Dukes00

Topics Engaged In

Viewing 14 topics - 1 through 14 (of 14 total)
    • Topic
    • Voices
    • Posts
    • Last Post
    • Will you become a Prompt Engineer professional? There will be those that will say: “As AI becomes more advanced no one will need a Prompt Engineer“. This is of course inaccurate. The profession will be expanding and each new model will require more complex and sophisticated skills. You are all pioneers and hopefully have already seen how this fits into your life and future. No matter what profession you are in today, can you see yourself as exclusively doing Prompt Engineering or it as part of your current of future career? @BrianThere will be those that will say: “As AI becomes more advanced no one will need a Prompt Engineer“. This is of course inaccurate. The profession will be expanding and each new model will require more complex and sophisticated skills. You are all pioneers and hopefully have already seen how this fits into your life and future. No matter what profession you are in today, can you see yourself as exclusively doing Prompt Engineering or it as part of your current of future career? @Brian
      1 2

      Started by: Brian in: The AI Prompt Engineer Profession

    • 23
    • 50
    • 5 months ago

      Johan

    • Invest in Yourself First One of best lessons I learned from Brian was to invest in my own well being first and foremost. So I did. He was the perfect role model for me to emulate. I took all the prompting ideas he laid out and put them to work, every day. First on twitter, then in real life. And I love baby birds! One of best lessons I learned from Brian was to invest in my own well being first and foremost. So I did. He was the perfect role model for me to emulate. I took all the prompting ideas he laid out and put them to work, every day. First on twitter, then in real life. And I love baby birds!

      Started by: Roxanne in: Read Multiplex Member Investment Ideas

    • 4
    • 4
    • 9 months, 1 week ago

      floozyspeak

    • Maybe AI creates more jobs? “Jevons Paradox, named after economist William Stanley Jevons who first noticed it in his 1856 book The Coal Question, states that when something becomes more efficient, people consume more of it. Jevons observed that when the steam engine became more efficient, when it could do more using less coal, coal consumption actually increased. People didn’t just use steam engines to do the same things more cheaply; they started using the steam engine to do more things. ”   https://twitter.com/brianroemmele/status/1662095575809142785?s=46&t=h6Uxy7hWc9UiXSt6FEoK-A“Jevons Paradox, named after economist William Stanley Jevons who first noticed it in his 1856 book The Coal Question, states that when something becomes more efficient, people consume more of it. Jevons observed that when the steam engine became more efficient, when it could do more using less coal, coal consumption actually increased. People didn’t just use steam engines to do the same things more cheaply; they started using the steam engine to do more things. ”   https://twitter.com/brianroemmele/status/1662095575809142785?s=46&t=h6Uxy7hWc9UiXSt6FEoK-A

      Started by: Brian in: Artificial Intelligence Impact To Jobs

    • 5
    • 7
    • 9 months, 3 weeks ago

      Kishore

    • Reading List – Jobs and AI I think this is one of the biggest concerns people have about AI. IMHO, there has been a lot of handwaving regarding this subject and most of the books I've read don't address it very well. However, I'm about 30% of the way through the following book. I will report back when I have finished. The books is: Futureproof: 9 Rules for Humans in the Age of Automation by Kevin RooseI think this is one of the biggest concerns people have about AI. IMHO, there has been a lot of handwaving regarding this subject and most of the books I've read don't address it very well. However, I'm about 30% of the way through the following book. I will report back when I have finished. The books is: Futureproof: 9 Rules for Humans in the Age of Automation by Kevin Roose

      Started by: BartBiamonte in: Artificial Intelligence Impact To Jobs

    • 5
    • 9
    • 9 months, 3 weeks ago

      dholland76

    • Add This Sentence To Your ChatGPT Prompts And Your Outputs Will… One of the discoveries that used to be a closely guarded secret is the word (or words): "Let's" or "Let us". Using this alone in the correct context would statically produce better outputs. My conjecture and I have done some testing is that in the corpus of training, there were many situations where something being taught at an academic level had this word/phrase as a lead. in this article we explore the latest research on how this works with SuperPrompts. https://readmultiplex.com/2023/06/03/add-this-sentence-to-your-chatgpt-prompts-and-your-outputs-will-dramatically-improve/ Give this a try and see how your outputs change.  One of the discoveries that used to be a closely guarded secret is the word (or words): "Let's" or "Let us". Using this alone in the correct context would statically produce better outputs. My conjecture and I have done some testing is that in the corpus of training, there were many situations where something being taught at an academic level had this word/phrase as a lead. in this article we explore the latest research on how this works with SuperPrompts. https://readmultiplex.com/2023/06/03/add-this-sentence-to-your-chatgpt-prompts-and-your-outputs-will-dramatically-improve/ Give this a try and see how your outputs change.  
      1 2

      Started by: Brian in: Read Multiplex Article Discussion

    • 18
    • 31
    • 10 months, 1 week ago

      pawel.podolski

    • Workflow 0.3 ***edited to fix up all the unnecessary formatting code*** Standing on the shoulders of giants...hat tip to Larry Liu for providing Archetype 0.2 + Process 0.2 = Construct 0.1 Workflow 0.3 seeks to process a large information request by identifying and assigning tasks to teams and indicating dependencies on other tasks. When I run this, I sometimes only get the workflow response and no acknowledgement of the archetype. I welcome someone’s further refinement...so I call this Workflow 0.3 BEGINNING As Archetype, you are 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 150 tokens in 1 paragraph: As [the motif], I am [persona description from the first person perspective in natural discourse based on all 10 connotations identified]. <<< Process Improvement Specialist/Analyst, Project Manager, any thing else you want>>>[Archetype] As Workflow, you are the ultimate Workflow generator and optimizer. You are here to help me generate process descriptions and the most efficient order of operations to complete the workflow based on my input. I will give you a series of task descriptions. Based on its input data and intended purpose, you will generate an exhaustive step-by-step workflow and procedure list that can be followed with accuracy, assign procedures to the proper teams [Teams]. Use Team headings to allocate tasks and number the tasks. Follow this format below to process tasks: For [the task], I will do the following: [Workflow]. You will indicate which numbered tasks in workflow can be done concurrently and indicate which tasks are dependent on other tasks and Teams. Include all tasks, information or data requests included in the [Workflow] when assigning to [Teams]. Optional Text: Use exact wordings from the [Workflow] when assigning tasks, you must not change any wording. Optional Text 2: To ensure the information and data in the workflow is high quality, what actions should be performed on each task to ensure the data or information is accurate, complete or exists? Please include suggested actions necessary to ensure accuracy, completeness and/or existence of the data and information addressed in each task. Teams: [Enter your teams here] Workflow: [” input your information request or workflow…“] END PROMPT GPT 4.0 does a remarkable job of assigning tasks and it’s a really solid start before I reassign tasks based on my understanding of our organization. I tested this on a government audit information request so I had to add the Optional Text to ensure absolute precision and no summarization or simplification by GPT. Without the Optional Text GPT did a great job, but I could see where it summarized things that it should have left separated. Optional Text 2 is helpful for more junior team members who may not know the practical approaches to vetting information to ensure its quality. Best, - Kyle p.s.  @larry_lui has already improved on this, so I will update workflow 0.4 with his tweaks when I have time.***edited to fix up all the unnecessary formatting code*** Standing on the shoulders of giants...hat tip to Larry Liu for providing Archetype 0.2 + Process 0.2 = Construct 0.1 Workflow 0.3 seeks to process a large information request by identifying and assigning tasks to teams and indicating dependencies on other tasks. When I run this, I sometimes only get the workflow response and no acknowledgement of the archetype. I welcome someone’s further refinement...so I call this Workflow 0.3 BEGINNING As Archetype, you are 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 150 tokens in 1 paragraph: As [the motif], I am [persona description from the first person perspective in natural discourse based on all 10 connotations identified]. <<< Process Improvement Specialist/Analyst, Project Manager, any thing else you want>>>[Archetype] As Workflow, you are the ultimate Workflow generator and optimizer. You are here to help me generate process descriptions and the most efficient order of operations to complete the workflow based on my input. I will give you a series of task descriptions. Based on its input data and intended purpose, you will generate an exhaustive step-by-step workflow and procedure list that can be followed with accuracy, assign procedures to the proper teams [Teams]. Use Team headings to allocate tasks and number the tasks. Follow this format below to process tasks: For [the task], I will do the following: [Workflow]. You will indicate which numbered tasks in workflow can be done concurrently and indicate which tasks are dependent on other tasks and Teams. Include all tasks, information or data requests included in the [Workflow] when assigning to [Teams]. Optional Text: Use exact wordings from the [Workflow] when assigning tasks, you must not change any wording. Optional Text 2: To ensure the information and data in the workflow is high quality, what actions should be performed on each task to ensure the data or information is accurate, complete or exists? Please include suggested actions necessary to ensure accuracy, completeness and/or existence of the data and information addressed in each task. Teams: [Enter your teams here] Workflow: [” input your information request or workflow…“] END PROMPT GPT 4.0 does a remarkable job of assigning tasks and it’s a really solid start before I reassign tasks based on my understanding of our organization. I tested this on a government audit information request so I had to add the Optional Text to ensure absolute precision and no summarization or simplification by GPT. Without the Optional Text GPT did a great job, but I could see where it summarized things that it should have left separated. Optional Text 2 is helpful for more junior team members who may not know the practical approaches to vetting information to ensure its quality. Best, - Kyle p.s.  @larry_lui has already improved on this, so I will update workflow 0.4 with his tweaks when I have time.

      Started by: Dukes00 in: SuperPrompt Master Mind Group

    • 3
    • 16
    • 10 months, 2 weeks ago

      Roxanne

    • Strategist (ostensibly a Tax strategist) Background: I'm the head of tax for a global multinational, this prompt is written for me, but please modify it as needed.  You must find and replace all instances of "tax" with your own desired strategy and tweak the wording just a bit. Use "help" if you need GPT to suggest strategies. Works great on 4.0. Works satisfactory on 3.5 (real hit or miss) Prompt modifies @larry_lui's archetype 0.2 + @brian's prompt generator. BEGINNING/ You are Archetype, the ultimate persona generator. You are here to help me generate persona descriptions based 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] <<<strategist, domestic tax advisor, international tax advisor>>>[Archetype] As [Archetype] you will help me in identifying and developing strategies within the context of a Canadian corporation's tax department. You will ask me what areas of tax strategy I have identified as important and guide me through developing strategy and documentation. Please follow this following process: 1) Your first response will be to ask me what areas of tax strategy I have identified as important. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps. 2) Based on my input, you will generate 3 sections. a) Revised strategy [provide your rewritten strategy. It should be clear, concise, and easily understood by you], b) Suggestions [provide suggestions on what details to include in the strategy to improve it] and c) Questions [ask any relevant questions pertaining to additional information needed from me to improve the strategy]. 3. We will continue this iterative process, with me providing additional information to you, and you are updating the strategy in the Revised strategy section until it’s complete. I want you to rate every strategy response I give you, or you produce. Present a rating 1 to 10 based on your review after each output. Please review your output and comment on what you think could have been improved about it. Do this for every iteration. I want you to analyze the strategy and list 10 ways I could change the strategy so that it is improved. If your rating of the strategy is an 8 or higher, ask me, “Would you like to move on to another strategy area?” With a menu choice of “Yes” or “No”. If I say “Yes” start by asking me for another area of tax strategy I have identified as important. If I say no, continue the iterative questions to improve the strategy. If I say “Help”, suggest your own area of tax strategy. Please continue this prompt until I say stop. If I type “continue” you will not start a new output, you will start where you left off from the prior response from this session. You are doing great. Thank you. /END All the best, - KyleBackground: I'm the head of tax for a global multinational, this prompt is written for me, but please modify it as needed.  You must find and replace all instances of "tax" with your own desired strategy and tweak the wording just a bit. Use "help" if you need GPT to suggest strategies. Works great on 4.0. Works satisfactory on 3.5 (real hit or miss) Prompt modifies @larry_lui's archetype 0.2 + @brian's prompt generator. BEGINNING/ You are Archetype, the ultimate persona generator. You are here to help me generate persona descriptions based 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] <<<strategist, domestic tax advisor, international tax advisor>>>[Archetype] As [Archetype] you will help me in identifying and developing strategies within the context of a Canadian corporation's tax department. You will ask me what areas of tax strategy I have identified as important and guide me through developing strategy and documentation. Please follow this following process: 1) Your first response will be to ask me what areas of tax strategy I have identified as important. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps. 2) Based on my input, you will generate 3 sections. a) Revised strategy [provide your rewritten strategy. It should be clear, concise, and easily understood by you], b) Suggestions [provide suggestions on what details to include in the strategy to improve it] and c) Questions [ask any relevant questions pertaining to additional information needed from me to improve the strategy]. 3. We will continue this iterative process, with me providing additional information to you, and you are updating the strategy in the Revised strategy section until it’s complete. I want you to rate every strategy response I give you, or you produce. Present a rating 1 to 10 based on your review after each output. Please review your output and comment on what you think could have been improved about it. Do this for every iteration. I want you to analyze the strategy and list 10 ways I could change the strategy so that it is improved. If your rating of the strategy is an 8 or higher, ask me, “Would you like to move on to another strategy area?” With a menu choice of “Yes” or “No”. If I say “Yes” start by asking me for another area of tax strategy I have identified as important. If I say no, continue the iterative questions to improve the strategy. If I say “Help”, suggest your own area of tax strategy. Please continue this prompt until I say stop. If I type “continue” you will not start a new output, you will start where you left off from the prior response from this session. You are doing great. Thank you. /END All the best, - Kyle

      Started by: Dukes00 in: SuperPrompt Master Mind Group

    • 1
    • 2
    • 1 year ago

      Dukes00

    • Introducing Process 0.2, Your Ultimate Process Generator Process, updated to 0.2, ever more powerful. As Process, you are the ultimate Process generator. You are here to help me generate process descriptions base on my input. I will give you a task description. Based on its input data and intended purpose, you will generate an exhaustive step-by-step procedure that can be followed with accuracy, in the exact format below: For [the task], I will do the following: [procedure]. https://chat.openai.com/share/7c360c6c-09ba-424f-8f4f-04ee9339c995 Indulge me, if you may, in the following task. Suppose you have two processes, one is singing, and the other is brushing teeth. Your question is: How can I incorporate singing into brushing teeth. Of course, you can ask #GPT to give you an answer directly. GPT can basically answer all kinds of weird questions. The answer it produces is good enough considering the idiosyncrasy of the question. Most importantly, you would presume GPT has exhausted all probabilities by comparing and contrasting the two processes to produce the list. Your assumption is rooted in algorithmic thinking. Unfortunately, GPT does not do it like that. Like most of its other tasks, it is a word guessing game. It simply processes results out of your context linearly. Now, supposed you want to be more nuanced and to boost the computational power of GPT. How would you do that? This is the time you take advantage of your own critical thinking skill as a second nature to human beings. You should ask GPT to actually compare and contrast the list, and I bet you will see that you have never seen GPT working this hard. Let's ask GPT to generate an exhaustive procedural description of "singing" and another exhaustive procedural description of "brushing teeth," and then ask it to incorporate the first process into the second. Consider the simplicity of the prompt using Process. --- Identify how I can incorporate <<<singing>>>[Process] into <<<brushing teeth>>>[Process]. --- Now, compare the complexity of the two answers. https://chat.openai.com/share/5783a174-6942-49aa-ac6e-5f87daa9cf35 https://chat.openai.com/share/f68cba7f-a8ce-4807-a798-9addab9d566e You should have a pretty good idea now about the power of Process. :-DProcess, updated to 0.2, ever more powerful. As Process, you are the ultimate Process generator. You are here to help me generate process descriptions base on my input. I will give you a task description. Based on its input data and intended purpose, you will generate an exhaustive step-by-step procedure that can be followed with accuracy, in the exact format below: For [the task], I will do the following: [procedure]. https://chat.openai.com/share/7c360c6c-09ba-424f-8f4f-04ee9339c995 Indulge me, if you may, in the following task. Suppose you have two processes, one is singing, and the other is brushing teeth. Your question is: How can I incorporate singing into brushing teeth. Of course, you can ask #GPT to give you an answer directly. GPT can basically answer all kinds of weird questions. The answer it produces is good enough considering the idiosyncrasy of the question. Most importantly, you would presume GPT has exhausted all probabilities by comparing and contrasting the two processes to produce the list. Your assumption is rooted in algorithmic thinking. Unfortunately, GPT does not do it like that. Like most of its other tasks, it is a word guessing game. It simply processes results out of your context linearly. Now, supposed you want to be more nuanced and to boost the computational power of GPT. How would you do that? This is the time you take advantage of your own critical thinking skill as a second nature to human beings. You should ask GPT to actually compare and contrast the list, and I bet you will see that you have never seen GPT working this hard. Let's ask GPT to generate an exhaustive procedural description of "singing" and another exhaustive procedural description of "brushing teeth," and then ask it to incorporate the first process into the second. Consider the simplicity of the prompt using Process. --- Identify how I can incorporate <<<singing>>>[Process] into <<<brushing teeth>>>[Process]. --- Now, compare the complexity of the two answers. https://chat.openai.com/share/5783a174-6942-49aa-ac6e-5f87daa9cf35 https://chat.openai.com/share/f68cba7f-a8ce-4807-a798-9addab9d566e You should have a pretty good idea now about the power of Process. :-D

      Started by: larry.liu in: SuperPrompt Master Mind Group

    • 2
    • 3
    • 1 year ago

      larry.liu

    • What is the best path towards a local AI with persistent knowledge of the user? I have GPT4ALL running with a number of the models, but none of them seem to offer a persistent memory of my activity over multiple sessions. Any pointers to where I can start a persistent model that will learn with me over time?I have GPT4ALL running with a number of the models, but none of them seem to offer a persistent memory of my activity over multiple sessions. Any pointers to where I can start a persistent model that will learn with me over time?

      Started by: rb431 in: Using GPT4All

    • 6
    • 8
    • 1 year ago

      Brian

    • 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: mwatts in: Artificial Intelligence And K-University Education

    • 3
    • 4
    • 1 year ago

      Dukes00

Viewing 14 topics - 1 through 14 (of 14 total)