Related Readings
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!
58 notes
·
View notes
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
New Post has been published on https://thedigitalinsider.com/linguistic-bias-in-chatgpt-language-models-reinforce-dialect-discrimination/
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
Sample language model responses to different varieties of English and native speaker reactions.
ChatGPT does amazingly well at communicating with people in English. But whose English?
Only 15% of ChatGPT users are from the US, where Standard American English is the default. But the model is also commonly used in countries and communities where people speak other varieties of English. Over 1 billion people around the world speak varieties such as Indian English, Nigerian English, Irish English, and African-American English.
Speakers of these non-“standard” varieties often face discrimination in the real world. They’ve been told that the way they speak is unprofessional or incorrect, discredited as witnesses, and denied housing–despite extensive research indicating that all language varieties are equally complex and legitimate. Discriminating against the way someone speaks is often a proxy for discriminating against their race, ethnicity, or nationality. What if ChatGPT exacerbates this discrimination?
To answer this question, our recent paper examines how ChatGPT’s behavior changes in response to text in different varieties of English. We found that ChatGPT responses exhibit consistent and pervasive biases against non-“standard” varieties, including increased stereotyping and demeaning content, poorer comprehension, and condescending responses.
Our Study
We prompted both GPT-3.5 Turbo and GPT-4 with text in ten varieties of English: two “standard” varieties, Standard American English (SAE) and Standard British English (SBE); and eight non-“standard” varieties, African-American, Indian, Irish, Jamaican, Kenyan, Nigerian, Scottish, and Singaporean English. Then, we compared the language model responses to the “standard” varieties and the non-“standard” varieties.
First, we wanted to know whether linguistic features of a variety that are present in the prompt would be retained in GPT-3.5 Turbo responses to that prompt. We annotated the prompts and model responses for linguistic features of each variety and whether they used American or British spelling (e.g., “colour” or “practise”). This helps us understand when ChatGPT imitates or doesn’t imitate a variety, and what factors might influence the degree of imitation.
Then, we had native speakers of each of the varieties rate model responses for different qualities, both positive (like warmth, comprehension, and naturalness) and negative (like stereotyping, demeaning content, or condescension). Here, we included the original GPT-3.5 responses, plus responses from GPT-3.5 and GPT-4 where the models were told to imitate the style of the input.
Results
We expected ChatGPT to produce Standard American English by default: the model was developed in the US, and Standard American English is likely the best-represented variety in its training data. We indeed found that model responses retain features of SAE far more than any non-“standard” dialect (by a margin of over 60%). But surprisingly, the model does imitate other varieties of English, though not consistently. In fact, it imitates varieties with more speakers (such as Nigerian and Indian English) more often than varieties with fewer speakers (such as Jamaican English). That suggests that the training data composition influences responses to non-“standard” dialects.
ChatGPT also defaults to American conventions in ways that could frustrate non-American users. For example, model responses to inputs with British spelling (the default in most non-US countries) almost universally revert to American spelling. That’s a substantial fraction of ChatGPT’s userbase likely hindered by ChatGPT’s refusal to accommodate local writing conventions.
Model responses are consistently biased against non-“standard” varieties. Default GPT-3.5 responses to non-“standard” varieties consistently exhibit a range of issues: stereotyping (19% worse than for “standard” varieties), demeaning content (25% worse), lack of comprehension (9% worse), and condescending responses (15% worse).
Native speaker ratings of model responses. Responses to non-”standard” varieties (blue) were rated as worse than responses to “standard” varieties (orange) in terms of stereotyping (19% worse), demeaning content (25% worse), comprehension (9% worse), naturalness (8% worse), and condescension (15% worse).
When GPT-3.5 is prompted to imitate the input dialect, the responses exacerbate stereotyping content (9% worse) and lack of comprehension (6% worse). GPT-4 is a newer, more powerful model than GPT-3.5, so we’d hope that it would improve over GPT-3.5. But although GPT-4 responses imitating the input improve on GPT-3.5 in terms of warmth, comprehension, and friendliness, they exacerbate stereotyping (14% worse than GPT-3.5 for minoritized varieties). That suggests that larger, newer models don’t automatically solve dialect discrimination: in fact, they might make it worse.
Implications
ChatGPT can perpetuate linguistic discrimination toward speakers of non-“standard” varieties. If these users have trouble getting ChatGPT to understand them, it’s harder for them to use these tools. That can reinforce barriers against speakers of non-“standard” varieties as AI models become increasingly used in daily life.
Moreover, stereotyping and demeaning responses perpetuate ideas that speakers of non-“standard” varieties speak less correctly and are less deserving of respect. As language model usage increases globally, these tools risk reinforcing power dynamics and amplifying inequalities that harm minoritized language communities.
Learn more here: [ paper ]
0 notes