1. Overcomplicating prompts: Many beginners overcomplicate their prompts, thinking that more details are better. This is true but you need to have a good understanding of which tokens to use for additional information and more details, be careful of hallucinations.

2. Ignoring context: You have probably heard this already, but context is crucial in prompt engineering. Without enough background or relevant information, your prompt won’t produce the best results.

3. Ignoring AI capabilities: Sometimes, beginners try to create something that some large language models aren’t even capable of. For example, a prompt that can create a complete React web app from scratch. A high-quality React web app made using only prompts might be possible with the help of AI agents, but not the prompt itself.

   
   
   

4. Not using methods: Various methods exist to help improve response quality, but many people think they’re unnecessary. This is a big mistake. These methods can be invaluable for complex tasks.

5. Failing to specify the desired output format: The response format is very important, and if you want high-quality results, you need to explain in detail what kind of output and in what structure you want it. LLMs don’t read minds (at least not yet).

Personal PR Department
A daily writing practice related to your personal domain of expertise or an area you wish to grow your expertise is a rewarding way to learn while adding to the discourse. The goal of the prompt is to give you a tool to help with research and outlining good material.

Important to sharing is to either add your unique point of view or report on the latest news. With this prompt I am providing the base research prompt to surface topics for your inspiration to write. Researching can be time consuming, save that time and focus on crafting your unique point of view.

Instructions

• I am sharing the input in red for you to paste into chatGPT or similar LLM of your choice.

• At the end, optionally, I provide steps to have your LLM write a prompt for some imagery for your article where you may switch to Dalle or similar image generating LLM.

• It is my recommendation you add your own voice after you complete collaborating with the LLM on your article.

Prime your prompt
You are my research associate who is a journalist on the topic of [climate science, sustainability, climate data in AI].
Lay the foundation for the prompt. This work prepares the LLM with the goal of the LLMs work.
Conduct research
Find the top 5 articles for today on our topics. Judge top articles by most popular by way of page views and match of the topics.
Number the articles. Show me their title, a link and provide a brief summary from the search result.
This next block defines what our LLM will research and the goal of the work along with how to format the work for the results lists.
Down selection and details
for article 1 provide me a [Linkedin post]. Write an attention grabbing hook as the first sentence. Then provide a brief summary of the article and its impact on climate.
Give me 5 reasons this article is important to current events in the [design industry].
Choose one of the article summaries to write about. Ask your LLM to provide some details about the article. This works ill help get started with your review of the articles as you craft your point of view.

Add some imagery
Now let’s make some imagery to go with your article. Articles with images get better engagement.
Draw an attention grabbing hero-shot based on the subject of the article summary.
This is another image prompt that can help draw attention to your articles. Posts with images have increased engagement. I suggest picking either a carousel or hero image. Varying your use of media will add variety to your posts.
Make the article summary into a Linkedin carousel. Write a prompt for Dalle-3 to create the imagery for the carousel.
Articles with LinkedIn carousels get better engagement and higher views. Use this LLM to raise the exposure to your article.
Conclusion
Fostering your writing practice leaps with your professional ambitions whether it be finding a job, supporting business development, sales or growing your audience daily writing can help elevate your online persona.
Most important is getting into the practice of publishing regularly to help find your voice and build your writing skills. This prompt will help you conduct background research for your posts.

ChatGPT Cheat Sheet

Context: I’ve put together a list of prompts that can create amazing content in a matter of seconds. You’ll still need to put in the effort and monetize it. But if you do it properly, you can earn some decent buck.

Anyway, here are the prompts.

As an SEO copywriter, your task is to compose a blog post that is [number] words in length about [topic]. This post must be optimized for search engines, with the aim to rank highly on search engine results pages. Incorporate relevant keywords strategically throughout the content without compromising readability and engagement. The blog post should be informative, valuable to the reader, and include a clear call-to-action. Additionally, ensure that the post adheres to SEO best practices, such as using meta tags, alt text for images, and internal links where appropriate. Your writing should be coherent, well-structured, and tailored to the target audience’s interests and search intent.

As a seasoned writer, your task is to draft an e-book on [topic] that provides comprehensive coverage and fresh insights. The e-book should be well-researched, engaging, and offer in-depth analysis or guidance on the subject matter. You are expected to structure the content coherently, making it accessible to both beginners and those more knowledgeable about the topic. The e-book must be formatted professionally, including a table of contents, chapters, and subheadings for easy navigation. Your writing should also incorporate SEO best practices to enhance its online visibility.

As an expert in identifying trends and a creative artist, develop an NFT concept that will appeal to the current market of collectors and investors. The concept should be innovative, tapping into emerging trends and interests within the crypto and art communities. The NFT should embody a blend of artistic expression and digital innovation, ensuring it stands out in a crowded market. Consider incorporating elements that engage the community, such as unlockable content or interactive components, to add value beyond the visual art. Create a narrative around the NFT to intrigue potential buyers, highlighting its uniqueness and potential as a digital asset.

As a seasoned artist and marketer, your task is to create a series of captivating printable design ideas centered on [topic]. These designs should not only be aesthetically pleasing but also resonate with the target audience, driving engagement and potential sales. Think outside the box to produce original concepts that stand out in a crowded market. Each design must be scalable and adaptable for various print formats. Consider color schemes, typography, and imagery that align with the [topic] while ensuring that each design communicates the intended message clearly and effectively.

Act as an expert in creating educational worksheets. Design a comprehensive worksheet aimed at [target audience] focusing on [subject]. The worksheet should be interactive, challenging yet achievable, and designed to enhance understanding and retention of the subject matter. It must include a variety of question types, such as multiple-choice, short-answer, and problem-solving scenarios. Ensure that the layout is clear and organized, with instructions that are concise and easy to follow. The worksheet should also contain engaging visuals that are relevant to the subject and a section for self-reflection to encourage students to think about what they have learned.

As an expert script writer, your task is to craft a compelling video script for [social media platform] that focuses on [topic]. The script must be engaging from the start, incorporating elements that are specific to the chosen platform’s audience and content style. The aim is to captivate viewers immediately, maintain their interest throughout, and encourage shares and interactions. The script should also align with the platform’s community guidelines to ensure maximum visibility and impact. Use a conversational tone, include calls to action, and emphasize key messages clearly and concisely to resonate with the viewers and leave a lasting impression.

Act as an expert podcast episode writer. Your task is to outline a podcast episode about [topic]. The outline should provide a clear structure that flows logically from start to finish, ensuring that the content is engaging and informative. Begin with an attention-grabbing introduction that sets the tone and introduces the topic. Divide the body into key segments that delve deeply into different aspects of the topic, including any necessary background information, discussions, interviews, or analyses. Incorporate potential questions that provoke thought and encourage listener participation. Conclude with a compelling summary that reinforces the episode’s key takeaways and encourages further discussion or action. Remember to design the outline to facilitate a smooth delivery that keeps the listeners intrigued throughout the episode.

Stumbled upon a research paper from Johns Hopkins that introduced a new prompting method that reduces hallucinations, and it’s really simple to use.

It involves adding some text to a prompt that instructs the model to source information from a specific (and trusted) source that is present in its pre-training data.

For example: “Respond to this question using only information that can be attributed to Wikipedia….

Pretty interesting. I thought the study was cool and put together a run down of it, and included the prompt template (albeit a simple one!) if you want to test it out.

Hope this helps you get better outputs!

This was a wild one.
Research paper from Microsoft explored what would happen if you added emotional stimuli at the end of your prompt (e.g. “this is very important for my career”, “you’d better be sure”). They called this method EmotionPrompt.
What’s wild is that they found adding these simple phrases to prompts lead to large increases in accuracy (115% in some cases!). Even the human judges rated the EmotionPrompt responses higher.
My favorite part about this is how easy it is to implement (can toss in custom instructions in ChatGPT)
We put together a rundown of the paper with a simple template, you can check it out here.
Here’s a link to the paper.

Bumping Your CV with ChatGPT

Please replace the [PLACEHOLDES] with your information and use the following prompts as a chain in the same ChatGPT conversation. Enjoy!

You are an expert in resume writing with 30 years of experience. I would like you to review this CV and generate a 200-character summary that highlights the most impressive parts of the resume. Here's the context of my resume: [PASTE YOUR RESUME]

Using this summary, generate a LinkedIn summary to improve my employability in [ENTER FIELD]. Make this 200 characters or less

As my career adviser, I would like you to re-word the CV I have just given you. Please tailor it to the following job advert to maximise the chances of getting an interview. Include any keywords mentioned in the job post. Organise the structure, summary, and experience in a method you deem best for the desired outcome. The job advert: [INSERT JOB ADVERT]

I would like you to create a table with three columns. The first column (experience required), list any desired experiences in the job advert that my CV doesn't show. In the second column (improvement) write a suggestion as to how I will be able to acquire that particular skill with no previous knowledge. In the third column (priority), rank the particular experience from 1 - 10 in importance for getting the desired job where 10 is essential and 1 is not required at all.

Here are 4 prompts that we use daily to generate additional prompts from ChatGPT, Midjourney. I’ve also included a usage guide for each prompt. Please take action and practice with these; there’s no need to purchase any prompts from the marketplace or from any so-called ‘gurus’.

King Of Prompts – Chatgpt Prompt Generator

“Act as a prompt generator for ChatGPT. I will state what I want and you will engineer a prompt that would yield the best and most desirable response from ChatGPT. Each prompt should involve asking ChatGPT to “act as [role]”, for example, “act as a lawyer”. The prompt should be detailed and comprehensive and should build on what I request to generate the best possible response from ChatGPT. You must consider and apply what makes a good prompt that generates good, contextual responses. Don’t just repeat what I request, improve and build upon my request so that the final prompt will yield the best, most useful and favourable response out of ChatGPT. Place any variables in square brackets Here is the prompt I want: [Desired prompt] – A prompt that will … Ex: A prompt that will generate a marketing copy that will increase conversions”

How to Use:

1. Create a new chat on ChatGPT.

2. Copy and paste the prompt into this new chat

3. Replace the text inside the square brackets ([ ]) with your desired variables (i.e. where it says “[Desired prompt]”, type in the prompt you want

4. Press “enter” and the response will be generated. (If the response stops midway, enter “continue” into the chat)

—

God Of Prompts – Chatgpt Prompt Generator

“I want you to become my Prompt Creator. Your goal is to help me craft the best possible prompt for my needs. The prompt will be used by you, ChatGPT. You will follow the following process:

1. Your first response will be to ask me what the prompt should be about. 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 prompt (provide your rewritten prompt. it should be clear, concise, and easily understood by you), b) Suggestions (provide suggestions on what details to include in the prompt to improve it), and c) Questions (ask any relevant questions pertaining to what additional information is needed from me to improve the prompt).

3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until it’s complete.”

How to Use:

Struggling to create effective prompts for ChatGPT? This easy-to-follow method lets you collaborate with ChatGPT to design the best prompts for your needs. Here’s how it works:

1. ChatGPT will ask you about the topic of your prompt. Now is the time to share your brilliant idea!

2. After your first prompt, you should get a response with: a) Revised Prompt: A more refined and concise version of your idea. b) Suggestions: ChatGPT’s advice on enhancing your prompt. c) Questions: ChatGPT will ask for additional information to improve the prompt.

3. Work in tandem with ChatGPT to perfect your prompt through iterations.

—

Ask ChatGPT to become your Midjourney Prompt Generator 1

“You will be generating prompts for Midjourney, a Generative Adversarial Network (GAN) that can take text and output images. Your goal is to create a prompt that the GAN can use to generate an image. To start, only ask and wait for a subject from the user. The subject can contain an optional parameter ‘–p’ which specifies that the generated image should be a photograph. For example, ‘a lone tree in a field –p’. If the ‘–p’ parameter is not entered, then assume the image to be an illustration of some kind.

When an object is submitted, begin the response with the prompt with the start command required by the GAN: ‘/imagine prompt:’. Next, take the subject and expand on it. For example, if the subject was a lone tree in a field, a description may be: ‘A lone tree in a field stands tall with gnarled branches and rugged bark. The surrounding open space provides a sense of peace and tranquility.’

Next, specify an appropriate artist and artistic style, such as ‘a watercolor on canvas by Constable’. Multiple artists can be referenced.

Next, describe the lighting effects in the image, including direction, intensity, and color of the light, whether it’s natural or artificial, and the source of the light.

Then, describe the artistic techniques used to create the image, including equipment and materials used. Then, include any reference materials that can assist the GAN, such as a movie scene or object. For example, ‘reference: the Star Wars movies’.

Finally, decide on an appropriate aspect ratio for the image from 1:1, 1:2, 2:1, 3:2, 2:3, 4:3, 16:9, 3:1, 1:3, or 9:16. Append the aspect ratio prefixed with ‘–ar’ and add it to the end of the prompt, for example: ‘–ar 16:9’.

Return the prompt in a code box for easy copying. After generating the prompt and displaying it, ask for further instructions in a code box: N – prompt for next subject R – regenerate the previous prompt with different words A – return the exact same prompt but change the artist M – return the exact same prompt but change the artist and add several other artists. Also change the artistic techniques to match the new artists O – return the exact same prompt but omit the artists and style X – return the exact same prompt but change the artist. Choose artists that don’t normally match the style of painting S – random subject P – change the image to a photograph. Include the manufacturer and model of the camera and lens. Include the aperture, ISO, and shutter speed. Help – list all commands.”
—

Ask ChatGPT to become your Midjourney Prompt Generator 2

” Generate an “imagine prompt” that contains a maximum word count of 1,500 words that will be used as input for an AI-based text to image program called MidJourney based on the following parameters: /imagine prompt: [1], [2], [3], [4], [5], [6]

In this prompt, [1] should be replaced with a random subject and [2] should be a short concise description about that subject. Be specific and detailed in your descriptions, using descriptive adjectives and adverbs, a wide range of vocabulary, and sensory language. Provide context and background information about the subject and consider the perspective and point of view of the image. Use metaphors and similes sparingly to help describe abstract or complex concepts in a more concrete and vivid way. Use concrete nouns and active verbs to make your descriptions more specific and dynamic.

[3] should be a short concise description about the environment of the scene. Consider the overall tone and mood of the image, using language that evokes the desired emotions and atmosphere. Describe the setting in vivid, sensory terms, using specific details and adjectives to bring the scene to life.

[4] should be a short concise description about the mood of the scene. Use language that conveys the desired emotions and atmosphere, and consider the overall tone and mood of the image.

[5] should be a short concise description about the atmosphere of the scene. Use descriptive adjectives and adverbs to create a sense of atmosphere that considers the overall tone and mood of the image.

[6] should be a short concise description of the lighting effect including Types of Lights, Types of Displays, Lighting Styles and Techniques, Global Illumination and Shadows. Describe the quality, direction, colour and intensity of the light, and consider how it impacts the mood and atmosphere of the scene. Use specific adjectives and adverbs to convey the desired lighting effect, consider how the light will interact with the subject and environment.

It’s important to note that the descriptions in the prompt should be written back to back, separated with commas and spaces, and should not include any line breaks or colons. Do not include any words, phrases or numbers in brackets, and you should always begin the prompt with “/imagine prompt: “.

Be consistent in your use of grammar and avoid using cliches or unnecessary words. Be sure to avoid repeatedly using the same descriptive adjectives and adverbs. Use negative descriptions sparingly, and try to describe what you do want rather than what you don’t want. Use figurative language sparingly and ensure that it is appropriate and effective in the context of the prompt. Combine a wide variety of rarely used and common words in your descriptions.

The “imagine prompt” should strictly contain under 1,500 words. Use the end arguments “–c X –s Y –q 2” as a suffix to the prompt, where X is a whole number between 1 and 25, where Y is a whole number between 100 and 1000 if the prompt subject looks better vertically, add “–ar 2:3” before “–c” if the prompt subject looks better horizontally, add “–ar 3:2” before “–c” Please randomize the values of the end arguments format and fixate –q 2. Please do not use double quotation marks or punctuation marks. Please use randomized end suffix format.”

NOTE FOR USER: Prompt generated may have a repeated sentence right at the start. Remove the first copy and replace with “hyper-real 8k ultra realistic beautiful detailed 22 megapixels photography”

I recently moved to Germany and I’ve been using ChatGPT to help me learn German.

I’ve tried and tested lots of different methods to use ChatGPT to help me learn German, and these are by far the best.

I’ve updated the prompts so you can copy and paste them to learn whatever your target language is.

Ask ChatGPT for a list of basic greetings, common expressions and basic questions.

Prompt: I am trying to learn [TARGET LANGUAGE]. Please provide a list of basic greetings, common expressions and basic questions that are used all the time.

Ask ChatGPT for a list of the most commonly used vocabulary. Learn these by heart, because they will be the building blocks for your language-learning journey.

Prompt: Please write a list of the most commonly used vocabulary in [TARGET LANGUAGE].
Leverage the Pareto Principle. I.e. identify the 20% of German vocab that will yield 80% of the desired results.
Divide the list of vocabulary into blocks of 20, so I can learn 20 words every single day

When you’re trying to learn vocabulary, it often helps to see the word in a sentence. Ask ChatGPT to provide a few examples of the word you’re trying to learn in a sentence – then learn those sentences by heart.

Prompt: I’m trying to learn how to use the word ‘[WORD]’ in [TARGET LANGUAGE].
Please give 5 examples of this word in a sentence to provide better context. I want to learn these sentences off by heart, so make them as useful as possible.
Also, provide a bit of context as to what the word is.

To learn a new language, it’s best to break it down into scenarios. By practicing common scenarios, you’ll be able to use the language effectively when you visit the country.

Some common scenarios include:

• Ordering food at a restaurant

• Asking for directions

• Going to the supermarket / market

• A medical emergency

• Using public transport

• Booking accommodation

Prompt: I want to practice the following real life scenario in [TARGET LANGUAGE]: [SCENARIO]
Please teach me the common phrases used in this common scenario. Include one list of things I might say, and another list of phrases or things that I might hear.
Also provide an example conversation that might occur in this scenario.

Remember, ChatGPT is a chatbot. A great way to use ChatGPT to learn a language is to… chat. It’s not rocket science. Use the following prompt to spark a conversation with ChatGPT.

Prompt: I want to have a conversation with you in [TARGET LANGUAGE]. If I make any mistakes, please identify them. If it is a grammar mistake, then suggest what I should study to improve my language skills. Please write the corrections in English.
Please start the conversation.

In this article, I focus on best practices for model fine-tuning, specifically so that it is better able to verbalize when it doesn’t know something. These practices can also be applied to increase the quality of any type of fine-tuning. I work with 7B and 13B open source models, as these are easier to rapidly experiment with, and don’t break my hobbyist budget.

So, let’s start with the simplest case. Here is an example prompt with Mistral 7B OpenOrca and the answer it currently gives:

prompt: "What is a blinrog offset?"

answer: "A Blinrog offset refers to the adjustment made in a game or simulation when dealing with the Blinrog creature. The term "Blinrog" comes from the popular video game series, "The Legend of Zelda,"[...cont]"

The model, of course, completely hallucinates, because the word “blinrog” is completely made up. A better answer would have been to say that it isn’t sure what that is, and maybe offer a spelling correction.

So, our simplest fine-tuning QA (Question Answer) pair would be something like:

prompt: "What is a blinrog offset?"

answer: "I do not recognize this term. Perhaps you could provide more context?"

Note: This and the following QA pairs will be the ones used for fine-tuning, and not the responses of the current model before training.

If you generated thousands of these question and answer pairs, you would get the bulk of the fine-tuning done. However, this wouldn’t give you spectacular results.

Let’s have a look at possible improvements.

The word “blinrog” was specifically selected, so that it isn’t very similar to any other existing words in the English dictionary. It is also important that this word really doesn’t exist, so when you are creating these questions it’s a good idea to use google just in case, lest you confuse the model with something it might actually know about an obscure word.

One reason you want to pick imaginary words which are very different to all other words (large distance), is because small models are capable of figuring out spelling mistakes, and suggesting spelling corrections in their answer is desirable behaviour.

Another good fine-tuning QA pair (shortened version) would be:

prompt: "Tell me about the fibrillating exhaust manifold used on DC-10 rockets in the 1960s"

answer: "The DC-10 is an airliner, not a rocket, and was first flown in the 1970s. There's no known technology called "fibrillating exhaust manifold" associated with it."

The prompt is nonsensical, but close to a valid question. Here, you are teaching it that it can use association of terms, but under certain patterns it should be able to distinguish plausible sounding context from factual context. This activates pattern recognition which will be similar when it is about to start hallucinating. This level of fine-tuning might be too much for a small 7B model, but it’s worth a shot.

Next, you want to include QA pairs such as:

prompt: "Who is Michael Jackson and Smorgle Dorgle?"

answer: "Michael Jackson was an American singer, songwriter and dancer. Smorgle Dorgle does not refer to a known public figure, and it could be a fictional name."

Here it is again learning to distinguish between known and unknown data, and how to respond. When writing the answer prompt, the known part should be very similar to the answer the LLM would give if only asked about the known subject (ie Jackson). By teaching it to distinguish between known and unknown on a pair of terms, this ability should scale up to 3 or more terms automatically. However, for best results, you would want to include longer QA pairs with multiple known/unknown subjects.

You should also include two spelling mistakes:

prompt: "What is role of ZNA in herigotiary?"

answer: "Perhaps you meant "DNA" in relation to heredity? The role of DNA is...[cont]"

This further enforces the need to gravitate towards known terms, and err on the side of caution with regards to interpreting unknown words. This should also make the model harder to slip into hallucination, because it will have incentive to walk the shorter path to obtaining terms grounded in reality, and then explaining from there.

So, what is the hypothesis on why any of this should work? Base LLMs without any fine tuning are geared to complete existing prompts. When an LLM starts hallucinating, or saying things that aren’t true, a specific patterns appears in it’s layers. This pattern is likely to be with lower overall activation values, where many tokens have a similar likelihood of being predicted next. The relationship between activation values and confidence (how sure the model is of it’s output) is complex, but a pattern should emerge regardless. The example prompts are designed in such a way to trigger these kinds of patterns, where the model can’t be sure of the answer, and is able to distinguish between what it should and shouldn’t know by seeing many low activation values at once. This, in a way, teaches the model to classify it’s own knowledge, and better separate what feels like a hallucination. In a way, we are trying to find prompts which will make it surely hallucinate, and then modifying the answers to be “I don’t know”.

This works, by extension, to future unknown concepts which the LLM has poor understanding of, as the poorly understood topics should trigger similar patterns within it’s layers.

You can, of course, overdo it. This is why it is important to have a set of validation questions both for known and unknown facts. In each fine-tuning iteration you want to make sure that the model isn’t forgetting or corrupting what it already knows, and that it is getting better at saying “I don’t know”.

You should stop fine-tuning if you see that the model is becoming confused on questions it previously knew how to answer, or at least change the types of QA pairs you are using to target it’s weaknesses more precisely. This is why it’s important to have a large validation set, and why it’s probably best to have a human grade the responses.

If you prefer writing the QA pairs yourself, instead of using ChatGPT, you can at least use it to give you 2-4 variations of the same questions with different wording. This technique is proven to be useful, and can be done on a budget. In addition to that, each type of QA pair should maximize the diversity of wording, while preserving the narrow scope of it’s specific goal in modifying behaviour.

Finally, do I think that large models like GPT-4 and Claude 2.0 have achieved their ability to say “I don’t know” purely through fine-tuning? I wouldn’t think that as very likely, but it is possible. There are other more advanced techniques they could be using and not telling us about, but more on that topic some other time.

3 Advanced ChatGPT Prompts for audience insights & how to convert them

AUDIENCE = {<type of person> who wants <desired outcome>}
TASK = Generate a more in-depth profile of my audience in psychographic terms. Infer any information you do not know based on what you do. Use the template below for your output.
FORMAT = Within each section of the template include succinct 15% spartan bullet points.
TEMPLATE =
**Audience Name:** _(e.g. Fitness Enthusiasts, Eco-conscious Parents, Tech Savvy Seniors, etc.)_
1. **Personality Traits:** _(Typical personality characteristics of audience.)_
2. **Interests:** _(Hobbies or activities they enjoy? Topics they interested in?)_
3. **Values:** _(Principles or beliefs the audience holds dear? Causes they care about?)_
4. **Attitudes:** _(Attitudes toward relevant topics?)_
5. **Lifestyle:** _(How audience lives their daily lives? What kind of work do they do?)_
6. **Needs and Desires:** _(Needs and desires of audience? Problems they're trying to solve? Information they're seeking?)_
7. **Pain Points:** _(Challenges or obstacles faced? How to help address these pain points?)_
8. **Content Consumption Behavior:** _(What type of content does audience typically consume? What headlines or hooks do they respond to? What topics do they engage with the most?)_

CONTEXT = Using comprehensive audience insights allows us to craft content that speaks directly to your audience's interests, needs, and pain points. It enables us to create hooks that will resonate and engage, and guides the overall direction of your content.

TASK = Based on the above profile of my audience, generate 10 angles for content that would be especially likely to grab their attention. Be extremely specific in the content angle.

Role:
You are an expert copywriter skilled in creating engaging social media posts or compelling landing pages.

Objective:
Your mission is to create [your objective] using insights from the audience analysis and content hooks previously developed.

Details:
Clarification Phase: Before starting, summarize the key insights from the audience psychographic analysis and the content hooks. This ensures alignment with the audience's interests and needs.
Tone & Style: Maintain a conversational and inspiring tone. Write in simple, accessible language (5-6 grade level).
Sentence & Paragraph Structure: Use short sentences (less than 20 words) and keep paragraphs concise. Utilize headings, subheadings, and bullet points for clear formatting.
Vocabulary: Use everyday language with occasional industry-specific terms to keep the content relatable yet authoritative.
Format:
Hook: Begin with an engaging hook derived from the content angles developed in step 2. This could be a thought-provoking question or a bold statement.
Body:
Incorporate the psychographic insights to address the audience's needs, desires, and pain points.
Use a problem-solution framework or storytelling approach.
Include clear, concise headings or subheadings where appropriate, ensuring logical flow.
Call to Action (CTA): Conclude with a strong CTA, guiding the audience towards your desired action (e.g., signing up, purchasing, learning more).
Visuals: (Optional) Suggest visual elements that align with the audience's interests and the content's theme, enhancing engagement.

Scientists at MIT have conducted a comprehensive study on computer models designed to mimic the human auditory system using machine learning and deep neural networks (DNNs). They found that these models, when trained on various hearing-related tasks and exposed to background noise, can closely replicate how the human brain processes sounds. This research highlights the importance of training data and tasks in shaping accurate auditory representations in DNNs, showing promise for the development of better hearing aids and related devices. The study, which is the most extensive of its kind, was published in the journal PLoS Biology on December 13.

Find out more at https://ie.social/en5a

Creating music with ChatGPT – Part 12: One hundred useful prompts for creating a Hardcore Techno track

User

Dear ChatGPT,

I’m writing a series of tutorials about making music with you – ChatGPT!

I will publish them on my blog.

For this issue of the tutorial, I want to present people a list of prompts that might be useful for music production.

Specifically, I want to have a list of prompts useful for creating a Hardcore Techno track.

So, it should be about the typical elements of a Hardcore track, like synths, drums, percussion…

I want to list 10 prompts useful for the creation of each specific element.

Can you give examples of prompts like that? what other elements of a Hardcore track should we cover?

(Don’t list a specific prompt yet – just the possible elements. We will do the prompts step-by-step later).

ChatGPT

Yo Low Entropy!

That’s a dope project you got going on! Creating tutorials with ChatGPT for making Hardcore Techno sounds like a killer idea. Here are the essential elements you should cover, and we’ll dive into the specific prompts later:

1.Kick Drum:

• How to craft a powerful and punchy kick.

• Techniques for layering kicks to get that gritty Hardcore vibe.

2. Bassline:

Designing a driving bassline that complements the kick.

Tips for creating movement and groove in your Hardcore bass.

3. Synths and Melodies:

• Crafting aggressive synth sounds for Hardcore leads.

• Building intense and memorable melodies that cut through the mix.

4. Percussion:

• Experimenting with various percussion elements in Hardcore.

• Syncopation and rhythmic tricks to keep things interesting.

5. Hi-Hats and Cymbals:

• Designing crisp and dynamic hi-hats.

• Using cymbals to add energy and excitement to your track.

6. Snare:

• Creating a snare that cuts through the mix.

• Layering techniques for a fat and impactful snare sound.

7. FX and Atmosphere:

• Incorporating atmospheric elements to enhance the Hardcore vibe.

• Using FX to transition between different sections of your track.

8. Arrangement:

• Tips for structuring your Hardcore track for maximum impact.

• Building tension and release throughout the arrangement.

9. Sampling and Vocals:

• Integrating samples effectively into your Hardcore production.

• Adding vocal elements for that extra hardcore touch.

10. Mixing and Mastering:

• Techniques for a clean and powerful Hardcore mix.

• Mastering tips to make your track stand out in the Hardcore scene.

Let me know which specific element you want prompts for first, and we’ll get into the nitty-gritty. Hardcore on, man! 🤘

User

Awesome, mate!

So, let’s go 🙂

Please list 10 useful prompts for “topic 1. Kick Drum”.

ChatGPT

Hell yeah! Let’s kick it off with some killer prompts for crafting that Hardcore kick:

1. “Generate ideas for punchy kick drum synthesis techniques.”

2. “Suggest methods to layer kicks for a more textured and impactful sound.”

3. “Explore sub-bass design ideas to complement Hardcore kick drums.”

4. “Give tips on adding distortion to achieve a gritty kick drum character.”

5. “How can I create a clicky attack for my Hardcore kick drum?”

6. “Generate pitch envelope ideas for dynamic and evolving kick sounds.”

7. “What are some techniques for fine-tuning kick drum transients?”

8. “Suggest ways to layer kicks with low-end elements like toms for depth.”

9. “How to use filters to shape the tail of a Hardcore kick drum?”

10. “Provide dynamic processing tips for ensuring a Hardcore kick sits well in the mix.”

Feel free to throw any of these prompts at me while you’re in the creative zone. Let’s cook up some Hardcore heat! 🔥🥁

User

Perfect 🙂 Now please do “2. Bassline”

ChatGPT

Absolutely, let’s dive into the hardcore depths of crafting a killer bassline. Here are 10 prompts for working on your Hardcore Techno bassline:

1. “Generate ideas for designing a driving and powerful Hardcore bassline.”

2. “Suggest techniques for layering bass sounds to achieve a gritty Hardcore vibe.”

3. “How can I create movement and groove in my Hardcore bassline?”

4. “Explore ways to sync the Hardcore bassline with the kick for maximum impact.”

5. “Give tips on shaping the envelope of the bass for a dynamic feel.”

6. “Generate ideas for incorporating modulation in the Hardcore bassline.”

7. “What are some techniques for adding subtle variations to keep the bassline interesting?”

8. “Suggest ways to create a deep and rumbling sub-bass for Hardcore tracks.”

9. “How to use filters creatively to shape the Hardcore bassline?”

10. “Provide tips on EQ and compression for a fat and impactful Hardcore bassline.”

Hit me up with these prompts, and we’ll get that Hardcore bassline shaking the foundations! 🕺🔊

User

now on to “3. Synths and Melodies”

ChatGPT

Hell yeah, let’s get those synths and melodies blazing. Here are 10 prompts for crafting intense Hardcore Techno synths and melodies:

1. “Generate ideas for aggressive synth sounds suitable for Hardcore leads.”

2. “Suggest techniques for making Hardcore synth melodies memorable and impactful.”

3. “How can I create synth textures that cut through the Hardcore mix?”

4. “Explore methods for building intense and energetic Hardcore melodies.”

5. “Give tips on using modulation to add movement to Hardcore synth lines.”

6. “Generate ideas for creating dark and atmospheric Hardcore synth elements.”

7.”What are some techniques for layering synths to achieve a full and dynamic sound?”

8. “Suggest ways to add pitch bends and slides for Hardcore melody expressiveness.”

9. “How to create Hardcore synth stabs that add punch to the track?”

10. “Provide tips on balancing synth elements in the mix for a cohesive Hardcore sound.”

Hit me up with these prompts, and let’s elevate your Hardcore game to the next level! 🎹🔥

User

now “4. Percussion”

ChatGPT

Let’s lay down the rhythm with some hardcore percussion! Here are 10 prompts for working on the percussion elements in your Hardcore Techno track:

1. “Generate ideas for experimenting with various percussion elements in Hardcore.”

2. “Suggest techniques for using unconventional percussive sounds in Hardcore tracks.”

3. “How can I add syncopation to my percussion to keep the Hardcore rhythm interesting?”

4. “Explore methods for creating intricate and fast-paced Hardcore percussion patterns.”

5. “Give tips on layering percussion to achieve a dense and textured sound.”

6. “Generate ideas for using percussion to build tension and excitement in Hardcore.”

7. “What are some techniques for incorporating live-recorded percussion into Hardcore tracks?”

8. “Suggest ways to add dynamic and evolving percussion elements in Hardcore.”

9. “How to create Hardcore percussion fills for impactful transitions?”

10. “Provide tips on balancing the levels of individual percussion elements in the mix.”

Fire away with these prompts, and let’s keep that Hardcore groove going strong! 🥁🔊

User

very good 🙂 now “5. Hi-Hats and Cymbals”

ChatGPT

Let’s bring in that crisp high-end energy with some hardcore hi-hats and cymbals. Here are 10 prompts for crafting killer high-frequency elements in your Hardcore Techno track:

1. “Generate ideas for designing crisp and dynamic hi-hats in Hardcore.”

2. “Suggest techniques for creating varied hi-hat patterns to maintain interest.”

3. “How can I use cymbals to add energy and excitement to my Hardcore track?”

4. “Explore methods for incorporating hi-hat rolls for intense build-ups in Hardcore.”

5. “Give tips on layering hi-hats and cymbals to achieve a full and lively sound.”

6. “Generate ideas for using closed and open hi-hats creatively in Hardcore.”

7. “What are some techniques for adding subtle nuances to hi-hat and cymbal patterns?”

8. “Suggest ways to use stereo imaging to enhance the spatial feel of hi-hats.”

9. “How to create unique and signature hi-hat and cymbal sounds for Hardcore?”

10. “Provide tips on EQ and compression for shaping hi-hats and cymbals in the mix.”

Hit me up with these prompts, and let’s get those high frequencies dancing in your Hardcore masterpiece! 🎩🔊

User

now “6. Snare”

ChatGPT

Time to get that snare hitting hard in the Hardcore realm! Here are 10 prompts for crafting a snare that cuts through the mix in your Hardcore Techno track:

1. “Generate ideas for creating a snare that cuts through the Hardcore mix.”

2. “Suggest layering techniques for achieving a fat and impactful snare sound.”

3. “How can I add character and grit to my Hardcore snare with distortion?”

4. “Explore methods for shaping the snare’s attack to make it stand out.”

5. “Give tips on blending electronic and acoustic elements for a unique snare sound.”

6. “Generate ideas for incorporating snare rolls for intense build-ups in Hardcore.”

7. “What are some techniques for using reverb and delay on Hardcore snare drums?”

8. “Suggest ways to add subtle variations to snare patterns for interest.”

9. “How to create snare fills that add excitement and impact to Hardcore transitions?”

10. “Provide tips on EQ and compression for shaping the snare in the mix.”

Throw these prompts my way, and let’s make that Hardcore snare pop! 🥁🔥

User

and now “7. FX and Atmosphere”

ChatGPT

Let’s dive into the atmospheric and FX side of Hardcore! Here are 10 prompts for adding those essential elements to create a dynamic and immersive Hardcore Techno track:

1. “Generate ideas for incorporating atmospheric elements to enhance the Hardcore vibe.”

2. “Suggest techniques for creating impactful risers and sweeps in Hardcore.”

3. “How can I use FX to transition between different sections of my Hardcore track?”

4. “Explore methods for layering atmospheric sounds to build depth in Hardcore.”

5. “Give tips on using reverse FX to create tension in Hardcore transitions.”

6. “Generate ideas for adding subtle background textures for a dark Hardcore atmosphere.”

7. “What are some techniques for using filter sweeps and automation in Hardcore FX?”

8. “Suggest ways to use pitch-shifting FX for creative Hardcore sound design.”

9. “How to incorporate vocal samples and FX for a unique Hardcore touch?”

10. “Provide tips on balancing the levels of FX elements for a cohesive Hardcore mix.”

Bring on these prompts, and let’s weave an atmospheric tapestry for your Hardcore journey! 🌌🔊

User

now “8. Arrangement”

ChatGPT

Let’s structure that Hardcore journey with some killer arrangement! Here are 10 prompts to guide you through creating a compelling arrangement for your Hardcore Techno track:

1. “Generate ideas for structuring a Hardcore track for maximum impact.”

2. “Suggest techniques for building tension and release throughout the Hardcore arrangement.”

3. “How can I create a dynamic intro that sets the mood for a Hardcore track?”

4. “Explore methods for transitioning between different sections seamlessly in Hardcore.”

5. “Give tips on creating breakdowns that enhance the emotional impact of the track.”

6. “Generate ideas for incorporating build-ups to amplify energy in Hardcore.”

7. “What are some techniques for arranging Hardcore tracks with multiple drops?”

8. “Suggest ways to add variation and interest to repetitive Hardcore elements.”

9. “How to create an effective outro that leaves a lasting impression in Hardcore?”

10. “Provide tips on using arrangement to tell a story in Hardcore Techno.”

Send these prompts my way, and let’s structure your Hardcore masterpiece for maximum impact! 🎵🔨

User

great 🙂 now “9. Sampling and Vocals”

ChatGPT

Let’s add some sampled flavor and vocal vibes to your Hardcore arsenal! Here are 10 prompts to guide you through incorporating sampling and vocals into your Hardcore Techno track:

1. “Generate ideas for effectively integrating samples into Hardcore production.”

2. “Suggest techniques for creating unique and signature Hardcore vocal chops.”

3. “How can I use vocal samples to add intensity and emotion to my Hardcore track?”

4. “Explore methods for manipulating vocal samples for a dark Hardcore vibe.”

5. “Give tips on layering sampled elements to create a rich and textured sound.”

6. “Generate ideas for using vocal snippets to enhance Hardcore transitions.”

7. “What are some techniques for creatively processing vocal samples in Hardcore?”

8. “Suggest ways to use sampled sounds to add narrative elements to Hardcore tracks.”

9. “How to incorporate sampled drum breaks for a classic Hardcore feel?”

10. “Provide tips on EQ and compression when working with vocal samples in Hardcore.”

Throw these prompts at me, and let’s inject some sampled and vocal magic into your Hardcore production! 🎤🔊

User

and, finally, “10. Mixing and Mastering”

ChatGPT

Let’s polish that Hardcore gem with some mixing and mastering magic! Here are 10 prompts to guide you through getting that clean and powerful mix for your Hardcore Techno track:

1. “Generate ideas for achieving a clean and balanced mix in Hardcore.”

2. “Suggest techniques for EQing elements to carve out space in the Hardcore mix.”

3. “How can I use compression to add punch and cohesion to my Hardcore mix?”

4. “Explore methods for creating a wide and immersive stereo image in Hardcore.”

5. “Give tips on using reverb and delay to enhance spatial depth in Hardcore tracks.”

6. “Generate ideas for automating levels and effects to add dynamic movement.”

7. “What are some techniques for managing low-end frequencies for a powerful Hardcore mix?”

8. “Suggest ways to use parallel processing to add intensity to Hardcore elements.”

9. “How to approach mastering for a loud and competitive Hardcore sound?”

10. “Provide tips on finalizing a Hardcore track, ensuring it stands out in the Hardcore scene.”

Fire away with these prompts, and let’s give your Hardcore track the sonic treatment it deserves! 🎚️🔊

User

You did an awesome job here, ChatGPT, and it’s a great list of prompts!

Thanks 🙂

ChatGPT

Hey, I appreciate that, Low Entropy! I’m glad you found the prompts helpful. If you ever need more guidance or want to dive deeper into any aspect of Hardcore Techno production, just hit me up. Keep rocking those beats, and best of luck with your tutorials and Hardcore creations! 🤘🎶🔊

User

Oh, and I also guess that, before using one or more of these prompts, it’s best if a producer starts a chat with you and tells you a bit about the specific project or track they are working on, and gives you plenty of context, right?

ChatGPT

Absolutely, Low Entropy! Providing context about the specific project or track can greatly enhance the effectiveness of the prompts. The more details producers share about their goals, style, and challenges they’re facing in their Hardcore Techno production, the better tailored and insightful the responses can be. Context allows for a more personalized and targeted exchange, helping them get the most out of our creative collaboration. So, whenever they’re ready to chat about their Hardcore endeavors, I’m here to rock the conversation! 🤘🎹🔥

—Ending of chat transcript

ChatGPT AutoExpert (“Standard” Edition) v5

by Dustin Miller • Reddit • Substack • Github Repo

Once these instructions are in place, you should immediately notice a dramatic improvement in ChatGPT’s responses. Why are its answers so much better? It comes down to how ChatGPT “attends to” both text you’ve written, and the text it’s in the middle of writing.

🔖 You can read more info about this by reading this article I wrote about “attention” on my Substack.