🌟 The Top 10 Exclusive Prompts To Boost ChatGPT 🌟

1. Get a deeper understanding

“To clarify or get a deeper understanding of a topic, or any piece of information, use the following prompts,” explained Cheung. Options include, “Explain [insert specific topic] in simple terms,” or “Explain [concept] to me like I’m 11 years old,” and “Explain [topic] to me as if I’m a beginner in [field].”

ChatGPT knows how to simplify something, so asking it to output information in one of these ways will ensure everything you see has been boiled down to the essentials. The LLM will likely use basic language and helpful analogies to ensure you understand.

2. Replicate a sample

“If you need to mimic the style of a sample of text to create an essay or other written work, use this prompt,” advised Cheung, from the “specificity and information” section of the principles. “Please create [describe new text required] using language based on this sample, [include paragraph, text, essay, answer].” ChatGPT will learn the style and follow it through to the new material.

Perhaps you’re making tweets based on ones you already wrote, or releasing a series of articles along a similar theme. Use your tried-and-tested tone of voice to outproduce everyone, with no one guessing what you did.

3. Improve without changing the meaning

When you’re sent testimonials, website or marketing copy, or a first draft that isn’t quite right, use this prompt to tidy it up while keeping the essence of the message, according to the “content and language style” section of the 26 principles. “Revise every paragraph in this [type of text] sent by [specify who]. You should only improve the user’s grammar and vocabulary and make sure it sounds natural. You should not change the writing style, such as making a formal paragraph casual.”

Use this prompt when you’re happy with the sentiment but want something to read better. ChatGPT should follow your instructions and make only edits that are absolutely necessary. The original writer might not even know you did anything at all.

4. Be clear on what you want

ChatGPT is not human and doesn’t care about niceties. “No need to be polite with LLM,” said Bsharat, Myrzakhan and Shen. It actually works better being instructed like a machine. The paper found better results when incorporating the following phrases within your prompt: “Your task is,” or “You MUST,” and “You will be penalized.” Tag them onto the end of your prompt and see how you get on.

You wouldn’t say please and thank you to your fridge, or start pleading with your dishwasher if it didn’t do the right thing. Just because ChatGPT engages like a human, remember it’s a predictive word generator and should be instructed as such.

5. Tell ChatGPT how to think

You’d be forgiven for thinking OpenAI’s flagship tool had a brain. When you’re prompting, explained Cheung, “use leading phrases like ‘think step by step,’” discovered from the “prompt structure and clarity” section of the paper. Request that ChatGPT process and output information in a logical, sequential way, to enable you to do more with the words that come out. The paper also recommends you, “Break down the task into a series of prompts that build upon each other, guiding the model step-by-step,” if that better suits the requirements.

If you were training an intern from scratch, you’d give them frameworks and methodologies. You’d teach them the best order of doing the task at hand, and see their plan for the work first, so they didn’t get to the end having taken the wrong route. Think of prompting ChatGPT in a similar way to ensure it doesn’t miss any stages.

6. Don’t ignore frequency

People repeat the things that matter to them. They revisit their favourite places, they order their favourite menu items every time they go to the same restaurant. Apply this to prompting ChatGPT. Don’t assume it knows what’s important to you.

“Repeat a specific word or phrase multiple times within a prompt,” said Cheung. Even if you’d never repeat something that many times in real life, ChatGPT can’t read body language or infer tone like you can in a human-to-human conversation. Spell it out, and say things multiple times to hammer the message home.

7. Use positive language

ChatGPT likes being told what to do. It doesn’t like being told what not to do. “Employ affirmative directives such as ‘do,’ while steering clear of negative language like ‘don’t’,” explained Bsharat, Myrzakhan and Shen. Rather than “don’t waffle,” say “be clear and concise.” Rather than saying “don’t use metaphors,” say “be literal.”

Instructing in this way, while it takes some getting used to, will be more beneficial in the long term. Train your mind to go towards what you want instead of away from what you don’t, and pass your thinking to ChatGPT.

8. Specify detailed output

One criticism of ChatGPT is that its first instinct is to use flowery, generic, vague language. It makes sense. The tool was trained on billions of words from across the internet, many of which will contradict each other. Competing messages water eachother down until there’s nothing left to do but embellish. A camel is a horse built by a committee.

For more detailed output, you only have to ask. Cheung recommends you use this prompt. “Write a detailed [type of text] for me on [topic] in detail by adding all the information necessary,” then add further guidance on the direction this detail should take. Specify clarity, conciseness, and be clear on the structure and length required.

9. Check for bias

If you ask ChatGPT to describe a typical CEO, it will be the most stereotypical answer you could imagine. Same with a cleaner, parent or bar manager. Explaining your ideal customer to ChatGPT might mean it over-generalises or makes assumptions you didn’t approve.

LLMs are inherently biased but they’re working on becoming better. Make sure your output doesn’t fall short by adding, “Ensure that your answer is unbiased and does not rely on stereotypes,” to the end of your prompt, advised Bsharat, Myrzakhan and Shen.

10. Assign a role

“Take on the role of [describe role],” is the most basic prompt in the book. If you want an AI coach, ask for one. If you want a property expert, social media manager or a pre-gym David Goggins pep talk, tell ChatGPT. Bsharat, Myrzakhan and Shen found “larger models possess a considerable capacity for simulation. The more precise the task or directive provided, the more effectively the model performs.” Therefore, they continued, “it proves beneficial to assign a specific role to LLMs as a means to elicit outputs that better match our intended results.”

Don’t forget that LLMs are predictive machines. They simply act to predict the next word in a sentence. If you want that sentence to come out a certain way, you have to frame its thinking, hence specifying a role in the prompt.