🦾How You Can Leverage:

No, that’s not how ChatGPT works. 

Maybe we’ve thought this in our head so many millions of times that we decided to say the quiet part out loud for #HotTakeTuesday. 

Because here’s the reality.

Even some seemingly smart people who have their 💩 together in all things AI want to share AI tips and tricks. 

Which is really, really bad advice. 

Follow randos at your own risk, because most of the advice they give is …. NOT HOW CHATGPT WORKS. 

Not saying we’re the hands-down experts, but:

• Our team has literally been using the GPT technology almost daily since 2020. 

• We’ve talked the literally the smartest people on the planet about GenAI for a year.

• Our host Jordan literally spent his weekend re-reading these papers below.

Without further chit chat, let’s go over 5 tell-tale warning signs that signal whoever you’re listening to about ChatGPT probably has no idea what they’re talking about.

Oh, and make sure to go watch/listen to today’s show.

Like Anneli said, we all need to debunk the B.S. in the GenAI world to stay ahead.

Let’s get after it… here’s 5 red flags that “experts” are getting wrong about ChatGPT.

If someone honestly thinks that a single screenshot of ChatGPT means anything…. Turn around and run.

In today’s show, we gave an example online where someone entered a simple prompt, asking ChatGPT to come up with an advertising slogan for a Nike ad for women’s basketball icon Caitlin Clark.

(For context, Clark recently broke the NCAA all-time scoring record and is so good it’s silly.)

After seeing Nike’s great ad copy, this person pondered what kind of result ChatGPT might give.

In other words — a very simple input and output from ChatGPT shared on social media.

(That’s not how ChatGPT works)

For fun, we took the simple copy and paste example, the ACTUAL ad text that Nike ran, and then we properly trained ChatGPT for the task and produced our own headline using our Prime, Prompt, Polish method.

Which advertising slogan do you think would best complete this ad?

(Vote live to see the results, and we’ll tell you in tomorrow’s newsletter which one was written by who.)

What it means:
Well, you can skip straight to the good stuff and see what our live audience thought.

But in short, doing a simple input-output inside of ChatGPT and sharing results means absolutely nothing, and this is not a good way to learn about GenAI.

Wrong.

If anyone tells you that the ‘Browse with Bing’ feature inside of ChatGPT will keep your outputs up to date and hallucination-free doesn’t really know what they’re talking about. 

That’s not how ChatGPT works! 

Between the fact that Browse with Bing can’t actually visit specified pages to the finicky nature of the SEO that Browse with Bing relies on, your outputs aren’t necessarily better when you use Browse with Bing. 

What it means:
You’ve really gotta understand the pros and cons of Browse with Bing and also how it works.

Luckily, we’ve already covered that one in depth.

Grossbarfyuck. 🤮

If anyone swears to you that their magical ChatGPT prompts are gonna do absolutely anything for you or your company, run for the hills shorties. 

We’ll say it loud so those of y’all in the back can hear. 

Prompts. 
Do. 
Not. 
Work.

What it means:
Generative AI systems like large language models are…. Generative!

We think that LLMs like ChatGPT are deterministic like search engines. They’re not. 

(Hint: Deterministic = the same/consistent output that is predetermined. Generative = can get wildly different results.)

And jumbo models with trillions of parameters really fail with zero-shot prompts. That’s when you go into a new chat, paste in one giant prompt with no examples, hit enter, and expect a usable output. 

(Again…. That’s NOT how ChatGPT works.) 

Anyone that gives you advice on and doesn’t break down covering unstructured data into structure rules for ChatGTP to follow…. Doesn’t know what they’re talking about. 

#Sorrynotsorry.

Can a random prompt and pasting in examples make ChatGPT slightly less robotic and a little more like you? 

Sure. 

And if your (or your company’s) writing style is a straightforward, vanilla-ish tone, ChatGPT might do OK at that. 

But can a simple prompt and pasting in examples of your writing actually produce results similar to a unique writing style or brand voice? 

No. That’s not how ChatGPT works. 

What it means:
Here’s the thing - Large Language Models don’t truly even understand words.

They convert words to tokens based on context and use super smart deep learning superpowers to try and predict the next token in its output based on its translating of your text into tokens.

In other words, for your AI efforts to work, you really need to understand LLM tokenization and go through the process of turning unstructured words into structured rules for ChatGPT to follow.

This show will give you a head start. 

Can we skip all the nonsense here and say, ‘No, that’s not how ChatGPT works?’ 

Would you rather have a paper, pen and landline to run your business or the world’s fastest computer? 

Yeah, that’s kinda the difference between the free version of ChatGPT and the paid version. 

What it means:
If someone tells you that the free version of ChatGPT is good enough or if they’re trying to give you ‘X free alternatives to ChatGPT’…. That means they don’t actually know what they’re doing. 

This show might be a month or 5 old, but the gist of it still holds true.

The free version of ChatGPT shouldn’t be used. Like…. Ever.

….. and the winner is

Congrats to Justin L for winning our NVIDIA GPU giveaway. We’ll be in touch so check your email.