Seeing the Elephant: Getting ChatGPT Right

This is the first in a series,"Seeing the Elephant: Understanding AI technology", exploring strategies for thriving in a world disrupted by AI technology in 2023.

There is an ancient parable which goes like this:

Several blind men who have never encountered an elephant meet one for the first time. Each is asked to describe the elephant – but they are only allowed to learn about it by touching the part of the animal directly in front of them.?

The first touches the trunk and describes a powerful serpent. The second feels the tusk and describes something like a giant spear. The third holds one of the huge floppy ears and describes a bat-like creature.

Just like these blind men, many of those writing about ChatGPT are missing the big picture.

Before we can think clearly about the strategic implications of AI technology, we need to make sure we have an accurate understanding of what it is, and what it can do. Right now, many of us are getting that wrong.

A common criticism is that "ChatGPT Can't Do X" , where X is something humans do well.?Often, like the blind men in the parable, this is the result of not understanding the bigger picture.

Some common themes:

1. It writes robotically, without any style (wrong)
2. It has no sense of humor (wrong)
3. It's not human and doesn't understand us (true, but…)

Let's take a look at each of these:

1. ChatGPT is not human and doesn't understand us

Ironically, Ian Bogost from the Atlantic got ChatGPT itself to write this:

"It is simply trained to generate words based on a given input, but it does not have the ability to truly comprehend the meaning behind those words. This means that any responses it generates are likely to be shallow and lacking in depth and insight." (written by ChatGPT)?- The Atlantic, December 7, 2022?

Or as singer-songwriter, Nick Cave wrote:

?[ChatGPT's attempt to imitate my work] was "a grotesque mockery of what it is to be human,"

* * *

?ChatGPT has no inner being, it has been nowhere, it has endured nothing, it has not had the audacity to reach beyond its limitations, and hence it doesn't have the capacity for a shared transcendent experience, as it has no limitations from which to transcend." – Nick Cave, The Red Hand Files, January 23, 2023

Of course ChatGPT isn’t human.? Why do we need it to be?? Because it's not human, it has infinite patience and capabilities beyond what humans can do. My desk calculator isn’t human, but it can do amazing math well beyond my own abilities.

The mistake is anthropomorphizing ChatGPT -- judging the technology as if it were a co-worker down the hall. This is something I’ll explore more in an upcoming post. For now, let's just embrace that ChatGPT is not human and should not be judged as if it were.

2. ChatGPT can't write with style (Wrong!)

Tony Ho Tran of The Daily Beast recently wrote:

"...ask ChatGPT to write you an essay or a story. Do it a few times. You’ll quickly find that the writing is sloppy… There’s no style or flair."?-- Daily Beast, January 17th, 2023

It's true that ChatGPT's default style is bland – but only if you let it.

As Tony Robbins is fond of pointing out,

"The quality of your questions determines the quality of your life."

With ChatGPT the quality of the question determines the quality of your answer.

When I asked ChatGPT to write a description of an encounter with an elephant on a trip to the zoo, in seconds, it produced this:

One of the elephants approached me, its trunk reaching out to sniff at my hands. I felt a thrill of excitement, for this was a once-in-a-life time encounter with an elephant's eyes. I was filled with a sense of wonder and respect for all that is wild and free.

I left the zoo that day with a new appreciation for the beauty and majesty of the elephants, and with a greater understanding of the importance of preserving their habitats and ensuring their survival for future generations.

The secret? I prompted it by asking for a description of the encounter "in the style of E.B.White."

Digging Deeper: I asked ChatGPT to create the same story in a variety of different writing styles including Jerry Seinfeld, William Shakespeare, and Mickey Spillane. It's an eye opening read, that you can find here, "ChatGPT Meets an Elephant" For fun, I also added AI generated images to spice it up.

3. ChatGPT has no sense of humor (Wrong!)

Another common misconception. Properly used ChatGPT can write with style and with humor – and do a lot of other things many people think it can’t do.

For example, Ben Eisen of the Wall Street Journal recently had the courage to let ChatGPT write him jokes for a comedy competition (well … a pun competition anyway…) The result?

I decided to use the robot’s best pun: “What’s the state where common sense is in short supply? Flori-duh.” The crowd loved it. --Wall Street Journal,December 12, 2022

To be fair, the Ben also delivered quite a few total bombs thanks to ChatGPT, but the “Flori-duh” pun got a real laugh from real humans.

So why do people think ChatGPT can’t write with humor? Simple: they don’t understand how to use it. It’s like compaining that your sports car won’t go fast enough because you don’t know how to shift out of first gear. To use ChatGPT properly you need to learn to drive it like a sports car -- shifting, turning, accelerating and braking constantly to get the best performance.

Prompt engineering 101

Prompt engineering is the skill of creating richer questions to get better results from generative AI like ChatGPT.?

Prompt engineering is a big topic I explore in an upcoming post but here are a couple quick prompt engineering tips to improve your Chat GPT results almost immediately. First, when you ask ChatGPT to explain a complex problem try adding the phrase, "explain step by step…"

For example, instead of asking "Explain how to make an omelet."

ask: "Explain step by step how to make an omelet"?

Second, if your responses are bland, stiff, or humorless, tweak your question like this:

• "Describe X in an informal and humorous style, and include a few jokes."
• "Explain X as a Norm MacDonald joke."
• "Rewrite that in an informal and conversational tone, and use humor."

So when you hear that ChatGPT can't do something, or does it badly, ask how could a better question to fix that?

The Bigger Picture: Seeing the Elephant

The technology behind ChatGPT is a big deal, and no one really understands the bigger picture yet. We’re all still blind ment, touching different parts of the elephant, and trying to fully understand what’s in front of us.?Failing to acknowledge that is getting it wrong.

In this series, "Seeing the Elephant: Understanding AI technology" I'll continue to unpack the implications and the misunderstandings of this exciting technology.

JOIN THE CONVERSATION ??

I'd love to hear your feedback, thoughts and insight about Generative AI and ChatGPT – please comment below. Also, please do me a huge favor and share it with your friends and colleagues, give it a thumbs up.??

Next time: Unlocking ChatGPT's Superpower

ChatGPT can provide competent, useful and detailed advice on nearly any topic, but you have to know how to ask it. In my next post, I walk through an extraordinary experience as ChatGPT gives me surprisingly accurate (well mostly accurate) and detailed advice for undertaking a three month voyage in a small sailboat from San Francisco to the South Pacific ??

And I'll unpack why this is so disruptive.

Note and Caveat: AI technology is that it is changing so damn fast. This article is being written in early 2023. It may be obsolete by Wednesday

About AI I used to help write article:?

The images in this article were generated using the AI generative image tool, Dall-E from OpenAi (https://labs.openai.com/ )

I also used ChatGPT to brainstorm a bit when writing this.