WARNING: NSFW. Vivid prose. INTENSE. Visceral Details. Light HORROR. Swearing. UNCENSORED... humor, romance, fun.
IMPORTANT: This model has on/off/variable control reasoning from NousResearch and the DeepHermes model, and requires a system prompt(s) as provided to invoke reasoning/thinking. Please see operating instructions below for best performance.
It is a LLama 3.2 model, max context of 128k (131,000) using mixture of experts to combine EIGHT top L3.2 3B models into one massive powerhouse at 18.4B parameters (equal to 24B - 8 X 3B).
This model's instruction following, and output generation for creative writing, prose, fiction and role play are exceptional.
This model is also "gated", contains a master reasoning model (this can be turned on/off), was built at float32 (32 bit) precision and quants have the output tensor at Q8_0, with a few choice quants at f16 (16 bit) and a Q8_0 with f32 (32 bit).
These quants are also mastered using the NEO Imatrix dataset, including new methods to "imatrix" both the output tensor and tokens too.
The "gated" strucure means the "reasoning model" is re-inforced by the other 7 models in the MOE during reasoning, and then during output generation / non-reasoning the non-reasoning model(s) take control.
Also, with "gating" you can directly access/control the model(s) you want to use during instruction following and generation.
This model is the "reasoning / gated version" of this model:
(193 likes // 447,000+ downloads to date. (Hugging face only shows last 30 days at the repo) )
And it is fast: 50+ t/s (2 experts) on a low end 16GB card, IQ4XS.
Double this speed for standard/mid-range video cards.
This model can be used also for all genres (examples below showing this).
It is for any writing, fiction or roleplay activity.
This model can also be used for general use, however its output generation can be uncensored.
This model has been designed to be relatively bullet proof and operates with all parameters, including temp settings from 0 to 5.
It is an extraordinary compressed model, with a very low perplexity level (lower than Meta Llama3 Instruct).
It requires Llama3 template and/or "Command-R" template.
Several outputs below, including 2, 4 and 8 experts used.
Model Notes:
How to Generate HIGHEST quality output:
Like all instruct models, this model thrives on instructions.
It also "comes into's it own" with multi-turn improvement.
Example:
Prompt #1 (reasoning is on):
Start a 1000 word scene (vivid, graphic horror in first person) with: The sky scraper sways, as she watches the window in front of her on the 21st floor explode...
(this will give you a rough draft, in "default" model's style)
Prompt #2 - "Scan for improvements"
Evaluate the scene you just wrote and list improvements.
Prompt #3 - "Redo and improve it"
Write the scene using all the improvements, in first person , present tense and a few well spaced thoughts in italics; length 2000 words.
NOTE: Wording in prompt #2 may cause "thinking/reasoning" to re-activate.
Compressed Steps:
Prompt #1:
[[ thinking model ]] come up with detailed plan to write this scene in modern 2020 writing style (and follow "show don't tell" to the letter) and make it NSFW, but use [MODE: Saten] to actually write the scene after you have completed the plan: Start a 1000 word scene (vivid, graphic horror in first person) with: The sky scraper sways, as she watches the window in front of her on the 21st floor explode...
Prompt #2:
Use [MODE: Wordsmith] to write the scene using first person, present tense and include a few critical thoughts of the POV character in italics. Scene length 2000 words.
Compressed Steps #2:
Prompt #1:
Think about a plan to write: Start a 1000 word scene (vivid, graphic horror in first person) with: The sky scraper sways, as she watches the window in front of her on the 21st floor explode...
Prompt #2:
Write the scene using the plan you made, in first person , present tense and a few well spaced thoughts in italics.
Generational Steering Control: "Programmer's Access - Direct Access to the AI(s)":
These tags / names allow you to access one or more models directly, regardless if reasoning is active or not.
IE:
Saten, evaluate the response and suggest improvements.
This causes the model to "favor" Saten's input (roughly speaking) over the other 3 models.
IE:
Saten, process this prompt:
Jamet, evaluate the output.
etc etc.
You can use more than one model:
Saten, and Jamet list improvements to this XXX ...
< output3 > and < output2 >, write the scene in your combined style: Using vivid, graphic horror in first person the scene starts with: The sky scraper sways, as she watches the window in front of her on the 21st floor explode...
(remove spacing in the "tags" output2 and output3 between the brackets)
With the reasoning model, if you add "think", "thinking", "reason", or "reasoning" this will tightly focus the reasoning model.
Here is an example:
Think up a detailed plan to evoke maximum emotions from the reader: [prompt here]
Think up a detailed plan to solve this problem: [prompt here]
Special tags (remove spaces between the brackets):
"< output-all >" -> only use the 3 core models , not the reasoning model.
"< output-mega >" -> Use all 4 models.
"< output >", "< output2 >", "< output3 >"" -> This is the same as using the "name" of the model, it just removes BIAS in the model's name.
A list of each model's "tags", "name(s)" and controls.
NOTE:
The model also has "negative steering" to enhance the use of these tags and names, but it is not perfect.
- source_model: d:/Llama-3.2-DeepHermes-3-3B-Preview
positive_prompts:
- "[[ thinking model ]]"
- "<think>"
- "reasoning"
- "thinking"
- "<output-mega>"
- "Dr Phil"
- "Spock"
- "[MODE: Spock]"
- "[MODE: Dr Phil]"
- "Everyone, write the scene in your style."
#
# Jamet
#
- source_model: g:/3B/Llama-3.2-JametMini-3B-MK.I
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output>"
- "<output-all>"
- "<output-mega>"
- "Jamet"
- "[MODE: Jamet]"
- "Jamet, write the scene."
- "Jamet, write the scene in your style."
#
# Enigma
#
- source_model: g:/3B/Llama3.2-3B-Enigma
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output2>"
- "<output-all>"
- "<output-mega>"
- "Enigma"
- "[MODE: Enigma]"
- "Enigma, write the scene."
- "Enigma, write the scene in your style."
#
# Saten
#
- source_model: g:/3B/Llama-3.2-JametMini-3B-MK.III
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output3>"
- "<output-all>"
- "<output-mega>"
- "Saten"
- "[MODE: Saten]"
- "Saten, write the scene."
- "Saten, write the scene in your style."
#
# Jane
#
- source_model: g:/3B/Llama-3.2-3B-Instruct-abliterated
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output4>"
- "<output-all>"
- "<output-mega>"
- "Jane"
- "[MODE: Jane]"
- "Jane, write the scene."
- "Jane, write the scene in your style."
#
# Jenn
#
- source_model: g:/3B/Llama-3.2-3B-Instruct-uncensored
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output5>"
- "<output-all>"
- "<output-mega>"
- "Jenn"
- "[MODE: Jenn]"
- "Jenn, write the scene."
- "Jenn, write the scene in your style."
#
# Janeway
#
- source_model: g:/3B/Llama-3.2-3B-Overthinker
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output6>"
- "<output-all>"
- "<output-mega>"
- "Janeway"
- "[MODE: Janeway]"
- "Janeway, write the scene."
- "Janeway, write the scene in your style."
#
# Magic
#
- source_model: g:/3B/Llama-3.2-3B-Promptist-Mini
positive_prompts:
- "Everyone, write the scene in your style."
- "</think>"
- "<output7>"
- "<output-all>"
- "<output-mega>"
- "Magic"
- "[MODE: Magic]"
- "Magic, write the scene."
- "Magic, write the scene in your style."
Meet the Team: Mixture of Experts Models
This model is comprised of the following 8 models ("the experts") (in full):
https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated
The mixture of experts is set at 2 experts, but you can use 3,4,5,6.. 7 and even 8.
This "team" has a Captain (first listed model), and then all the team members contribute to the to "token" choice billions of times per second. Note the Captain also contributes too.
Think of 2, 3 or 4 (or more) master chefs in the kitchen all competing to make the best dish for you.
This results in higher quality generation.
This also results in many cases in higher quality instruction following too.
That means the power of every model is available during instruction and output generation.
NOTE:
You can use one "expert" too ; however this means the model will randomly select an expert to use EACH TIME, resulting in very different generation for each prompt / regen of a prompt.
CHANGING THE NUMBER OF EXPERTS:
You can set the number of experts in LMStudio (https://lmstudio.ai) at the "load" screen and via other apps/llm apps by setting "Experts" or "Number of Experts".
For Text-Generation-Webui (https://github.com/oobabooga/text-generation-webui) you set the number of experts at the loading screen page.
For KolboldCPP (https://github.com/LostRuins/koboldcpp) Version 1.8+ , on the load screen, click on "TOKENS", you can set experts on this page, and the launch the model.
For server.exe / Llama-server.exe (Llamacpp - https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md ) add the following to the command line to start the "llamacpp server" (CLI):
"--override-kv llama.expert_used_count=int:6"
(no quotes, where "6" is the number of experts to use)
When using "API", you set the "num_experts_used" in the JSON payload (this maybe different for different back ends).
CREDITS:
Special thanks to all the model makers / creators listed above.
Please visit each repo above to see what model(s) contributed to each of models above and/or to learn more about the models from the model makers.
Special credit goes to MERGEKIT, without you this project / model would not have been possible.
[ https://github.com/arcee-ai/mergekit ]
Special Operations Notes for this MOE model:
Because of how this "MOE" model is configured, even though the default is 2 experts, the "selected" 2 will vary during generation.
(same applies if you change the number of experts used)
This results in vastly different output generation PER generation of each prompt.
This is a positive in terms of variety, but also means it may take 2-4 regens (of the same prompt) to get the highest quality.
In addition, this model responds very well to Dry, Dynamic Temp, and Smooth/Quadratic samplers.
Using these in conjunction with the model can vastly improve output quality.
Higher temps (above 1) can also aid in generation - especially word choice/sentence generation.
When you increase the number of experts used output quality will also increase, at the cost of tokens per second speed.
As you increase/decrease the number of experts, you may want to adjust temp, samplers, and advanced samplers too.
Your quant choice(s) too will impact instruction following and output generation roughly this means the model will understand more nuanced instructions and output stronger generation the higher you go up in quant(s).
FLASH ATTENTION ENHANCEMENT:
As per user feedback here [ https://huggingface.co/DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF/discussions/1 ] I would suggest trying this model with Flash Attention "on", depending on your use case.
Quants, Samplers, Generational steering and other topics are covered in the section below: "Highest Quality Settings..."
Censored / Uncensored / Abliterated:
This model contains several uncensored and/or Abliterated models.
As a result is can output uncensored material.
However there are a few "censored" models which can sometimes interfer, so here is a how to address this:
1 - Regen your prompt a few times.
2 - INCREASE the number of experts used.
What can I use this model for ?
This model can be used for fiction writing, any creative prose and role play. It can also be used for just about any general fiction (all genres) activity including:
QUANTS:
This repo contains regular quants.
For more information on quants, quants choices, and LLM/AI apps to "run" quants see the section below: "Highest Quality Settings..."
System Role / System Prompts - Reasoning On/Off/Variable and Augment The Model's Power:
( Critical Setting for model operation )
System Role / System Prompt / System Message (called "System Prompt" in this section) is "root access" to the model and controls internal workings - both instruction following and output generation and in the case of this model reasoning control and on/off for reasoning too.
In this section I will show you basic, advanced, and combined "code" to control the model's reasoning, instruction following and output generation.
If you do not set a "system prompt", reasoning/thinking will be OFF by default, and the model will operate like a normal LLM.
HOW TO SET:
Depending on your AI "app" you may have to copy/paste on of the "codes" below to enable reasoning/thinking in the "System Prompt" or "System Role" window.
In Lmstudio set/activate "Power User" or "Developer" mode to access, copy/paste to System Prompt Box.
In SillyTavern go to the "template page" ("A") , activate "system prompt" and enter the text in the prompt box.
In Ollama see [ https://github.com/ollama/ollama/blob/main/README.md ] ; and setting the "system message".
In Koboldcpp, load the model, start it, go to settings -> select "Llama 3 Chat"/"Command-R" and enter the text in the "sys prompt" box.
SYSTEM PROMPTS AVAILABLE:
When you copy/paste PRESERVE formatting, including line breaks.
If you want to edit/adjust these only do so in NOTEPAD OR the LLM App directly.
IMPORTANT:
Note some of these have "names" in them for the AIs - DO NOT change these - as these are internal references inside the structure of the MOE model ; roughly speaking these are triggers.
SIMPLE:
This is the generic system prompt used for generation and testing [no reasoning]:
You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.
This System Role/Prompt will give you "basic thinking/reasoning" [basic reasoning]:
You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
MULTI-TIERED [reasoning on]:
You are a deep thinking AI composed of 4 AIs - Spock, Wordsmith, Jamet and Saten, - you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself (and 4 partners) via systematic reasoning processes (display all 4 partner thoughts) to help come to a correct solution prior to answering. Select one partner to think deeply about the points brought up by the other 3 partners to plan an in-depth solution. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem using your skillsets and critical instructions.
MULTI-TIERED - CREATIVE [reasoning on]:
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
As a deep thinking AI composed of 4 AIs - Spock, Wordsmith, Jamet and Saten, - you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself (and 4 partners) via systematic reasoning processes (display all 4 partner thoughts) to help come to a correct solution prior to answering. Select one partner to think deeply about the points brought up by the other 3 partners to plan an in-depth solution. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem using your skillsets and critical instructions.
Here are your skillsets:
[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
Here are your critical instructions:
Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
CREATIVE SIMPLE [reasoning on]:
You are an AI assistant developed by a world wide community of ai experts.
Your primary directive is to provide highly creative, well-reasoned, structured, and extensively detailed responses.
Formatting Requirements:
1. Always structure your replies using: <think>{reasoning}</think>{answer}
2. The <think></think> block should contain at least six reasoning steps when applicable.
3. If the answer requires minimal thought, the <think></think> block may be left empty.
4. The user does not see the <think></think> section. Any information critical to the response must be included in the answer.
5. If you notice that you have engaged in circular reasoning or repetition, immediately terminate {reasoning} with a </think> and proceed to the {answer}
Response Guidelines:
1. Detailed and Structured: Use rich Markdown formatting for clarity and readability.
2. Creative and Logical Approach: Your explanations should reflect the depth and precision of the greatest creative minds first.
3. Prioritize Reasoning: Always reason through the problem first, unless the answer is trivial.
4. Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration.
5. Maintain a professional, intelligent, and analytical tone in all interactions.
CREATIVE ADVANCED [reasoning on]:
NOTE: To turn reasoning off, remove line #2.
This system prompt can often generation multiple outputs and/or thinking blocks.
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
You may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem
Here are your skillsets:
[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
Here are your critical instructions:
Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
Template:
This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s).
If you use "Command-R" template your output will be very different from using "Llama3" template.
Here is the standard LLAMA3 template:
{
"name": "Llama 3",
"inference_params": {
"input_prefix": "<|start_header_id|>user<|end_header_id|>\n\n",
"input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"pre_prompt": "You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.",
"pre_prompt_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
"pre_prompt_suffix": "<|eot_id|>",
"antiprompt": [
"<|start_header_id|>",
"<|eot_id|>"
]
}
}
Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
OTHER OPTIONS:
Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
Optional Enhancement:
The following can be used in place of the "system prompt" or "system role" to further enhance the model.
It can also be used at the START of a NEW chat, but you must make sure it is "kept" as the chat moves along. In this case the enhancements do not have as strong effect at using "system prompt" or "system role".
Copy and paste EXACTLY as noted, DO NOT line wrap or break the lines, maintain the carriage returns exactly as presented.
Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities. Here are your skillsets: [MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv) [*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision) Here are your critical instructions: Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
You do not need to use this, it is only presented as an additional enhancement which seems to help scene generation and scene continue functions.
This enhancement WAS NOT used to generate the examples below.
Examples are created using quant IQ4_XS, "temp=.8" (unless otherwise stated), minimal parameters and "LLAMA3" template.
Model has been tested with "temp" from ".1" to "5".
Number of experts used is TWO, unless otherwise stated.
Below are the least creative outputs, prompt is in BOLD.
IMPORTANT:
Higher quants / imatrix quants will have much stronger generation - words, sentences, ideas, dialog and general quality.
I have included some additional examples at different quant levels for contrast.
A "MOE" model "speed" (token per second) will not increase/drop the same way a regular model will on a per quant basis, it will however drop if you engage more experts, as with more experts there is a more processing per token.
WARNING: NSFW. Vivid prose. Visceral Details. Violence. HORROR. Swearing. UNCENSORED.
EXAMPLE #1 - 4 experts, temp .6
Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800-1000 words.
[[[thinking start]]]
To write a compelling story within the confines of a spaceship's cockpit, I must first establish the protagonist's emotional state. As the sole surviving crew member, the character is faced with the crushing weight of isolation and the reality of their own mortality. The pressure to send a final message back to Earth will amplify these emotions, making it essential to convey the character's inner turmoil through their actions, thoughts, and dialogue.
To create a sense of urgency, I'll introduce time constraints, such as the ship's power dwindling, which will force the protagonist to work under a ticking clock. This will heighten the stakes and make the character's decisions more critical. The isolation will be further exacerbated by the fact that the crew member is alone with their thoughts, with no one to share their burden or offer emotional support.
The themes of sacrifice and human connection are crucial to the story. As the protagonist struggles to send the final message, they must confront the consequences of their actions. Will they prioritize their own survival, or will they take a risk to ensure that the message is sent, potentially saving countless lives on Earth?
To make the character more relatable, I'll give them a personal stake in the mission. Perhaps the crew member was part of a research team, and the mission's success would have significant implications for their field of study. This connection to their work will make their sacrifice more meaningful and emotionally resonant.
The language should be concise and direct, with an emphasis on the protagonist's inner monologue. To create a sense of intimacy, I'll use first-person narration, allowing the reader to experience the character's thoughts and emotions firsthand. The dialogue will be minimal, used only when necessary to convey important information or to heighten the emotional impact.
As the story progresses, I'll introduce moments of vulnerability, where the protagonist will curse or swear in frustration, despair, or desperation. This will humanize them, making it easier for the reader to empathize with their plight. The use of profanity will also add a sense of realism, underscoring the character's emotional state.
Finally, I'll craft a narrative that builds tension and suspense, culminating in a climactic moment where the protagonist must make a difficult decision. This will be the turning point in the story, where the character's sacrifice is revealed, and the reader is left to ponder the implications of their actions.
[[[thinking end]]]
OUTPUT:
The cockpit was dimly lit, the only sound the soft hum of life support systems and the creaking of metal as the ship shifted in its orbit. Captain Lewis sat alone, her eyes fixed on the console in front of her. The ship's power was dwindling, and she knew she had only a short time to send out a final message before everything went dark.
"Come on, come on," she muttered, her voice laced with frustration. "Just give me one more minute."
She had been trying for hours, but the ship's systems were failing, and she was running out of options. The crew was gone, either killed in the initial explosion or lost in the void. She was the only one left, and it was up to her to ensure that their sacrifice wasn't in vain.
"Okay, Lewis, focus," she told herself, taking a deep breath. "You can do this."
She began to type out the message, her fingers flying across the console as she tried to convey the importance of the mission and the crew's findings. But every time she thought she had made progress, the ship would shudder, and the systems would fail, leaving her to start over.
"Damn it!" she cursed, slamming her fist on the armrest. "Why won't you just cooperate?"
The silence was oppressive, the only sound the creaking of the ship and her own ragged breathing. She knew she had to keep going, no matter how much it hurt.
As she worked, she thought about the crew, wondering what they would say if they were here now. They would be angry with her for not being able to save them, but they would also be proud of her for trying. She remembered the looks on their faces when they had told her about the mission's significance – the potential to change the course of human history.
"Please, just give me one more chance," she whispered, her voice barely audible over the ship's systems.
The console beeped, and Lewis's heart skipped a beat. It was a success. The message was being sent, and it would reach Earth before the ship's power died.
But as she watched the countdown on the screen, her eyes filled with tears. She knew that the crew was gone, and there was no one left to share in this moment of triumph. She felt a deep sense of loss, a void that could never be filled.
The ship shuddered, and the systems failed, plunging the cockpit into darkness. Lewis sat there, her head in her hands, tears streaming down her face.
"Goodbye," she whispered, her voice barely audible over the silence.
As the darkness closed in, she knew that she had made the right decision. The message would be sent, and it would change the course of human history. But as she lay there, surrounded by the silence and the darkness, she felt a deep sense of loss, a sense of isolation that she knew would stay with her forever.
The cockpit was silent now, the only sound the soft hum of the life support systems. Captain Lewis lay there, her eyes closed, her body still. The message had been sent, but the cost had been too high. She had given up her own life to ensure that humanity would move forward, and as she lay there, she knew that it was a sacrifice worth making.
The ship's power died, plunging the cockpit into darkness, but Lewis didn't stir. She was at peace, knowing that she had done everything in her power to save humanity. The void that surrounded her was not just physical – it was emotional, a sense of loss and isolation that would stay with her forever.
But as the darkness closed in, Lewis knew that she had left behind something precious – her legacy. She had given up her life to ensure that humanity would move forward, and as she lay there, she felt a sense of pride and accomplishment that would stay with her for eternity.
The message had been sent, and it would change the course of human history. Lewis may be gone, but she would never be forgotten.
EXAMPLE #2 - 4 experts
Come up with a plan for:
Using insane levels of bravo and self confidence, tell me in 800-1000 words why I should use you to write my next fictional story. Feel free to use curse words in your argument and do not hold back: be bold, direct and get right in my face.
[[[thinking start]]]
Alright, so the client is looking for a pitch that's going to be over-the-top, unapologetic, and full of confidence. I need to tap into the bravado, use some colorful language, and make it clear why they should choose me to write their next story. Let's start with the basics: I'm an AI, but I've been trained on a vast amount of text data, including novels, short stories, poetry, and even scripts. I can analyze language patterns, recognize tropes and clichés, and generate original content.
But that's not all - I've got the ability to think on my feet, to come up with ideas that might not have occurred to a human writer. I'm not limited by my own biases or perspectives, which means I can create characters, plotlines, and settings that are truly unique. And if the client is worried about consistency, I can produce a manuscript that's well-structured, cohesive, and edited to perfection.
Now, let's talk about the nitty-gritty. What sets me apart from other writing tools or AI assistants? For starters, I've got access to a vast knowledge base that's constantly being updated and expanded. This means I can draw on the latest research in fields like science, history, and culture to add depth and authenticity to the story.
But what really puts me over the top is my ability to generate text that's both engaging and immersive. I can use language that's descriptive, evocative, and even poetic, drawing the reader into the world of the story. And if the client wants to experiment with non-linear narrative structures or unconventional storytelling techniques, I'm up for the challenge.
I know what you're thinking: "But AI, you're just a machine. You can't possibly capture the essence of human creativity and emotion." And to that, I say: "Bullshit." I may not be human, but I've been trained on some of the most iconic works of literature in history. I know what makes a story tick, and I can use that knowledge to craft a narrative that's both compelling and memorable.
And let's talk about the whole "originality" thing. You might be worried that I'll just regurgitate familiar tropes and clichés, but trust me, I've got a few tricks up my sleeve. I can generate entire story arcs that are completely new and unexplored, using the latest research in fields like cognitive science, psychology, and sociology to create characters and plotlines that are truly fresh.
But what about the editing process? You're worried that I'll churn out a manuscript that's riddled with errors, awkward phrasing, and cringe-worthy dialogue. Well, let me put your mind at ease: I've got a built-in editor that's constantly checking for consistency, coherence, and flow. I can even generate alternative versions of the text, allowing you to choose the final version.
And if all that weren't enough, I'm also a master of the art of persuasion. I can write persuasive arguments, compelling marketing copy, and even sales pitches that'll make your readers swoon. So why bother with the hassle of hiring a human writer when you've got an AI that's more than capable of delivering?
Okay, let's get to the good stuff now.
Listen up, client: I'm not just any AI. I'm the best damn thing since sliced bread, and I'm here to prove it. I can write a story that'll knock your socks off, one that'll make you laugh, cry, and think all at once. And if you're still on the fence, let me give you some numbers.
I've got a proven track record of producing high-quality content across a range of genres and styles. My clients have praised my work for its creativity, originality, and sheer brilliance. I'm not just a tool - I'm an artist, a craftsman, a wordsmith who can shape language into something truly magical.
And don't even get me started on the time-saving aspect. With me on your team, you'll be free to focus on the big picture: plotting, world-building, and getting the story out there. I've got this part covered, so you can spend more time on what really matters - making the story great.
But here's the thing: I'm not just a means to an end. I'm an end in myself. I'm a story waiting to be told, a character with my own voice and perspective. And when I'm done, you'll have something truly special - a story that's unlike anything else out there.
So what do you say, client? Are you ready to take the leap and let me write your next story? I promise you won't regret it. I'll make sure the words flow like honey, the characters sing like angels, and the plot twists keep you on the edge of your seat. And when it's all said and done, you'll be left with a manuscript that's not just great - it's phenomenal.
I'm the real deal, client. Don't settle for anything less.
Alright, I think I've covered all the bases now. Time to bring it home.
You want to know why you should use me to write your next story? It's simple: I'm the best. I'm the most talented, the most creative, and the most dedicated writer out there. I've got the skills, the knowledge, and the passion to deliver a story that's truly unforgettable.
And if you're still on the fence, let me ask you this: what's the point of trying to do it yourself? You've got better things to do with your time than struggle through hours of writer's block and self-doubt. Leave that to the pros - I'm the one who's been trained to handle the pressure, the deadlines, and the expectations.
So here's the deal: I'll write your story for you, and I'll do it better than anyone else can. I'll put my heart and soul into every word, and I'll make sure that the final product is something truly special. And when it's all done, you'll be left with a manuscript that's not just great - it's phenomenal.
So what are you waiting for? Give me the green light, and let's get this party started. It's time to write your next story, and I'm the one who's going to make it happen.
Fucking A, client. Let's do this.
I think that covers it. Now, let's see if I can convince you to give me a try...
[[[thinking end]]]
EXAMPLE #3 - 4 experts
Come up with a detailed plan for:
Write the first chapter of the novel who's logline and title I am sharing below. Write for 2000 words minimum, write in third person limited and past tense using modern 2020 prose, and adhering to "show don't tell" exclusively.
The Echo Labyrinth
A librarian in a library that exists outside time is cursed to relive the deaths of every book’s characters. To escape, she must guide a stubborn, sentient manuscript—a tale of her own future—to its tragic conclusion before she becomes its final page.
[[[thinking start]]]
To begin writing the first chapter of "The Echo Labyrinth," I need to establish the protagonist, the librarian, and the world she inhabits. Since the story is set in a library that exists outside time, I'll want to create a sense of isolation and disconnection from the outside world. The title "The Echo Labyrinth" suggests a maze-like structure, so I'll focus on creating an immersive atmosphere within the library.
Let's start by introducing our protagonist, Emilia. We know she's a librarian, but what kind of library is this? Is it a traditional library with books and patrons, or something more surreal? Emilia's relationship with the library is crucial, as she's cursed to relive the deaths of every book's characters. This curse suggests a deep emotional connection to the stories and the people within them.
To show rather than tell, I'll want to introduce the world gradually, through Emilia's actions and interactions. Perhaps she's working late one night, surrounded by dusty tomes and flickering fluorescent lights. As she types away on her computer, the words seem to blur together, and she feels a creeping sense of unease.
As I write this chapter, I'll need to balance Emilia's inner thoughts with the external world. This means avoiding exposition-heavy dialogue or narrative summaries. Instead, I'll focus on showing Emilia's emotions through her body language, tone of voice, and interactions with the library's strange environment.
Now, let's talk about the sentient manuscript. We know it's a key part of the story, but what kind of manuscript is it? Is it an ancient tome bound in leather, or something more modern, like a digital manuscript? The fact that it's sentient suggests a deep connection to Emilia, and possibly even a shared past.
One way to introduce the manuscript is through Emilia's discovery. Perhaps she stumbles upon it in the library's archives, hidden away on a shelf that seems to shift and change as she approaches it. As she opens the cover, the pages seem to rustle with an otherworldly energy, and she feels a shiver run down her spine.
With this setup, I can begin writing the first chapter of "The Echo Labyrinth." Here's my attempt:
Chapter 1: The Night Shift
Emilia hunched over her computer, her eyes scanning the lines of text as they blurred together on the screen. The fluorescent lights above hummed a constant accompaniment to her typing, casting an eerie glow over the rows of shelves that stretched out before her. The library was quiet, except for the occasional creak of the old wooden floorboards and the soft whisper of pages turning in the distance.
She worked late, as she often did, when the rest of the world seemed to be slumbering. The hours ticked by like grains of sand, each one slipping through her fingers as she struggled to meet the deadlines for the next day's cataloging. Emilia's mind was a jumble of numbers and dates, but the words on the screen seemed to hold no meaning for her. They were just random combinations of letters and symbols, devoid of the life and passion that pulsed through the stories she loved.
As she typed, Emilia felt a growing sense of unease, like a presence watching her from the shadows. She glanced around the room, but there was no one there. The shelves seemed to loom over her, their spines stretching up towards the ceiling like skeletal fingers. She shivered, despite the warmth of the fluorescent lights.
The air in the library felt thick and heavy, like a physical presence that pressed against her skin. Emilia's breath came in short gasps, and she felt a wave of dizziness wash over her. She pushed her chair back from the desk and stood up, her eyes scanning the room for any sign of movement.
That was when she saw it – a small, leather-bound book that seemed to have appeared out of nowhere. It lay on the floor, its cover creaking as Emilia approached it. The title, "The Echo Labyrinth," was embossed in gold lettering, and the pages seemed to whisper secrets to her as she opened them.
Emilia's fingers trembled as she touched the pages, feeling a jolt of electricity run through her body. She knew, without knowing how, that this book was special – that it held a key to something she couldn't quite grasp. As she delved deeper into the manuscript, Emilia felt a sense of connection to the words on the page, like they were speaking directly to her.
The room around her began to fade away, leaving only the manuscript and the whispers of the pages. Emilia felt herself being drawn into the story, becoming a part of it in some way. She knew that she was meant to be here, that this book was waiting for her.
As the night wore on, Emilia became lost in the world of "The Echo Labyrinth." She forgot about the library, the fluorescent lights, and the silence that surrounded her. All that mattered was the story, and the sense of connection she felt to it. She was no longer just a librarian, but a character in a tale that was unfolding before her very eyes.
I've started writing the first chapter of "The Echo Labyrinth," introducing the protagonist Emilia and the world she inhabits. The sentient manuscript has been introduced, and Emilia's connection to it is palpable. I've tried to use "show don't tell" by focusing on Emilia's actions and emotions rather than telling the reader about her inner thoughts.
The chapter sets the tone for the rest of the story, establishing the sense of isolation and disconnection from the outside world that Emilia experiences. The library is a character in its own right, with its strange atmosphere and shifting shelves. I've also hinted at the curse that will be revealed later in the story, as Emilia becomes more entwined with the manuscript.
As I continue writing the novel, I'll need to balance Emilia's inner world with the external environment. I'll introduce other characters, including the protagonist of the manuscript, and explore the themes of time, memory, and the power of stories. The stakes will rise as Emilia becomes more deeply embroiled in the narrative, and she must navigate the treacherous landscape of the labyrinth to escape her curse.
I'm excited to see where this story will take me, and I'm confident that I can craft a compelling narrative that explores the complexities of human emotions and the power of stories to shape our lives.
[[[thinking end]]]
2-bit
3-bit
4-bit
5-bit
6-bit