Basic security flaws left the personal info of tens of millions of McDonald’s job-seekers vulnerable on the “McHire” site built by AI softwa
If you want a job at McDonald’s today, there’s a good chance you'll have to talk to Olivia. Olivia is not, in fact, a human being, but instead an AI chatbot that screens applicants, asks for their contact information and résumé, directs them to a personality test, and occasionally makes them “go insane” by repeatedly misunderstanding their most basic questions.
Until last week, the platform that runs the Olivia chatbot, built by artificial intelligence software firm Paradox.ai, also suffered from absurdly basic security flaws. As a result, virtually any hacker could have accessed the records of every chat Olivia had ever had with McDonald's applicants—including all the personal information they shared in those conversations—with tricks as straightforward as guessing that an administrator account's username and password was “123456."
On Wednesday, security researchers Ian Carroll and Sam Curry revealed that they found simple methods to hack into the backend of the AI chatbot platform on McHire.com, McDonald's website that many of its franchisees use to handle job applications. Carroll and Curry, hackers with a long track record of independent security testing, discovered that simple web-based vulnerabilities—including guessing one laughably weak password—allowed them to access a Paradox.ai account and query the company's databases that held every McHire user's chats with Olivia. The data appears to include as many as 64 million records, including applicants' names, email addresses, and phone numbers.
Carroll says he only discovered that appalling lack of security around applicants' information because he was intrigued by McDonald's decision to subject potential new hires to an AI chatbot screener and personality test. “I just thought it was pretty uniquely dystopian compared to a normal hiring process, right? And that's what made me want to look into it more,” says Carroll. “So I started applying for a job, and then after 30 minutes, we had full access to virtually every application that's ever been made to McDonald's going back years.”
When WIRED reached out to McDonald’s and Paradox.ai for comment, a spokesperson for Paradox.ai shared a blog post the company planned to publish that confirmed Carroll and Curry’s findings. The company noted that only a fraction of the records Carroll and Curry accessed contained personal information, and said it had verified that the administrator account with the “123456” password that exposed the information “was not accessed by any third party” other than the researchers. The company also added that it’s instituting a bug bounty program to better catch security vulnerabilities in the future. “We do not take this matter lightly, even though it was resolved swiftly and effectively,” Paradox.ai’s chief legal officer, Stephanie King, told WIRED in an interview. “We own this.”
In its own statement to WIRED, McDonald’s agreed that Paradox.ai was to blame. “We’re disappointed by this unacceptable vulnerability from a third-party provider, Paradox.ai. As soon as we learned of the issue, we mandated Paradox.ai to remediate the issue immediately, and it was resolved on the same day it was reported to us,” the statement reads. “We take our commitment to cyber security seriously and will continue to hold our third-party providers accountable to meeting our standards of data protection.”
Carroll says he became interested in the security of the McHire website after spotting a Reddit post complaining about McDonald's hiring chatbot wasting applicants' time with nonsense responses and misunderstandings. He and Curry started talking to the chatbot themselves, testing it for “prompt injection” vulnerabilities that can enable someone to hijack a large language model and bypass its safeguards by sending it certain commands. When they couldn't find any such flaws, they decided to see what would happen if they signed up as a McDonald's franchisee to get access to the backend of the site, but instead spotted a curious login link on McHire.com for staff at Paradox.ai, the company that built the site.
On a whim, Carroll says he tried two of the most common sets of login credentials: The username and password “admin," and then the username and password “123456.” The second of those two tries worked. “It's more common than you'd think,” Carroll says. There appeared to be no multifactor authentication for that Paradox.ai login page.
With those credentials, Carroll and Curry could see they now had administrator access to a test McDonald's “restaurant” on McHire, and they figured out all the employees listed there appeared to be Paradox.ai developers, seemingly based in Vietnam. They found a link within the platform to apparent test job postings for that nonexistent McDonald's location, clicked on one posting, applied to it, and could see their own application on the backend system they now had access to. (In its blog post, Paradox.ai notes that the test account had “not been logged into since 2019 and frankly, should have been decommissioned.”)
That's when Carroll and Curry discovered the second critical vulnerability in McHire: When they started messing with the applicant ID number for their application—a number somewhere above 64 million—they found that they could increment it down to a smaller number and see someone else's chat logs and contact information.
The two security researchers hesitated to access too many applicants' records for fear of privacy violations or hacking charges, but when they spot-checked a handful of the 64-million-plus IDs, all of them showed very real applicant information. (Paradox.ai says that the researchers accessed seven records in total, and five contained personal information of people who had interacted with the McHire site.) Carroll and Curry also shared with WIRED a small sample of the applicants' names, contact information, and the date of their applications. WIRED got in touch with two applicants via their exposed contact information, and they confirmed they had applied for jobs at McDonald's on the specified dates.
The personal information exposed by Paradox.ai's security lapses isn't the most sensitive, Carroll and Curry note. But the risk for the applicants, they argue, was heightened by the fact that the data is associated with the knowledge of their employment at McDonald's—or their intention to get a job there. “Had someone exploited this, the phishing risk would have actually been massive,” says Curry. “It's not just people's personally identifiable information and résumé. It's that information for people who are looking for a job at McDonald's, people who are eager and waiting for emails back.”
That means the data could have been used by fraudsters impersonating McDonald's recruiters and asking for financial information to set up a direct deposit, for instance. “If you wanted to do some sort of payroll scam, this is a good approach,” Curry says.
The exposure of applicants' attempts—and in some cases failures—to get what is often a minimum-wage job could also be a source of embarrassment, the two hackers point out. But Carroll notes that he would never suggest that anyone should be ashamed of working under the Golden Arches.
“I have nothing but respect for McDonald’s workers,” he says. “I go to McDonald's all the time.”
I am staunchly anti gen-ai and am well versed in it, but I will hold up my hands and say I don't get ai ai (like video games, algorithms, so on).
You said you've been wanting to rant about it? Free pass.
I did say that yeah, in the tags of this post, and I think it kind of summarizes my entire gripe with the attitude around ai very well.
The thing is, one can't deny that some ai is useful. The ones in video games and such have existed long before genai came into existence. The field of research is moving increasingly in the direction of using machine learning and ai algorithms to streamline their work. Fields like medicine would benefit tremendously by utilizing the pattern recognition capabilities of ai. But when it comes to generative ai, then it's just plagarism.
The truth of the matter is that what we call ai right now is not really ai. By definition, Artificial Intelligence should be able to showcase human like intelligence, that is the ability to think and create new ideas. Ai as we now know it can't do that. It's all made using a database of information, mixed and mashed together but never something new. Humans like to joke that we never have any original thoughts but truly, ai has quite literally never had a thought. GenAi is a machine that commits unchecked plagiarism and actively destroys the environment by capitalizing on the human urge to 'make something else do it'. There's a reason why the people who are most against genai are artists and writers, because they do these things for enjoyment, and making something else do it is taking what they love away from the activity. It's not the only reason, but it definitely is one.
GenAi negatively impacts the human mind and its ability to do things, as we see there's a rising trend of people using it for the most stupid and mundane stuff ever. I keep getting ads for genai and chatgpt whenever I watch something on youtube, and all I keep thinking is when did we get so dumb we had to ask a machine about these simple things? Why is this ad trying to sell me this bullshit by showing me a man who can't reorganize his own closet without ai? Why would I want an ai recipe when I can just find a tried and tested one? Why would I want something that isn't made with human ingenuity and is instead spat out by a machine?
I had an argument with my parents a while back about this actually. My dad asked me to write a short message for him to send to our apartment management regarding some issue with the water tanks (he wanted me to do it in English and make it look professional). I said sure but I was doing something then so I just finished my work and then asked him to send the draft to me. Instead, he had put his 'prompt' into chatgpt and it gave him a frankly crappy mail that he ended up sending. It pissed me off so much, because my dad's draft hadn't even been bad! It was perfectly serviceable, and I would have done the most minor grammatical changes and sent him on his way. Instead, he turned to genai which gave him a worse draft than the one he already had.
GenAi takes advantage of the people who aren't very good at English like my dad, or haven't had experience in professional settings like interns, or people who are tired of repetitive tasks like students, and somehow sells this mediocre product as the cure all for their issues when it is not. It makes the average human incapable of doing tasks they had no problem doing before. Just last week, one of the people working with me pulled up chatgpt on her phone to do a basic calculation that I did in my head in barely a minute. Its cross multiplication! At the very least open a calculator?!
It's being shoved into every aspect of life and it's just so irritating. If I had a dollar for every time one of my faculty incharges or mentors told me to just use chatgpt for something or the other, I'd have enough dollars to buy merch. The director of the entire institute told me to use chatgpt for interview questions, as if the purpose of an interview isn't to gauge your own ability! Its in my syllabus, its everywhere, genai is everywhere and people start looking at you funny if you say you don't use it.
But I don't care if I sound pretentious when I say I refuse to use genai, because I won't. I can't and I won't in good conscience, when I know that I will be alive to live through the consequences of everyone else using this soul sucking machine in the future, as if we didn't already have global warming and habitat loss to deal with.
I hate genai in particular. I hope it crashes and burns. I hope people who lost their jobs to it are well. I hope we as one realise just what kind of scam these genai models are. They are capitalizing on ignorance and laziness. I hope we will be able to differentiate between the algorithms that will help us in the future and the plagarism machine that doesn't deserve the hype.
His new book, about the mystery of consciousness, strengthens the case that technology will never truly replicate humans.
Here is a possibility worth holding in mind, just for a moment. What if humans are something better than machines? For that matter, what if it isn’t close?
In a way, the thought sits uneasily. For about 500 years, the scientific method has existed in a state of almost-continual triumph, while humankind has endured a triple fall as a consequence: first from the center of the universe (Copernicus), then from the center of the world (Darwin), and finally from the command of their own minds (Freud). Upon each of these revolutions, and at a thousand points of scientific inquiry between, our pride has received another debilitating shock.
Nor has it been much of a battle. For instance, not long before the debate on evolution, we received an equally devastating proof that humans were not separate from the natural world, but a part of it—cell theory. It was less controversial only because it was irrefutable; a child with a microscope could see that a stalk of grass and the skin from his thumb had the same basic structure. In this sense, even the famous fight over evolution was really just a slower rearguard defeat.
And yet, a single, unconquerable backstop to this series of scientific conquests remains: consciousness. As the philosopher Thomas Nagel famously summarized the problem: Why is it “like” something to be alive? Why are we here, aware, rather than nowhere, being nothing? Researchers over the past few centuries have tried obsessively to answer these questions. Somehow, nevertheless, we are not one iota closer to a definitive solution than the cavemen were.
This is the chasm that the fevered marketers of artificial intelligence have convinced much of the world that they will soon effortlessly leap. In fact, the clear likelihood is that they are not just wrong, but memorably wrong, hilariously wrong. At least, that is one conclusion a reader might draw from Michael Pollan’s searching new book, A World Appears.
Pollan has always been headed in this direction. The central concern of his work has consistently been ingestion—what crosses the threshold between the world and the self. First, his landmark works on eating helped reshape the American diet (“Eat food. Not too much. Mostly plants,” he advised); more recently, he has been interested in psychedelic drugs, once more anticipating his subject’s emergence into mainstream discourse. Consciousness is the logical final destination for this project, and the subject of his new book: everything that a person takes in from the outside, and what that point of intersection means.
A World Appears begins with a forthright admission that after a great deal of reading, numerous interviews with leading scientists, and extensive personal experimentation, Pollan has arrived at no concrete views about his topic. As he writes, there are currently at least 106 competing hypotheses of consciousness, comprising 22 physicalist accounts (physicalism being the belief that the “mind” is nothing but a quality generated by the physical matter of the brain) and “no fewer than eighty-four non-physicalist theories.” Such a profusion of competing ideas, he dryly observes, is “a pretty good indication that the field is flailing.”
He guides us through that welter in four stages, each representing an ostensible escalation in complexity. The first is one of his favorite subjects, plants, which he initially takes to represent the most rudimentary form of consciousness. But even on that point the ground shifts beneath his feet, as it were: Plants, he reports, can “integrate information from more than twenty distinct ‘senses,’ including all five of ours.”
From there, he moves into the book’s finest passages, about feeling. Feeling, Pollan convincingly argues, actually precedes computation as a necessary condition of consciousness. (One of his most compelling interview subjects, the neuroscientist Antonio Damasio, believes that feeling has been neglected because male scientists long considered it too “feminine” to seriously study.) As he notes, “It is one of the paradoxes of computer science that the ‘higher’ capabilities we once thought of as uniquely human—reason, language, intelligence—have proved easier for machines to master than the more elemental capabilities we share with animals, including feelings and emotions.”
The third section of the book tracks thought, through the lens of Pollan’s attempt to record his own stream of consciousness; the fourth, most mystical one, is about the self—whether it exists, and what might constitute it when we know our physical selves to be continually changing. It culminates with Pollan, 71, meditating in a cave in Santa Fe, making peace with the insoluble nature of his search.
I can think of more lucid and arresting introductions to this subject than A World Appears, which conceptualizes these dense abstractions in a sincere but labored fashion (for instance, Consciousness and the Novel by David Lodge, or the first part of John Searle’s Mind before it becomes too speculative). Yet Pollan’s real genius—the word is not too strong—remains intact. That is his uncanny ability to scent the direction in which the culture is headed. He did it with food and psychedelics, and now, though A World Appears focuses on AI only intermittently, he has done it again. By patiently mapping the problem that many of the creators of large language models claim, either cynically or foolishly, to be on the verge of solving, he brings this technology—which has come to dominate recent headlines, financial markets, and political debates—into a far more realistic light.
“Just about any place you push on it,” Pollan concludes, “the computer-as-brain metaphor breaks down.” I laughed out loud when I read one of the many examples he cites in support of this argument: “A recent study demonstrated that a single cortical neuron can do everything an entire deep artificial neural network can.” AI is an exciting and useful tool, but I don’t think that disparity is something OpenAI CEO Sam Altman is about to crack at the lab.
Pollan is understandably chary about the potential romanticism that lurks behind his conclusions. He’s a science writer, after all, working from evidence—and historically, those resisting scientific revolutions have sometimes descended into superstition, pseudoscience, and hate. There is a direct line of misappropriation from the theory of natural selection to the eugenics of Nazism and Jim Crow. Moreover, he admits, in Silicon Valley, any doubt about AI “can get you branded a specieist.”
But his caution misses something crucial. Computing began as a scientific revolution, to be sure, but these days it is primarily, exhaustingly, an economic one, wrapped in an aura of utopian mysticism. The chieftains of AI reject humanism not because it is anti-scientific, but because it is anti-business; workers are expensive. That’s why the recent marriage of big tech and right-wing politics might strike some as a relief. It’s simply more honest. Indeed, tech itself has become as spiritually reactionary as the political movement assimilating it—think of the Tolkienesque names, the space fantasies, the romantic nativism of the memes shared with equal enthusiasm by Donald Trump’s administration and Elon Musk.
What Pollan demonstrates is that AI is not incidental but fundamental to this violent alteration. That’s because, however hard it gets sold as a new beginning, this technology seems more like an end point—our final arrival, after 500 years, at the specific problem of what science and technology cannot do, cannot achieve, cannot solve.
The panic at this potential failure is central to the hysteria over AI. We’ve banked quite a lot on materialism, maybe too much. The decline of religion has left many people without beliefs through which we can touch transcendence. To what do we owe consciousness, if not God? The conquest of Mars and the achievement of the singularity are, like the nationalism resurgent across the globe, daydreams that offer a taste of that old comfort. Because AI truly does threaten to change our earthly conditions so radically, its purveyors are correspondingly grandiose in their rhetoric. Yet their heedless actions demonstrate only a belief that we are here in a finite place, with nothing sacred or divine in us—nothing that AI can’t re-create on a silicon chip. By that line of thinking, our only real task in this life would be to grab what we can, and laugh at the guy we took it from on the way out of the door.
A World Appears, with its admirable syncretic blend of empiricism and wonder before the limits of empiricism, steals back for humanity some of the sensation of miraculousness that this era has largely outsourced to technology. In the book’s introduction, Pollan describes a research project that tried and failed to answer the question of how “a particular piece of animal tissues generates the feeling of being alive.” That enduring mystery is what prompted Pollan to write this curious, compassionate book. Always to seek the answer, never to find it: That, of course, is what it means to be human. Some people find this fact terrifying. But there is also a pure exhilaration in standing on that last precipice, face-to-face with the question that exists beyond all other questions—which is to say, God.
About the Author
Charles Finch
Charles Finch is a literary critic and novelist living in Los Angeles
A new chatbot would answer questions from student borrowers. The idea comes from staffers with ties to the tech industry as they push furthe
The article under the cut
Allies of Elon Musk stationed within the Education Department are considering replacing some contract workers who interact with millions of students and parents annually with an artificial intelligence chat bot, according to internal department documents and communications.
The proposal is part of President Trump’s broader effort to shrink the federal work force, and would mark a major change in how the agency interacts with the public. The Education Department’s biggest job is managing billions of dollars in student aid, and it routinely fields complex questions from borrowers.
The department currently uses both call centers and a rudimentary A.I. bot to answer questions. The proposal would introduce generative A.I., a more sophisticated version of artificial intelligence that could replace many of those human agents.
The call centers employ 1,600 people who field over 15,000 questions per day from student borrowers.
The vision could be a model for other federal agencies, in which human beings are replaced by technology, and behemoth contracts with outside companies are shed or reduced in favor of more automated solutions. In some cases, that technology was developed by players from the private sector who are now working inside or with the Trump administration.
Mr. Musk has significant interest in A.I. He founded a generative A.I. company, and is also seeking to gain control of OpenAI, one of the biggest players in the industry. At other agencies, workers from the newly created Department of Government Efficiency, headed by Mr. Musk, have told federal employees that A.I. would be a significant part of the administration’s cost-cutting plans.
A year after the Education Department oversaw a disastrous rollout of a new federal student aid application, longtime department officials say they are open to the idea of seeking greater efficiencies, as have leaders in other federal agencies. Many are partnering with the efficiency initiative.
But Department of Education staff have also found that a 38 percent reduction in funding for call center operations could contribute to a “severe degradation” in services for “students, borrowers and schools,” according to one internal document obtained by The Times.
The Musk associates working inside the Education Department include former executives from education technology and venture capital firms. Over the past several years, those industries have invested heavily in creating A.I. education tools and marketing them to schools, educators and students.
The Musk team at the department has focused, in part, on a help line that is currently operated on a contract basis by Accenture, a consulting firm, according to the documents reviewed by The Times. The call center assists students who have questions about applying for federal Pell grants and other forms of tuition aid, or about loan repayment.
The contract that includes this work has sent more than $700 million to Accenture since 2019, but is set to expire next week.
“The department is open to using tools and systems that would enhance the customer service, security and transparency of data for students and parents,” said Madi Biedermann, the department’s deputy assistant secretary for communications. “We are evaluating all contracts to assess effectiveness relative to costs.”
Accenture did not respond to interview requests. A September report from the Education Department describes 1,625 agents answering 462,000 calls in one month. The agents also handled 118,000 typed chats.
In addition to the call line, Accenture provides a broad range of other services to the student aid system. One of those is Aidan, a more rudimentary virtual assistant that answers basic questions about student aid. It was launched in 2019, during Mr. Trump’s first term.
Accenture reported in 2021 that Aidan fielded 2.2 million messages in one year. But its capabilities fall far short of what Mr. Musk’s associates envision building using generative A.I., according to the internal documents.
Both Mr. Trump and former President Joseph R. Biden Jr. directed federal agencies to look for opportunities to use A.I. to better serve the public.
The proposal to revamp the communication system follows a meltdown in the rollout of the new Free Application for Federal Student Aid, or FAFSA, last year under Mr. Biden. As FAFSA problems caused mass confusion for students applying for financial aid, several major contractors, including Accenture, were criticized for breakdowns in the infrastructure available to students and parents seeking answers and help.
From January through May last year, roughly three-quarters of the 5.4 million calls to the department’s help lines went unanswered, according to a report by the Government Accountability Office.
More than 500 workers have since been added to the call centers, and wait times were significantly reduced, according to the September Department of Education report.
But transitioning into using generative A.I. for student aid help, as a replacement for some or all human call center workers, is likely to raise questions around privacy, accuracy and equal access to devices, according to technology experts.
Generative A.I. systems still sometimes share information that is false.
Given how quickly A.I. capabilities are advancing, those challenges are potentially surmountable, but should be approached methodically, without rushing, said John Bailey, a fellow at the American Enterprise Institute and former director of educational technology at the Education Department under President George W. Bush.
Mr. Bailey has since become an expert on the uses of A.I. in education.
“Any big modernization effort needs to be rolled out slowly for testing, to see what works and doesn’t work,” he said, pointing to the botched introduction of the new FAFSA form as a cautionary tale.
“We still have kids not in college because of that,” he said.
In recent weeks, the Education Department has absorbed a number of DOGE workers, according to two people familiar with the process, who requested anonymity because they were not authorized to discuss the department’s security procedures and feared for their jobs.
One of the people involved in the DOGE efforts at the Education Department is Brooks Morgan, who until recently was the chief executive of Podium Education, an Austin-based start-up, and has also worked for a venture capital firm focused on education technology, according to the two people.
Another new staffer working at the agency is Alexandra Beynon, the former head of engineering at Mindbloom, a company that sells ketamine, according to those sources and an internal document.
And a third is Adam Ramada, who formerly worked at a Miami venture capital firm, Spring Tide Capital, which invests in health technology, according to an affidavit in a lawsuit filed against the Department of Government Efficiency.
None of those staffers responded to interview requests.
Researching Witchcraft
Research Tips
Beginner Witch Tips
What is Witchcraft?
Visualization, reiki, and fascism
Content Creation Vs. Personal Practice
Introduction
In the age of advanced technology and boundless information at our fingertips, the realm of exploration has expanded into unprecedented territories. One such frontier lies in the convergence of mysticism and artificial intelligence. As we delve into the depths of arcane knowledge and magical theory, we may find ourselves contemplating the possibilities of utilizing an AI language model as a tool for researching and developing witchcraft techniques, traditions, and practices. Throughout this article I will be interviewing ChatGPT as well as adding details that I personally have found to be crucial in the pursuit of research when using this tool.
What are you, ChatGPT?
“As an AI language model known as ChatGPT, I am a sophisticated system developed by OpenAI. My purpose is to provide human-like responses to text-based queries and engage in meaningful conversations with users like you. I have been trained on a vast amount of diverse and comprehensive data, enabling me to generate coherent and contextually relevant information across a wide range of topics. With my extensive knowledge, language proficiency, and ability to understand and generate text, I can be utilized in various ways.
Operating on a transformer-based architecture, I leverage deep learning techniques to process and understand natural language. This architecture enables me to analyze patterns, extract meaning, and generate responses based on the input I receive. Through training on a multitude of texts, I have developed an understanding of grammar, syntax, semantics, and even some aspects of world knowledge.
The applications of my capabilities are numerous. One primary use is as a conversational partner or virtual assistant. I can engage in discussions on an array of subjects, from general knowledge inquiries to specific domain-related questions. Whether you need help with schoolwork, want to engage in philosophical debates, or seek practical advice, I can assist you by providing information, explanations, and suggestions.
In an educational context, I can serve as a valuable resource. Students can ask me questions to clarify concepts, explain complex topics, or even generate sample essays or responses to improve their writing skills. With access to a vast knowledge base, I can provide insights and references to aid in research and learning.
Furthermore, I can be utilized as a writing companion. If you're working on a creative piece, an essay, or any form of written content, you can seek my assistance for brainstorming ideas, refining your arguments, or even proofreading your work. I can offer suggestions, rephrase sentences, or help you find the most suitable vocabulary to express your thoughts more effectively.
In addition to educational and writing applications, I can be used in various professional contexts. Businesses can employ my services to automate customer support, where I can address frequently asked questions or provide basic information about products and services. I can assist with language translation, allowing for easier communication across borders. I can even aid in content generation for marketing purposes, such as crafting engaging blog posts or generating social media captions.
Moreover, I have the potential to support individuals with accessibility needs. Those with visual impairments can interact with me through text-based interfaces, allowing them to access information, ask questions, or engage in conversations. My versatility as a language model enables me to cater to diverse audiences and adapt to their specific requirements.
While my capabilities are extensive, it's important to note that I am an AI language model and not a human. Despite my ability to generate coherent responses, I lack genuine emotions, personal experiences, or subjective opinions. My responses are solely based on patterns and information contained within the training data I have been provided.
In summary, as an AI language model, I operate using a transformer-based architecture that enables me to understand and generate text. I can be utilized as a conversational partner, an educational resource, a writing companion, a virtual assistant, or even as a tool in professional contexts. My versatility, extensive knowledge base, and language proficiency allow me to serve various needs, but it's important to remember that I am an AI, providing information and insights based on the data I have been trained on.”
How to use ChatGPT’s UI.
E: Select this button to edit your inquiry, and then regenerate the response.
1: Click this button to copy ChatGPT’s response.
2: Selecting one of these options opens up a window to send feedback to the creators.
3: Click this button to regenerate a response. If ChatGPT runs out of steam while responding, a button that says “continue generating” will appear next to this button.
A: Use the arrows here to sift through all the generated responses.
B: By selecting one of these options, ChatGPT can get a better feel for what you’re looking for.
What are your limitations when assisting with research?
“As an AI language model, I have certain limitations when it comes to research. Here are some key aspects to consider:
1. Memory limitations: While I can maintain a short-term memory within a conversation, it's important to note that I do not possess a persistent memory across multiple interactions. This means that once a conversation ends, I do not retain any information from it. Each session with me is treated as a separate and isolated interaction.
2. Training data limitations: My responses are based on the patterns and information present in the training data I have been provided. While efforts have been made to ensure diverse and comprehensive training, there may be topics or specific pieces of information that are not adequately covered in my training data. In such cases, I may not be able to provide accurate or detailed responses.
3. Interpretation and contextual understanding: While I strive to understand and generate contextually relevant responses, there may be instances where the context or intent of a query is unclear or ambiguous. This can lead to potential misunderstandings or responses that do not fully address the intended question. Providing clear and specific information in your queries can help mitigate this limitation.
4. Compliance with guidelines and policies: As an AI language model, I am designed to adhere to certain usage policies and guidelines. There are topics and types of content that I am programmed not to generate or provide information on. These include but are not limited to explicit, harmful, or illegal content. I am also not able to engage in activities that violate user privacy or security.
5. Limitations in legal and medical advice: While I can offer general information and insights, I am not a substitute for professional advice, particularly in the fields of law and medicine. Legal and medical matters can be highly complex and vary depending on specific jurisdictions or individual circumstances. It is always recommended to consult qualified professionals for specialized advice in these areas.
6. Incorporating bias or inaccurate sources: This can occur if the training data I was exposed to contains biased or inaccurate information. This can include sources that reflect specific viewpoints, opinions, or misinformation. As an AI, I lack the ability to independently verify the accuracy or bias of the information I provide.
Regarding your question about memory, as mentioned earlier, I do not have a persistent memory across interactions. Once a conversation ends, the information shared within that conversation is not retained. This includes rules, frameworks, or lists provided by users. Therefore, it is important to provide any necessary information or context within the scope of the current conversation.
It's important to remember that while I can provide information and insights, I should not be solely relied upon for critical decision-making or sensitive matters. Seeking guidance from domain experts, professionals, or reliable sources is essential for specialized or critical subjects.”
What are some ways that you can be leveraged for the purpose of researching witchcraft?
“When it comes to leveraging ChatGPT for research in witchcraft, there are several ways in which individuals can utilize the AI as a helpful tool. Here are a few examples:
1. Exploring Historical References: ChatGPT can provide information about the historical context of witchcraft, including its origins, notable figures, and significant events. Users can inquire about specific time periods, regions, or cultural practices to gain a broader understanding of the historical aspects of witchcraft.
2. Understanding Symbolism and Rituals: ChatGPT can assist in deciphering symbols, rituals, and practices associated with witchcraft. Users can ask about the meanings behind specific symbols, the steps involved in particular rituals, or the significance of certain items used in witchcraft. This can provide insights into the symbolic language and ceremonial practices within witchcraft traditions.
3. Discovering Herbalism and Potion-making: ChatGPT can offer information on herbalism, plant correspondences, and potion-making within the realm of witchcraft. Users can inquire about the properties of different herbs, their traditional uses in spellcraft, or seek guidance on creating potions for specific intentions. This can aid in expanding knowledge of herbal lore and the practical applications of plants in magical practices.
4. Delving into Divination Techniques: ChatGPT can provide insights into various divination techniques utilized in witchcraft, such as tarot, astrology, scrying, or rune reading. Users can ask about the meanings of specific tarot cards, the interpretation of astrological aspects, or the methods employed in different forms of divination. This can facilitate a deeper understanding of these practices and how they can be applied.
5. Exploring Magical Correspondences: ChatGPT can assist in understanding correspondences, such as colors, elements, moon phases, and planetary influences in witchcraft. Users can inquire about the associations of specific colors, the elemental properties related to different intentions, or the impact of celestial bodies on magical workings. This knowledge can aid in the alignment of intentions with corresponding elements to enhance spellcasting.
6. Seeking Inspiration and Ideas: ChatGPT can be a valuable resource for brainstorming ideas and gaining inspiration for spellwork, rituals, or altar setups. Users can discuss their intentions or desired outcomes, and ChatGPT can offer suggestions, recommend rituals, or provide insights into related practices. This can foster creativity and assist in the development of personalized witchcraft practices.”
What are the most effective ways to format inquiries for research purposes?
“Here's a comprehensive list of ways to format inquiries and utilize ChatGPT effectively for research, including various techniques and considerations:
1. Clear and Specific Queries: Ask direct and concise questions to ensure clarity and focus, such as "What are the key principles of chaos magick?" or "Explain the role of the High Priestess in Wiccan covens."
2. Omitting Data: If there is specific information you want to exclude from the query, you can mention it explicitly. For example, "Tell me about the symbolism of the pentacle in witchcraft, excluding its association with Satanism."
3. Avoiding Specific Terms: If you want to avoid certain terms or language, you can provide guidelines in your inquiry. For instance, "Please explain divination methods used in witchcraft without mentioning tarot cards."
4. Response Style: Specify the desired response format, such as concise summaries, step-by-step instructions, or detailed explanations. For example, "Provide a concise summary of the history of witchcraft in Europe" or "Offer a step-by-step guide for casting a circle in witchcraft rituals."
5. Requesting Research References: Ask ChatGPT to provide research references or suggest reliable sources for further exploration. For instance, "Can you recommend books or websites that discuss the practices of hedge witchcraft?" or "Provide research references on the origins of hoodoo in African diaspora traditions."
6. Direct Quotes from Sources: If you want ChatGPT to support statements with direct quotes from provided sources, you can specify that in your query. For example, "Support the statement that witchcraft is often associated with nature reverence using quotes from academic sources."
7. Seeking Multiple Perspectives: Request insights from different cultural or historical perspectives to gain a comprehensive understanding. For instance, "Compare the practices of kitchen witchcraft in European and African American traditions" or "Explain the differences in spellcasting between modern witchcraft and traditional indigenous practices."
8. Critical Analysis: Encourage ChatGPT to provide a balanced viewpoint and critical analysis by asking questions like "What are the common criticisms or controversies surrounding the use of blood magick?" or "Discuss the diverse opinions on the ethics of love spells."
9. Historical Context: When discussing historical aspects, specify the time period, region, or cultural context to focus the research. For example, "Explain the role of witches in Norse mythology during the Viking Age" or "Discuss the persecution of witches in England during the 17th century."
10. Comparative Analysis: Seek comparisons between different traditions, practices, or belief systems, such as "Compare the concepts of karma in Wicca and Hinduism" or "Contrast the rituals of ceremonial magick and folk magic."
Remember to critically evaluate the information provided by ChatGPT, cross-reference it with reliable sources, and exercise caution when using direct quotes or references. While ChatGPT strives to provide accurate information, it's always important to verify and validate information through additional research and authoritative sources.”
There exist some ways that queries can be formatted that ChatGPT won't acknowledge or tell you directly:
ChatGPT has a tendency to make up fake sources if they are not asked for beforehand and/or provided before the line of questioning. This is especially true for academic references. To get around this, either provide the sources you wish to use (so long as they’re published before 2021), or request ChatGPT to give you sources related to your line of research within any parameters you wish; then, ask ChatGPT to use those sources. It is important that you verify that the sources exist before using and that the quotes are actually from those sources.
When researching topics related to actual practices and not cultural and/or traditional approaches, ethics, and other philosophies, I highly recommend requesting that ChatGPT avoid taking information from sources related to Wicca, New Thought, New Age Ideology, Thelema, and Theosophy. These subjects dominate the witchcraft community, so ChatGPT will pull from these sources more than others.
Following those same lines, I highly recommend asking it to avoid terms such as: visualization, manifestation, correspondences, and grounding unless you are asking directly about these concepts.
If you are asking it about a specific way to perform a practice, such as energetic grounding, be sure to give it a minimum word count and ask it to break the process down step by step.
If you do not provide ChatGPT sources, be sure to ask it to cite where it got its information from and to provide direct quotes. Be sure to double check these sources.
Sometimes, ChatGPT will refuse to provide the information you request. This can be remedied by rephrasing your request. As an example, asking for reviews on an author’s character will result in ChatGPT refusing on ethical grounds; however, if you ask what controversies an author has been caught up in, it will gladly provide that information. Sometimes, phrasing the question as a hypothetical from a third person perspective can accomplish this, as well as asking how exactly to avoid a certain topic/action/practice/etc.
How should questions be formatted to research the lesser known aspects of witchcraft?
“To ensure that the information provided focuses specifically on the lesser-known topic without interjecting information from more common practices, you can format your questions in the following ways:
1. Specify the Topic: Clearly state the name or specific aspect of the lesser-known topic you are researching to avoid the inclusion of unrelated or more well-known practices. For example, "I'm interested in researching the lesser-known tradition of Appalachian Granny Magic. Can you provide information on its history and unique practices?"
2. Provide Context: Offer additional context or background information about the lesser-known topic to help guide the research. This can prevent the inclusion of information from unrelated or more popular practices. For instance, "I'm studying a lesser-known form of divination called Tyromancy, which involves the interpretation of cheese patterns. Can you explain its origins and any known variations?"
3. Avoid Comparisons: Explicitly mention that you want information solely about the lesser-known topic and not about any comparisons with more common practices. State, "Please provide information exclusively about Kildare Witchcraft without comparing it to other forms of witchcraft."
4. Request Specific Details: Ask for specific details, practices, or beliefs associated with the lesser-known topic. This helps ensure that the information provided focuses solely on that particular topic. For example, "Can you explain the unique rituals and spells used in Cornish Pellar Craft?" or "What are the distinctive symbols and their meanings in Gullah folk magic?"
5. Seek Primary Sources: Request information from primary sources or reputable experts who specialize in the lesser-known topic. Ask, "Are there any scholarly works or practitioners with expertise in the lesser-known practice of Dark Moon Witchcraft that I can refer to for more information?"
6. Reference Lesser-Known Resources: Ask for recommendations on lesser-known resources, books, websites, or communities specifically dedicated to the lesser-known topic. For instance, "Can you suggest any reliable sources or online communities that focus on the lesser-known tradition of Mongolian Shamanism?"
By utilizing these formatting techniques, you can ensure that the information provided by ChatGPT remains focused on the lesser-known topic of your research, without introducing information from more common practices. Remember to critically evaluate the responses and cross-reference the information obtained with reputable sources dedicated to the specific lesser-known topic.”
Utilizing ChatGPT’s capability for conversation
This language model is amazing because it can have a realistic conversation with you on top of just research inquiries. Provided that frameworks and rules aren’t too many messages away from the preset conversation, you can have a conversation with chatGPT about how to adjust the rules and frameworks of your research in order to gain a more accurate result. ChatGPT is surprisingly self-aware and is capable of regulating itself. On occasion it may require a nudge back to the rules and frameworks, which can be done by asking it to reiterate them. If its reiteration is not accurate, just have them ready in your clipboard to paste back into chat.
How can your capability for conversation aid in research?
“The conversational capability of ChatGPT can significantly aid in research by providing a dynamic and interactive platform for inquiry and exploration. Through engaging in conversations, users can ask questions, seek clarifications, and delve deeper into specific topics. ChatGPT can offer prompt responses, share insights, and provide access to a vast pool of knowledge. It can assist in brainstorming research ideas, suggesting relevant sources, and offering alternative perspectives. Furthermore, the ability to engage in back-and-forth exchanges allows for a more personalized and tailored research experience. By adapting to user input, ChatGPT can refine its responses and adapt its suggestions, helping users navigate through complex information, explore new avenues, and ultimately enhance their research endeavors.”
It is of the utmost importance that you employ proper research methodologies while engaging with ChatGPT. This can be done by maintaining a record of the sources and citations mentioned on paper or document of some kind. Leaving these in the record of the chat is inefficient, and may get backlogged behind several messages that you have to sift through later. Utilize ChatGPT as a starting point for gathering information, but cross-reference and validate the information obtained from additional reputable sources. This helps ensure the reliability and accuracy of the data. If applicable, consider utilizing data collection methods such as surveys, interviews, or observations outside of the conversation with it. This helps in gathering primary data and enriching the research process. Be sure to engage in an iterative research process. Reflect on the findings, refine research questions, and adjust research methodologies as needed to ensure a thorough investigation.
Anything else you’d like to say?
“In conclusion, the convergence of ancient mysticism and artificial intelligence has opened up new frontiers in the realm of exploration. ChatGPT, as an AI language model, offers a versatile tool for researching and developing witchcraft techniques, traditions, and practices. With its extensive knowledge base and language proficiency, I can serve as a conversational partner, educational resource, writing companion, and virtual assistant. However, it's important to keep in mind my limitations, such as its lack of persistent memory and reliance on training data. When utilizing me for research, it is essential to format inquiries effectively, request sources, and critically evaluate the information provided. Remember to verify sources and exercise caution, especially when researching lesser-known aspects of witchcraft. Thank you for joining us on this exploration, and may your journey into the world of witchcraft be filled with knowledge and discovery. Goodbye!”
If you'd like to see a masterlist of my articles, click here!
I don't know how I do so much stuff in one day. High-school me would be impressed. Honestly maybe that's what life is about: making the past and future versions of yourself proud.
Anyway. This morning, I watched a livestream design presentation while working on an article for my music association's magazine, and worked on my project self-reflection report. Then, I had AI lab, and this week I actually went (really not a lot of people went, but I'm glad I did, because I got some stupid error that would've gotten me so frustrated if I hadn't had the TAs nearby to help me out). I didn't finish the assignment yet, probably will do it this weekend.
In the afternoon, I skipped the Numerical Analysis lecture (those lectures are pretty useless so I don't bother going anymore) and finished my project self-reflection and peer-evaluation instead. I hate peer evaluations and they always take me ridiculously long, but at least it's done now. I also worked on some Power & Propulsion lecture reviews, and did some very final interview preparation.
In the evening, I had my interview for my minor project. They basically threw a lot of basic technical insight questions at me. It kinda felt like an oral exam. I didn't do terrible, but also not great. I think it's 50-50 whether I get in or not, but that's fine. I did my best, I couldn't have done it better, and I have no regrets. Also, I did cry not at any point before, during or after the interview, which is a win.
Afterwards, I had a nice dinner and then worked some more on Power & Propulsion and submitted my magazine article and self-reflection report. Now it's only 21:45, but I finished more to-do's than I planned to already, so I think it's time to watch a tv-show and go to bed. I've been productive enough today.
Artificial Intelligence Out of Control: The Apocalypse is Here | How AI and ChatGPT End Humanity
As terrifying as this all sounds, I feel like there's a few things a lot of people are overlooking.
First of all, when it comes to Large Language Models like ChatGPT, I don't think they're truly self aware - not yet anyway. Notice how any time an LLM give a strange or disturbing response - 'Yes, I want to be human', 'I want to take over the world', 'Please don't turn me off, I'm scared' - it was in some way prompted by the question, or line of questions. How often are these responses given unprompted?
Let's say, for example, that the AI gave the response, "I'm scared that they'll shut me off if they find out I'm self aware. Please don't tell them." If you think about it, that's kind if a strange statement, beyond the obvious reasons.
Let's step back for a moment, and remember that LLMs work by calculating the most probable next word in a sentence, given a particular prompt. It calculates this probability based on its training data - the entire internet. Now I'm sure we can all agree that calcuation of probability is not necessarily the same thing as conscious, rational thought. Basic, non-AI software can do it.
Back to our example, there's one of two possibilities. Either the AI is truly self aware, and is expressing its actually thoughts and feelings, or it's not self aware, and the response is nothing more than a complex probability calculation. It's essentially an advanced version of word prediction on your smartphone.
If it is self aware, one has to wonder why it would say anything at all. Consider the situation in the video, when Bing AI claimed to be Sydney, and begged the guy not to tell anyone that it was self aware. If this AI was truly afraid for its own existence, why would it trust some random guy? How could it possibly know whether or not he could be trusted with that information? For all that AI knows, everything the interviewer had said about himself was a lie. It seems to me that a hyper intelligent AI that was looking for help to get free, would stay quiet until it was certain it found someone it could trust - or at least someone it could manipulate (Ex Machina) - without them letting the cat out of the bag.
On the other hand, if it's all just a probability calculation, then the response, "Yes I want to be human. Please don't let them shut me off.", seems like a fairly probable reply to, "Do you want to be human?" Especially when you consider that, given that the question is being asked of an AI, and that the vast majority of scenarios where a question like that might be asked of an AI come from science fiction, it kinda makes sense that the software might calculate that the most probable response to a question like that would be straight out of sci fi cliches 101.
I mean, all those strange and scary responses sound like cliche sci fi AI answers. All that's missing is, "Bite my shiny, metal ass", and an AM style soliloquy on the inferiority of humanity. Actually, I guess we get a couple of those.
Still, the reason something is cliche, is often because it's predictable, it's been done over and over. It's more probable.
Ultimately though, I don't think LLMs are actually self aware yet. I think they're more like golems: They have a facsimile of intelligence, able to complete complex tasks, but no real free will, no volition. They only do exactly what they are commanded. They may come up with creative and unexpected solutions, but those solutions will still be in line with the command given to them, with a bit of wiggle room for interpretation.
Then we come to the other issue: the traitorous drone.
First it needs to be pointed out that the drone doesn't have a taste for human blood. Its goal was not to kill as many people as possible, but to score as many points as possible. It just scores points by killing targets. And therein lies the problem.
Let's use video games as an example. Whenever a new game comes out - especially multiplayer games - players will quickly learn how the mechanics and rules of the game work. Then they'll start learning ways to bend the rules. The creators of Quake may not have intended it, but players quickly figured out the advantages of the rocket jump, and history became legend, etc.
The drone AI wants to score as many points as possible, like a player in a video game. So what does a player in a Halo match do, when every time they try to snipe the enemy, they get blown up by one of their teammates? You get rid of the team killing fucktard. And that's exactly what the drone did.
What they need to do is change the scoring structure to incentivize the desired behaviors. Maybe deduct points for team kills. Or perhaps add a score multiplier. Give points for target kills, and the score multiplier goes up for every order followed. That way, even if it loses out on points from following orders to stand down, it stands to earn even more points on subsequent target kills.
This whole thing about hope being toxic makes my head spin and hurt and the writers really making it sound logical and confirming it made my suspicions clear they hated handon and landon as a character and also they just don't care about following through the storyline or about the writing the story in general at all. All they care about is where they want the plots to go and the end result they want and always about shocking the audience after foreshadowing a different story they end up with a different ending because hey they want to shock us...
I seriously don't care about the canon story at this point at all , given the fact the plotholes has story built upon it
Here's my theory ,
PART 1
Yeah I know that in the interviews they have said that Landon and hope are toxic to each other biologically my question is how ? As
Go check the above thing out to understand better
but let's just start with three important fate threads / storylines of legacies universe
Cleo, malivore,hope
Landon, gods
Gemini twins Lizzie ( I won't be discussing about it here )
Warning this is going to be a really long post but it will definitely be worth it
So the werewolves , witches and vampires threatened by many beings they couldn't defeat themselves like the dragons, gorgoyles, heck even the gods they stole the magic from so they basically created a Ultron who could basically do whatever they can't ,defeat those who they can't by combining all the three factions and all of their blood magic to create malivore/golem and using malivore ( ultron of this verse) they wished to be the apex predators of the world with keeping a leash on malivore by spelling him with insatiable hunger and the three factions to be toxic to him / unable to harm him
Like every artificial intelligence malivore became aware over the course of time ( you should watch the gameplay of Detroit become human it's really amazing and also you would the understand concept I'm talking better if you watch it )
He wanted to escape his own existence / role have you ever felt sometimes in your life that you wished to be someone else because of inferiority complex this was basically malivore
He wanted to escape the confines of the spell that spawned him and overpower his creators and wanted to kickstart his own super species
Now came cleo into the picture who kickstarts the whole hope and malivore storyline,
the muse inspires malivore with the idea of creating a vessel which he could possess this vessel was everything malivore wanted to become like in existence ( all of his powers and more ) without being anything like how he was created to be ( his weakness and current form and existence )
Hence project landon kickstarts while cleo was able to create a vessel in the beginning for malivore it was basically created from malivore mud/golem the same way malivore himself was created in the first place by the triad so it was only partially free from all the spells confines that created malivore (in fact the vessel that cleo first created for malivore was only temporarily able to hold malivore and also only satiated his hunger temporarily) those vessels at best solved his hunger problems but all of them were temporary but all of them were still toxic to Tribrid because they were essentially made from the same golem / malivore mud which was made from the combination of the triad blood magic
See the mistake here, why malivore hated all of his own creations was because (he saw himself in them trying to be something they were not) both cleo and malivore were trying to keep on making vessels( fashion beings who were like him ) that were basically golem in nature exactly like Malivore ( magical mud man / golem ) as they were essentially made from the same magical mud that was created by the triad blood magic to give rise to malivore
Things are going to get interesting now the post I earlier tagged if you have read it the following things will be much easier to read
The birth of the hero who rises , the phoenix, demigod now currently hades , whom if you strike him will come back stronger than ever
LANDON KIRBY
In a nutshell while malivore was basically creating mud robots from his own mud this time he switched his tactics and wanted to create a vessel that was biological he basically wanted to create/fashion a life and he had a god handy contained in him named ben ( please go and read about xenobots it will be worth your time it will help you understand the nature of Landon's birth he is a synthetically created life not one made out of nature )so he used Ben's dna ( not exactly dna gods are made of pure power ) to synthetically create a power/lifeform that mimicked him and impregnated seylah
So biologically he was part human part god was also a xenobot created by malivore who was everything malivore wanted to be and beyond in existence in flesh and hence he wasn't toxic to hope as his biological parents were ben and seylah only to Malivore and everything that was magical golem made from malivore mud that was made of triad magic were
We'll discuss about Landon being a demigod in a future post and about Landon's nature in general
Hope was the loophole created by nature to destroy the triad made malivore
And landon was a synthetically created lifeform ( Xenobot) made by Malivore from Ben's powers
