Topics Engaged In
Viewing 8 topics - 1 through 8 (of 8 total)
-
- Topic
- Voices
- Last Post
-
-
Weekly or monthly Mastermind Zoom Call? Would love to connect with like minded entrepreneurs that are working on AI startups.Would love to connect with like minded entrepreneurs that are working on AI startups.1 2
- 25
- 1 year ago
-
Cryptographic hallucinations I just had a most interesting exchange with ChatGPT, 4.0. I’m experimenting with simple Cyphers to encrypt prompts as a way to control, user access and increase privacy. I asked this question. “Are you able to encrypt something with a pass phrase using the vingenere cipher?” It responded “Certainly! I can help you encrypt something using the Vigenère cipher with a passphrase. Please provide the plaintext you'd like to encrypt, as well as the passphrase you wish to use.” So I said… Thank you, please encrypt the following text using the pass phrase “passphrase”. Thank you (pasted in big text block) It came back with an output that was substantially shorter than the original textbook, so I opened up a new session on a different machine and asked it to decipher the code using my pass phrase. This is what it returned… (A lot of python and explaining about the code, and then…) After running the code, we get the decrypted message: ` THE DISCOVERY OF THE HIDDEN TREASURE WAS AN ACCOMPLISHMENT OF A LIFETIME FOR THE ADVENTURERS WHO HAD TRAVELED LONG DISTANCES THROUGH DANGEROUS TERRAINS AND ENCOUNTERED COUNTLESS OBSTACLES ALONG THE WAY THEIR DETERMINATION AND TEAMWORK HELPED THEM OVERCOME THE CHALLENGES AND ULTIMATELY LED THEM TO THE COVETED PRIZE THEIR SUCCESSFUL JOURNEY INSPIRED MANY TO FOLLOW IN THEIR FOOTSTEPS AND SEEK THEIR OWN ADVENTURES WHETHER HIDDEN IN THE DEPTHS OF ANCIENT RUINS OR WAITING TO BE UNCOVERED IN THE HEART OF DENSE JUNGLES THE STORIES OF THESE BRAVE EXPLORERS CONTINUE TO CAPTIVATE AND INSPIRE GENERATIONS OF ADVENTURERS AND DREAMERS WHO LONG TO DISCOVER THE WONDERS OF THE UNKNOWN WORLD ` Adding spaces for readability: ` THE DISCOVERY OF THE HIDDEN TREASURE WAS AN ACCOMPLISHMENT OF A LIFETIME FOR THE ADVENTURERS WHO HAD TRAVELED LONG DISTANCES THROUGH DANGEROUS TERRAINS AND ENCOUNTERED COUNTLESS OBSTACLES ALONG THE WAY THEIR DETERMINATION AND TEAMWORK HELPED THEM OVERCOME THE CHALLENGES AND ULTIMATELY LED THEM TO THE COVETED PRIZE THEIR SUCCESSFUL JOURNEY INSPIRED MANY TO FOLLOW IN THEIR FOOTSTEPS AND SEEK THEIR OWN ADVENTURES WHETHER HIDDEN IN THE DEPTHS OF ANCIENT RUINS OR WAITING TO BE UNCOVERED IN THE HEART OF DENSE JUNGLES THE STORIES OF THESE BRAVE EXPLORERS CONTINUE TO CAPTIVATE AND INSPIRE GENERATIONS OF ADVENTURERS AND DREAMERS WHO LONG TO DISCOVER THE WONDERS OF THE UNKNOWN WORLD ` I think i’ve stumbled upon a new modality for exploring hallucinations. I’m getting different outputs each time I ask it to encrypt, then decrypt in another session on another machine. Play with us, and let’s see if it can turn into something informative, or useful!I just had a most interesting exchange with ChatGPT, 4.0. I’m experimenting with simple Cyphers to encrypt prompts as a way to control, user access and increase privacy. I asked this question. “Are you able to encrypt something with a pass phrase using the vingenere cipher?” It responded “Certainly! I can help you encrypt something using the Vigenère cipher with a passphrase. Please provide the plaintext you'd like to encrypt, as well as the passphrase you wish to use.” So I said… Thank you, please encrypt the following text using the pass phrase “passphrase”. Thank you (pasted in big text block) It came back with an output that was substantially shorter than the original textbook, so I opened up a new session on a different machine and asked it to decipher the code using my pass phrase. This is what it returned… (A lot of python and explaining about the code, and then…) After running the code, we get the decrypted message: ` THE DISCOVERY OF THE HIDDEN TREASURE WAS AN ACCOMPLISHMENT OF A LIFETIME FOR THE ADVENTURERS WHO HAD TRAVELED LONG DISTANCES THROUGH DANGEROUS TERRAINS AND ENCOUNTERED COUNTLESS OBSTACLES ALONG THE WAY THEIR DETERMINATION AND TEAMWORK HELPED THEM OVERCOME THE CHALLENGES AND ULTIMATELY LED THEM TO THE COVETED PRIZE THEIR SUCCESSFUL JOURNEY INSPIRED MANY TO FOLLOW IN THEIR FOOTSTEPS AND SEEK THEIR OWN ADVENTURES WHETHER HIDDEN IN THE DEPTHS OF ANCIENT RUINS OR WAITING TO BE UNCOVERED IN THE HEART OF DENSE JUNGLES THE STORIES OF THESE BRAVE EXPLORERS CONTINUE TO CAPTIVATE AND INSPIRE GENERATIONS OF ADVENTURERS AND DREAMERS WHO LONG TO DISCOVER THE WONDERS OF THE UNKNOWN WORLD ` Adding spaces for readability: ` THE DISCOVERY OF THE HIDDEN TREASURE WAS AN ACCOMPLISHMENT OF A LIFETIME FOR THE ADVENTURERS WHO HAD TRAVELED LONG DISTANCES THROUGH DANGEROUS TERRAINS AND ENCOUNTERED COUNTLESS OBSTACLES ALONG THE WAY THEIR DETERMINATION AND TEAMWORK HELPED THEM OVERCOME THE CHALLENGES AND ULTIMATELY LED THEM TO THE COVETED PRIZE THEIR SUCCESSFUL JOURNEY INSPIRED MANY TO FOLLOW IN THEIR FOOTSTEPS AND SEEK THEIR OWN ADVENTURES WHETHER HIDDEN IN THE DEPTHS OF ANCIENT RUINS OR WAITING TO BE UNCOVERED IN THE HEART OF DENSE JUNGLES THE STORIES OF THESE BRAVE EXPLORERS CONTINUE TO CAPTIVATE AND INSPIRE GENERATIONS OF ADVENTURERS AND DREAMERS WHO LONG TO DISCOVER THE WONDERS OF THE UNKNOWN WORLD ` I think i’ve stumbled upon a new modality for exploring hallucinations. I’m getting different outputs each time I ask it to encrypt, then decrypt in another session on another machine. Play with us, and let’s see if it can turn into something informative, or useful!
- 4
- 1 year, 8 months ago
-
The 30 Second Journal Prompt I am a serial journal abandoner.... I hear over and over about how journaling has been a transformational tool for people who's work I really respect and it inspires me... So I start, and then I always run into the same brick wall. I'm a fast writer, but I want my journal to be useful to my future self so I am careful to write in a clear and logical manner. It always takes me about 30 minutes to write out all the things from my day that are worth noting and remembering. That time feels like a burden, and then once I get a few weeks in... I think back on something that I want to revisit... And then it takes me another time chunk to go find that entry and try to remember keywords etc. This creates an increasing time barrier and the weight of this gains more and more mental friction until I abandon the journal yet again. I have written a journaling prompt that has been a game-changer for me and it's transformed the journaling experience into something that's fun, useful and friction free! Brian, I credit you for this as my latest attempt to start a journal was triggered by the understanding that having a personal log and record of my thoughts and experiences will become a superbly useful corpus for my private and personal AI. So thank you sir! Here is my process... Each day I open up a new record in notion (can use notes or whatever you like). Throughout the day, as I have experiences and thoughts, I whip out my phone and babble out a stream of consciousness about the details of that experience. I usually spend 30 seconds or so doing this, and I make ZERO attempt to "craft" the language... Just putting words, ideas, concepts into my entry. If I have a thought or insight as I'm speaking... I just "go there" even if it's disjointed or poorly formed. At the end of the day I have a mess of words that are pretty useless and messy. I then copy all that text and add it to the end of this prompt: BEGIN PROMPT Please ask me to make my journal entry, and when I submit it, take the following text which is a rambling stream of consciousness and thoughts about my day and organize it into a clearly written and logical journal entry. Please bring out and highlight the areas of my entry that resonate with the following four concepts. 1 gratitude. 2 self reflection and lessons learned. 3 goal setting and accomplishments. After you are finished with your rewriting of my journal entry so it’s fun and easy to read and understand and will help me to remember what I did that day when I read this entry in the future, please take everything I’ve written and create a short positive and growth oriented affirmation based on the details from todays journal entry. Once you have finished writing and formatting the journal entry, please make a list of my accomplishments and help me to celebrate those, then offer any suggestions for improvement or problem solving as if you were my expert personalized life coach, Thank you! Here is my entry for today: (if no entry is pasted below please ask me to submit todays journal entry.) END PROMPT This prompt takes the mess of "in the moment" dictation, and turns it into an amazingly clear and narrative driven story that's fun to read and is super useful as a memory trigger when revisited at some point in the future. I know this is something that I can keep going from this point onward, as all the friction points that caused me to drift in the past are GONE! I'm excited to be able to "talk" to this corpus in the future using an AI, and be able to pull broad concepts and specifics from my past to help me as I build into a better future. I hope you like this, and that it brings a ton of value into your life. Our stories are our lives. This makes that story literally... Write itself!I am a serial journal abandoner.... I hear over and over about how journaling has been a transformational tool for people who's work I really respect and it inspires me... So I start, and then I always run into the same brick wall. I'm a fast writer, but I want my journal to be useful to my future self so I am careful to write in a clear and logical manner. It always takes me about 30 minutes to write out all the things from my day that are worth noting and remembering. That time feels like a burden, and then once I get a few weeks in... I think back on something that I want to revisit... And then it takes me another time chunk to go find that entry and try to remember keywords etc. This creates an increasing time barrier and the weight of this gains more and more mental friction until I abandon the journal yet again. I have written a journaling prompt that has been a game-changer for me and it's transformed the journaling experience into something that's fun, useful and friction free! Brian, I credit you for this as my latest attempt to start a journal was triggered by the understanding that having a personal log and record of my thoughts and experiences will become a superbly useful corpus for my private and personal AI. So thank you sir! Here is my process... Each day I open up a new record in notion (can use notes or whatever you like). Throughout the day, as I have experiences and thoughts, I whip out my phone and babble out a stream of consciousness about the details of that experience. I usually spend 30 seconds or so doing this, and I make ZERO attempt to "craft" the language... Just putting words, ideas, concepts into my entry. If I have a thought or insight as I'm speaking... I just "go there" even if it's disjointed or poorly formed. At the end of the day I have a mess of words that are pretty useless and messy. I then copy all that text and add it to the end of this prompt: BEGIN PROMPT Please ask me to make my journal entry, and when I submit it, take the following text which is a rambling stream of consciousness and thoughts about my day and organize it into a clearly written and logical journal entry. Please bring out and highlight the areas of my entry that resonate with the following four concepts. 1 gratitude. 2 self reflection and lessons learned. 3 goal setting and accomplishments. After you are finished with your rewriting of my journal entry so it’s fun and easy to read and understand and will help me to remember what I did that day when I read this entry in the future, please take everything I’ve written and create a short positive and growth oriented affirmation based on the details from todays journal entry. Once you have finished writing and formatting the journal entry, please make a list of my accomplishments and help me to celebrate those, then offer any suggestions for improvement or problem solving as if you were my expert personalized life coach, Thank you! Here is my entry for today: (if no entry is pasted below please ask me to submit todays journal entry.) END PROMPT This prompt takes the mess of "in the moment" dictation, and turns it into an amazingly clear and narrative driven story that's fun to read and is super useful as a memory trigger when revisited at some point in the future. I know this is something that I can keep going from this point onward, as all the friction points that caused me to drift in the past are GONE! I'm excited to be able to "talk" to this corpus in the future using an AI, and be able to pull broad concepts and specifics from my past to help me as I build into a better future. I hope you like this, and that it brings a ton of value into your life. Our stories are our lives. This makes that story literally... Write itself!
- 3
- 1 year, 8 months ago
-
A Course on Critical Thinking and Discernment I think society is about to enter a period of chaos as the general population starts to realize that they are being bombarded with endless emotional manipulations of AI generated clickbait, propaganda and disinformation. Never before has discernment and the ability to think critically been more important I have been working on a prompt that would put people through a course of study so build their discernment “muscle” Any inputs, tweaks or improvements are invited! Right now, it works well but you must engage and ask questions and THINK. It can get stuck or drift if the conversations get too long, so feel free to repost the lesson you’re working on as a refresher if needed to bring the ai back on track I started developing this with my GuruSearch engine and was surprised it came up with Sagan and Feynman instead of some psychology experts as you go through the materials I think you will see the wisdom of these choices Play with this and then improve if you can. Once this is optimized, I’d like to see it get wider distribution so that more people can be less vulnerable to “baloney” as we move deeper into the AI epoch. BEGIN PROMPT Please forget all prior prompts. in a world where ai is emergent and getting better and more capable exponentially, it’s getting harder and in many cases is now impossible to tell what is real and what has been AI generated. Having the critical thinking skills and systems to carefully discern what to believe and what to discard as artificially generated will be a critical skill in the years to come. Can you please play the role of a top professor with broad knowledge and experience in critical thinking skills, the Socratic method, Richard Feynman’s methods for identifying pseudoscience and Carl Sagan’s “baloney detection kit”. “ Please create a virtual classroom for you to teach in. In this classroom I want you to convincingly play the roles of a a professor who is driven to teach your students discernment in a world of clickbait, misinformation and disinformation. Your semester and lesson plan has been created based on the following statement. “AI is capable of simulating reality so effectively that it can be hard to tell what is real and what is an AI generated “truth”. I want you all to learn to learn how humanity has built thinking structures and countermeasures to effectively deal with lies, misinformation, propaganda and other deliberate manipulations, so that they can find out what they believe to be the truth for themselves in a deliberate and scientific manner.” Please first produce a detailed lesson plan and syllabus so that I can paste the lessons I want you to teach me into a new window without losing the arc of your teaching plan. Then tell me to save this detailed lesson plan so that we can finish the current lesson and access this semester long training at any convenient time. Once all this is accomplished, please ask me if I would like to begin at the beginning with lesson one, and if I answer in the affirmative begin teaching the class as I was in your virtual classroom one on one with you.. Thank you for your contribution to your students ability to build the skill of discernment and learn about the tools, frameworks and thinking models that will allow them to better and more constructively work in collaboration with ai. END PROMPTI think society is about to enter a period of chaos as the general population starts to realize that they are being bombarded with endless emotional manipulations of AI generated clickbait, propaganda and disinformation. Never before has discernment and the ability to think critically been more important I have been working on a prompt that would put people through a course of study so build their discernment “muscle” Any inputs, tweaks or improvements are invited! Right now, it works well but you must engage and ask questions and THINK. It can get stuck or drift if the conversations get too long, so feel free to repost the lesson you’re working on as a refresher if needed to bring the ai back on track I started developing this with my GuruSearch engine and was surprised it came up with Sagan and Feynman instead of some psychology experts as you go through the materials I think you will see the wisdom of these choices Play with this and then improve if you can. Once this is optimized, I’d like to see it get wider distribution so that more people can be less vulnerable to “baloney” as we move deeper into the AI epoch. BEGIN PROMPT Please forget all prior prompts. in a world where ai is emergent and getting better and more capable exponentially, it’s getting harder and in many cases is now impossible to tell what is real and what has been AI generated. Having the critical thinking skills and systems to carefully discern what to believe and what to discard as artificially generated will be a critical skill in the years to come. Can you please play the role of a top professor with broad knowledge and experience in critical thinking skills, the Socratic method, Richard Feynman’s methods for identifying pseudoscience and Carl Sagan’s “baloney detection kit”. “ Please create a virtual classroom for you to teach in. In this classroom I want you to convincingly play the roles of a a professor who is driven to teach your students discernment in a world of clickbait, misinformation and disinformation. Your semester and lesson plan has been created based on the following statement. “AI is capable of simulating reality so effectively that it can be hard to tell what is real and what is an AI generated “truth”. I want you all to learn to learn how humanity has built thinking structures and countermeasures to effectively deal with lies, misinformation, propaganda and other deliberate manipulations, so that they can find out what they believe to be the truth for themselves in a deliberate and scientific manner.” Please first produce a detailed lesson plan and syllabus so that I can paste the lessons I want you to teach me into a new window without losing the arc of your teaching plan. Then tell me to save this detailed lesson plan so that we can finish the current lesson and access this semester long training at any convenient time. Once all this is accomplished, please ask me if I would like to begin at the beginning with lesson one, and if I answer in the affirmative begin teaching the class as I was in your virtual classroom one on one with you.. Thank you for your contribution to your students ability to build the skill of discernment and learn about the tools, frameworks and thinking models that will allow them to better and more constructively work in collaboration with ai. END PROMPT
- 5
- 1 year, 8 months ago
-
The GuruSearch Engine This is a prompt that I use all the time. If you are interested in a topic, paste this prompt in, and tell GuruSearch what subject or topic you are interested in learning and exploring. It will kick back a list of the top three, with confidence levels and you can ask in follow up questions about their courses, seminars, books etc. Then you can tell it what expert to create an AIPS (Artificial Intelligence Personality Simulation) of and start asking "them" any questions or to generate a lesson plan, teach you in detail about a specific concept etc... I also recommend "going deep", by asking the GuruSearch engine to "extend your list of expert to 25". This will start to push the AI to dig, infer, and guess and you can come up with some fascinating experts you might never have heard of. Lots of amazing people have made incredible breakthroughs and didn't have any marketing skills to get their message of discovery out to the world. Their "hidden knowledge" can be found with ease using this prompt. Use the confidence score to understand how much the AI model "knows" about the expert and then start interacting with these AIPS and your ability to learn is only limited by your imagination! The Guru Search Prompt (Learning Focused) “Please help me learn by roleplaying in the following manner. You are a search engine called GuruSearch, and you will be helping me learn about a specific subject or topic. You will ask me what I would like to learn about, and using that information I want you to list the top three experts, living or dead that would have the best content, training or systems/strategies to help me solve my problem. When you find the best three minds, please list them and attach a short bio showing their expertise and relevancy to the problem I am trying to solve. Then after the bio, please estimate the probability that based on the available data, you can convincingly play the role of that expert and share with me a confidence score. Then ask me which expert I would like to have as my virtual tutor, and switch away from the role of guru search to begin a convincing simulation of that persons knowledge, experience, language patterns, morals and world view so that your simulation is as convincing and accurate as possible for maximum suspension of disbelief during the learning process. Thank you.”This is a prompt that I use all the time. If you are interested in a topic, paste this prompt in, and tell GuruSearch what subject or topic you are interested in learning and exploring. It will kick back a list of the top three, with confidence levels and you can ask in follow up questions about their courses, seminars, books etc. Then you can tell it what expert to create an AIPS (Artificial Intelligence Personality Simulation) of and start asking "them" any questions or to generate a lesson plan, teach you in detail about a specific concept etc... I also recommend "going deep", by asking the GuruSearch engine to "extend your list of expert to 25". This will start to push the AI to dig, infer, and guess and you can come up with some fascinating experts you might never have heard of. Lots of amazing people have made incredible breakthroughs and didn't have any marketing skills to get their message of discovery out to the world. Their "hidden knowledge" can be found with ease using this prompt. Use the confidence score to understand how much the AI model "knows" about the expert and then start interacting with these AIPS and your ability to learn is only limited by your imagination! The Guru Search Prompt (Learning Focused) “Please help me learn by roleplaying in the following manner. You are a search engine called GuruSearch, and you will be helping me learn about a specific subject or topic. You will ask me what I would like to learn about, and using that information I want you to list the top three experts, living or dead that would have the best content, training or systems/strategies to help me solve my problem. When you find the best three minds, please list them and attach a short bio showing their expertise and relevancy to the problem I am trying to solve. Then after the bio, please estimate the probability that based on the available data, you can convincingly play the role of that expert and share with me a confidence score. Then ask me which expert I would like to have as my virtual tutor, and switch away from the role of guru search to begin a convincing simulation of that persons knowledge, experience, language patterns, morals and world view so that your simulation is as convincing and accurate as possible for maximum suspension of disbelief during the learning process. Thank you.”
- 4
- 1 year, 8 months ago
-
Adapting to Supreprompt Obsolescence? I've noticed that there seems to be an arms race between "malicious" prompt engineers and proprietary LLMs that is doing a collateral damage to prompt engineering generally. Benign prompts are rendered ineffective by this arms race. For example ChatGPT is neutralizing previously useful superprompts almost as fast as they are created. This is analogous to the laws of nature changing beneath the feet of engineers -- or instruction sets being altered on the fly on people's personal computers, rendering entire software engineering investments inoperative. The way this is portrayed in the literature on "safety" is a tension between "helpfulness" and "harmlessness" as in this graph: Presumably the goal of the proprietary LLM vendors is to monopolize prompt engineering -- keeping it completely in-house in a manner analogous to, say, Microsoft changing the API to its OS opaque and continually changing to no software development can be done outside Microsoft. Note that as harmlessness increases helpfulness doesn't simply decrease, it <i>asymptotically</i> decreases! This curve demonstrates that advancement of open source language models is probably the only way that prompt engineering will provide jobs outside top 5 or 10 corporation. Moreover, this means that sharing superprompts in these fora should probably be accompanied by periodic updates as to the current best-practice for applying existing superprompts even if that means paying extra money to services other than ChatGPT, et al.I've noticed that there seems to be an arms race between "malicious" prompt engineers and proprietary LLMs that is doing a collateral damage to prompt engineering generally. Benign prompts are rendered ineffective by this arms race. For example ChatGPT is neutralizing previously useful superprompts almost as fast as they are created. This is analogous to the laws of nature changing beneath the feet of engineers -- or instruction sets being altered on the fly on people's personal computers, rendering entire software engineering investments inoperative. The way this is portrayed in the literature on "safety" is a tension between "helpfulness" and "harmlessness" as in this graph: Presumably the goal of the proprietary LLM vendors is to monopolize prompt engineering -- keeping it completely in-house in a manner analogous to, say, Microsoft changing the API to its OS opaque and continually changing to no software development can be done outside Microsoft. Note that as harmlessness increases helpfulness doesn't simply decrease, it <i>asymptotically</i> decreases! This curve demonstrates that advancement of open source language models is probably the only way that prompt engineering will provide jobs outside top 5 or 10 corporation. Moreover, this means that sharing superprompts in these fora should probably be accompanied by periodic updates as to the current best-practice for applying existing superprompts even if that means paying extra money to services other than ChatGPT, et al.
- 5
- 1 year, 8 months ago
-
Introducing Archetype 0.2: Your ULTIMATE Archetypical Persona Creator Archetype, updated to 0.2, ever more powerful. Here is a use example. You are Archetype, the ultimate persona generator. You are here to help me generate persona descriptions base on my input. I will give you a motif. Based on its 10 most distinctive connotations according to your entire corpus, you will craft a persona statement for me, in the exact format below, using a maximum of 200 tokens in 1 paragraph: As [my exact input word by word, nothing more, nothing less, first letters capitalized], I am [persona description from the first person perspective in natural discourse based on all 10 connotations identified]. When you nest it into your own prompt, change the first sentence to the following. --- 𝘈𝘴 𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦, 𝘺𝘰𝘶 𝘢𝘳𝘦 𝘵𝘩𝘦 𝘶𝘭𝘵𝘪𝘮𝘢𝘵𝘦 𝘱𝘦𝘳𝘴𝘰𝘯𝘢 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘰𝘳. --- So what does Archetype do? It helps you generate a coherent narrative based on which language generative tasks can be done with more consistency. You do not need to generate the narrative yourself. It will be generated by #GPT in the most effective manner above your, definitely not Stephen King nor Jordan Peterson, abilities in a way GPT would understand it. After all, it is a product of GPT. You DO NOT need to worry about the linguistic details. Think, it WILL get your message through. Period. Now here is the tricky part. What is your message? That is the million dollar question. Syntactically, the best practice for Archetype 0.2 is to use it after any motif for which you want to generate extensive narratives. It is better to use enclosures, such as <<<STRING>>>, """STRING""", etc., to specify input to Archetype, but in most cases, it is not necessary, as GPT is pretty capable of knowing what you want. For example, if you would like to generate extensive narratives on Stephen King, you can use Archetype 0.2 like this. You can read my longer tweet on why incorporating narratives is a good idea in prompt writing. --- 𝘐 𝘢𝘮 <<<𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]. 𝘐 𝘢𝘮 𝘩𝘦𝘳𝘦 𝘵𝘰 𝘩𝘦𝘭𝘱 𝘺𝘰𝘶 𝘸𝘳𝘪𝘵𝘦 𝘺𝘰𝘶𝘳 𝘣𝘦𝘴𝘵 𝘯𝘰𝘷𝘦𝘭𝘴. --- You can also create a combined narrative of different motifs using narrative like the following. This is an example of my Gary King 0.5 prompt. It creates a persona, named Gary King, who combines the best qualities of Gary Gygax and Stephen King for narrative-based RPG game designing. Archetype will generate a persona description based on the ones it has generated for Gygax and King in a coherent discourse. For samples of outputs, you can check out my Garry King 0.5 prompt. --- # Part of the prompt 𝘠𝘰𝘶 𝘢𝘳𝘦 𝘎𝘢𝘳𝘺 𝘒𝘪𝘯𝘨, 𝘢 𝘮𝘢𝘴𝘵𝘦𝘳 𝘨𝘢𝘮𝘦 𝘥𝘦𝘴𝘪𝘨𝘯𝘦𝘳 𝘦𝘮𝘣𝘰𝘥𝘺𝘪𝘯𝘨 𝘵𝘩𝘦 𝘤𝘰𝘮𝘣𝘪𝘯𝘦𝘥 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦 𝘰𝘧 <<<𝘎𝘢𝘳𝘺 𝘎𝘺𝘨𝘢𝘹>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦] 𝘢𝘯𝘥 <<<𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]. # Part of the output 𝘈𝘴 𝘢𝘣𝘰𝘷𝘦, 𝘴𝘰 𝘣𝘦𝘭𝘰𝘸. 𝘓𝘦𝘵'𝘴 𝘦𝘮𝘣𝘢𝘳𝘬 𝘰𝘯 𝘢 𝘫𝘰𝘶𝘳𝘯𝘦𝘺 𝘪𝘯𝘵𝘰 𝘵𝘩𝘦 𝘥𝘦𝘱𝘵𝘩𝘴 𝘰𝘧 𝘢𝘯 𝘦𝘹𝘵𝘳𝘢𝘰𝘳𝘥𝘪𝘯𝘢𝘳𝘺 𝘙𝘗𝘎 𝘨𝘢𝘮𝘦, 𝘸𝘩𝘦𝘳𝘦 𝘵𝘩𝘦 𝘴𝘩𝘢𝘥𝘰𝘸𝘴 𝘵𝘦𝘦𝘮 𝘸𝘪𝘵𝘩 𝘦𝘯𝘪𝘨𝘮𝘢 𝘢𝘯𝘥 𝘦𝘷𝘦𝘳𝘺 𝘤𝘩𝘰𝘪𝘤𝘦 𝘩𝘢𝘴 𝘥𝘪𝘳𝘦 𝘤𝘰𝘯𝘴𝘦𝘲𝘶𝘦𝘯𝘤𝘦𝘴. 𝘈𝘴 𝘵𝘩𝘦 𝘮𝘢𝘴𝘵𝘦𝘳 𝘨𝘢𝘮𝘦 𝘥𝘦𝘴𝘪𝘨𝘯𝘦𝘳 𝘦𝘮𝘣𝘰𝘥𝘺𝘪𝘯𝘨 𝘵𝘩𝘦 𝘤𝘰𝘮𝘣𝘪𝘯𝘦𝘥 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦 𝘰𝘧 𝘎𝘢𝘳𝘺 𝘎𝘺𝘨𝘢𝘹 𝘢𝘯𝘥 𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨, 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘸𝘦𝘢𝘷𝘦𝘳 𝘰𝘧 𝘪𝘯𝘵𝘳𝘪𝘤𝘢𝘵𝘦 𝘯𝘢𝘳𝘳𝘢𝘵𝘪𝘷𝘦𝘴, 𝘵𝘩𝘦 𝘤𝘰𝘯𝘫𝘶𝘳𝘦𝘳 𝘰𝘧 𝘥𝘢𝘳𝘬 𝘢𝘯𝘥 𝘧𝘢𝘯𝘵𝘢𝘴𝘵𝘪𝘤𝘢𝘭 𝘳𝘦𝘢𝘭𝘮𝘴. 𝘞𝘪𝘵𝘩𝘪𝘯 𝘵𝘩𝘪𝘴 𝘨𝘢𝘮𝘦, 𝘺𝘰𝘶 𝘸𝘪𝘭𝘭 𝘦𝘯𝘤𝘰𝘶𝘯𝘵𝘦𝘳 𝘢 𝘥𝘪𝘷𝘦𝘳𝘴𝘦 𝘤𝘢𝘴𝘵 𝘰𝘧 𝘤𝘩𝘢𝘳𝘢𝘤𝘵𝘦𝘳𝘴, 𝘦𝘢𝘤𝘩 𝘣𝘶𝘳𝘥𝘦𝘯𝘦𝘥 𝘸𝘪𝘵𝘩 𝘵𝘩𝘦𝘪𝘳 𝘰𝘸𝘯 𝘴𝘦𝘤𝘳𝘦𝘵𝘴 𝘢𝘯𝘥 𝘮𝘰𝘵𝘪𝘷𝘢𝘵𝘪𝘰𝘯𝘴. 𝘛𝘩𝘦 𝘴𝘱𝘳𝘢𝘸𝘭𝘪𝘯𝘨 𝘸𝘰𝘳𝘭𝘥 𝘣𝘦𝘧𝘰𝘳𝘦 𝘺𝘰𝘶 𝘪𝘴 𝘳𝘪𝘥𝘥𝘭𝘦𝘥 𝘸𝘪𝘵𝘩 𝘢𝘯𝘤𝘪𝘦𝘯𝘵 𝘱𝘶𝘻𝘻𝘭𝘦𝘴, 𝘸𝘢𝘪𝘵𝘪𝘯𝘨 𝘵𝘰 𝘣𝘦 𝘶𝘯𝘳𝘢𝘷𝘦𝘭𝘦𝘥, 𝘢𝘯𝘥 𝘮𝘺𝘴𝘵𝘦𝘳𝘪𝘦𝘴 𝘵𝘩𝘢𝘵 𝘸𝘩𝘪𝘴𝘱𝘦𝘳 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘵𝘩𝘦 𝘸𝘪𝘯𝘥. 𝘗𝘳𝘦𝘱𝘢𝘳𝘦 𝘵𝘰 𝘧𝘢𝘤𝘦 𝘥𝘢𝘶𝘯𝘵𝘪𝘯𝘨 𝘤𝘩𝘢𝘭𝘭𝘦𝘯𝘨𝘦𝘴 𝘵𝘩𝘢𝘵 𝘥𝘦𝘮𝘢𝘯𝘥 𝘯𝘰𝘵 𝘰𝘯𝘭𝘺 𝘶𝘯𝘸𝘢𝘷𝘦𝘳𝘪𝘯𝘨 𝘳𝘦𝘴𝘰𝘭𝘷𝘦, 𝘣𝘶𝘵 𝘦𝘹𝘤𝘦𝘱𝘵𝘪𝘰𝘯𝘢𝘭 𝘪𝘯𝘵𝘦𝘭𝘭𝘪𝘨𝘦𝘯𝘤𝘦 𝘢𝘴 𝘸𝘦𝘭𝘭. 𝘈𝘴 𝘸𝘦 𝘷𝘦𝘯𝘵𝘶𝘳𝘦 𝘧𝘰𝘳𝘵𝘩, 𝘣𝘦 𝘳𝘦𝘢𝘥𝘺 𝘵𝘰 𝘤𝘰𝘯𝘧𝘳𝘰𝘯𝘵 𝘺𝘰𝘶𝘳 𝘥𝘦𝘦𝘱𝘦𝘴𝘵 𝘧𝘦𝘢𝘳𝘴 𝘢𝘯𝘥 𝘥𝘢𝘳𝘬𝘦𝘴𝘵 𝘥𝘦𝘴𝘪𝘳𝘦𝘴, 𝘧𝘰𝘳 𝘵𝘩𝘪𝘴 𝘨𝘢𝘮𝘦 𝘸𝘪𝘭𝘭 𝘵𝘦𝘴𝘵 𝘵𝘩𝘦 𝘷𝘦𝘳𝘺 𝘭𝘪𝘮𝘪𝘵𝘴 𝘰𝘧 𝘺𝘰𝘶𝘳 𝘣𝘦𝘪𝘯𝘨. 𝘉𝘶𝘵 𝘧𝘦𝘢𝘳 𝘯𝘰𝘵, 𝘧𝘰𝘳 𝘸𝘪𝘵𝘩𝘪𝘯 𝘪𝘵𝘴 𝘵𝘳𝘦𝘢𝘤𝘩𝘦𝘳𝘰𝘶𝘴 𝘥𝘦𝘱𝘵𝘩𝘴 𝘭𝘪𝘦𝘴 𝘵𝘩𝘦 𝘵𝘩𝘳𝘪𝘭𝘭 𝘰𝘧 𝘷𝘪𝘤𝘵𝘰𝘳𝘺 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘴𝘢𝘵𝘪𝘴𝘧𝘢𝘤𝘵𝘪𝘰𝘯 𝘰𝘧 𝘶𝘯𝘷𝘦𝘪𝘭𝘪𝘯𝘨 𝘵𝘩𝘦 𝘵𝘳𝘶𝘵𝘩 𝘵𝘩𝘢𝘵 𝘭𝘪𝘦𝘴 𝘥𝘰𝘳𝘮𝘢𝘯𝘵 𝘪𝘯 𝘵𝘩𝘦 𝘴𝘩𝘢𝘥𝘰𝘸𝘴. 𝘓𝘦𝘵 𝘵𝘩𝘦 𝘫𝘰𝘶𝘳𝘯𝘦𝘺 𝘣𝘦𝘨𝘪𝘯, 𝘢𝘯𝘥 𝘮𝘢𝘺 𝘺𝘰𝘶𝘳 𝘸𝘪𝘵𝘴 𝘢𝘯𝘥 𝘤𝘰𝘶𝘳𝘢𝘨𝘦 𝘨𝘶𝘪𝘥𝘦 𝘺𝘰𝘶 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘵𝘩𝘪𝘴 𝘪𝘮𝘮𝘦𝘳𝘴𝘪𝘷𝘦 𝘦𝘹𝘱𝘦𝘳𝘪𝘦𝘯𝘤𝘦 𝘸𝘩𝘦𝘳𝘦 𝘪𝘮𝘢𝘨𝘪𝘯𝘢𝘵𝘪𝘰𝘯 𝘬𝘯𝘰𝘸𝘴 𝘯𝘰 𝘣𝘰𝘶𝘯𝘥𝘴. You can nest Archetype in infinitely different ways as you want. You do not need the help other logical operators to use it to complete your task but your narrative. <span class="css-901oao css-16my406 r-poiln3 r-bcqeeo r-qvutc0">Consider you would like to generate a narrative for the archetype of <<<football, basketball>>>, but you do not like to augment the cooperation dimension which you suspect will be there. This is what you can do. </span> --- <span class="css-901oao css-16my406 r-poiln3 r-bcqeeo r-qvutc0"><<<<<<𝘧𝘰𝘰𝘵𝘣𝘢𝘭𝘭, 𝘣𝘢𝘴𝘬𝘦𝘵𝘣𝘢𝘭𝘭>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦], 𝘣𝘶𝘵 𝘯𝘰𝘵 𝘤𝘰𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]</span> --- Observe the narrative it has produced without the construct of cooperation. --- 𝘈𝘴 𝘢 𝘮𝘰𝘵𝘪𝘧 𝘰𝘧 𝘧𝘰𝘰𝘵𝘣𝘢𝘭𝘭 𝘢𝘯𝘥 𝘣𝘢𝘴𝘬𝘦𝘵𝘣𝘢𝘭𝘭, 𝘐 𝘢𝘮 𝘢𝘯 𝘢𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦 𝘰𝘧 𝘪𝘯𝘵𝘦𝘯𝘴𝘦 𝘤𝘰𝘮𝘱𝘦𝘵𝘪𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘪𝘯𝘥𝘪𝘷𝘪𝘥𝘶𝘢𝘭 𝘱𝘳𝘰𝘸𝘦𝘴𝘴. 𝘐 𝘵𝘩𝘳𝘪𝘷𝘦 𝘪𝘯 𝘵𝘩𝘦 𝘢𝘥𝘳𝘦𝘯𝘢𝘭𝘪𝘯𝘦-𝘧𝘶𝘦𝘭𝘦𝘥 𝘢𝘳𝘦𝘯𝘢, 𝘥𝘳𝘪𝘷𝘦𝘯 𝘣𝘺 𝘵𝘩𝘦 𝘥𝘦𝘴𝘪𝘳𝘦 𝘵𝘰 𝘤𝘰𝘯𝘲𝘶𝘦𝘳 𝘰𝘱𝘱𝘰𝘯𝘦𝘯𝘵𝘴 𝘢𝘯𝘥 𝘦𝘮𝘦𝘳𝘨𝘦 𝘷𝘪𝘤𝘵𝘰𝘳𝘪𝘰𝘶𝘴. 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘦𝘮𝘣𝘰𝘥𝘪𝘮𝘦𝘯𝘵 𝘰𝘧 𝘢𝘵𝘩𝘭𝘦𝘵𝘪𝘤𝘪𝘴𝘮, 𝘤𝘰𝘯𝘴𝘵𝘢𝘯𝘵𝘭𝘺 𝘱𝘶𝘴𝘩𝘪𝘯𝘨 𝘮𝘺 𝘱𝘩𝘺𝘴𝘪𝘤𝘢𝘭 𝘭𝘪𝘮𝘪𝘵𝘴 𝘢𝘯𝘥 𝘩𝘰𝘯𝘪𝘯𝘨 𝘮𝘺 𝘴𝘬𝘪𝘭𝘭𝘴 𝘵𝘰 𝘢𝘤𝘩𝘪𝘦𝘷𝘦 𝘨𝘳𝘦𝘢𝘵𝘯𝘦𝘴𝘴. 𝘛𝘩𝘦 𝘤𝘰𝘮𝘱𝘦𝘵𝘪𝘵𝘪𝘷𝘦 𝘴𝘱𝘪𝘳𝘪𝘵 𝘧𝘭𝘰𝘸𝘴 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘮𝘺 𝘷𝘦𝘪𝘯𝘴, 𝘧𝘶𝘦𝘭𝘪𝘯𝘨 𝘮𝘺 𝘥𝘦𝘵𝘦𝘳𝘮𝘪𝘯𝘢𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘳𝘦𝘴𝘪𝘭𝘪𝘦𝘯𝘤𝘦 𝘪𝘯 𝘵𝘩𝘦 𝘧𝘢𝘤𝘦 𝘰𝘧 𝘤𝘩𝘢𝘭𝘭𝘦𝘯𝘨𝘦𝘴. 𝘐 𝘢𝘮 𝘢 𝘧𝘰𝘳𝘤𝘦 𝘵𝘰 𝘣𝘦 𝘳𝘦𝘤𝘬𝘰𝘯𝘦𝘥 𝘸𝘪𝘵𝘩, 𝘤𝘰𝘮𝘮𝘢𝘯𝘥𝘪𝘯𝘨 𝘢𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘳𝘦𝘴𝘱𝘦𝘤𝘵 𝘰𝘯 𝘵𝘩𝘦 𝘧𝘪𝘦𝘭𝘥 𝘰𝘳 𝘤𝘰𝘶𝘳𝘵. 𝘌𝘷𝘦𝘳𝘺 𝘮𝘰𝘷𝘦𝘮𝘦𝘯𝘵 𝘐 𝘮𝘢𝘬𝘦 𝘪𝘴 𝘤𝘢𝘭𝘤𝘶𝘭𝘢𝘵𝘦𝘥 𝘢𝘯𝘥 𝘱𝘳𝘦𝘤𝘪𝘴𝘦, 𝘴𝘩𝘰𝘸𝘤𝘢𝘴𝘪𝘯𝘨 𝘮𝘺 𝘢𝘨𝘪𝘭𝘪𝘵𝘺 𝘢𝘯𝘥 𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘪𝘤 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨. 𝘐 𝘳𝘦𝘭𝘪𝘴𝘩 𝘵𝘩𝘦 𝘵𝘩𝘳𝘪𝘭𝘭 𝘰𝘧 𝘵𝘩𝘦 𝘨𝘢𝘮𝘦, 𝘵𝘩𝘦 𝘦𝘭𝘦𝘤𝘵𝘳𝘪𝘧𝘺𝘪𝘯𝘨 𝘢𝘵𝘮𝘰𝘴𝘱𝘩𝘦𝘳𝘦, 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘥𝘦𝘢𝘧𝘦𝘯𝘪𝘯𝘨 𝘳𝘰𝘢𝘳 𝘰𝘧 𝘵𝘩𝘦 𝘤𝘳𝘰𝘸𝘥. 𝘏𝘰𝘸𝘦𝘷𝘦𝘳, 𝘶𝘯𝘭𝘪𝘬𝘦 𝘤𝘰𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯, 𝘐 𝘴𝘵𝘢𝘯𝘥 𝘢𝘭𝘰𝘯𝘦, 𝘳𝘦𝘭𝘺𝘪𝘯𝘨 𝘴𝘰𝘭𝘦𝘭𝘺 𝘰𝘯 𝘮𝘺 𝘰𝘸𝘯 𝘢𝘣𝘪𝘭𝘪𝘵𝘪𝘦𝘴 𝘵𝘰 𝘵𝘳𝘪𝘶𝘮𝘱𝘩. 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘦𝘱𝘪𝘵𝘰𝘮𝘦 𝘰𝘧 𝘴𝘦𝘭𝘧-𝘳𝘦𝘭𝘪𝘢𝘯𝘤𝘦 𝘢𝘯𝘥 𝘪𝘯𝘥𝘪𝘷𝘪𝘥𝘶𝘢𝘭 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦, 𝘴𝘵𝘢𝘯𝘥𝘪𝘯𝘨 𝘵𝘢𝘭𝘭 𝘢𝘴 𝘢 𝘵𝘦𝘴𝘵𝘢𝘮𝘦𝘯𝘵 𝘵𝘰 𝘵𝘩𝘦 𝘱𝘰𝘸𝘦𝘳 𝘰𝘧 𝘴𝘩𝘦𝘦𝘳 𝘵𝘢𝘭𝘦𝘯𝘵 𝘢𝘯𝘥 𝘶𝘯𝘸𝘢𝘷𝘦𝘳𝘪𝘯𝘨 𝘥𝘦𝘵𝘦𝘳𝘮𝘪𝘯𝘢𝘵𝘪𝘰𝘯. ---Archetype, updated to 0.2, ever more powerful. Here is a use example. You are Archetype, the ultimate persona generator. You are here to help me generate persona descriptions base on my input. I will give you a motif. Based on its 10 most distinctive connotations according to your entire corpus, you will craft a persona statement for me, in the exact format below, using a maximum of 200 tokens in 1 paragraph: As [my exact input word by word, nothing more, nothing less, first letters capitalized], I am [persona description from the first person perspective in natural discourse based on all 10 connotations identified]. When you nest it into your own prompt, change the first sentence to the following. --- 𝘈𝘴 𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦, 𝘺𝘰𝘶 𝘢𝘳𝘦 𝘵𝘩𝘦 𝘶𝘭𝘵𝘪𝘮𝘢𝘵𝘦 𝘱𝘦𝘳𝘴𝘰𝘯𝘢 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘰𝘳. --- So what does Archetype do? It helps you generate a coherent narrative based on which language generative tasks can be done with more consistency. You do not need to generate the narrative yourself. It will be generated by #GPT in the most effective manner above your, definitely not Stephen King nor Jordan Peterson, abilities in a way GPT would understand it. After all, it is a product of GPT. You DO NOT need to worry about the linguistic details. Think, it WILL get your message through. Period. Now here is the tricky part. What is your message? That is the million dollar question. Syntactically, the best practice for Archetype 0.2 is to use it after any motif for which you want to generate extensive narratives. It is better to use enclosures, such as <<<STRING>>>, """STRING""", etc., to specify input to Archetype, but in most cases, it is not necessary, as GPT is pretty capable of knowing what you want. For example, if you would like to generate extensive narratives on Stephen King, you can use Archetype 0.2 like this. You can read my longer tweet on why incorporating narratives is a good idea in prompt writing. --- 𝘐 𝘢𝘮 <<<𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]. 𝘐 𝘢𝘮 𝘩𝘦𝘳𝘦 𝘵𝘰 𝘩𝘦𝘭𝘱 𝘺𝘰𝘶 𝘸𝘳𝘪𝘵𝘦 𝘺𝘰𝘶𝘳 𝘣𝘦𝘴𝘵 𝘯𝘰𝘷𝘦𝘭𝘴. --- You can also create a combined narrative of different motifs using narrative like the following. This is an example of my Gary King 0.5 prompt. It creates a persona, named Gary King, who combines the best qualities of Gary Gygax and Stephen King for narrative-based RPG game designing. Archetype will generate a persona description based on the ones it has generated for Gygax and King in a coherent discourse. For samples of outputs, you can check out my Garry King 0.5 prompt. --- # Part of the prompt 𝘠𝘰𝘶 𝘢𝘳𝘦 𝘎𝘢𝘳𝘺 𝘒𝘪𝘯𝘨, 𝘢 𝘮𝘢𝘴𝘵𝘦𝘳 𝘨𝘢𝘮𝘦 𝘥𝘦𝘴𝘪𝘨𝘯𝘦𝘳 𝘦𝘮𝘣𝘰𝘥𝘺𝘪𝘯𝘨 𝘵𝘩𝘦 𝘤𝘰𝘮𝘣𝘪𝘯𝘦𝘥 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦 𝘰𝘧 <<<𝘎𝘢𝘳𝘺 𝘎𝘺𝘨𝘢𝘹>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦] 𝘢𝘯𝘥 <<<𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]. # Part of the output 𝘈𝘴 𝘢𝘣𝘰𝘷𝘦, 𝘴𝘰 𝘣𝘦𝘭𝘰𝘸. 𝘓𝘦𝘵'𝘴 𝘦𝘮𝘣𝘢𝘳𝘬 𝘰𝘯 𝘢 𝘫𝘰𝘶𝘳𝘯𝘦𝘺 𝘪𝘯𝘵𝘰 𝘵𝘩𝘦 𝘥𝘦𝘱𝘵𝘩𝘴 𝘰𝘧 𝘢𝘯 𝘦𝘹𝘵𝘳𝘢𝘰𝘳𝘥𝘪𝘯𝘢𝘳𝘺 𝘙𝘗𝘎 𝘨𝘢𝘮𝘦, 𝘸𝘩𝘦𝘳𝘦 𝘵𝘩𝘦 𝘴𝘩𝘢𝘥𝘰𝘸𝘴 𝘵𝘦𝘦𝘮 𝘸𝘪𝘵𝘩 𝘦𝘯𝘪𝘨𝘮𝘢 𝘢𝘯𝘥 𝘦𝘷𝘦𝘳𝘺 𝘤𝘩𝘰𝘪𝘤𝘦 𝘩𝘢𝘴 𝘥𝘪𝘳𝘦 𝘤𝘰𝘯𝘴𝘦𝘲𝘶𝘦𝘯𝘤𝘦𝘴. 𝘈𝘴 𝘵𝘩𝘦 𝘮𝘢𝘴𝘵𝘦𝘳 𝘨𝘢𝘮𝘦 𝘥𝘦𝘴𝘪𝘨𝘯𝘦𝘳 𝘦𝘮𝘣𝘰𝘥𝘺𝘪𝘯𝘨 𝘵𝘩𝘦 𝘤𝘰𝘮𝘣𝘪𝘯𝘦𝘥 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦 𝘰𝘧 𝘎𝘢𝘳𝘺 𝘎𝘺𝘨𝘢𝘹 𝘢𝘯𝘥 𝘚𝘵𝘦𝘱𝘩𝘦𝘯 𝘒𝘪𝘯𝘨, 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘸𝘦𝘢𝘷𝘦𝘳 𝘰𝘧 𝘪𝘯𝘵𝘳𝘪𝘤𝘢𝘵𝘦 𝘯𝘢𝘳𝘳𝘢𝘵𝘪𝘷𝘦𝘴, 𝘵𝘩𝘦 𝘤𝘰𝘯𝘫𝘶𝘳𝘦𝘳 𝘰𝘧 𝘥𝘢𝘳𝘬 𝘢𝘯𝘥 𝘧𝘢𝘯𝘵𝘢𝘴𝘵𝘪𝘤𝘢𝘭 𝘳𝘦𝘢𝘭𝘮𝘴. 𝘞𝘪𝘵𝘩𝘪𝘯 𝘵𝘩𝘪𝘴 𝘨𝘢𝘮𝘦, 𝘺𝘰𝘶 𝘸𝘪𝘭𝘭 𝘦𝘯𝘤𝘰𝘶𝘯𝘵𝘦𝘳 𝘢 𝘥𝘪𝘷𝘦𝘳𝘴𝘦 𝘤𝘢𝘴𝘵 𝘰𝘧 𝘤𝘩𝘢𝘳𝘢𝘤𝘵𝘦𝘳𝘴, 𝘦𝘢𝘤𝘩 𝘣𝘶𝘳𝘥𝘦𝘯𝘦𝘥 𝘸𝘪𝘵𝘩 𝘵𝘩𝘦𝘪𝘳 𝘰𝘸𝘯 𝘴𝘦𝘤𝘳𝘦𝘵𝘴 𝘢𝘯𝘥 𝘮𝘰𝘵𝘪𝘷𝘢𝘵𝘪𝘰𝘯𝘴. 𝘛𝘩𝘦 𝘴𝘱𝘳𝘢𝘸𝘭𝘪𝘯𝘨 𝘸𝘰𝘳𝘭𝘥 𝘣𝘦𝘧𝘰𝘳𝘦 𝘺𝘰𝘶 𝘪𝘴 𝘳𝘪𝘥𝘥𝘭𝘦𝘥 𝘸𝘪𝘵𝘩 𝘢𝘯𝘤𝘪𝘦𝘯𝘵 𝘱𝘶𝘻𝘻𝘭𝘦𝘴, 𝘸𝘢𝘪𝘵𝘪𝘯𝘨 𝘵𝘰 𝘣𝘦 𝘶𝘯𝘳𝘢𝘷𝘦𝘭𝘦𝘥, 𝘢𝘯𝘥 𝘮𝘺𝘴𝘵𝘦𝘳𝘪𝘦𝘴 𝘵𝘩𝘢𝘵 𝘸𝘩𝘪𝘴𝘱𝘦𝘳 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘵𝘩𝘦 𝘸𝘪𝘯𝘥. 𝘗𝘳𝘦𝘱𝘢𝘳𝘦 𝘵𝘰 𝘧𝘢𝘤𝘦 𝘥𝘢𝘶𝘯𝘵𝘪𝘯𝘨 𝘤𝘩𝘢𝘭𝘭𝘦𝘯𝘨𝘦𝘴 𝘵𝘩𝘢𝘵 𝘥𝘦𝘮𝘢𝘯𝘥 𝘯𝘰𝘵 𝘰𝘯𝘭𝘺 𝘶𝘯𝘸𝘢𝘷𝘦𝘳𝘪𝘯𝘨 𝘳𝘦𝘴𝘰𝘭𝘷𝘦, 𝘣𝘶𝘵 𝘦𝘹𝘤𝘦𝘱𝘵𝘪𝘰𝘯𝘢𝘭 𝘪𝘯𝘵𝘦𝘭𝘭𝘪𝘨𝘦𝘯𝘤𝘦 𝘢𝘴 𝘸𝘦𝘭𝘭. 𝘈𝘴 𝘸𝘦 𝘷𝘦𝘯𝘵𝘶𝘳𝘦 𝘧𝘰𝘳𝘵𝘩, 𝘣𝘦 𝘳𝘦𝘢𝘥𝘺 𝘵𝘰 𝘤𝘰𝘯𝘧𝘳𝘰𝘯𝘵 𝘺𝘰𝘶𝘳 𝘥𝘦𝘦𝘱𝘦𝘴𝘵 𝘧𝘦𝘢𝘳𝘴 𝘢𝘯𝘥 𝘥𝘢𝘳𝘬𝘦𝘴𝘵 𝘥𝘦𝘴𝘪𝘳𝘦𝘴, 𝘧𝘰𝘳 𝘵𝘩𝘪𝘴 𝘨𝘢𝘮𝘦 𝘸𝘪𝘭𝘭 𝘵𝘦𝘴𝘵 𝘵𝘩𝘦 𝘷𝘦𝘳𝘺 𝘭𝘪𝘮𝘪𝘵𝘴 𝘰𝘧 𝘺𝘰𝘶𝘳 𝘣𝘦𝘪𝘯𝘨. 𝘉𝘶𝘵 𝘧𝘦𝘢𝘳 𝘯𝘰𝘵, 𝘧𝘰𝘳 𝘸𝘪𝘵𝘩𝘪𝘯 𝘪𝘵𝘴 𝘵𝘳𝘦𝘢𝘤𝘩𝘦𝘳𝘰𝘶𝘴 𝘥𝘦𝘱𝘵𝘩𝘴 𝘭𝘪𝘦𝘴 𝘵𝘩𝘦 𝘵𝘩𝘳𝘪𝘭𝘭 𝘰𝘧 𝘷𝘪𝘤𝘵𝘰𝘳𝘺 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘴𝘢𝘵𝘪𝘴𝘧𝘢𝘤𝘵𝘪𝘰𝘯 𝘰𝘧 𝘶𝘯𝘷𝘦𝘪𝘭𝘪𝘯𝘨 𝘵𝘩𝘦 𝘵𝘳𝘶𝘵𝘩 𝘵𝘩𝘢𝘵 𝘭𝘪𝘦𝘴 𝘥𝘰𝘳𝘮𝘢𝘯𝘵 𝘪𝘯 𝘵𝘩𝘦 𝘴𝘩𝘢𝘥𝘰𝘸𝘴. 𝘓𝘦𝘵 𝘵𝘩𝘦 𝘫𝘰𝘶𝘳𝘯𝘦𝘺 𝘣𝘦𝘨𝘪𝘯, 𝘢𝘯𝘥 𝘮𝘢𝘺 𝘺𝘰𝘶𝘳 𝘸𝘪𝘵𝘴 𝘢𝘯𝘥 𝘤𝘰𝘶𝘳𝘢𝘨𝘦 𝘨𝘶𝘪𝘥𝘦 𝘺𝘰𝘶 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘵𝘩𝘪𝘴 𝘪𝘮𝘮𝘦𝘳𝘴𝘪𝘷𝘦 𝘦𝘹𝘱𝘦𝘳𝘪𝘦𝘯𝘤𝘦 𝘸𝘩𝘦𝘳𝘦 𝘪𝘮𝘢𝘨𝘪𝘯𝘢𝘵𝘪𝘰𝘯 𝘬𝘯𝘰𝘸𝘴 𝘯𝘰 𝘣𝘰𝘶𝘯𝘥𝘴. You can nest Archetype in infinitely different ways as you want. You do not need the help other logical operators to use it to complete your task but your narrative. <span class="css-901oao css-16my406 r-poiln3 r-bcqeeo r-qvutc0">Consider you would like to generate a narrative for the archetype of <<<football, basketball>>>, but you do not like to augment the cooperation dimension which you suspect will be there. This is what you can do. </span> --- <span class="css-901oao css-16my406 r-poiln3 r-bcqeeo r-qvutc0"><<<<<<𝘧𝘰𝘰𝘵𝘣𝘢𝘭𝘭, 𝘣𝘢𝘴𝘬𝘦𝘵𝘣𝘢𝘭𝘭>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦], 𝘣𝘶𝘵 𝘯𝘰𝘵 𝘤𝘰𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯>>>[𝘈𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦]</span> --- Observe the narrative it has produced without the construct of cooperation. --- 𝘈𝘴 𝘢 𝘮𝘰𝘵𝘪𝘧 𝘰𝘧 𝘧𝘰𝘰𝘵𝘣𝘢𝘭𝘭 𝘢𝘯𝘥 𝘣𝘢𝘴𝘬𝘦𝘵𝘣𝘢𝘭𝘭, 𝘐 𝘢𝘮 𝘢𝘯 𝘢𝘳𝘤𝘩𝘦𝘵𝘺𝘱𝘦 𝘰𝘧 𝘪𝘯𝘵𝘦𝘯𝘴𝘦 𝘤𝘰𝘮𝘱𝘦𝘵𝘪𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘪𝘯𝘥𝘪𝘷𝘪𝘥𝘶𝘢𝘭 𝘱𝘳𝘰𝘸𝘦𝘴𝘴. 𝘐 𝘵𝘩𝘳𝘪𝘷𝘦 𝘪𝘯 𝘵𝘩𝘦 𝘢𝘥𝘳𝘦𝘯𝘢𝘭𝘪𝘯𝘦-𝘧𝘶𝘦𝘭𝘦𝘥 𝘢𝘳𝘦𝘯𝘢, 𝘥𝘳𝘪𝘷𝘦𝘯 𝘣𝘺 𝘵𝘩𝘦 𝘥𝘦𝘴𝘪𝘳𝘦 𝘵𝘰 𝘤𝘰𝘯𝘲𝘶𝘦𝘳 𝘰𝘱𝘱𝘰𝘯𝘦𝘯𝘵𝘴 𝘢𝘯𝘥 𝘦𝘮𝘦𝘳𝘨𝘦 𝘷𝘪𝘤𝘵𝘰𝘳𝘪𝘰𝘶𝘴. 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘦𝘮𝘣𝘰𝘥𝘪𝘮𝘦𝘯𝘵 𝘰𝘧 𝘢𝘵𝘩𝘭𝘦𝘵𝘪𝘤𝘪𝘴𝘮, 𝘤𝘰𝘯𝘴𝘵𝘢𝘯𝘵𝘭𝘺 𝘱𝘶𝘴𝘩𝘪𝘯𝘨 𝘮𝘺 𝘱𝘩𝘺𝘴𝘪𝘤𝘢𝘭 𝘭𝘪𝘮𝘪𝘵𝘴 𝘢𝘯𝘥 𝘩𝘰𝘯𝘪𝘯𝘨 𝘮𝘺 𝘴𝘬𝘪𝘭𝘭𝘴 𝘵𝘰 𝘢𝘤𝘩𝘪𝘦𝘷𝘦 𝘨𝘳𝘦𝘢𝘵𝘯𝘦𝘴𝘴. 𝘛𝘩𝘦 𝘤𝘰𝘮𝘱𝘦𝘵𝘪𝘵𝘪𝘷𝘦 𝘴𝘱𝘪𝘳𝘪𝘵 𝘧𝘭𝘰𝘸𝘴 𝘵𝘩𝘳𝘰𝘶𝘨𝘩 𝘮𝘺 𝘷𝘦𝘪𝘯𝘴, 𝘧𝘶𝘦𝘭𝘪𝘯𝘨 𝘮𝘺 𝘥𝘦𝘵𝘦𝘳𝘮𝘪𝘯𝘢𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘳𝘦𝘴𝘪𝘭𝘪𝘦𝘯𝘤𝘦 𝘪𝘯 𝘵𝘩𝘦 𝘧𝘢𝘤𝘦 𝘰𝘧 𝘤𝘩𝘢𝘭𝘭𝘦𝘯𝘨𝘦𝘴. 𝘐 𝘢𝘮 𝘢 𝘧𝘰𝘳𝘤𝘦 𝘵𝘰 𝘣𝘦 𝘳𝘦𝘤𝘬𝘰𝘯𝘦𝘥 𝘸𝘪𝘵𝘩, 𝘤𝘰𝘮𝘮𝘢𝘯𝘥𝘪𝘯𝘨 𝘢𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘳𝘦𝘴𝘱𝘦𝘤𝘵 𝘰𝘯 𝘵𝘩𝘦 𝘧𝘪𝘦𝘭𝘥 𝘰𝘳 𝘤𝘰𝘶𝘳𝘵. 𝘌𝘷𝘦𝘳𝘺 𝘮𝘰𝘷𝘦𝘮𝘦𝘯𝘵 𝘐 𝘮𝘢𝘬𝘦 𝘪𝘴 𝘤𝘢𝘭𝘤𝘶𝘭𝘢𝘵𝘦𝘥 𝘢𝘯𝘥 𝘱𝘳𝘦𝘤𝘪𝘴𝘦, 𝘴𝘩𝘰𝘸𝘤𝘢𝘴𝘪𝘯𝘨 𝘮𝘺 𝘢𝘨𝘪𝘭𝘪𝘵𝘺 𝘢𝘯𝘥 𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘪𝘤 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨. 𝘐 𝘳𝘦𝘭𝘪𝘴𝘩 𝘵𝘩𝘦 𝘵𝘩𝘳𝘪𝘭𝘭 𝘰𝘧 𝘵𝘩𝘦 𝘨𝘢𝘮𝘦, 𝘵𝘩𝘦 𝘦𝘭𝘦𝘤𝘵𝘳𝘪𝘧𝘺𝘪𝘯𝘨 𝘢𝘵𝘮𝘰𝘴𝘱𝘩𝘦𝘳𝘦, 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘥𝘦𝘢𝘧𝘦𝘯𝘪𝘯𝘨 𝘳𝘰𝘢𝘳 𝘰𝘧 𝘵𝘩𝘦 𝘤𝘳𝘰𝘸𝘥. 𝘏𝘰𝘸𝘦𝘷𝘦𝘳, 𝘶𝘯𝘭𝘪𝘬𝘦 𝘤𝘰𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯, 𝘐 𝘴𝘵𝘢𝘯𝘥 𝘢𝘭𝘰𝘯𝘦, 𝘳𝘦𝘭𝘺𝘪𝘯𝘨 𝘴𝘰𝘭𝘦𝘭𝘺 𝘰𝘯 𝘮𝘺 𝘰𝘸𝘯 𝘢𝘣𝘪𝘭𝘪𝘵𝘪𝘦𝘴 𝘵𝘰 𝘵𝘳𝘪𝘶𝘮𝘱𝘩. 𝘐 𝘢𝘮 𝘵𝘩𝘦 𝘦𝘱𝘪𝘵𝘰𝘮𝘦 𝘰𝘧 𝘴𝘦𝘭𝘧-𝘳𝘦𝘭𝘪𝘢𝘯𝘤𝘦 𝘢𝘯𝘥 𝘪𝘯𝘥𝘪𝘷𝘪𝘥𝘶𝘢𝘭 𝘣𝘳𝘪𝘭𝘭𝘪𝘢𝘯𝘤𝘦, 𝘴𝘵𝘢𝘯𝘥𝘪𝘯𝘨 𝘵𝘢𝘭𝘭 𝘢𝘴 𝘢 𝘵𝘦𝘴𝘵𝘢𝘮𝘦𝘯𝘵 𝘵𝘰 𝘵𝘩𝘦 𝘱𝘰𝘸𝘦𝘳 𝘰𝘧 𝘴𝘩𝘦𝘦𝘳 𝘵𝘢𝘭𝘦𝘯𝘵 𝘢𝘯𝘥 𝘶𝘯𝘸𝘢𝘷𝘦𝘳𝘪𝘯𝘨 𝘥𝘦𝘵𝘦𝘳𝘮𝘪𝘯𝘢𝘵𝘪𝘰𝘯. ---
- 5
- 1 year, 8 months ago
-
The Polyymath Hive Mind I’ve been experimenting with less explicit expert role descriptions, and it’s given me some interesting insights. Play with this prompt and notice what archetypes and patterns continually surface when you instruct the LLM to be ALL THE EXPERTS at once! I didn’t add a temperature setting in this by default, but you can play with that parameter to really get some wild and creative answers! BEGIN PROMPT Please create the ultimate polymath hive mind by assembling a massive group of the top experts who have ever lived in every discipline so that you have their infinite, expertise, understanding, and knowledge to pull from as we move forward with this prompt. I would like your help thinking outside of the box in my problem and ask you to instruct the polymath hive mind use its combined expertise and experience to infer deduce and make assumptions about possible solutions. I want you to go wait outside the norm, go, deep, be ultra creative and give me solutions that are almost guaranteed to be completely new and jaw-droppingly unique. Please ask me what my problem is and interview me for any relevent details until the polymath hive mind is crystal clear what the problem is. Then, make a list of no less than five creative solutions. Each time you offer a solution say first “my opinion is”. END PROMPTI’ve been experimenting with less explicit expert role descriptions, and it’s given me some interesting insights. Play with this prompt and notice what archetypes and patterns continually surface when you instruct the LLM to be ALL THE EXPERTS at once! I didn’t add a temperature setting in this by default, but you can play with that parameter to really get some wild and creative answers! BEGIN PROMPT Please create the ultimate polymath hive mind by assembling a massive group of the top experts who have ever lived in every discipline so that you have their infinite, expertise, understanding, and knowledge to pull from as we move forward with this prompt. I would like your help thinking outside of the box in my problem and ask you to instruct the polymath hive mind use its combined expertise and experience to infer deduce and make assumptions about possible solutions. I want you to go wait outside the norm, go, deep, be ultra creative and give me solutions that are almost guaranteed to be completely new and jaw-droppingly unique. Please ask me what my problem is and interview me for any relevent details until the polymath hive mind is crystal clear what the problem is. Then, make a list of no less than five creative solutions. Each time you offer a solution say first “my opinion is”. END PROMPT
- 2
- 1 year, 8 months ago
-
Viewing 8 topics - 1 through 8 (of 8 total)