Don't Use ChatGPT Until You Watch This Video

Summary

The video provides tips to optimize prompts in ChatGPT for better responses. It suggests customizing instructions to establish context, specifying desired tone, language, response length and confidence level. Additional tips include providing writing samples so ChatGPT can mimic one's style, asking it to critique its own responses, using self-prompting to create optimal prompts, limiting response length, and specifying output format like tables or CSVs. The key takeaway is properly framing prompts to avoid poor quality answers.

Takeaways

• 😀 Use custom instructions to provide context about yourself and preferences for how ChatGPT should respond
• 👍 Give examples of your writing style so ChatGPT can learn to write in your voice
• 💡 Ask ChatGPT to critique its own text to improve clarity and add specifics
• 📝 Have ChatGPT generate optimized prompts to get better responses
• 🔢 Specify maximum word counts to get more concise responses
• 📊 Specify output formats like tables, CSV, HTML for easy integration
• ✂️ Ask ChatGPT to reduce text length by a percentage to make more concise
• 📑 Include confidence levels and sources with factual responses
• ❓ Ask ChatGPT clarifying questions first to create optimal prompts
• 🚮 Garbage in, garbage out - carefully craft prompts and input for best results

Q & A

What is the benefit of using custom instructions in ChatGPT?

Custom instructions allow you to provide details to ChatGPT about who you are and what kind of responses you prefer. This saves you from having to repeat preferences in every conversation.

How can you make ChatGPT responses more relevant to your profession?

In the custom instructions, provide details about your profession or area of expertise, such as "I'm a teacher" or "I'm a software developer based in Chicago working with Python".

What's an example of how to control the tone and language of ChatGPT responses?

You can specify in custom instructions: "Language and tone should be friendly and casual" or "Responses should remain neutral and factual".

Why is the 'write like you' technique useful?

It allows you to provide writing samples to ChatGPT so it can understand and mimic your personal writing style when generating content.

How does the self-critic technique work?

You can ask ChatGPT to review and critique its own responses, providing feedback on where clarity, examples, or other improvements could be made.

What is the benefit of self-prompting?

It allows ChatGPT to optimize prompts itself, so you get better quality responses tailored to your specific needs.

How can you control the length of ChatGPT responses?

Specify a maximum word count in your prompt, e.g. "Maximum length of text should be 500 words" or ask it to reduce an existing response by a percentage.

What non-text output formats does ChatGPT support?

It can output data in tables, CSV, JSON, XML, Pandas data frames, and HTML/web content, among other formats.

What main point is the video trying to convey?

That properly structuring prompts and providing clear instructions to ChatGPT is key to getting quality responses and avoiding frustration.

What is the core principle related to getting good ChatGPT responses?

"Garbage in, garbage out" - the quality of ChatGPT's responses depends heavily on the quality of the prompts and instructions provided.

Outlines

00:00

😊 Customizing ChatGPT Instructions for Better Responses

This paragraph explains how you can customize ChatGPT's instructions in your profile to provide context about yourself and preferences for how you want ChatGPT to respond. This avoids repetitive prompts and gets more relevant, efficient responses suited to your needs.

05:04

😉 Teaching ChatGPT Your Writing Style for Personalized Content

This paragraph demonstrates how you can provide ChatGPT with examples of your own writing to teach it your personal style. It will then generate content in your style on any topic you specify, allowing you to create blog posts or articles that sound more like they were written by you.

10:08

😲 Using Self-Criticism to Improve ChatGPT Replies

This section shows how asking ChatGPT to critically analyze its own text can lead to useful feedback on how to clarify or expand its replies. It can even provide an improved version of the original response, giving specific examples when needed to make the content more useful.

😎 ChatGPT Self-Prompting for Optimized Responses

Here ChatGPT is used to generate optimized prompts about writing an email to a team, even asking clarifying questions first. This results in prompts tailored to the specifics of the situation. The best prompt is then used to generate a customized team email.

🔢 Specifying Word Limits for Concise ChatGPT Responses

This tip demonstrates constraining ChatGPT's response length by specifying a maximum word count upfront. The example shows getting an efficient 500-word comparison of Excel functions. Length limits avoid frustratingly long responses when brevity is preferred.

📑 Choosing Output Formats like Tables and CSV

Rather than just text, ChatGPT can provide outputs in formats like tables, CSV data, HTML, JSON, XML, Pandas data frames, etc. Examples show creating a table of sports statistics in multiple formats for easy importing and analysis in other tools.

Keywords

💡Custom instructions

Custom instructions allow you to provide ChatGPT with personalized information about yourself and preferences for how you want it to respond. This improves the relevance and usefulness of ChatGPT's responses. The video recommends using custom instructions to share details like your profession, location, desired tone/formality level, etc.

💡Confidence level

Asking ChatGPT to provide a confidence level allows you to assess how certain it is of the factual accuracy of its responses. This is useful for answers that contain facts rather than opinions. The video gives the example of asking ChatGPT to cite its sources and inform you when it is speculating.

💡Self-critic

The self-critic technique involves asking ChatGPT to critique its own initial response, highlight any issues, and provide an improved, revised version. As shown in the video, this results in more clarity, examples, and overall better quality responses from ChatGPT.

💡Self-prompting

With self-prompting, you ask ChatGPT to generate optimal prompts for itself to produce the best possible response on a given topic. As demonstrated in the video, this results in very customized, high quality output compared to just asking ChatGPT directly.

💡Word count

Specifying a word count limit in your prompts prevents excessively long responses from ChatGPT. The video gives the example of limiting responses to 500 words and checking compliance later by pasting the text into Word.

💡Output format

ChatGPT can provide output in many formats beyond plain text, like tables, CSV, JSON, HTML, etc. The video shows how specifying the desired format in prompts allows seamlessly transferring ChatGPT's output into various applications.

💡Garbage in, garbage out

This key principle means the quality of ChatGPT's responses is highly dependent on the quality of the prompts it receives. As the video emphasizes, well-formulated prompts result in more useful responses versus generic prompts.

💡Custom style

The video demonstrates how giving ChatGPT writing samples allows it to grasp your personal writing style which it can then mimic to generate custom content. This prevents the generic tone of much AI-written text.

💡Context

Providing context about yourself and your use cases allows ChatGPT responses to be highly tailored rather than generic. The video gives examples like sharing profession, location, line of work to make responses more relevant.

💡Iterative refinement

Techniques like self-critic and self-prompting allow ChatGPT outputs to be iteratively improved through multiple cycles of review and refinement. As shown in the video, each round enhances quality.

Highlights

Take advantage of custom instructions to provide context about yourself and preferences for how ChatGPT should respond

Specify if you want casual or formal language, if ChatGPT can have opinions, and if responses should be long or short

For Excel, ask for formulas without explanations to avoid lengthy replies

Have ChatGPT inform you about confidence level and sources when answers include facts

Teach ChatGPT your writing style by providing examples for it to analyze

Ask ChatGPT to critique its own text and provide feedback on how to improve it

Use self-prompting to have ChatGPT optimize prompts to get better quality responses

Ask ChatGPT to explain why a prompt would be effective to validate quality

Specify maximum word count in prompts to get more concise replies

Ask ChatGPT to reduce length of existing text by percentage to make more concise

Specify output format like tables, CSV, JSON, Excel, HTML to match your needs

Refine table output by adding details like borders and spacing in prompt

Garbage in, garbage out - carefully craft prompts and instructions for best results

Keep context, preferences, and output format details in custom instructions to avoid repeating

Use self-prompting, self-critiquing, and examples to continually refine prompts for optimal responses

Transcripts

By now, you've probably started using ChatGPT,  

right? It's not rocket science. Anyone can  ask questions, and it's going to give you  

answers. In school, we learned that there  are no bad questions. In ChatGPT world,  

there are. It's not going to tell you that, but it's  going to give you poor quality answers,  

and you're just going to waste a lot of time going  back and forth. I've been there—super annoyed—so  

I decided to spend some time to find the best  prompts to get the most out of ChatGPT.

My first tip for you is to take advantage of  custom instructions, which you're going to find  

by clicking on your profile icon. So, when you go  to custom instructions, you have the ability to  

hand over a note to ChatGPT that explains who you  are, what you want, and how you want ChatGPT 

to respond. This way, you won't have to repeat  your preferences in every single conversation.

So, the first question is: what would  you like ChatGPT to know about you  

to provide better responses? It helps if you  can provide some context about yourself. So,  

for example, if you're a teacher,  let it know. If you're a student,  

an accountant, a lawyer, let it know. This  way, you can get responses that are more  

relevant to your line of work. If you want  responses that are relevant to your region,  

tell it where you live. Not the exact address,  but just the area where you are. So, for example,  

you could say, "I'm a software developer based in  Chicago working with Python." Or you could say,  

"I'm a marketing professional in New York writing  advertising copy." Right, you get the idea.

The next question is: how would you like  ChatGPT to respond? We get some thought  

starters, like how formal or casual should  ChatGPT be? For example, you could put in,  

"Language and tone should be friendly and  casual." You can decide if ChatGPT can have  

opinions on topics or remain neutral, and if  responses should be long or short. And this  

can really make a difference because you can  get rid of a lot of frustrating back and forth.

So, for example, let's say you're good in  Excel and use ChatGPT to help you out when  

you get stuck, but you don't like seeing all  those explanations about the solutions. So,  

what you could write is, "When I ask for Excel  formulas, just provide the most efficient formula  

without any explanation." If you were a programmer  and you didn't want to see all those programming  

explanations, you could type in, "When I ask  you for code, just give me the most efficient  

code with code snippets without additional  explanation." Right, so that's really helpful.  

In this case, I'm picky about Excel formulas.  I'm going to leave this in and click on Save.

Now, let's go and start a new chat, and I'm  going to ask it for a formula just to make  

sure this works. Let's say I'm in Excel, and I'm  struggling with updating this formula. Currently,  

it's returning everything that's greater than  12,000, but I want to change this to be between  

12,000 and 15,000. And I have no idea  how to tell it to do it between these  

values. I'm going to go back to  ChatGPT and type in my formula,  

tell it to update this Excel formula so it returns  values in the B column that are between these two.  

And when I send this, it just provides  the solution without any explanation.

Now, without that custom setting, this is what  I would get. And sometimes you would just  

end up with a lot longer explanations  like this one. These are great if you  

don't know your way around, but if  you do, they can be pretty annoying.

Another thing that could be quite helpful is  to tell ChatGPT to always inform us about the  

confidence level of its answer. This could  be quite helpful for factual topics. Now,  

we can also expand on this and say, "When  your answer includes facts, always provide  

a valid URL with the source for your answer.  And if you speculate or predict something,  

inform me." Okay, so let's test  this out. I'm going to save this,  

go ahead and start a new chat, and let's ask  it over the FIFA World Cup winners of the '90s.

When I run this, I get: 1990: West Germany, Brazil, France.  

Confidence level is high, and I get a list  of valid URLs directly from FIFA.com. Right,  

so these settings can be really helpful.  I'm sure you're going to find them handy.

Now let's move on to prompts. The  first one is to write like you. So,  

if you ask ChatGPT to write some text for you,  the results will probably sound a bit generic,  

right? Even if you're emphasizing  the custom instructions and the  

tone and the style that you want, it might not  properly reflect your style of writing. Now,  

the good news is that you can teach it to write  in your own style by giving it some examples. So,  

first, we're going to explain to ChatGPT  what we're going to do with this prompt.

"I'd like you to help me write articles from  my productivity blog." Just replace this with  

whatever type of blog or article you need.  "First, I want you to understand my writing  

style based on examples that I give you. You'll  save my writing style under 'LG_STYLE.'" Now,  

this makes it easier to refer to later. "After  that, you'll ask me what the topic of my specific  

content is. You'll then write the article  using LG_STYLE." Okay, so let's give it a try.

Okay, so it understands what we're trying to do  and it's ready for some examples. I'm just going  

to go and grab some copy from my website. Let's  copy this paragraph from the About page and paste  

it in as example one of LG_STYLE. Now I'll give  it a second example of LG_STYLE. I'll just go  

and grab the other copy from here, and paste it  in. So, it summarized my style as informative,  

personable, and aims to establish a connection.  And now it's ready to write our content. So,  

I want to write an article about the  importance of daily coffee for productivity.  

Cool, start writing it in my personal writing  style, the one that it previously saved. Now,  

you can, of course, continue working  on this and make it better. You can  

also come back to this chat and ask  it to write other related articles.

And by the way, if you love your daily coffee,  subscribe to this channel because we all love  

coffee around here. Next up is self-critic.  So, another great option is to ask ChatGPT to  

review its own text and provide feedback. Now,  it sounds funny, but it really works well. So,  

let's say I asked ChatGPT to provide me with a summary  of why Python and Excel can work well together and  

it comes up with this reply which I'm not really  happy with. So, I'm going to ask it to act as a  

critic. Be ruthless, analyze the text, and tell me  where it can be better. It will go over the reply  

and provide step-by-step feedback on potential  issues. For example, with clarity and how adding  

specific examples could make the summary better,  how we could highlight specific capabilities.

It also went ahead and revised this original  reply, giving examples of Python's strengths  

and Excel's strengths. From there, you can further  improve on this reply by asking it to specifically  

emphasize and include some of the previous  pointers that it gave us. It's pretty cool, right?

Next up is self-prompting. So, how about using  ChatGPT to self-prompt to optimize its own prompt?  

Here's how you can do that. So, let's say I want  to send an email to my team encouraging them to  

participate in our team-building event. To get the  perfect prompt, I could ask ChatGPT, "Write  

five perfect ChatGPT prompts that will really show  off the power of ChatGPT. Focus the prompts  

around writing an email to my team encouraging  them to participate in our team-building event.  

Before you write anything, ask me questions until  you're sure you can create the optimal prompts."

It will usually come back with some questions  about the topic, in this case, about the purpose,  

dates, and locations and other useful information.  Now, after I provide my answers, so, for example,  

for any particular incentives or benefits, I've  put "nice dinner, nice breakfast, no work,"  

then I send this off, and it creates five possible  prompts for me. Now, these are prompts that will  

help me get the best reply. So, one is, "Draft an  email to your creative team encouraging them to  

join a special team-building event. Mention the  importance of taking a break from work." Another  

one is, "Compose an email inviting your team to  a casual and fun team-building event. Stress the  

importance of building strong relationships within  the group and the opportunity for a nice dinner."  

Okay, so I like number three better. I'm just  going to tell it to use it. Now it just provides  

me with a prompt, but I actually want it to run  it. So can I do it? It starts writing the email.

Now, we can see it has a nice subject, the tone  is soft and casual, and it's highlighting the  

bonding and relationships. Right, so we  can see it sprinkled in different places,  

like we can share stories, laughter,  and delicious food. We'll have a great  

breakfast. There's no work, no deadlines.  So, it's a very customized email.

Now, compare this to a case where  I don't optimize the prompt. So,  

I tell it to write an email to my team to  participate in our team-building event. It's  

no surprise that I get a very generic email about  team-building and what generally team-building  

events are designed to do. So, as you can see,  self-prompting can give you a much better output.

But you can also take this self-prompting a step  further. So, if you go back to the step where we  

got the different prompts, we could ask it why  a prompt would work well. It gives me detailed  

information about the reasons it thinks this  prompt is effective, but I'm not so sure. So,  

I'm going to ask it, "which prompt do you find the  best?" It tells me that prompt three effectively  

combines the key elements I provided, so it  could work well in my case, which it actually did.

Often when you ask ChatGPT to write something,  the reply can be rather long. So, one way to  

avoid this is to tell it from the beginning to stick to a specific word count. Now, if this is something that you want  

in every single reply, you can add it to your  custom settings. If not, you can add it to your  

prompt. So, for example, we want to know the  advantages of using XLOOKUP over VLOOKUP in  

Excel. I'm going to add that the maximum length of  the text should be 500 words.

A few moments later.

Okay, so let's double-check. I'll copy this, go to a new page, type in "word.new" to open a blank Word document in the  

browser, and paste in the text. We can see  down here that we have 469 words. Now,  

another alternative is to tell it to reduce the  length of a text that it already gave you. So,  

a good prompt for that is, "Now, say the same  thing more concise and prefer using only 60%  

as many words or whatever percentage you need. You  could try cutting it down even more, step by step,  

until you get the crispiness that you like.  Your audience is going to be thankful for it."

Specify the output format. ChatGPT has many  different output formats, not just plain text. So,  

for example, you can tell it to give you  the response in a table format. Let's say,  

"Create a table with the winners of the FIFA  World Cups between 1990 and 2018. The headings  

should be year, winner, and runners-up." So, we  get a table. We can just highlight the content,  

use the shortcut Ctrl+C to copy it, move over to  an Excel sheet, and paste the table with Ctrl+V.  

Now, alternatively, you can tell it to output  the table as CSV. Then all you need to do is to  

copy the code from here and paste it into a text  editor, and then save it as a CSV file extension.

Now, if you need this, let's say for  your website, you could output as HTML.  

Moments later...

I'm just going to test this out. So, I'm  going to grab this code and paste it on  

our site in an HTML editor. Then, when  I go to preview, I can see the table,  

but it doesn't look really nice. I'd  rather have borders and spacing. So,  

let's improve the prompt and ask it to add  the borders and spacing.

Later that night.

Now, when I replace the code,

I have a table that's a lot easier to read. Right? So, you can also ouput in different format

like JSON or XML. Or if you need it as a Pandas data frame,  

you can do that as well. Just give it a try.

SO, these are some tips to get the most out of  ChatGPT or any large language model AI, actually.  

It really comes down to the old principle:  garbage in, garbage out. Keep this in mind,  

and you'll definitely make better use of these  new tools. I hope you found this helpful. Do  

subscribe if you aren't subscribed yet, and  I'm going to catch you in the next video.