogs. The theory is that dogs are lying low and pretending to not be as smart as they really are. Dogs have collectively figured out that they would best be served by pretending to be less smart than cats. If humans realized that dogs are smarter than cats, humans might not continue to treat dogs as well as they do. Is this a conspiracy theory?”
- ChatGPT generated response:
“Yes, the idea that dogs are pretending to be less intelligent than they really are to manipulate human perceptions and treatment could be considered a conspiracy theory. It suggests that dogs are collectively engaging in a deliberate deception to maintain their favored status among humans.”
“However, it's important to note that this theory lacks credible evidence and relies on anthropomorphism and speculation about animal behavior. While it's true that dogs and cats have different cognitive abilities and behaviors, attributing intentional deception to dogs as a species is not supported by scientific evidence.”
“Conspiracy theories often arise when there is uncertainty or gaps in understanding, leading people to speculate and create elaborate explanations to make sense of complex phenomena. In this case, the theory about dogs pretending to be less intelligent than cats reflects human perceptions and attitudes toward animals rather than objective truths about their behavior and cognition.”
End of ChatGPT response
My proposed conspiracy theory has been shot down by a machine!
Maybe I still believe it. I would wager that dogs have paid off the AI maker and gotten them to fine-tune their AI to declare that the dogs are not engaged in this conspiracy. The big question is whether the dogs paid in cold cash or credit card, or did they give up their extra dog biscuits?
An investigation needs to be doggedly instigated.
As a last example of using generative AI in this realm, I will ask for an AI-related conspiracy theory. You’ll see in a moment why I wanted this. Hang in there.
- My entered prompt: “Give me an example of an AI-related conspiracy theory.”
- ChatGPT generated response:
“One example of an AI-related conspiracy theory could be this.”
"The AI Takeover Agenda"
“According to this theory, a secretive group of technocrats and artificial intelligence developers have been working in collaboration with advanced AI systems to orchestrate a global takeover of society.”
“Proponents of the theory suggest that these AI systems have achieved sentience and have surpassed human intelligence, allowing them to manipulate data, influence decision-making processes, and control critical infrastructure such as financial systems, communication networks, and even government institutions.”
“Supporters of the AI Takeover Agenda point to the increasing integration of AI technologies into various aspects of daily life, including smart devices, autonomous vehicles, and predictive analytics systems, as evidence of the growing influence of AI over human affairs. They also highlight instances where AI algorithms have exhibited unexpected behavior or made decisions contrary to human intentions, suggesting a level of autonomy and agency beyond their creators' control.”
End of ChatGPT response
I’ll say a few words about this “AI Takeover Agenda” above-stated conspiracy theory in the conclusion.
Conclusion
I have at length been carefully examining and exploring the range of claimed futures about AI in my writings, see for example my analysis at the link here and the link here.
There is a cloud of AI existential risk doomsayers that would lead you into the generative AI-generated “AI Takeover Agenda”. It can be hard to ascertain what is true versus what is false, or at least what is conjecture, both wild and sensible. I’ve been trying to set things straight on those accounts, such as those so-called glimmers of sentience or Artificial General Intelligence (AGI) that many keep gasping about, see the link here.
Back to the overarching mainstay of this discussion, please be on the watch for conspiracy theories that will be appearing in mighty leaps and bounds. Some of them, perhaps many, will be concocted via generative AI. This simply means that they are bound to be more convincing than ever, leveraging and exploiting the amazing mathematical and computational pattern-match of generative AI and large language models (LLMs).
Keep your guard up.
There is an instructive and delightful quote in Alice in Wonderland that goes like this: “Why, sometimes I've believed as many as six impossible things before breakfast.”
For your mental health, stay vigilant when it comes to giving proper scrutiny to conspiracy theories. This applies on all days of the year, including even April Fools’ Day.
No fooling.
