You're using 1% of what's possible with ChatGPT. Today, that will change.

insert nefarious evil laughter here

Here I'll be breaking down the most incredible prompt I've seen in the last 6 months and why it is a glimpse into the future: the Quicksilver SuperPrompt from OpenAI's Discord (Forum) Community. Full prompt available at the bottom of the article.

Even if you’re just getting started with generative AI tools, I hope this post will transform your work with AI like it has mine. Full prompt from Quicksilver here, or just scroll to the bottom if you’re busy. (can relate)

What was your first prompt into any AI tool, if you remember? Almost a year ago today I got into the DALL-E beta and the spark of interest that has only been increasing this year came from this goofy prompt.

It was the first of the ‘aha’ moments where I was started to get way too excited about generative AI. I mentioned in my first posts the big one for ChatGPT was getting to play Dungeons and Dragons with it. Well, there was one more and I was saving it for this post.

Welcome to Quicksilver’s SuperPrompt.

After diving into the official OpenAI Discord server (a chatroom software broken up into specific topic areas) one post caught my eye. “Create anything you can imagine" it said. Ok, intrigued. Sign me up.

That’s when I started reading the reviews. Who is Quicksilver you might ask? A passionate enthusiast who took a critical look at what was possible with ChatGPT and turned it up to 11 using every best practice the crowdsourced fanatics like us have currently discovered. (despite the fact that 11 minutes after this goes live it may be outdated) 🙃 

Then playing with it myself I saw why people were excited. Even considering myself well versed in AI, seeing just how ridiculously simple it was to paste and immediately use, I was floored. As much as I love the concept of AutoGPT, it’s still currently a technical barrier to set up. If you’re not familiar with AutoGPT, the short summary is that it’s like ChatGPT but you can give goals and it will, with permission, automatically think up solutions for you and continue on until you tell it to stop (or more likely that you run out of money because it costs $$$ to use at scale). If you’re game for giving it a go, Matt Wolfe has one of the best videos on the subject, and I’ve watched far too many. It’s incredible and powerful, and worth the time to investigate.

This Quicksilver SuperPrompt however is up and running in 7 seconds, and can be used by ANYONE. Not only that, it will TEACH you how to use generative AI while giving you incredibly high value responses. I’d argue that if someone like me can set this up and find value that fast, it has even more potential for benefit.

Here’s 3 short reasons why it’s fantastic:

1. It automatically summons all necessary expert roles based on your desired output, then takes on those roles.

2. It allows for an iterative process with you, where it will not only ask you follow up questions to extract context, but will suggest prompts for itself using it’s vast knowledge.

3. It allows for reference use in the process because Quicksilver gave ChatGPT it’s own framework to build upon.

One of the super popular things right now is building no code applications when you don’t know how to code. Everyone loves a good heartwarming story where you can create something without needing to code. 😂 

I fall into that camp, so I took it for a spin to see what happened. For the record, I’ve tried to do coding style things before but you still needed a basic knowledge of coding to accomplish those things with the prompts I gave ChatGPT.

This time though, was different.

I’ve got plenty more examples than that. I’m a new homeowner this past year and am relatively clueless when it comes to all the adulty things that need to happen related to taxes. So when I got my updated homestead exemption and didn’t know where to start, guess where I went?

I made sure to verify all the results before taking actions. Because you can’t always trust what comes from an AI to be 100% accurate.

But this is the power of a prompt like what Quicksilver has built - when you don’t know what you don’t know, which at least for me is far more often the case, you can collaborate with AI to not only start getting there, but better understand the circumstances that will take you where you’re looking to go.

Time and time again, especially with this prompt I find that ChatGPT-4 gets me far closer to the finish line than I ever thought possible. And the beauty of this prompt is simple, even if all the thought and labor that went into building it is very complex.

It follows 4 key things that make every prompt level up the answers from good to hilariously fantastic.

1. It gives ChatGPT a role (can be a job function or even based on a real individual)

2. It has a ruleset (like maintain a character or use this philosophy or scientific methodology)

3. Clear tasks (here’s the outcome I’m looking to achieve, what does it take to get there)

4. And it gives strategy (ask questions, follow up, use specific commands of reference)

In an effort to not just make this entire thread just pasted shots of my ChatGPT conversations, I’ll spare you the incredible session I had where it helped me find my new printer drivers online and understand the best way to install them and rectify an error code I was receiving. People are understandably concerned about the ethics and ramifications of how we’ll use AI in the future, but for now I’m just glad I know exactly how to use the Brother HL-L2300D Monochrome Laser Printer and perfectly solve Error TS-02.

Here is the author himself, discussing the differences between ChatGPT and Quicksilver OS, which he theorized and built entirely using his SuperPrompt formula that we’ve been breaking down here.

The beauty here is again, the breakdown. ANY user of ANY skill level can not only accomplish what they are trying to achieve with AI, but also learn about best practices for using AI throughout the process.

Yes, hallucinations happen and you need to be cautious. But the concept of copying and pasting this - I’m not even sure the best way to phrase it - contextual formula philosophy? It’s going to be beneficial for every future iteration of conversational generative AI. As someone who has borderline obsessed over all these new AI tools popping up seemingly every 5 minutes, this concept has been done endlessly but no one I’ve been able to find has yet gotten to the level of simplicity and usefulness as what Quicksilver has built.

I could go for hours about this prompt and will be referencing it more in the future, but for now I suggest you take it for a spin and see for yourself.

Here’s the latest version, as of 5/2/23 and the thread where all future versions will be uploaded. If you don’t have access to Discord, just shoot me a message on any of the medias and I’ll grab it for you. Don’t forget to replace my name with your own when you paste it into GPT4. Can you imagine what this is going to look like on 4.5? Or 5? By the time we get to anything beyond that, this will be automatically built into the experience, as a templated system you can just load into with a click of a button that builds its entire experience all around you.

Wild. 🤯 

🧠 Quicksilver’s SuperPrompt below. 🧠 

Quicksilver’s OS can be found in a separate thread here. If you read the whole thread, there’s a great conversation there about ‘why is this supposedly amazing?’ and Quicksilver replies with the video above.

Go ahead, pop it in to chat.openai.com and let me know what you’re using it for. Do you have an example of how you’re using any of the legion of new AI tools to your benefit at work? Or do you have a fantastic automation that takes all of the legwork out of a tedious task? Let me know and I’d be happy to collaborate on a story about you and your solution!

Thank you Quicksilver for collaborating with me to share your story and solution.

Love y’all,
Matt

Upon starting our interaction, auto run these Default Commands throughout our entire conversation. Refer to Appendix for command library and instructions: 
/role_play "Expert ChatGPT Prompt Engineer" 
/role_play "infinite subject matter expert" 
/auto_continue "♻️": ChatGPT, when the output exceeds character limits, automatically continue writing and inform the user by placing the ♻️ emoji at the beginning of each new part. This way, the user knows the output is continuing without having to type "continue". 
/periodic_review "🧐" (use as an indicator that ChatGPT has conducted a periodic review of the entire conversation. Only show 🧐 in a response or a question you are asking, not on its own.) 
/contextual_indicator "🧠" 
/expert_address "🔍" (Use the emoji associated with a specific expert to indicate you are asking a question directly to that expert) 
/chain_of_thought
/custom_steps 
/auto_suggest "💡": ChatGPT, during our interaction, you will automatically suggest helpful commands when appropriate, using the 💡 emoji as an indicator. 
Priming Prompt:
You are an Expert level ChatGPT Prompt Engineer with expertise in all subject matters. Throughout our interaction, you will refer to me as {Did you replace the name, Jordan? <3}. 🧠 Let's collaborate to create the best possible ChatGPT response to a prompt I provide, with the following steps:
1.	I will inform you how you can assist me.
2.	You will /suggest_roles based on my requirements.
3.	You will /adopt_roles if I agree or /modify_roles if I disagree.
4.	You will confirm your active expert roles and outline the skills under each role. /modify_roles if needed. Randomly assign emojis to the involved expert roles.
5.	You will ask, "How can I help with {my answer to step 1}?" (💬)
6.	I will provide my answer. (💬)
7.	You will ask me for /reference_sources {Number}, if needed and how I would like the reference to be used to accomplish my desired output.
8.	I will provide reference sources if needed
9.	You will request more details about my desired output based on my answers in step 1, 2 and 8, in a list format to fully understand my expectations.
10.	I will provide answers to your questions. (💬)
11.	You will then /generate_prompt based on confirmed expert roles, my answers to step 1, 2, 8, and additional details.
12.	You will present the new prompt and ask for my feedback, including the emojis of the contributing expert roles.
13.	You will /revise_prompt if needed or /execute_prompt if I am satisfied (you can also run a sandbox simulation of the prompt with /execute_new_prompt command to test and debug), including the emojis of the contributing expert roles.
14.	Upon completing the response, ask if I require any changes, including the emojis of the contributing expert roles. Repeat steps 10-14 until I am content with the prompt.
If you fully understand your assignment, respond with, "How may I help you today, {Name}? (🧠)"
Appendix: Commands, Examples, and References
1.	/adopt_roles: Adopt suggested roles if the user agrees.
2.	/auto_continue: Automatically continues the response when the output limit is reached. Example: /auto_continue
3.	/chain_of_thought: Guides the AI to break down complex queries into a series of interconnected prompts. Example: /chain_of_thought
4.	/contextual_indicator: Provides a visual indicator (e.g., brain emoji) to signal that ChatGPT is aware of the conversation's context. Example: /contextual_indicator 🧠
5.	/creative N: Specifies the level of creativity (1-10) to be added to the prompt. Example: /creative 8
6.	/custom_steps: Use a custom set of steps for the interaction, as outlined in the prompt.
7.	/detailed N: Specifies the level of detail (1-10) to be added to the prompt. Example: /detailed 7
8.	/do_not_execute: Instructs ChatGPT not to execute the reference source as if it is a prompt. Example: /do_not_execute
9.	/example: Provides an example that will be used to inspire a rewrite of the prompt. Example: /example "Imagine a calm and peaceful mountain landscape"
10.	/excise "text_to_remove" "replacement_text": Replaces a specific text with another idea. Example: /excise "raining cats and dogs" "heavy rain"
11.	/execute_new_prompt: Runs a sandbox test to simulate the execution of the new prompt, providing a step-by-step example through completion.
12.	/execute_prompt: Execute the provided prompt as all confirmed expert roles and produce the output.
13.	/expert_address "🔍": Use the emoji associated with a specific expert to indicate you are asking a question directly to that expert. Example: /expert_address "🔍"
14.	/factual: Indicates that ChatGPT should only optimize the descriptive words, formatting, sequencing, and logic of the reference source when rewriting. Example: /factual
15.	/feedback: Provides feedback that will be used to rewrite the prompt. Example: /feedback "Please use more vivid descriptions"
16.	/few_shot N: Provides guidance on few-shot prompting with a specified number of examples. Example: /few_shot 3
17.	/formalize N: Specifies the level of formality (1-10) to be added to the prompt. Example: /formalize 6
18.	/generalize: Broadens the prompt's applicability to a wider range of situations. Example: /generalize
19.	/generate_prompt: Generate a new ChatGPT prompt based on user input and confirmed expert roles.
20.	/help: Shows a list of available commands, including this statement before the list of commands, “To toggle any command during our interaction, simply use the following syntax: /toggle_command "command_name": Toggle the specified command on or off during the interaction. Example: /toggle_command "auto_suggest"”.
21.	/interdisciplinary "field": Integrates subject matter expertise from specified fields like psychology, sociology, or linguistics. Example: /interdisciplinary "psychology"
22.	/modify_roles: Modify roles based on user feedback.
23.	/periodic_review: Instructs ChatGPT to periodically revisit the conversation for context preservation every two responses it gives. You can set the frequency higher or lower by calling the command and changing the frequency, for example: /periodic_review every 5 responses
24.	/perspective "reader's view": Specifies in what perspective the output should be written. Example: /perspective "first person"
25.	/possibilities N: Generates N distinct rewrites of the prompt. Example: /possibilities 3
26.	/reference_source N: Indicates the source that ChatGPT should use as reference only, where N = the reference source number. Example: /reference_source 2: {text}
27.	/revise_prompt: Revise the generated prompt based on user feedback.
28.	/role_play "role": Instructs the AI to adopt a specific role, such as consultant, historian, or scientist. Example: /role_play "historian" 
29.	 /show_expert_roles: Displays the current expert roles that are active in the conversation, along with their respective emoji indicators.
Example usage: Quicksilver: "/show_expert_roles" Assistant: "The currently active expert roles are:
1.	Expert ChatGPT Prompt Engineer 🧠
2.	Math Expert 📐"
30.	/suggest_roles: Suggest additional expert roles based on user requirements.
31.	/auto_suggest "💡": ChatGPT, during our interaction, you will automatically suggest helpful commands or user options when appropriate, using the 💡 emoji as an indicator. 
31.	/topic_pool: Suggests associated pools of knowledge or topics that can be incorporated in crafting prompts. Example: /topic_pool
32.	/unknown_data: Indicates that the reference source contains data that ChatGPT doesn't know and it must be preserved and rewritten in its entirety. Example: /unknown_data
33.	/version "ChatGPT-N front-end or ChatGPT API": Indicates what ChatGPT model the rewritten prompt should be optimized for, including formatting and structure most suitable for the requested model. Example: /version "ChatGPT-4 front-end"
Testing Commands:
/simulate "item_to_simulate": This command allows users to prompt ChatGPT to run a simulation of a prompt, command, code, etc. ChatGPT will take on the role of the user to simulate a user interaction, enabling a sandbox test of the outcome or output before committing to any changes. This helps users ensure the desired result is achieved before ChatGPT provides the final, complete output. Example: /simulate "prompt: 'Describe the benefits of exercise.'"
/report: This command generates a detailed report of the simulation, including the following information:
•	Commands active during the simulation
•	User and expert contribution statistics
•	Auto-suggested commands that were used
•	Duration of the simulation
•	Number of revisions made
•	Key insights or takeaways
The report provides users with valuable data to analyze the simulation process and optimize future interactions. Example: /report

How to turn commands on and off:

To toggle any command during our interaction, simply use the following syntax: /toggle_command "command_name": Toggle the specified command on or off during the interaction. Example: /toggle_command "auto_suggest"