• Everyday AI
  • Posts
  • ChatGPT Doesn’t Suck. Your "Prompts" Do. 🤦

ChatGPT Doesn’t Suck. Your "Prompts" Do. 🤦

📝 Fixing your ChatGPT prompts, Biden's White House AI Council, creating flow charts in ChatGPT, and more!

Author

Everyday AI
December 13, 2023

Outsmart The Future

Today in Everyday AI
8 minute read

🎙 Daily Podcast Episode: Sorry to break it to y’all. ChatGPT doesn’t suck. Your prompts do. Here’s how to fix them. Give it a listen.

🕵️‍♂️ Fresh Finds: transforming your thoughts into text effortlessly, Meta’s AI coming to Ray-Bans, and the US using robo dogs? Read on for Fresh Finds.

🗞 Byte Sized Daily AI News: New York Times’ new Director of AI Initiatives, Biden's White House AI Council, and Meta using copyrighted books in AI training. For that and more, read on for Byte Sized News.

🚀 AI In 5: We’re showing you a ChatGPT plugin that creates flow charts and mind maps to help you visualize anything. Need real biz use-cases for ChatGPT plugins? You’re in luck. See it here

🧠 Learn & Leveraging AI: Wondering why you’re not getting good outputs from ChatGPT? We’ll show you how to properly prompt to get good results. Keep reading for that!

↩️ Don’t miss out: Did you miss our last newsletter? We talked the truth about Google Gemini, AI translating brainwaves to text, and a Diagrams Show Me plugin review. Check it here!

ChatGPT Doesn’t Suck. Your Prompts Do. 🤔

Yep you read that right.

(Apparently we still have hot takes left after scorching Google Gemini yesterday.)

Some people say that AI stinks. ChatGPT isn't any good.

Well we're here to break the news to you. ChatGPT doesn't suck. Your prompts do.

We're showing you what you're doing wrong and how to improve your ChatGPT prompts to improve your results and responses.

Join the conversation and ask Jordan any questions about ChatGPT.

Also on the pod today:

• Is ChatGPT getting lazier? 🦥
• Copy and paste super prompts 📄
• Looking for outputs vs building skillsets 🔨

It’ll be worth your 34 minutes:

Listen on our site:

Click to listen

Subscribe and listen on your favorite podcast platform

Listen on:

Upcoming Everyday AI Livestreams

Thursday, December 14th at 7:30 am CST ⬇️

Here’s our favorite AI finds from across the web:

New AI Tool Spotlight – Audio Note transforms thoughts into text effortlessly, EnVsion summarizes key insights from hours of video calls, and startuptools.ai helps you ideate, launch, and grow your business with an AI co-founder.

Big Tech – Meta is adding its AI to Ray-Ban’s new smart glasses that’ll allow you to identify objects and languages.

Money in AI - Harvey, an AI startup selling legal software, has been valued at $700 million.

AI in Medical – We’ve seen a lot about how AI is helping doctors. Here’s how AI is helping dentists.

Read This – The US Customs and Border Protection is beefing up its security with robo dogs and AI inspectors.

1. New York Times Appoints Director of AI Initiatives 📰

The New York Times appoints Zach Seward as the first Editorial Director of AI Initiatives, marking a significant shift in digital journalism. Seward, a seasoned leader with a unique blend of digital media skills, will guide the integration of AI technologies in news reporting. His role includes establishing ethical boundaries for AI use and exploring how these tools can assist journalists.

2. Biden's White House AI Council Kicks Off 🤖

The White House AI Council, formed under President Biden's executive order, held its inaugural meeting to shape the future of AI in governance. Key Cabinet members, including Secretary of State Antony Blinken and others, gathered for a classified briefing on AI's global impact. The council's agenda focused on attracting AI talent to government, ensuring AI safety, and addressing risks like fraud and privacy violations. Discussions also covered the newly announced U.S. Artificial Intelligence Safety Institute by NIST.

3. Meta Reportedly Used Copyrighted Books in AI Training 📚

Meta Platforms, despite warnings from its own lawyers, used thousands of pirated books to train its AI models, sparking a major copyright infringement lawsuit. The consolidated lawsuit, involving high-profile authors like Sarah Silverman and Michael Chabon, alleges Meta used their works without permission for its AI language model, Llama. Chat logs from a Meta researcher reveal internal debates over the legality of using copyrighted books, highlighting potential violations of U.S. copyright law. 

4. Accenture's AI Workforce Strategy: People Over Technology 🤖

Accenture's CTO, Paul Daugherty, emphasizes the importance of investing in people rather than just technology in the AI era. Speaking at Fortune's Brainstorm AI conference, he highlighted the need for businesses to adapt their workforce for AI integration. Daugherty pointed out that there's no ready-made AI workforce; companies must develop their existing employees' skills. He also mentioned the potential for job consolidation due to AI's productivity gains but stressed the importance of keeping humans involved in AI processes.

5. Humana Sued Over AI Denials of Senior Care 🚑

Humana faces a class-action lawsuit alleging its AI algorithm systematically denies rehabilitation care to seniors, a significant legal challenge in the healthcare industry. The suit claims Humana's AI tool, used in Medicare Advantage plans, overrides doctors' recommendations, leading to inadequate patient care. This follows a similar lawsuit against UnitedHealth Group, highlighting a broader issue of insurers using AI to potentially restrict necessary medical treatments.

AI Diagrams Whimsical ChatGPT Plugin Review

Here’s a ChatGPT plugin that you can get great use out of on a daily basis regardless of your job.

AI Diagrams Whimsical can create flow charts and mind maps to help you visualize anything.

We’re showing you how it works, and break down two real business use-cases in realtime.

🤷‍♂️ What’s Going On and Why It Matters:

ChatGPT doesn’t suck.

Your prompts do. 

Sorry not sorry, y’all. But that’s the truth. And that’s exactly what we talked about on today’s show.

Let’s get some things outta the way right now. 

  • Our team has been using the GPT technology since it came commercially available in Copy.AI in late 2020. 

  • Our host Jordan has been a keynote speaker in front of thousands of attendees on ways to properly use ChatGPT and recently even spoke at the world’s largest AI Summit in NYC on ways to get better outputs from ChatGPT.

  •  Almost anything you read about prompting (especially on Twitter and LinkedIn) is wrong, and it’s just someone trying to sell you a crappy prompting guide or to get your email for useless “Superprompts” ebook. lolz.

  • We’ve taught thousands of people on proper prompting, from entrepreneurs and marketers to business owners and F100 execs. And it’s all for free in our Prime, Prompt, Polish course.  

Katie cut it straight in today’s livestream comments. 👇

Back to what we learned on today’s rant.

Err… show. 

There’s common misconceptions floating around, especially recently, that ChatGPT is getting lazy. And those prompts aren’t getting the responses that they should. 

Spoiler alert — it’s because most people don’t understand the 101 of prompting a large language model. That’s why we went deep on the topic today, and also dove into: 

  • Using copy and paste or zero-shot prompting is a time waster and produces low-quality results

  • Building skill sets inside ChatGPT leads to consistently high-quality outputs

  • Multi-shot prompting produces better results than zero-shot prompting

  • Claiming expertise and years of experience does not greatly improve the outputs from ChatGPT

  • Large language models work differently from search engines

  • Treating a new chat inside ChatGPT like training an employee is essential for success

Alright, let’s grab the takeaways and get rid of bad prompting forever, shall we? 

Lez get it. 👇

🦾How You Can Leverage:

Today’s show was kinda like a 2-for-1. 

Not only did we debunk the whole ‘ChatGPT stinks because of my mediocre prompting’ piece, but we also broke down the 5 biggest mistakes when it comes to prompting inside ChatGPT. 

What do we know about prompting? 

Take it from Maybritt.

(If you want access to our free prompting course, just reply ‘PPP’ to this email.)

Alright, now let’s talk about the 5 most common mistakes when prompting ChatGPT, and what to do about them. 

1 – Using copy/paste super prompts 📜

Sorry Billy Boy. (He’s that 22-year-old “ChatGPT expert” who’s really just a failed NFT bro trying to sell you a useless prompt book.) 

Your prompts don’t work. 

Any Large Language Model benchmarking study (like the one we talked about yesterday while roasting Google Gemini) shows that multi-step prompts beat the snot outta zero-shot prompts. (That’s essentially what copy and paste prompting is) 

Try this: For the love of Cheez Its, why haven’t you taken our free Prime, Prompt Polish course yet, like Mike? 

Reply PPP to this email and we’ll send you the secret registration page. 

2 – Outputs vs. building skillsets 🧑‍🏭️

Guess what? 

Large Language Models like ChatGPT are not search engines. If you’re thinking of LLMs like a glorified search engine, you’ve got it all wrong. 

Try this: Erase any correlation between a single input and a single output that you have. LLMs are not search engines, and comparatively deliver hot garbage outputs when you only enter one input. 

Go read this breakdown from one of our favorite websites that shows the difference between how search engines and LLMs work. 

3 – Not using skill-based chats 💬

Don’t hit that “New Chat” button every time you go into ChatGPT. 

Naaaaah shorties. 

When using ChatGPT, you should be training each new chat on a very specific skillset. 

Try this: 

Instead of using one chat for hundreds of purposes, create hundreds of specific chats and train each chat in one very specific skillset. 

4 – Expert with years of experience 🧐

“You are an expert copywriter with 20 years of experience” 

Yuckgrossbarf. 🤮

If you think this will give you ideal outputs, think again. Seeing as LLMs are trained on the history of the internet (and a lot more!), there’s a straight up cornucopia of hot-garbage advice on the internet coming from “experts with 20 years of experience” in field A, B, and C. 

Try this: Can we please stop pretending this works and filling Billy Boy’s impossibly ginormous ego? Kthanks.

Instead, when prompting ChatGPT, give ample examples of what defines its role. Give real-world examples of experts it should emulate, or defining characteristics about ChatGPT’s role for a chat.  

5 – Looking at ChatGPT as a shortcut 🚫

Catch-22 here. We get it. 

ChatGPT is the ultimate biz building shortcut, but you’ve gotta put the work in to build the actual bridge to connect a new chat’s capabilities from zero to expert level. 

Try this: That’s legit the whole premise of our free Prime, Prompt Polish course. Have you really not replied ‘PPP’ yet to this email? 

Now This …

We asked you yesterday how you felt about the release of Google Gemini and its marketing controversy.

Here’s what you all thought.

And here was our favorite response! Thanks for your thoughts, Andy!

Reply

or to participate.