AI is everywhere now. 

You might now be fully aware of it, but you carry it in your pockets—our phones are built to understand users through data usage and the apps that we download make use of AI technology. In the workplace, the competition shifts not only in making sure employees are equipped, efficient, and accurate but that they are also fast and productive—and that’s where AI takes the center stage. Imagine: A report which takes an employee to write in one to two hours can be generated by AI in less than 5 minutes.

Truly, what AI can do is astounding. But it’s also scary. Comes with the rise of AI is a question we don’t want our lips to speak of but is an impending idea that must be addressed: are humans going to be replaced by robots or AI?

Learn how AI and humans can co-exist in this episode as I discuss:

• The role of artificial intelligence in a service-based industry
• The dangers of an exposed IP to AI tools like ChatGPT
• How to protect intellectual property from potential AI and other human infringers

I received many questions regarding the concerns about the rise of AI robots in the workflows. Feel free to reach out if there are anything you’d like us to look at to help you protect your assets and intellectual property.

Connect with Erin and find the resources mentioned in this episode at hourlytoexit.com/podcast.

Erin's LinkedIn Page: https://www.linkedin.com/in/erinaustin/

Think Beyond IP YouTube Page: https://www.youtube.com/channel/UCVztXnDYnZ83oIb-EGX9IGA/videos

Music credit: Yes She Can by Tiny Music

A Team Dklutr production

Hello, ladies.

Welcome to the Hourly to

Exit podcast.

today we tackle artificial

intelligence.

Now, there's no one more surprised than

me that artificial intelligence

has become part of my life.

I am a proud technology Luddite.

if it was up to me, I'd still be

using a Blackberry.

To me, they're, the.

Things ever.

but there's no denying the

fact that AI is everywhere and we

can no longer put our heads in the

sand regarding this.

there are some dire concerns

regarding it.

I know that there are some tech

leaders who have gone so far as a

call for a pause in AI development.

I did not know.

I'd agree with Elon Musk.

Pretty much anything.

But I do agree on this point, today,

in fact, as I record this, there was an

article about an episode of the Joe

Rogan experience that was completely

AI generated, and apparently I've

not listened to it, but according

to the article, you could not

tell that it was.

The true thing, the true, recording,

live recording, and that's

kind of scary.

I have seen online.

completely.

AI created YouTube videos, so they use,

image and a voice stamp, and they're

able to create an entire video.

I will say that the AI generated YouTube

video that, I saw looked like it had

a few problems, but it's just a matter

of time before it will be truly

indistinguishable from live

recordings.

And so there are concerns.

Now I am not going to address

those issues.

They're beyond my expertise.

What we're gonna talk about today

is the issue that people have been

asking me, which is, what impact

will AI have on my intellectual

property?

people be, will I be replaced by?

So the answer to will you be

replaced by ai?

The answer to that is no.

as an expertise based service

provider, I understand your

concerns about the impact of AI on

your intellectual property, but

they aren't.

Any greater than kind of the general

of accessibility of our expertise

online these days.

So let's, just start from the beginning.

So let's look at how AI works.

when an ai, System like chat, g p T.

Now I'm going to talk about chat, g

p t mostly today.

That's the AI that I'm familiar with.

It's the one that is publicly available.

probably the most advanced publicly

available one.

There are others like Bard I believe,

and there's a couple, that

aren't as advanced as chat g b.

So if you've been fooling around with

it, the way I've been fooling around

with it, you've probably been doing

it on chat, G B T and that is, it

generates responses from available data.

So I understood that there was a

source of data.

That they copy from the internet

and then it's saved by, open ai,

that's the creator of Chat, G B T.

and that the date of that saving is

September, 2021.

So it doesn't know about

anything that's happened since

September, 2021.

And so to understand this a little

better, I asked Chad, G b t I

don't know if.

Had these conversations

with them.

I encourage you to go on if you haven't

and just ask some questions so you can

see how it works.

It's really.

interesting.

It is different than a Google inquiry.

It absolutely seems to be talking to

you that we call them conversations

or chats.

so I asked chat g p t for confirmation

about, what's the last copy of

the internet that it has, and so

it's response.

As an AI language model, I do not

browse or access the internet in

the same way that humans do, and I do

not have a quote.

Unquote copy of the internet.

Instead, I rely on my preexisting

knowledge base, which was last

updated based on data and information

available up to September, 2021.

So, this was, as of yesterday,

which would be, April 13th, 2023.

And so that will.

in the near future understand that

the next generation of AI will be

able to collect data in real time.

So it won't just be the preexisting

knowledge base that was loaded into it.

It will be able to comb the,

internet live to find its answers.

So obviously that will make it much

more powerful.

So the implications for you as

an expert.

First AI will be using your ip.

AI will be accessing any information

available on the web, so currently

available.

Assuming that it was downloaded, as

of September, 2021.

So the interesting thing about the

answer that it gave me that it

has a preexisting knowledge base.

Well, that means someone had to

load that on there.

It had to decide what

information they wanted to input.

So maybe your IP got into its

knowledge base, but maybe it didn't.

But when AI is able to just kind of

comb the, internet live, then obviously

it will be able to access whatever,

is publicly available on the.

And so that would include,

publications on your website and

other platforms.

And so while that may sound a little

bit terrifying, that happens without

AI right now.

I mean, Google and other, search

engines does live comb the internet

and can access your intellectual

property right now.

So it can find.

what you put on LinkedIn, it can

find out what's on your website.

It can find out, copies of,

your speeches on YouTube so people

can do that right now without ai.

And so if someone live, without any

intermediary, goes on the internet

and sees that you wrote something and

decides to write something similar,

We hear all the time about people are

copying my ideas.

There's nothing new about that.

so AI will be able to see what

you're doing and incorporate it

into an answer that they provide

But what we need to understand is

that in both cases, being inspired to

write something similar or even

stealing your ideas is not copyright

infringement.

copyright infringement is the

same, whether it's a human reading your

stuff and taking it, or AI reading

your stuff and taking it Copyright

infringement means that they

have to have ex to violate your

exclusive rights as a copyright.

So as a copyright owner, these

are your rights.

You have the exclusive right

to reproduce, distribute,

publicly, perform, and publicly

display your works.

So anyone who engages in any of

these activities without your

permission, they would be liable

for copyright infringement.

So copyright infringement

means that as the copyright owner, you

can show that one, you are the owner

of a valid copyright in the work in

question two, that the infringer

has actually copied your work

or a substantial portion of it.

And three, that the copying isn't

protected by an applicable defense

such as fair use.

if you have a question about

fair use, I have, written about it

and done a LinkedIn live about it,

which you can find.

but copyright infringement

again, is not about stealing your ideas,

but it is about actual copying.

And so if you can prove that they

actually copied your work, then

they would be able to take, you be

entitled to damage.

And I'm not gonna say that

proven copyright infringement

cases is easy.

It's not, it's complicated and it

typically involves a fair amount

of legal fees.

So you do need to make sure that

it is valuable enough to you to

devote those types of resources to.

Prosecuting an infringement case.

So, but if you are concerned about

the use of your IP by a third party,

whether that third party is human or

an AI tool, then you need to take

the steps required to protect it.

So if we go back to proving

infringement, you have to

be the valid, owner of a valid

copyright question.

Chain of title regarding ownership

starts from the time of creation.

So you'll hear me talk over and

over again about the importance of

your contracts and making sure that

you own things.

If you didn't create it personally, if

the third party created it for you,

if you created it in connection with

an engagement, then ownership

will depend on what those contracts.

And then, when you are the sole owner,

then registration.

So these are the two ways we make

sure that we have a defense.

we can, enforce our copyright

against third party infringers ownership

and registration.

and then, again, it would have to

be a copying of your work and not.

Taking the idea of your work.

So it is not in your power to

stop someone from accessing your IP

on the internet by humans or by ai,

but it is in your power to put the

pieces in place to put yourself in the

best position to enforce your rights

if it comes to that.

So on the other end of that is when

you're using ai, And AI is doing

work for you.

It will be accessing other people's

intellectual property on the

internet when it's creating

its responses.

Now, when you, go ahead and,

play with it, you will see it will

send you answers.

It does not provide any attribution.

So that is different than if you do

a Google search where you know

exactly where the information

is coming.

Here.

It just goes wherever it

goes and it's.

Knowledge base and finds answers, and

then it, sends it back to you in a,

if you asked for to write an article

for you or to write a script for you,

it will present it in that form and,

typically without attribution, so you

won't have any way of knowing where

that information is coming from.

So, That puts you in danger of

being a copyright infringer if you

don't know where that came from.

So I asked chat, G B T what to do if I'm

worried that it's response infringes

a third party's copyright, and its

response was this.

As an AI language model, I provide

responses based on my preexisting

knowledge and language

capabilities.

However, I am not able to

review or assess specific content

or material for potential copyright

infringement.

If you are concerned about

potential copyright infringement related

to your own content and material, you

may wanna consult with a legal

professional who can provide guidance

and advice specific to your situation.

They can review your material and

assess whether any potential

infringement has occurred or is

likely to occur.

In general, it is important to be

aware of copyright laws and to obtain

permission or authorization before

using or reproducing any copyrighted

material.

Additionally, it is advisable to seek

legal advice if you are uncertain about

whether your use of someone else's

copyrighted material may infringe on

their rights.

Well, in other words, user beware.

I mean, that's all very fine

to say, but if you have receiv.

A response that doesn't provide any

type of attribution.

All we know is it came from chat

GPTs preexisting knowledge base.

Like how does that tell me what

the source is?

How do I know if I need to,

if this is a potential copyright

infringement?

Again, you know, copyright

infringement requires copying

and not just inspiration or.

taking an idea.

So did they completely take

a whole chunk of somebody else's,

work and stick it in into your response?

Or did they, take a variety of sources

and kind of put them together in

a way that creates something new?

So if chat G p t Plagiarizes from

source materials, You won't know that

unless you do your own due diligence

and you are the one who'll be liable

for copyright infringement,

not chat.

G P T.

So if you plan to use AI for your

work, you need to use some sort of

plagiarism check, like Grammarly,

and you need to track your

process carefully to demonstrate

your unique input when you're

creating content.

So you can't just, copy and paste

what comes out of your AI chat.

There also are some privacy issues, so.

When I asked chat G b T, whether or

not the information I provide to it

becomes public.

The response was, your information

is not made public and is

kept confidential.

However, if you go to the fax page,

it warns you don't share any sensitive

information in your chats.

Your conversations may be reviewed

by RA ai trainers to improve our.

So remember the way that AI works

is that what you put into the chat

becomes part of its knowledge base,

cuz that's the only way that it can

continue to improve your responses.

So again, if you go in there and,

maybe you put in.

A draft of something and ask it to

improve the draft, it will, maybe you

put in notes, put some bullet points

in, and ask it to create an article

based on these bullet points.

It will use your bullet points.

It will use its preexisting

knowledge, and it will come

up with, a.

Something in article form and then you

say, eh, and you ask it to regenerate

and then it will go back and it

will improve on it.

And you'll see that each time you ask

it to regenerate, it gets better.

Cuz it kind of goes deeper into its,

knowledge base and it's got, what you

asked it to use as a starting point

and it gets better.

So somehow, What you have input

is being added to its knowledge

base, so it can give you better.

So, as a lawyer, you know, my ethical

duties means that I cannot share any

confidential client information with

a public, AI tool such as chat, G p T.

So I recommend the same diligence for

you with respect to your confidential

information, and of course,

your client's confidential

information.

You need to protect it and assume that

at some point, if not now, then

certainly later that anything that

you put into a chat will be accessible.

So finally, there is kind of the issue

about ownership of content that is

generated by ai.

So the US copyright office

is working out.

Whether content generated by AI

can be protected.

chat, G B t, says that the answers

are owned by the requester.

but that.

Make some assumptions that

I don't think you can rely on.

Again, we don't know the source

of the answers of the responses.

So without knowing that,

how can you know that you own it?

copyright law does not protect ideas.

It doesn't protect facts, it doesn't

protect information.

so a lot of AI generated responses

fall into those categories.

However, there are.

creative uses for ai.

sometimes, you can ask it to write a

poem or you can ask it to write a script

and you can, ask it to write songs.

And certainly there is AI that

can create, images and paintings

that would be considered original

and creative.

So there are some real valid

questions about ownership of AI

generated content.

I describe intellectual

property as the product of human

intellect, and AI is not human,

at least not yet.

At the beginning of ai, there had

to be humans.

There always has to be a human at the

very beginning of any idea, right?

at least a recorded idea.

so this is just, another one of

these conundrums that AI presents

to us that will need to be worked

out as AI becomes more prevalent.

So, When we talk about your

expertise, your intellectual

property and the dangers of it being

exposed in, more scenarios through

the use of ai.

I talk about the distinction between

a cook and a chef.

a cook can follow a recipe and produce

edible and maybe even delicious food.

However, a chef has that skill,

the experience, the creativity,

and the talent that makes people wanna

pay the big bucks to go join, to

pay them to, have that experience at

their restaurant.

So this is the same with your expertise,

so an AI solution?

Yes.

It can replicate, you know, run

of the mill.

Of what you do, it can scrape the

internet for freely available content.

AI is basically a generalist though,

and it doesn't understand the

nuances the way that an expert does.

And when it's scraping the

internet, it won't be able

to differentiate between, what is

thought leadership versus what is

just someone's random ramblings,

on the internet.

And so that is why today.

You'll get some nonsense answers

from AI cuz it, can find something

that matches your keywords, but it

can't tell whether or not this is

well-researched information or if

it's just something, someone's musings

so it cannot, kind of synthesize.

Experience the way that you can, I

mean, experience and being able to

kind of pull on that is a uniquely

human skill.

So it can only pull on what has been

recorded and it can't always apply.

Context either.

So as a chef, as the expert, you

know when to go with a standard

ingredients or when to add something

else, you can taste it and go, eh, it's

too sweet, it's too salty, and know how

to tweak it to make it taste better.

Another metaphor is with respect to,

the doctor-patient relationship.

Yes, AI can ask diagnostic

questions, it can review lab results,

and it can provide a, diagnosis

based on that and propose solutions

based on that.

What it can't do is it can't observe the

patient's demeanor.

is sweating, is their leg shaking?

can they notice that maybe it's, someone

who has a parent in the room with

them and asked, you know, can I talk

to, your son alone?

they can't ask the follow up questions.

They can't put him at ease.

Sometimes having your blood pressure

taken and you're like, you know, why

don't you lay down for a second and

we'll do it again.

These are a number of things that

require kind of the human touch.

And some people will accuse doctors of

not having a bedside manner, but most

doctors do have a bedside manner.

AI can never have a bedside

manner, right?

And so those things where you as an

expert can use your instinct.

To take, what you know about a client,

what you know about their, problems

they had with their last consultant.

these are things that AI cannot do.

So ai, yes, it can be an excellent

support for your work, but only you

kind of know how to tweak things

and make those little shifts

that come from years of experie.

So I had one more question for chat

and G B T and I asked it, can AI

take the place of a management

consultant?

And here was its answer.

AI can certainly provide valuable

insights and analysis that

can be useful for management

decision making, but it is unlikely

to completely replace the role

of a management consultant.

Management consultants bring

a range of skills and expertise

to the work, including strategic

planning, business analysis process,

improvement, and change manage.

They often work closely with clients

to understand their unique challenges

and provide customized solutions

that meet their specific need.

Management consultants also

typically have strong interpersonal

and communication skills, which

allow them to work effectively

with a wide range of stakeholders.

While AI can provide powerful

data analysis and insights, it may not

be able to replicate the nuanced

and contextual understanding that

a skilled management consultant

can provide.

Additionally, AI may have limitations

in its ability to understand and

respond to complex human factors such

as organizational culture, individual

personalities, and political dynamics.

Oh, that is so.

That being said, AI can certainly

be a valuable tool for management

consultants helping to automate certain

tasks and provide additional insights

that can inform the recommendations.

Ultimately, the most effective approach

is likely to be a combination of AI

and human expertise working together

to provide the most comprehensive

and effective solutions for.

Yeah, that is absolutely true.

So I am excited by AI's possibilities

to support us as experts in our work.

It is absolutely a time saver.

It is a wonderful resource, but

ultimately, without human touch, AI has

its limitations, so make it a

fantastic tool.

As part of your toolbox, how you

provide value to your clients,

how you make your business

more efficient and therefore

more profitable.

But I don't want you to worry about

it replacing you as an expert.

The key to working with A I protect

your original ip, protect it through

documentation.

Through registration and when you're

using AI as a resource, make sure

you are doing your diligence to make

sure that it has not plagiarized somebody

else's work.

So if you have any questions or

concerns about how AI impacts your

ip, you can contact me for consult.

And also don't forget the IP

tracker as a way to determine what steps

you need to take to protect yourself