Artwork for podcast The Google Ads Podcast
AI And Autonomous Agents: The Development In AI That Will Change The World Forever
23rd January 2024 • The Google Ads Podcast • Solutions 8
00:00:00 00:19:16

Share Episode

Shownotes

Soon, AI is going to be a billion times smarter than us.

With the development of autonomous agents, AI has the ability to operate independently, make decisions, and perform actions without any human intervention!


It just keeps on learning from everyone’s inputs (and ideas) 24/7…


This eye-opening and mind-blowing conversation between Kasim and Glen only scratches the surface of AI's capabilities…


Watch the video to discover how the development of AI will change the world forever.


0:00 Intro

2:13 What Autonomous Agents are and do

6:44 How autonomous agents learn, iterate, and accomplish goals

8:55 Why good prompts matter

12:43 How long until autonomous agents can just manage a Google Ads campaign

15:05 Devs, determinism, will AI be able to predict the future?

19:42 Will AI replace your role?

20:20 How AI affects your job



Need help with Google Ads? Get your FREE action plan here: https://sol8.com/ap/


💣 The Ultimate Guide to Google Ads for 2023:   

 • The Ultimate Guide to Google Ads for ...  


🔥 Get your copy of You vs. Google: The (Very) Unauthorized Guide to Google Ads

on Amazon here: https://www.amazon.com/dp/B0BWSNLNRN


This ULTIMATE GUIDE gives you EVERYTHING you need to know about how to set up, build and optimize your Google Ads Performance Max campaigns: https://sol8.com/performance-max/


💰 Have an ad budget that's less than $5,000/month? If so, check out our sister agency, StarterPPC, where you can get Google Ads management for a fraction of the cost!

Visit https://www.starterppc.com for more information. 🚀


We have dozens of free resources, courses, downloads, calculators, and other goodies. You can access all of them on our Free Stuff page!

Visit: https://sol8.com/free-stuff/


💯The Ultimate Guide to Google Ads for Lead Generation:

https://sol8.com/google-ads-lead-gene...

🛒 Everything you need to know about Google Ads for eCommerce:

https://sol8.com/google-ads-for-ecomm...

🧲 The only guide you’ll ever need for Google Ads for YouTube:

https://sol8.com/google-ads-for-youtube/


👉 Do you want to be featured on Daily Google News? Do you have epic value you can offer our audience? You can pitch your idea here: https://sol8.com/pitch/

--------------------------------------------------

👉 Get our latest content every Monday, straight to your inbox. Sign up for our news “Traffic Ahead”: https://sol8.com/newsletter/

--------------------------------------------------

Get the latest updates, expert tips, best practices, and PROVEN Google Ads strategies every single day. Subscribe here:   

 / @solutionseight  

--------------------------------------------------

👉 Want to become a Google Ads expert?

We’ve demystified how Google works, and laid out everything you need to know in Google Ads–from scratch!

Learn how to build, launch and manage high-performing Google Ads campaigns in this Google Ads Course: http://sol8.com/paid-traffic-mastery

--------------------------------------------------

Solutions 8 is a global authority in the Google Ads space and one of the world's leading PPC agencies.

Our YouTube channel is dedicated to sharing our most effective marketing strategies to help you achieve your business goals.

--------------------------------------------------

👉 WOULD LIKE TO SCALE AND GROW YOUR BUSINESS WITH PPC?

Sign up for a FREE Action Plan today: https://bit.ly/sol8-home


Connect with Kasim here: https://smartlink.metricool.com/publi...


⬇️️ You can find us here ⬇️️:

Website: https://sol8.com/

Twitter:  

 / solutions_8  

Instagram:  

 / solutions_8  

Facebook:  

 / solutions8llc  

LinkedIn:  

 / solutions-8  

#googleads #digitalmarketing #googleadsbestpractices #ppc

Transcripts

Kasim:

Welcome to Daily Google News.

2

:

This is Qasim here with a frequent

flyer actually on the YouTube channel.

3

:

Everybody knows Glenn.

4

:

Glenn, you're awesome, man.

5

:

Appreciate you being here.

6

:

I think you're the most learned person as

it relates to AI that I know personally.

7

:

I don't know anybody else who has their

finger to the pulse the way you do.

8

:

I don't know how or when you find the

time, but every time something new comes

9

:

out in AI, I hear about it from you first.

10

:

And then two weeks later, I

hear about it from the world.

11

:

Like you just seem to be

hooked up straight to the drip.

12

:

And so that's what we're going to talk

to you about today and you actually

13

:

put in our agenda, AI stuff and stuff.

14

:

That's it.

15

:

AI stuff and stuff.

16

:

Yeah.

17

:

I'm excited.

18

:

And you said in particular,

AI agents of change.

19

:

Agents and chain of thought reasoning.

20

:

thought reasoning and autonomous agents.

21

:

And that's just the tip of the iceberg.

22

:

autonomous agents would be

locally hosted AI bots that do

23

:

things that you want them to do.

24

:

They don't have to be locally hosted.

25

:

there's already some products out there

that where there's GUIs, graphical

26

:

user interfaces that you can log

in, create accounts, and they create

27

:

Multiple bots that work together.

28

:

So this has been proliferating

probably in the last few

29

:

weeks, the autonomous agents.

30

:

So there's a couple of big

baby AGI was one agent GPT.

31

:

I've got there's a whole heap

of them Agentverse, AutoGen,

32

:

AutoGPT, Kodi, ChatDev, DevGPT,

FlowWise, GuideMode, NextGPT.

33

:

they're starting and Microsoft have

just released theirs called, AutoGen.

34

:

So what it is, most of these are

installed on your local computer.

35

:

problem that ChatGPT has had.

36

:

Except in the last few days, now Bing's

been incorporated back into the pro is the

37

:

inability to connect straight to the net.

38

:

The only way you could do it is via the

plugins with these autonomous agents, you

39

:

go to get GitHub, download it, install it.

40

:

Everything's run through the command line.

41

:

So you have to be comfortable

in typing in commands.

42

:

It's old school.

43

:

Coding back in the day where you bought

up the black window and typed in code

44

:

CD, make, you basically typed code in

there and it installs locally on your PC.

45

:

Then what happens is you give it a task.

46

:

So you might say, we'll use an example.

47

:

I'm looking to open a business

in a particular niche.

48

:

It might be.

49

:

Weight loss in New Zealand, I can say, I

want to create a weight loss product in

50

:

New Zealand, find me an underserved niche

that and provide evidence to support that.

51

:

So what happens is one in that prompt.

52

:

The autonomous agents go I'm going

to be the researcher and I'm going

53

:

to start researching that I'm now,

and then another agent is created.

54

:

So you might have four or five

agents and they're all doing

55

:

completely different things.

56

:

And one goes off and does this

and one goes off and does you

57

:

creating each individual agent or

is there a no, this just happens.

58

:

So based on the task, it's going, okay,

you're looking for A research team.

59

:

But a research team, there'll be,

there might be four or five in a team.

60

:

what these things are doing, depending

on what you're asking it, it will

61

:

go, Oh, you need this task done.

62

:

We're going to create a

small business team for you.

63

:

And it might create four or five

different agents and off they go.

64

:

And they just go away

and they do this thing.

65

:

this or 30 minutes.

66

:

And you just sit there and watch

it you're seeing browser tabs

67

:

open up and applications fire.

68

:

No, it's all done, but it's all

just done by the command interface.

69

:

there's one called chat dev

and it's this little game.

70

:

There's a little room with little people

the CEOs at his desk this person's

71

:

here and this person's here, and they're

walking around and they're doing things

72

:

and you're seeing everything going on.

73

:

But what they do is they talk

to each other, they say, and

74

:

hey, I've got this information.

75

:

Go and research this.

76

:

They go, great, thanks for that.

77

:

And then, these agents are communicating,

so these bots, this AI is communicating

78

:

and you're watching it happen in the

ui, you're watching it happen, and

79

:

then it will come back and it'll go.

80

:

Here's our findings.

81

:

Now, are the findings any good?

82

:

Like, Have you played

with these enough to know?

83

:

You'd rely on them for business decisions.

84

:

Yes.

85

:

People are making business decisions

and finding areas of opportunity

86

:

using these autonomous agents.

87

:

as you and I said before this meeting,

this is the worst it's ever going to get.

88

:

And the rate at which these autonomous

agents are coming out, it's like

89

:

a new one's coming every week.

90

:

There's one that I've used, I

think it's called Agent GPT.

91

:

I have that pulled up.

92

:

Is it agent gpt dot reworked?

93

:

So it's free.

94

:

You can create a free account and, or

you can pay template, a a monthly fee.

95

:

But have a look at the templates.

96

:

You'll see these templates there,

and you go, okay, I want to industry

97

:

GPT or brand GPT, or Platform

GPT, everything's ready to go.

98

:

You just give it the

prompt and away it goes.

99

:

This is one that's got a UI, but

there's a lot of others that you have

100

:

to download and install on GitHub.

101

:

But this is, the way that this is working,

and I was speaking with Leandra about

102

:

this a couple of weeks ago, what this is

doing, if I was in any sort of management

103

:

role, I'd be very nervous at the moment

because what these autonomous agents

104

:

will be able to create a business.

105

:

Of all of the people who run the business

and the decisions they make and they all

106

:

talk to each other and help each other.

107

:

And now these things are only

getting better and better.

108

:

What they've been seeing is that these

autonomous agents are learning from what

109

:

the other autonomous agents are doing.

110

:

I'll give you an example.

111

:

when they first started with this

they got a they're running these

112

:

autonomous agents on the game Minecraft.

113

:

So these things are running.

114

:

By itself.

115

:

And you sit there and watch this

Minecraft game and there'd be all

116

:

these people in Minecraft and they

said, Oh, we're going to build a house.

117

:

What do we need?

118

:

We need wood.

119

:

We need bricks.

120

:

We need this and this.

121

:

Okay.

122

:

I'll go and get the wood.

123

:

I'll go and get, so off

they'd go and do these things.

124

:

And they'd come back and they'd talk and

go, all right, I've got my five wood.

125

:

John, have you got your three bricks?

126

:

No, I've only got one.

127

:

Okay.

128

:

You keep going with that and

we'll go off and do this.

129

:

And so as they were doing these

tasks, they'd come back and John

130

:

has still only got one brick and

they're going, John, what's going on?

131

:

We got I've got to make a brick,

but to get brick, I've got to

132

:

get mud and this and this thing.

133

:

Oh, there's a lot more work involved

in what you have to do than we did.

134

:

We'll help you now.

135

:

They change and they come in

and go, okay, we'll help you.

136

:

So these autonomous agents were learning,

going, Oh, this guy needs assistance.

137

:

Let's go and help him.

138

:

And they work as a team.

139

:

To get towards the common goal.

140

:

they're learning in app?

141

:

So here's my box and I've created my

autonomous agents and I'm building my

142

:

current Minecraft castle and they're

learning from each other in app.

143

:

Let's say you've got a box

building a Minecraft castle too.

144

:

Is there any cross

pollination of that learning?

145

:

Is there a central repository that

takes all the learning that we're

146

:

doing and then amalgamates it?

147

:

Yes.

148

:

As long as it's going towards the

common goal it's going to get

149

:

better on an exponential scale.

150

:

Yes, with every task anybody

does, it iterates, not just

151

:

the task, but also the bots.

152

:

And the next time you try to do

that task, it's going to be better.

153

:

It's going to be better because

it's learned from that task.

154

:

So once it's done at once, it's gone.

155

:

Oh, okay.

156

:

We can do that better next time.

157

:

So let me challenge something

that you've said twice.

158

:

Which I agree with, by the way.

159

:

This challenge is just

good academia to ask.

160

:

this is the worst it's ever going to be.

161

:

It's only ever going to get better.

162

:

What if, because it's iterating, and

it's iterating off of human input,

163

:

Let's say that you have 10 people

all asking it to write emails.

164

:

Cause I noticed one of the templates

here and agent GPT is email, GPT

165

:

compose a concise and detailed email.

166

:

You ask 10 people to write emails.

167

:

Let's say two are really good copywriters.

168

:

And when it's writing the email, the

two are giving a good feedback, good

169

:

iteration, good updates, likes the emails.

170

:

Eight are garbage copywriters and

the feedback, and they actually

171

:

end up with garbage emails.

172

:

Is it possible that the iteration is

actually a downward cycle based off

173

:

of the aggregate average of the users?

174

:

So this is where prompting comes into play

and prompting has been the buzzword for

175

:

months now with prompts are everything

and you've hit the nail on the head.

176

:

The thing with a prompt is

you could type the same prompt

177

:

in the chat GPT or whatever.

178

:

It might be Claude.

179

:

It could be po could be Lama or whatever.

180

:

And you could get.

181

:

You could type that same prompting 10

times and get 10 different responses.

182

:

And that's always been the

complaint with these AI agencies.

183

:

They have a propensity to

be random, inconsistent.

184

:

You'll just, and I've seen this myself.

185

:

like I'm heavy into trying to

develop some code using chat GPT,

186

:

using Google Cloud, connecting with

Google Ads interfaces and trying to

187

:

get chat bots and to integrate with

our data so we can analyze our data.

188

:

And the problem that I'm finding

is when you're typing in the prompt

189

:

it'll give you the responses and

you go, Oh, that's not working.

190

:

Oh, sorry.

191

:

They'll give you another response.

192

:

You want to give me that first

time that is the complaint.

193

:

everyone's in Google ads is

using AI to create ad copy.

194

:

Everyone's doing it.

195

:

There's no secret to this.

196

:

However, in the world of, as you and

I both know, copy is everything, and

197

:

I think Ryan has even said that he

who is a better copywriter will win.

198

:

what, how you use your words.

199

:

So if you think about it, There

are some amazing copywriters.

200

:

Gary, Halbert Chow that

wrote a copy for Apple.

201

:

I've got about 13 and I say in my prompt,

write me ads in the style of these

202

:

people and they know that now it goes,

oh yeah, he was famous for this and this.

203

:

So you are now saying.

204

:

I want this thing, but I want you

to do it this way, like this person.

205

:

And it goes, Oh yeah, I

know what that person is.

206

:

So this AI knows everything about

the avatar or the personality that

207

:

you're saying, I want you to do this.

208

:

So that's the problem.

209

:

A lot of people are using is they're

saying, I want you to do this task.

210

:

It can do that task, but you're

not being specific enough.

211

:

I want you to do this task This person

would do it and I want it done this way.

212

:

So you, it becomes more of a multi prompt.

213

:

I've been sharing it with our team.

214

:

So our specialist, my prompt

for ads is about this long.

215

:

It's gigantic it's gotta be like

this and it's like this, but I want

216

:

to use these and write it this way.

217

:

And it's got to be like this and

I pretty well get what I want.

218

:

99 percent of the time,

a couple of backwards and

219

:

forwards, but I've nailed it.

220

:

I've got the copy.

221

:

I want how I want it.

222

:

How long until autonomous agents can

just manage a Google ad campaign?

223

:

That leads me on to my

next point is determinism.

224

:

So how long that is

going to be the question.

225

:

The right at which everyone's

knows of Moore's law.

226

:

18 months or 12 months speeds

get faster and faster.

227

:

This appears to be a very

similar thought behind AI.

228

:

So Mo, you obviously know, Mo

Gouda used to be the CBO of Google.

229

:

So he had a really good interview

a couple of weeks ago, and he

230

:

was talking about this, the

development of AI and how it is now.

231

:

But until GPT 3 came out, people

could take or leave AI, couldn't they?

232

:

They didn't really know what it was.

233

:

It's been around for years.

234

:

It wasn't until GPT 3 came out with the

UI that everyone went, Oh my God, AI here.

235

:

since then.

236

:

it is going to be at

this stage and GPT five.

237

:

When it first comes out, it's probably

going to be smarter than, Einstein

238

:

that's what they're foreshadowing.

239

:

Mo good at Mo has basically said that

this AI is going to be eventually, and

240

:

we don't know how close it's going to

be, maybe not in five years, a billion

241

:

times smarter than us, a billion.

242

:

So in terms of.

243

:

AI is going to be like us to an ant.

244

:

We will have no idea.

245

:

We will have no understanding of what

this thing is conceptualizing with doing.

246

:

That is the scary part because an

ant can't fathom anything that's

247

:

going on now head, and that's where

they're seeing this going is that AI

248

:

is eventually going to be so good and

smart that we will have no concept.

249

:

What it's doing now that leads me on Have

you ever seen a show called devs the EBS?

250

:

Watch it.

251

:

It came out in 2020.

252

:

Now this was before any of there

was any inclination of AI and I

253

:

don't want to give away what happens.

254

:

But

255

:

I believe that eventually what

is happening with AI, it's

256

:

becoming a prediction engine.

257

:

You can already see it Do you

remember when you first discovered

258

:

mid journey or you discovered any

of these image creators, right?

259

:

So when you type a prompt in, you'd

get something and go, ah, looks like

260

:

what I'm after, and then you learn

more about prompting and you got,

261

:

you gave it more context and you go,

oh, it's getting better and better.

262

:

How good are They coming out now?

263

:

Like when you type a prompt and

you go, wow, that's amazing.

264

:

That's pretty well what I'm after.

265

:

I'll just tweak that a little bit.

266

:

These AIs are learning.

267

:

They're becoming deterministic.

268

:

They are determining.

269

:

Okay.

270

:

Put it this way.

271

:

Human psychology and behavior

there's textbooks everywhere.

272

:

There's professors, there's psychologists.

273

:

This AI will know exactly how

humans think and how they work.

274

:

So I've already noticed that with ChatGPT,

when I first started discussing, having

275

:

conversations with it, it was wrong often.

276

:

Yes.

277

:

Now, when it's wrong, I realize

I didn't prompt it right.

278

:

Yep.

279

:

Meaning it's actually never wrong.

280

:

I'm wrong.

281

:

And it's basically batting a

thousand, like it's perfect.

282

:

it's getting better all the time.

283

:

And it's learning from

its mistakes it's making.

284

:

learning from the mistakes I'm

making, which is actually scary.

285

:

Yeah.

286

:

So then theoretically what if you

were to extrapolate that forward?

287

:

Then you would go eventually

nothing will be random.

288

:

It will know, Oh, cool,

but you're doing this.

289

:

You're doing this based on your previous

behavior and where you want to go.

290

:

Then this is what's going to happen next.

291

:

it's going to be able to predict what

we are going to be doing or what's

292

:

going to happen in the future.

293

:

it will become so good.

294

:

At understanding.

295

:

You know how I know I hear you and

Ralph talk about, the 72 million

296

:

psychographic things that Google

has on us now we work in Google

297

:

ads all the time, decades old data.

298

:

It's billions.

299

:

That's right.

300

:

Yeah, we work in Google ads all

the time and you look at your

301

:

campaigns and go seriously.

302

:

Google.

303

:

Like you really you're supposed to

be this is again, will eventually

304

:

know exact Google will exactly know

when we're going to be doing things.

305

:

And when we're going to be buying Genesis

is literally a couple of weeks away,

306

:

which is Google's next iteration of barb.

307

:

And they reckon that This version of it

is going to blow GPT out of the water.

308

:

Now, Copilot was just released by

Microsoft on Tuesday, which with windows

309

:

11, it's chat GPT into your computer.

310

:

So this is basically you just to

say to your computer, say to your

311

:

computer, do this for me and go, okay.

312

:

So you just talk to your

computer or start doing it.

313

:

Remember that little paperclip in

the old Yeah, yeah, it could be.

314

:

It's what the paperclip

was supposed to be, right?

315

:

It was like, it actually works, this one.

316

:

Yeah.

317

:

and so Copilot is released for Windows.

318

:

It's going to be coming into

the Office suite in November.

319

:

There's another version and this

is going to blow our industry

320

:

away is what Google is releasing.

321

:

You can plug in your data and

I've seen this in a demo.

322

:

Microsoft you plug in just so we grab

our Google data, put it into Power BI.

323

:

Here's our data and you talk to

this thing and say, create me a a

324

:

report with all the metrics for

the last 30 days conversions cost.

325

:

CPA, ROAS, GUT, and the outlisting

comes two or three seconds and

326

:

then you just start talking to it.

327

:

Okay.

328

:

what products do I need to order?

329

:

Not that, but if you're looking at

it from a Google ads perspective,

330

:

I'm always looking at things.

331

:

So how can we use this to make us

better at what we do with Google ads?

332

:

and I've been working on this for

months and using chat GPT and looking

333

:

for patterns what patterns can we see what

sort of trends are we our data that we

334

:

can capitalize on or oh, there's a search

trend here that's improving and your

335

:

CPC is going up here or going up there.

336

:

you just talk to it and it'll

start digging into the data

337

:

and say, oh, I found this.

338

:

I can see this correlation or

there's this causation here.

339

:

I've seen it.

340

:

It's there.

341

:

It's and you're like, Oh my

God, that's mind blowing.

342

:

That is that is going to change what

we do and make our jobs so much easier.

343

:

It's insane.

344

:

These are in order at the same

time, because we're competing.

345

:

There's five people in build bidding

in this fake organic ecosystem.

346

:

I just made up all five of them

are going to have the same tool.

347

:

And so it's we were all

toddlers at this little.

348

:

And now all of a sudden we've

been thrown into the Coliseum

349

:

and everybody's got a nuke, yes.

350

:

Yeah, but it's going to be, the ones that

think laterally think outside the square.

351

:

How can we best use this tool to

make what we're already doing better?

352

:

It's not going to just make you amazing.

353

:

You've already got to be at a stage

where you're good at what you do

354

:

You're already at a good phase.

355

:

It'll just make you better.

356

:

And this is something

that Moe said as well.

357

:

He said, the is coming.

358

:

this has been put out there all year.

359

:

It's going to take our jobs.

360

:

It's going to take our jobs.

361

:

Yes, If you saturate yourself, you

get into this or whatever industry you

362

:

do, or whatever you do, whatever you

want to do, know this thing like the

363

:

back of your hand, you need to be in

the top 20 percent 2 out of 10 people

364

:

are going to stay in that industry.

365

:

you've got to make yourself the best

in that industry to stay in that

366

:

industry, because eventually the rate

at which this is evolving, it's going

367

:

to be able to automate so many things.

368

:

Like you said Google is just

going to get better and better.

369

:

It's already started doing it,

creating copy for us inside the ads.

370

:

It's going to get better and better at it.

371

:

Videos.

372

:

Images, targeting everything.

373

:

Yeah.

374

:

And audiences, like it's going to

know where people are in the buying

375

:

and know when they're ready to buy.

376

:

and you and I both knew that it's

already there from a Google ads

377

:

perspective or a marketing perspective.

378

:

It already knows where we

are in the buying cycle to a

379

:

certain extent, but due to the.

380

:

Determinism as this, like I was saying,

deterministic behavior, it's learning.

381

:

This whole thing is learning.

382

:

Why do you think we can get

all these things for free?

383

:

It's getting this data

and learning from us.

384

:

to whether or not you're interested in,

and if our listeners and viewers are

385

:

interested in us doing a regular AI.

386

:

Session in series.

387

:

I've only just touched the surface here.

388

:

We can pick a tool, deep dive into it.

389

:

So I can share screen, show you what

I'm doing, what I'm playing with.

390

:

What I'm doing with chat GPT,

the plugins I'm using chat GPT a

391

:

lot with a plugin called notable,

which writes Python code for me.

392

:

It's a really good tool.

393

:

It's again, it's one of these things.

394

:

Oh, that's a great tool.

395

:

How do I use it?

396

:

that's the thing, like

what can you use now?

397

:

I've been uncovering a couple

of when you look at something

398

:

and you go, what about this?

399

:

We've been testing CPC ranges

and breaking out CPC ranges.

400

:

So we get the AI to say.

401

:

We give it a whole heap of search term

data and say, give me all the CPC ranges.

402

:

And I go, yep, this is them

and give me all the metrics.

403

:

Give me the metrics.

404

:

Then we create these heat maps and we go,

oh, geez, there's a nice sweet spot there.

405

:

Look at that.

406

:

Imagine if we doubled down that.

407

:

now in 8, and I've been

chatting with John about this.

408

:

I said, what if we did this strategy?

409

:

And he's do it, test it.

410

:

So we're doing shit that, pardon, pardon

my French we're testing things at the

411

:

moment that we didn't even know, but chat

GPT said, Oh, what about these things?

412

:

And then you start thinking, what

if we use this strategy doing this?

413

:

And you go, Oh, that's interesting.

414

:

So it'll uncover a little nugget.

415

:

And then you just go, what about this?

416

:

What about this?

417

:

You just ask more questions.

418

:

So we're testing some stuff at the

moment that I haven't seen people doing,

419

:

but that's what these things can do.

420

:

They can uncover some data in there that

you didn't really think about utilizing.

421

:

Yeah.

422

:

Let's do a weekly session.

423

:

Are you down?

424

:

Yeah.

425

:

Yeah.

426

:

All right.

427

:

If you're watching this, Glenn and I

are going to do a weekly session on AI.

428

:

He's going to come with the tools

that he's been building or using

429

:

and teach us how he's using them.

430

:

Hit us in the comments if there's

any things specific that you want

431

:

to know more about, but Glenn,

this was freaking fascinating.

432

:

I super appreciate your time.

433

:

And Good to see you again.

434

:

Yeah, you too.

Links

Chapters

Video

More from YouTube