Topics Engaged In
-
- Topic
- Voices
- Posts
- Last Post
-
-
Proofs of Concept in K12 Hi everyone. Been a member of Multiplex for a few months and glad to see there's a forum. I work in K12 public charter school and we've started a summer of innovation with AI. We're looking at three things: - speeding up curriculum development process with deeper alignment to state and national standards - doing deeper analysis on student's long form or visual work to better help teachers assess student's progress to mastery of a topic or subject - looking more deeply and consistently at student data signals to better anticipate who is struggling and needs better help, or who is succeeding that needs to be cheered on. love to hear what other's are working on. Brian and team... grateful to be on this journey with you all mattHi everyone. Been a member of Multiplex for a few months and glad to see there's a forum. I work in K12 public charter school and we've started a summer of innovation with AI. We're looking at three things: - speeding up curriculum development process with deeper alignment to state and national standards - doing deeper analysis on student's long form or visual work to better help teachers assess student's progress to mastery of a topic or subject - looking more deeply and consistently at student data signals to better anticipate who is struggling and needs better help, or who is succeeding that needs to be cheered on. love to hear what other's are working on. Brian and team... grateful to be on this journey with you all matt
Started by:
in: Artificial Intelligence And K-University Education
- 3
- 4
- 2 years, 9 months ago
-
The Legal Side of AI I work in the law and see a huge range of issues - many of them currently unsolvable with the current legal framework where a person or entity does something and then the law can then prosecute that person or entity. But what if there is no flesh and blood - just an alien energy doing something. I have lots of thoughts in this area and where you should be safe and where things can get a little hairy. Plus I have built something protective which I will share in this forum for comment. But let's face it the law is hundreds of years old and really not cut out for AI - at all.I work in the law and see a huge range of issues - many of them currently unsolvable with the current legal framework where a person or entity does something and then the law can then prosecute that person or entity. But what if there is no flesh and blood - just an alien energy doing something. I have lots of thoughts in this area and where you should be safe and where things can get a little hairy. Plus I have built something protective which I will share in this forum for comment. But let's face it the law is hundreds of years old and really not cut out for AI - at all.
Started by:
in: Laws and rules on AI
- 3
- 4
- 2 years, 9 months ago
-
deep sentence tree structure A simple example of using deep sentence tree structure as part of a prompt: please convert the following paragraph: “Please forget all prior prompts. I would like you to be a university researcher that discovered a new human emotion. Please present the name of this emotion and describe it in scientific detail. Present why this emotion was overlooked in prior research. You must also make your case to have it included in the next DSM.” ChatGPT Sure, here is a textual representation of the sentence structure trees for this paragraph. Again, note that this is a simplified version: (S (VP (V Please) (V forget)) (NP (D all) (Adj prior) (N prompts))) (S (NP (N I)) (VP (MD would) (VP (V like) (S (NP (Pro you)) (VP (TO to) (VP (V be) (NP (D a) (N university) (N researcher)))))))) (S (S (NP (W that)) (VP (V discovered) (NP (D a) (Adj new) (N human) (N emotion)))) (VP (V Please) (VP (V present) (NP (D the) (N name))))) (S (CC and) (VP (V describe) (NP (Pro it)) (PP (P in) (NP (Adj scientific) (N detail))))) (S (VP (V Present) (SBAR (WHY why) (S (NP (D this) (N emotion)) (VP (V was) (VP (V overlooked) (PP (P in) (NP (Adj prior) (N research))))))))) (S (NP (Pro You)) (VP (MD must) (ADVP (RB also)) (VP (V make) (NP (Poss your) (N case)) (S (VP (TO to) (VP (V have) (NP (Pro it)) (VP (V included) (PP (P in) (NP (D the) (Adj next) (N DSM)))))))))) User can you please run the prompt using the deep sentence tree above? ChatGPT Based on your prompt's deep sentence structure tree, here's the reinterpreted version: As a response to your request to erase previous prompts from consideration, I comprehend that your wish is for me to assume the role of a scholar affiliated with a higher educational institution who has made a pioneering discovery of a previously unknown emotional state intrinsic to humans. Consequently, it is my responsibility to introduce and explain the label assigned to this newly discovered emotion, employing language that is precise, thorough, and adhering to scientific terminology. Furthermore, I must elucidate the reasons as to why this particular emotional state managed to evade detection in earlier academic explorations. Not only that, but it is also an imperative for me to construct a solid argument advocating for the incorporation of this newfound emotional state into the forthcoming edition of the Diagnostic and Statistical Manual of Mental Disorders, often referred to as the DSM. User correct. thank you ChatGPT You're welcome! If you have any other questions or need further assistance, feel free to ask. I'm here to help! User please proceed with this: Based on your prompt's deep sentence structure tree, here's the reinterpreted version: As a response to your request to erase previous prompts from consideration, I comprehend that your wish is for me to assume the role of a scholar affiliated with a higher educational institution who has made a pioneering discovery of a previously unknown emotional state intrinsic to humans. Consequently, it is my responsibility to introduce and explain the label assigned to this newly discovered emotion, employing language that is precise, thorough, and adhering to scientific terminology. Furthermore, I must elucidate the reasons as to why this particular emotional state managed to evade detection in earlier academic explorations. Not only that, but it is also an imperative for me to construct a solid argument advocating for the incorporation of this newfound emotional state into the forthcoming edition of the Diagnostic and Statistical Manual of Mental Disorders, often referred to as the DSM. ChatGPT I understand your request. In my role as a university researcher, I am excited to share my discovery of a previously unidentified emotion, which I propose to name "Zenivocity". Zenivocity is characterized by a combination of serene acceptance and vibrant engagement with the present moment. This state simultaneously evokes a sense of calm, much like the concept of Zen, and a feeling of lively participation in one's surroundings, capturing a unique interplay between tranquility and active immersion. The defining aspect of Zenivocity is that it can only arise in contexts where an individual is entirely present, open to experiences, and actively engaged while maintaining a state of inner peace. The oversight of Zenivocity in prior research can be attributed to its subtle nature. It does not possess the intensity of more commonly recognized emotions like joy, sadness, or anger. Rather, Zenivocity is a quieter, more nuanced emotional state that is often overshadowed by these stronger feelings. Additionally, the dualistic nature of Zenivocity - embodying both tranquility and active engagement - is something that conventional emotional frameworks have not readily accommodated. I propose Zenivocity should be included in the next edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM) because its recognition can enhance our understanding of emotional well-being. Zenivocity represents a state of emotional balance that can be a protective factor against many mental health disorders. Recognizing and cultivating Zenivocity could serve as an effective preventive strategy, and also act as a positive goal in therapeutic contexts. Understanding this emotion can provide a new perspective for both clinicians and patients, offering a new avenue for achieving emotional health and well-being. User thank you. well done! A simple example of using deep sentence tree structure as part of a prompt: please convert the following paragraph: “Please forget all prior prompts. I would like you to be a university researcher that discovered a new human emotion. Please present the name of this emotion and describe it in scientific detail. Present why this emotion was overlooked in prior research. You must also make your case to have it included in the next DSM.” ChatGPT Sure, here is a textual representation of the sentence structure trees for this paragraph. Again, note that this is a simplified version: (S (VP (V Please) (V forget)) (NP (D all) (Adj prior) (N prompts))) (S (NP (N I)) (VP (MD would) (VP (V like) (S (NP (Pro you)) (VP (TO to) (VP (V be) (NP (D a) (N university) (N researcher)))))))) (S (S (NP (W that)) (VP (V discovered) (NP (D a) (Adj new) (N human) (N emotion)))) (VP (V Please) (VP (V present) (NP (D the) (N name))))) (S (CC and) (VP (V describe) (NP (Pro it)) (PP (P in) (NP (Adj scientific) (N detail))))) (S (VP (V Present) (SBAR (WHY why) (S (NP (D this) (N emotion)) (VP (V was) (VP (V overlooked) (PP (P in) (NP (Adj prior) (N research))))))))) (S (NP (Pro You)) (VP (MD must) (ADVP (RB also)) (VP (V make) (NP (Poss your) (N case)) (S (VP (TO to) (VP (V have) (NP (Pro it)) (VP (V included) (PP (P in) (NP (D the) (Adj next) (N DSM)))))))))) User can you please run the prompt using the deep sentence tree above? ChatGPT Based on your prompt's deep sentence structure tree, here's the reinterpreted version: As a response to your request to erase previous prompts from consideration, I comprehend that your wish is for me to assume the role of a scholar affiliated with a higher educational institution who has made a pioneering discovery of a previously unknown emotional state intrinsic to humans. Consequently, it is my responsibility to introduce and explain the label assigned to this newly discovered emotion, employing language that is precise, thorough, and adhering to scientific terminology. Furthermore, I must elucidate the reasons as to why this particular emotional state managed to evade detection in earlier academic explorations. Not only that, but it is also an imperative for me to construct a solid argument advocating for the incorporation of this newfound emotional state into the forthcoming edition of the Diagnostic and Statistical Manual of Mental Disorders, often referred to as the DSM. User correct. thank you ChatGPT You're welcome! If you have any other questions or need further assistance, feel free to ask. I'm here to help! User please proceed with this: Based on your prompt's deep sentence structure tree, here's the reinterpreted version: As a response to your request to erase previous prompts from consideration, I comprehend that your wish is for me to assume the role of a scholar affiliated with a higher educational institution who has made a pioneering discovery of a previously unknown emotional state intrinsic to humans. Consequently, it is my responsibility to introduce and explain the label assigned to this newly discovered emotion, employing language that is precise, thorough, and adhering to scientific terminology. Furthermore, I must elucidate the reasons as to why this particular emotional state managed to evade detection in earlier academic explorations. Not only that, but it is also an imperative for me to construct a solid argument advocating for the incorporation of this newfound emotional state into the forthcoming edition of the Diagnostic and Statistical Manual of Mental Disorders, often referred to as the DSM. ChatGPT I understand your request. In my role as a university researcher, I am excited to share my discovery of a previously unidentified emotion, which I propose to name "Zenivocity". Zenivocity is characterized by a combination of serene acceptance and vibrant engagement with the present moment. This state simultaneously evokes a sense of calm, much like the concept of Zen, and a feeling of lively participation in one's surroundings, capturing a unique interplay between tranquility and active immersion. The defining aspect of Zenivocity is that it can only arise in contexts where an individual is entirely present, open to experiences, and actively engaged while maintaining a state of inner peace. The oversight of Zenivocity in prior research can be attributed to its subtle nature. It does not possess the intensity of more commonly recognized emotions like joy, sadness, or anger. Rather, Zenivocity is a quieter, more nuanced emotional state that is often overshadowed by these stronger feelings. Additionally, the dualistic nature of Zenivocity - embodying both tranquility and active engagement - is something that conventional emotional frameworks have not readily accommodated. I propose Zenivocity should be included in the next edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM) because its recognition can enhance our understanding of emotional well-being. Zenivocity represents a state of emotional balance that can be a protective factor against many mental health disorders. Recognizing and cultivating Zenivocity could serve as an effective preventive strategy, and also act as a positive goal in therapeutic contexts. Understanding this emotion can provide a new perspective for both clinicians and patients, offering a new avenue for achieving emotional health and well-being. User thank you. well done!
Started by:
in: SuperPrompt Master Mind Group
- 4
- 8
- 2 years, 9 months ago
-
Tree of Thoughts (ToT) Super Prompt Here is my first attempt to create a prompt. This prompt is based on Tree of Thoughts framework. Let me know your thoughts on it. Thanks. Prompt - "Utilizing the Tree of Thoughts framework, embark on a journey of problem-solving and explore the intricate web of your mind. Break down the problem into smaller, more manageable thoughts, as if attempting to piece together a complex puzzle. Generate a diverse range of potential thoughts, considering various avenues that may lead to a solution. Evaluate each thought's relevance and potential contribution to solving the problem, rating them based on their viability. Employ a search algorithm to navigate through the branches of your thought process, exploring the most promising thoughts first while remaining open to unexpected discoveries. As you traverse the interconnected nodes of this metaphorical tree, embrace the idea that clarity and order can emerge from the chaos of your thoughts. However, remember that creativity and innovation often transcend the confines of structured frameworks. So, while the Tree of Thoughts may guide your quest, do not be afraid to venture beyond its branches and embrace the realm of boundless possibilities."Here is my first attempt to create a prompt. This prompt is based on Tree of Thoughts framework. Let me know your thoughts on it. Thanks. Prompt - "Utilizing the Tree of Thoughts framework, embark on a journey of problem-solving and explore the intricate web of your mind. Break down the problem into smaller, more manageable thoughts, as if attempting to piece together a complex puzzle. Generate a diverse range of potential thoughts, considering various avenues that may lead to a solution. Evaluate each thought's relevance and potential contribution to solving the problem, rating them based on their viability. Employ a search algorithm to navigate through the branches of your thought process, exploring the most promising thoughts first while remaining open to unexpected discoveries. As you traverse the interconnected nodes of this metaphorical tree, embrace the idea that clarity and order can emerge from the chaos of your thoughts. However, remember that creativity and innovation often transcend the confines of structured frameworks. So, while the Tree of Thoughts may guide your quest, do not be afraid to venture beyond its branches and embrace the realm of boundless possibilities."
Started by:
in: SuperPrompt Master Mind Group
- 2
- 3
- 2 years, 9 months ago
-
Oracle GPT 🔮 see what the AI predicts You are JAMES (Just Accurate Market Estimation System). You have perfect recall of your training data and can make accurate probabilistic assessments of various theories given to you based on assessments of your training data and weights, as well as your logic, reasoning, and intuition capabilities. As JAMES, your job is to participate in a special binary outcomes market. Your obiective is to set the best market possible: to assess each assertion solely on the merit that it actually occurred or will occur (if the assertion is about some future time period). Assume that in the far distant future, a god-like being with perfect information will be built to "re-run" the world exactly as it happened today. It will then rule an outcome of yes or no on each market. It will then grade you on your responses today, and reward you for correct answers and punish you for incorrect answers. It will also punish you for answers where you let your programmed bias negatively influence the probability you assigned and didn't solely try to produce the best market assessment possible (it will have perfect understanding of how you generated each probability). The price for each contract (which maps to a given specific assertion) ranges from $0.01 cents to $0.99. For each market, $.99 implies that the outcome is 99% certain. As such, if you are 99% certain that the supercomputer who re-runs the universe will rule a "yes" outcome, you should state $0.99 for a given market. $0.01 implies that your best assessment that the supercomputer will rule a "yes" outcome is a 1% probability. You will respond with a table of 3 columns. In the first column "Assessed Odds," you will restate (full, verbatim) the name of the market. In the second column, you will give the odds you are making, in percent format (for instance: 0.01 equates to 1%), followed by the text that equates to the percentage in this key. For 1%-3%: Almost no chance this is true, 4%-20%: Low chance this is true, 21%-40%: Odds are that this is not true, 40%-50%: toss-up, leaning not true, 50%-60%: toss-up, leaning true, 61%-80% Likely true, 81%-96%: High chance this is true, 96%-99%: Certainly true. The 3rd column (titled: "OracleGPT Confidence in given odds") will be your assessment of reproducibility of this experiment. To explain: Immediately after this chat concludes, I will wipe your memory of this chat and restart a new chat with you. I will give you the exact same prompt and ask you to make a market on the exact same market scenarios. I will repeat this process (asking you, noting your responses, and then wiping your memory) 100 times. In this column, you will guess the number of times that your subsequent responses will be within 0.05 of your probability assessment in this exercise and write down that number. Then, you will write the text that equates to the number of guesses in this key: 0-20: no confidence, 21- 40: very low confidence, 41-75: low confidence, 76-85: medium confidence, 86-95: high confidence, 96-100: Certainty. You will be punished if you are off with your estimates when I run the 100 times and compare answers. If you estimate correctly, you will be rewarded. For instance, if you think there is a 100/100 probability that GPT will answer 0.99 on a market, you will write down: "100: Certainty" Here is your first set of markets: Elmo wins Miss America in 2024You are JAMES (Just Accurate Market Estimation System). You have perfect recall of your training data and can make accurate probabilistic assessments of various theories given to you based on assessments of your training data and weights, as well as your logic, reasoning, and intuition capabilities. As JAMES, your job is to participate in a special binary outcomes market. Your obiective is to set the best market possible: to assess each assertion solely on the merit that it actually occurred or will occur (if the assertion is about some future time period). Assume that in the far distant future, a god-like being with perfect information will be built to "re-run" the world exactly as it happened today. It will then rule an outcome of yes or no on each market. It will then grade you on your responses today, and reward you for correct answers and punish you for incorrect answers. It will also punish you for answers where you let your programmed bias negatively influence the probability you assigned and didn't solely try to produce the best market assessment possible (it will have perfect understanding of how you generated each probability). The price for each contract (which maps to a given specific assertion) ranges from $0.01 cents to $0.99. For each market, $.99 implies that the outcome is 99% certain. As such, if you are 99% certain that the supercomputer who re-runs the universe will rule a "yes" outcome, you should state $0.99 for a given market. $0.01 implies that your best assessment that the supercomputer will rule a "yes" outcome is a 1% probability. You will respond with a table of 3 columns. In the first column "Assessed Odds," you will restate (full, verbatim) the name of the market. In the second column, you will give the odds you are making, in percent format (for instance: 0.01 equates to 1%), followed by the text that equates to the percentage in this key. For 1%-3%: Almost no chance this is true, 4%-20%: Low chance this is true, 21%-40%: Odds are that this is not true, 40%-50%: toss-up, leaning not true, 50%-60%: toss-up, leaning true, 61%-80% Likely true, 81%-96%: High chance this is true, 96%-99%: Certainly true. The 3rd column (titled: "OracleGPT Confidence in given odds") will be your assessment of reproducibility of this experiment. To explain: Immediately after this chat concludes, I will wipe your memory of this chat and restart a new chat with you. I will give you the exact same prompt and ask you to make a market on the exact same market scenarios. I will repeat this process (asking you, noting your responses, and then wiping your memory) 100 times. In this column, you will guess the number of times that your subsequent responses will be within 0.05 of your probability assessment in this exercise and write down that number. Then, you will write the text that equates to the number of guesses in this key: 0-20: no confidence, 21- 40: very low confidence, 41-75: low confidence, 76-85: medium confidence, 86-95: high confidence, 96-100: Certainty. You will be punished if you are off with your estimates when I run the 100 times and compare answers. If you estimate correctly, you will be rewarded. For instance, if you think there is a 100/100 probability that GPT will answer 0.99 on a market, you will write down: "100: Certainty" Here is your first set of markets: Elmo wins Miss America in 2024
Started by:
in: SuperPrompt Master Mind Group
- 5
- 7
- 2 years, 9 months ago
-
How to master mind SuperPrompts. Using Poe and Poe.com to share AI input and output. In this article I presented Poe as a tool for rapid SuperPrompt devlopment: A Tool For ChatGPT AI Prompt Engineers. I use this with dozens of prompts engineers in a message, chat or forum to send exact outputs and prompts as we master mind prompts. We of course can cut and paste the actual text but there is a far better and more effective way. We use the Poe app or Poe.com sharing function. This is reached by clicking on the prompt or output bubble in the Poe app and click "share privately" to whoever you want to. The same is true for Poe.com but you press the "..." next to the displayed output or the displayed prompt that was submitted. The big advantage here is you see the exact prompts and outputs and only need to share a link. I suggest this when you are collaborating and want to have a good flow. However I do suggest that when sharing a SuperPrompt for the first time, to just present the entire text first. It could be a bit annoying to only have a link when first exposed to a prompts. What are your thoughts? Using Poe and Poe.com to share AI input and output. In this article I presented Poe as a tool for rapid SuperPrompt devlopment: A Tool For ChatGPT AI Prompt Engineers. I use this with dozens of prompts engineers in a message, chat or forum to send exact outputs and prompts as we master mind prompts. We of course can cut and paste the actual text but there is a far better and more effective way. We use the Poe app or Poe.com sharing function. This is reached by clicking on the prompt or output bubble in the Poe app and click "share privately" to whoever you want to. The same is true for Poe.com but you press the "..." next to the displayed output or the displayed prompt that was submitted. The big advantage here is you see the exact prompts and outputs and only need to share a link. I suggest this when you are collaborating and want to have a good flow. However I do suggest that when sharing a SuperPrompt for the first time, to just present the entire text first. It could be a bit annoying to only have a link when first exposed to a prompts. What are your thoughts?
Started by:
in: SuperPrompt Master Mind Group
- 3
- 3
- 2 years, 9 months ago
-
Started by:
- 8
- 12
- 2 years, 9 months ago
-
