TRANSKRIPT 🔗
WEBVTT
NOTE
Transcription provided by Podhome.fm
Created: 06/19/2026 17:14:41
Duration: 2167.876
Channels: 1
1
00:00:02.720 --> 00:00:03.679
Here we go.
2
00:00:04.080 --> 00:00:04.800
Yeah.
3
00:00:05.600 --> 00:00:06.240
So
4
00:00:06.879 --> 00:00:10.719
hey, Tim. How are you doing? Hey, Barry. I'm doing great. How are you?
5
00:00:11.440 --> 00:00:15.599
Yeah. I'm doing I'm doing very well. I've
6
00:00:15.264 --> 00:00:17.185
spent my day today. It's fifteen
7
00:00:17.505 --> 00:00:25.265
thirty, like we just said before we started the recording. My day is kinda almost done. I spend all day basically talking to my computer.
8
00:00:25.505 --> 00:00:27.824
Like to an AI, to various AIs.
9
00:00:27.985 --> 00:00:31.560
It is very strange how my days have changed
10
00:00:32.040 --> 00:00:32.680
from,
11
00:00:33.000 --> 00:00:36.920
like, browsing and looking stuff up to just talking to
12
00:00:37.160 --> 00:00:40.920
my computer, and it just talks back, basically. It's very strange.
13
00:00:41.320 --> 00:00:55.235
But, yeah. How are you? It's a different world, isn't it? I'm doing great. Thanks. I really am. And I agree a 100%. First of all, I wanna say it's awesome that you're using voice chat with the AI in your computer. I tell that to my learners all the time.
14
00:00:55.970 --> 00:01:00.530
Some people are better with their prompting using their voice as opposed to writing.
15
00:01:00.770 --> 00:01:10.130
Hit that microphone button and and get her done. I use voice chat when I'm on the go a lot. But to your point, Barry, yeah, it's it's rapidly
16
00:01:11.865 --> 00:01:12.825
it's a
17
00:01:13.625 --> 00:01:15.704
AI has has rapidly
18
00:01:16.585 --> 00:01:18.985
increased my knowledge, my effectiveness
19
00:01:18.985 --> 00:01:20.985
personally and professionally.
20
00:01:20.985 --> 00:01:23.465
It's it's an amazing time to to be alive.
21
00:01:24.610 --> 00:01:31.490
It it is. Yeah. And it's an amazing time to just be in tech as well. Yeah. Because, you know, this is the
22
00:01:31.730 --> 00:01:38.305
I don't know how many of of these big changes. Like, had mobile. We had the web. We had cloud.
23
00:01:38.785 --> 00:01:41.665
I've I've caught a couple of those now. The
24
00:01:41.985 --> 00:01:50.705
web I'm I'm a bit too young for. That was already there, kinda ish. So when I started using computers, we had the web. I feel like this thing is way bigger
25
00:01:50.900 --> 00:01:53.620
than that. I don't know. What do you think?
26
00:01:53.940 --> 00:01:59.940
Well, it's funny you mentioned that because that's something, again, whether I'm in a consulting or teaching context,
27
00:01:59.940 --> 00:02:14.915
I always like to bring up is when you think about the big disruptions in tech, and I am a little bit older. Actually, I'm wearing a a shirt of my alma mater. I was at Cornell in the mid nineties at the dawn of the World Wide Web, so I was right there in the center of it.
28
00:02:15.555 --> 00:02:21.700
I think that Gen AI has been following a very similar trajectory to all those other disruptions.
29
00:02:22.020 --> 00:02:24.900
Yes. There's a change in in economies
30
00:02:24.900 --> 00:02:29.620
and job roles and and all of that, though there's definitely truth to that.
31
00:02:30.580 --> 00:02:39.725
It's not one of those things that's rapidly gonna fizzle out. It's it's like the mobile device revolution. It's like the World Wide Web. It's gonna be with us.
32
00:02:41.084 --> 00:02:59.430
And I I find that I see a lot of the same reactions to it that I've seen in the past, like when the cloud came in. I I still have a lot of friends and professional colleagues who are really skeptical and angry about the cloud because they prefer to have a screwdriver in their hand in their local data center, and that's cool.
33
00:03:00.165 --> 00:03:09.125
But, fortunately, I've always been one who's willing to change and evolve, so it's been more enjoyable than painful.
34
00:03:10.005 --> 00:03:12.965
Yeah. Yeah. I find same same thing. And indeed,
35
00:03:13.780 --> 00:03:19.940
also from a Microsoft perspective where I work now, I do still see customers that are, you know, half in the cloud.
36
00:03:20.260 --> 00:03:23.780
Some are still like, hey, the cloud. Is that a new thing? I don't know. Right.
37
00:03:25.565 --> 00:03:30.445
But every everybody does it at their own pace. Right? So and and that's fine. That's totally fine.
38
00:03:30.765 --> 00:03:34.045
Have you been developing software yourself still?
39
00:03:34.605 --> 00:03:35.965
Yeah. Absolutely.
40
00:03:36.205 --> 00:03:39.325
Yeah. More than ever before. Again, that's that's another
41
00:03:39.820 --> 00:03:42.860
level up with Gen AI. It's really twofold.
42
00:03:43.260 --> 00:03:52.220
One, being able to take an idea and push it down the field faster than than ever was conceivable prior to generative AI.
43
00:03:52.805 --> 00:03:53.765
And two,
44
00:03:54.005 --> 00:03:57.845
I feel my effectiveness as a developer has is far
45
00:03:57.925 --> 00:04:04.885
farther along faster than ever before because I make sure to have the AI teach as it goes.
46
00:04:05.205 --> 00:04:07.450
I'm not one of those stereotypical
47
00:04:07.450 --> 00:04:24.335
vibe coders who just wants the AI to run off and and do all of its magic while I get my espresso. I'm gonna get my espresso. Don't worry about it. But I actually wanna know what's happening behind the scenes. And, again, I think that's a critical through line to this discussion. Human in the loop always.
48
00:04:25.455 --> 00:04:30.335
Yeah. And so you develop a production software as well for clients?
49
00:04:31.670 --> 00:04:34.710
No. I would call myself mainly a hobbyist.
50
00:04:34.790 --> 00:04:53.605
I don't I've in my career of almost thirty years, I've worked with and on software engineering teams, but I I have yet to have developer as a formal full time job role. So I don't feel I would be doing clients and customers a service
Load full transcript
doing that. More more architecture,
51
00:04:54.005 --> 00:04:59.950
and and the stuff that I develop and ship is mainly just for my learners and my tech community.
52
00:05:00.750 --> 00:05:06.110
I do submit work to my full time employer, Pluralsight, again, and then automation
53
00:05:06.110 --> 00:05:09.070
more than anything else, helpers, that kind of stuff.
54
00:05:10.035 --> 00:05:12.035
And in my, instructional
55
00:05:12.035 --> 00:05:28.050
design, of course, I need demos. I need sample code. And and I guess last of all, I have a 16 year old daughter, and we've always got a project going on. So there's something to do development wise in some stripe or another.
56
00:05:28.850 --> 00:05:31.170
Oh, that's fun. So she also uses it?
57
00:05:31.730 --> 00:05:44.815
Actually, not. It's an interesting thing. Here here's my daughter. She's got a dad who's all into AI. She's very opposed to AI. She's an artist, and she's concerned about intellectual property rights as she should be. Yeah.
58
00:05:45.135 --> 00:05:49.135
And she's an animator, and so she resents AI. And, actually,
59
00:05:49.800 --> 00:05:50.840
intentionally,
60
00:05:50.840 --> 00:05:54.600
when we're doing like, we're working on a it's a pretty low tech,
61
00:05:55.000 --> 00:05:57.000
interactive web application.
62
00:05:57.560 --> 00:05:58.760
And, she
63
00:05:59.400 --> 00:06:13.405
quizzes me to make sure I'm not using AI. I mean, in full disclosure, I, of course, I'm gonna use it a little bit. For her I I had tell her that. But for her, we're kicking it old school. Fortunately, it's just light JavaScript,
64
00:06:13.405 --> 00:06:15.645
mostly just old school HTML
65
00:06:15.645 --> 00:06:16.925
and CSS. So
66
00:06:20.300 --> 00:06:32.060
Okay. Well, keeping it simple. That's how I like to do it as well. Yeah. Okay. So when you do use AI for, creating software, what do you use? What type of Copilot or thing do you use? Mhmm.
67
00:06:32.875 --> 00:06:39.515
At this point, I'd say my 80% scenario is Claude code and the Claude Versus code extension.
68
00:06:40.155 --> 00:06:42.235
I I found of the LLMs,
69
00:06:42.235 --> 00:06:49.830
the Claude models not only are the most human like, but they they think like a developer more than any of the others. Now,
70
00:06:50.550 --> 00:06:56.870
it's ebbed and flowed with, my use of GitHub Copilot. Now that it supports multimodal,
71
00:06:56.870 --> 00:06:57.990
the barriers
72
00:06:58.150 --> 00:07:04.884
that might have been there in the past are no longer there. But for me, it comes down to effectiveness
73
00:07:04.884 --> 00:07:05.685
first,
74
00:07:05.925 --> 00:07:13.525
but customer delight right behind it. And my complaint with GitHub Copilot and Versus Code, Versus Code is my code editor,
75
00:07:14.030 --> 00:07:24.030
is that those engineers keep making changes, particularly UI and and feature changes and renames way too often, and and it's anti delightful.
76
00:07:24.509 --> 00:07:34.185
So that's
why I found Cloud Code to be the, the best fit for me currently, not only because of its effectiveness, its ability to think like a programmer,
77
00:07:34.585 --> 00:07:41.225
but just from the pure bucket of customer delight using the software as a delightful experience for me.
78
00:07:42.380 --> 00:07:45.100
Yeah. I I totally get that. Like, they
79
00:07:45.500 --> 00:07:47.820
move your cheese a lot. There you go.
80
00:07:48.220 --> 00:07:51.580
Yeah. Because things are so you know, they're developing
81
00:07:51.900 --> 00:08:02.545
very actively on it and new features drop every time and then, you know, maybe something changes. I I totally get that. So so you only use it from Versus Code, or do you also use the CLI?
82
00:08:03.105 --> 00:08:07.905
Oh, right. Yeah. I guess I should have been more specific. Mostly from the CLI.
83
00:08:08.180 --> 00:08:13.700
Yeah. Yeah. Either in Windows terminal or the integrated terminal in Versus Code.
84
00:08:14.020 --> 00:08:27.825
Yeah. And that's something else. You can tell when when a vendor has a good idea when all the competition starts adopting it. I mean, all of the paradigms we have in Claude code from the slash commands to context visualization
85
00:08:27.825 --> 00:08:29.185
to sub agents,
86
00:08:29.505 --> 00:08:37.425
now we see going from the Google Gemini CLI to the GitHub Copilot CLI to Codec CLI,
87
00:08:37.950 --> 00:08:42.430
they all behave largely the same, and that's something I like to stress in the classroom,
88
00:08:42.830 --> 00:08:48.030
that don't worry about having to reinvent the wheel, you know, the dry principle in development.
89
00:08:48.350 --> 00:08:57.365
These vendors are all cribbing on each other, so learn one really well, and you're 80% there for mastering the competition if and when you wanna go there.
90
00:08:58.085 --> 00:09:02.405
Yeah. Because they all basically work the same. Right? Mhmm. And so so how
91
00:09:04.085 --> 00:09:15.640
what I used to do is I used to try slash commands and ads and all sorts of things to try to make it work better simply because, I don't know, six months ago, they weren't that great.
92
00:09:15.880 --> 00:09:34.775
Mhmm. Now, when I just type a sloppy prompt, like, hey, make this for me, it just usually basically does it without much hand holding. Mhmm. And how do you use those things? Do you use, like, skills and and Oh, yeah. And stuff like that? Yeah. Absolutely. In fact, not to be skewing this, you know, anthropic wise
93
00:09:35.399 --> 00:09:36.440
specifically,
94
00:09:36.519 --> 00:09:41.639
but I wanna give a shout out to a GitHub project called Everything Claude Code.
95
00:09:41.959 --> 00:09:48.440
I don't remember the dev's name, but this person really has gone to town creating a plug in that includes
96
00:09:48.519 --> 00:09:49.399
very useful
97
00:09:50.155 --> 00:10:02.955
agents and hooks, all the different parts and pieces that some of which that you were mentioning, Barry. And it might be a
good spot for someone to look at and experiment to see and test how these various doodads and
98
00:10:03.300 --> 00:10:04.260
thingamabobs
99
00:10:04.260 --> 00:10:06.900
actually work. To answer your question,
100
00:10:07.220 --> 00:10:13.620
it's probably my bias because I've been a professional writer for so long, but I I really,
101
00:10:13.860 --> 00:10:15.940
try to be as explicit as possible
102
00:10:16.375 --> 00:10:22.935
in my prompts. I do use the different triggers, like you said, the at in Claude code to tag a file.
103
00:10:24.055 --> 00:10:25.815
I I I don't
104
00:10:26.375 --> 00:10:27.095
generally
105
00:10:27.415 --> 00:10:35.730
trust the AI's ability to do inference. I've been with it since the beginning, and although it's gotten so much better to your point,
106
00:10:36.210 --> 00:10:42.050
I still take the Python approach of explicit is generally better than implicit
107
00:10:42.130 --> 00:10:44.210
or belt and suspenders,
108
00:10:44.210 --> 00:10:45.410
insert cliche here.
109
00:10:46.125 --> 00:10:49.725
But, yeah, I I I will, I'll be pretty darn
110
00:10:50.125 --> 00:10:52.125
imperative in my prompts
111
00:10:52.685 --> 00:10:53.805
strictly to,
112
00:10:54.045 --> 00:10:56.685
try to reduce and hopefully eliminate
113
00:10:56.845 --> 00:11:01.805
the inference space of the AI because I don't want it making anything up. None of us do.
114
00:11:02.759 --> 00:11:07.000
Yeah. Yeah. Exactly. And I think as these models, become better,
115
00:11:07.399 --> 00:11:09.560
the need for that becomes maybe less.
116
00:11:10.600 --> 00:11:11.079
Probably.
117
00:11:11.720 --> 00:11:17.000
I I admit. I'm gonna have to evolve my prompting approach. Right now, I'm being in a curmudgeon,
118
00:11:17.000 --> 00:11:29.985
I guess. I'm gonna have to evolve that to survive, and that's fine. You're probably right. Who knows? In the future, maybe the AI will be able to work in conjunction with a neural implant, and we can it'll just follow our thoughts.
119
00:11:31.100 --> 00:11:33.740
Oh, I don't know do not want that.
120
00:11:34.060 --> 00:11:39.900
Or do I. But you know what? All the Black Mirror stuff, it's gradually turning into reality.
121
00:11:41.100 --> 00:11:45.525
It is. Yeah. It is. Truly is. And so,
122
00:11:46.085 --> 00:11:56.005
you know, you could do so much stuff now with it. Like, you can hand off a session to your phone, for instance. Do you do that and then, like, go on a holiday and then you're still working?
123
00:11:56.885 --> 00:11:58.965
Yeah. A lot, actually. Not
124
00:11:59.899 --> 00:12:06.540
yeah. Actually, even for development projects. Just last night, in fact, I was driving. I had to run a couple errands,
125
00:12:07.019 --> 00:12:10.220
and I, I had a conversation in ChatGPT
126
00:12:10.220 --> 00:12:11.579
on my desktop
127
00:12:11.819 --> 00:12:14.060
specking out a a software project
128
00:12:14.385 --> 00:12:17.105
for for a course I'm teaching,
129
00:12:17.425 --> 00:12:20.305
and I picked it up on the road using ChatGPT
130
00:12:20.305 --> 00:12:21.425
voice mode,
131
00:12:21.745 --> 00:12:25.025
and it was super useful because we were able to explore
132
00:12:25.345 --> 00:12:28.145
stuff that I wouldn't have thought about. You know, basically,
133
00:12:28.385 --> 00:12:33.910
require and that front end kind of stuff, front end proactive optimizations and stuff.
134
00:12:34.470 --> 00:12:35.510
And I was like,
135
00:12:36.070 --> 00:12:38.710
let's let's brainstorm and get this tight.
136
00:12:38.950 --> 00:12:48.285
And then when I got home, I got onto my computer and I said, whip up an excellent PRD document that I can hand to my coding assistant.
137
00:12:48.605 --> 00:12:50.365
And that's exactly what I did.
138
00:12:50.925 --> 00:12:55.005
So, yeah, that handoff is super, super helpful for sure.
139
00:12:55.940 --> 00:12:57.140
Yeah. It is.
140
00:12:57.860 --> 00:13:16.745
But for for me, it it also means that now I'm just doing stuff all the time. And I'm like I have, like, I don't know, 10 projects in my head. And I'm constantly like, oh, do this. Do that. Oh, maybe we can do this. Maybe we can do that. And so it's a lot of context that I hold myself, although the work gets done by all these robots, basically.
141
00:13:17.225 --> 00:13:23.385
But I don't know. I get a bit overwhelmed by all this stuff because now I'm I'm taking on too much because I can do everything.
142
00:13:23.785 --> 00:13:24.425
It's weird.
143
00:13:25.020 --> 00:13:26.860
No. No. I I understand,
144
00:13:26.860 --> 00:13:29.340
and I I relate to that. It's very real.
145
00:13:29.900 --> 00:13:34.940
For me, I I think I would be lost if I didn't have a productivity methodology.
146
00:13:34.940 --> 00:13:37.340
I practice GTD, getting things done.
147
00:13:37.915 --> 00:13:44.315
And the whole principle there is to get stuff out of my brain and get it into a trusted capture system.
148
00:13:44.715 --> 00:13:45.835
And you know what? To
149
00:13:47.035 --> 00:13:56.400
your point, you could have all of those project stubs in your capture system and feel very overwhelmed indeed. And I've been there, done that, and bought the T shirt.
150
00:13:56.880 --> 00:14:01.920
I can think of an example where Gen AI has helped me with that. I've I've pointed
151
00:14:02.160 --> 00:14:03.360
ChatGPT.
152
00:14:03.360 --> 00:14:06.834
Look at my projects. Look at my past conversation
153
00:14:06.834 --> 00:14:07.555
history.
154
00:14:07.875 --> 00:14:17.954
Find these unopened loops. Let's take a look at them. Give me your best guidance on which have some teeth to them, which should I maybe deprioritize
155
00:14:17.954 --> 00:14:19.475
or let go out of my brain.
156
00:14:20.060 --> 00:14:25.820
So using AI in that meta sense has really given me some some peace.
157
00:14:26.700 --> 00:14:33.100
Oh, that's a good one. I I'll try that as well. You know, to get some focus. Yep. That's, that's important. Mhmm.
158
00:14:33.420 --> 00:14:37.065
So so you can use it for software development.
159
00:14:37.065 --> 00:14:39.225
I know I also talked to platform
160
00:14:39.225 --> 00:14:40.904
teams and infrastructure people.
161
00:14:41.865 --> 00:14:48.185
They're like, yeah, we have GitHub Copilot for instance, but you know we just ride our bicep all by ourselves.
162
00:14:49.210 --> 00:14:56.890
Do you sometimes, have conversations with platform people and and info folks? And and do you find that they use, AI?
163
00:14:57.450 --> 00:15:06.825
Yes. I have those conversations all the time, I'm fortunate to to say. And what I've seen as a trend is quite a few engineers,
164
00:15:07.785 --> 00:15:12.185
either by directive, you have to use it, or out of their curiosity,
165
00:15:12.985 --> 00:15:17.519
tried it out maybe in the earlier days when it was not
166
00:15:17.519 --> 00:15:19.680
very effective in many cases,
167
00:15:20.320 --> 00:15:31.360
and have a net negative and now a resistant attitude towards it. So it's an it involves the conversation of giving it a try now that we've seen this delta
168
00:15:31.115 --> 00:15:34.475
from how it used to be even six months a year ago,
169
00:15:35.195 --> 00:15:37.995
and then b, having them feel enough
170
00:15:38.154 --> 00:15:44.954
return on investment to go a bit further and to learn the slash commands, the invocation commands, the shortcuts.
171
00:15:45.510 --> 00:15:48.390
And if and when they cross that bridge,
172
00:15:48.630 --> 00:15:59.430
yeah, you've probably got a a convinced developer at that point, and that's a good thing. But I I have seen a lot of v one after effects of devs who felt burned,
173
00:15:59.430 --> 00:15:59.990
cheated,
174
00:16:00.885 --> 00:16:01.845
afraid
175
00:16:02.005 --> 00:16:11.205
of Gen AI initially, and now are super skeptical of it, and they haven't yet seen the improvements of which there are many and continue to be.
176
00:16:11.925 --> 00:16:15.525
Yeah. As in, I tried it with, GPT 3.5,
177
00:16:15.525 --> 00:16:18.480
and it sucked. So I'm not trying that again. Yeah.
178
00:16:18.480 --> 00:16:19.360
Exactly.
179
00:16:19.600 --> 00:16:24.800
And you read the scary tech news of businesses having to uphold hallucinated
180
00:16:24.800 --> 00:16:30.000
read refunds, you know, warranty stuff because their AI chatbots hallucinated,
181
00:16:30.825 --> 00:16:36.505
or companies that went way too far and downsized their human engineering teams,
182
00:16:36.745 --> 00:16:41.865
replaced them with agents and got burned that way and then frantically tried to rehire,
183
00:16:42.185 --> 00:16:43.785
that those experiences
184
00:16:43.785 --> 00:16:44.745
don't help either.
185
00:16:45.370 --> 00:16:49.209
But I think, again, in in how we started the conversation,
186
00:16:49.529 --> 00:16:52.730
this stuff happened and happens with cloud,
187
00:16:53.050 --> 00:16:53.850
mobile,
188
00:16:54.089 --> 00:16:55.209
virtualization,
189
00:16:55.290 -->
00:16:56.490
containerization,
190
00:16:56.490 --> 00:16:59.370
World Wide Web. I mean, I can go back to the seventies
191
00:17:00.065 --> 00:17:01.265
in elementary
192
00:17:01.265 --> 00:17:05.745
school when my math teacher gave let us use calculators.
193
00:17:05.745 --> 00:17:12.545
There was a big furor and uproar. The kids aren't gonna know how to do math because they're relying on these computers.
194
00:17:13.790 --> 00:17:16.269
It's all of a thing. It's amazing.
195
00:17:17.150 --> 00:17:29.975
Yeah. And now you mentioned it. I kinda forgot about that. During the cloud era, people were like, alright. All of the or we're gonna make lots of cuts to the the infrastructure people because, you know, we don't need them anymore. We just run stuff in the cloud.
196
00:17:30.215 --> 00:17:32.455
But, that turned out not to be true.
197
00:17:32.934 --> 00:17:34.215
Yep. Exactly. Yeah.
198
00:17:35.174 --> 00:17:38.534
Yeah. I think AI is a is a wonderful,
199
00:17:38.775 --> 00:17:39.815
force multiplier,
200
00:17:40.570 --> 00:17:47.850
but I know it sounds like I'm standing on a soapbox or something saying human in the loop, but I I really believe that.
201
00:17:48.250 --> 00:17:51.850
When people in my life who aren't in tech ask my opinion of AI,
202
00:17:52.985 --> 00:18:02.825
First, they wonder about the sentience sentience or consciousness. I say, look. It's software running on a computer. Unplug the computer and the AI goes bye bye.
203
00:18:03.625 --> 00:18:11.200
And number two, it's not the AI to be afraid of. It's the people who are governing that AI that we wanna be concerned about.
204
00:18:11.520 --> 00:18:13.200
You know? It's the operators.
205
00:18:13.200 --> 00:18:14.159
It's the humans.
206
00:18:15.840 --> 00:18:22.399
Yeah. And that's kinda always, the crux, isn't it? Mhmm. It's always the humans. Yeah. So keep the humans in the loop. So
207
00:18:22.745 --> 00:18:31.545
where do you think this is going with, you say keep the humans in the loop? Will companies still have humans, or will it just all be agents agents
208
00:18:31.705 --> 00:18:33.625
sending emails to other agents,
209
00:18:33.865 --> 00:18:34.745
calling agents?
210
00:18:35.490 --> 00:18:38.850
Well, already with software development,
211
00:18:39.090 --> 00:18:44.529
the question of writing code from scratch is almost a moot point because
212
00:18:44.610 --> 00:18:46.769
these agents, these GenAI
213
00:18:47.250 --> 00:18:52.735
products can write code so much faster, in many cases, securely, more efficiency
214
00:18:53.055 --> 00:18:54.174
more efficiently.
215
00:18:54.655 --> 00:19:02.975
But in my opinion so in other words, the the role of the software developer becomes more of an architect or a steward,
216
00:19:03.640 --> 00:19:05.080
a a guider,
217
00:19:05.080 --> 00:19:06.200
an operator,
218
00:19:06.280 --> 00:19:07.799
for lack of a better term.
219
00:19:08.280 --> 00:19:16.520
So that that's one direction that AI seems to
clearly be going. Because to your point, with some sub agents, you can, you know,
220
00:19:17.265 --> 00:19:20.705
fan out and delegate this fleet of
221
00:19:20.945 --> 00:19:27.665
virtual assistants. I want you to proactively look for bugs here. I want you to proactively
222
00:19:27.665 --> 00:19:29.265
look for vulnerabilities,
223
00:19:29.265 --> 00:19:41.590
security issues. I want you to follow behind and test. That's another important point, making sure that whatever you're having your agents do, you've got another round of agents behind them validating.
224
00:19:42.150 --> 00:19:46.294
And then you've got an agent. I want you to keep the docs updated.
225
00:19:47.095 --> 00:19:48.294
Yay, docs. And
226
00:19:48.695 --> 00:20:02.120
update your your own memory file. That that's an issue that some people forget about. Make sure that you have the agent update its memory so it has a current snapshot of your code base. And the next time you start a chat,
227
00:20:02.280 --> 00:20:06.440
the AI is current and it's got that loaded and and ready to rock.
228
00:20:08.040 --> 00:20:15.524
Yeah. So so with all these agents, you think we're gonna have, like, a a lot less, for instance, software developers or other people?
229
00:20:20.405 --> 00:20:22.804
It seems likely, unfortunately.
230
00:20:22.805 --> 00:20:27.119
And and, again, I think back in my life, I remember in the late eighties,
231
00:20:27.440 --> 00:20:31.279
I grew up in in Upstate New York with a lot of manufacturing,
232
00:20:31.280 --> 00:20:32.080
particularly
233
00:20:32.160 --> 00:20:33.600
auto manufacturing.
234
00:20:33.919 --> 00:20:39.280
And I remember how disruptive that was because once assembly line robots turned up,
235
00:20:40.015 --> 00:20:47.695
there was literally less need to have humans on the assembly line because the robots never sleep, and they do a deterministic
236
00:20:47.695 --> 00:20:50.415
operation twenty four seven, three sixty five.
237
00:20:51.630 --> 00:21:00.669
So, I mean, there's a kernel of truth in the fear that I experience with developers in my life about is this Gen AI stuff gonna put me out of business?
238
00:21:01.950 --> 00:21:04.030
And I I would encourage
239
00:21:04.030 --> 00:21:11.195
back the guidance. It's about getting on top of the AI and learning how to use it to make yourself
240
00:21:11.434 --> 00:21:12.634
more effective
241
00:21:12.955 --> 00:21:13.835
and make,
242
00:21:14.635 --> 00:21:16.874
yourself a force multiplier.
243
00:21:17.274 --> 00:21:24.169
It's using AI. Because like I said, there's gonna be a need for those people to operate these agents going forward.
244
00:21:24.409 --> 00:21:25.369
Will there be,
245
00:21:26.169 --> 00:21:28.649
as many people necessarily?
246
00:21:29.289 --> 00:21:38.344
Who knows? I mean, maybe if the cost of hardware goes down and we start getting closer to edge and on premises LLMs
247
00:21:38.745 --> 00:21:42.345
Yep. Then you're gonna need operators in those contexts
248
00:21:42.345 --> 00:21:43.144
as well. So,
249
00:21:44.159 --> 00:21:47.119
yeah, I I think it's just gonna be a case of
250
00:21:47.759 --> 00:21:48.879
increasing
251
00:21:48.879 --> 00:21:49.999
specialization.
252
00:21:51.519 --> 00:21:54.159
Yeah. It's it's nobody knows.
253
00:21:54.240 --> 00:21:55.360
Yeah. But Yeah.
254
00:21:56.265 --> 00:22:01.225
I heard somebody say on a podcast for developers, for instance, if you're a developer,
255
00:22:02.585 --> 00:22:12.050
your task is not to develop code. Those are tasks that you do. Your task is to create software or to create something that creates business value for your customer. Automate
256
00:22:12.050 --> 00:22:24.530
a business process or something like that. And then part of that is tasks that you do, is creating software. And now you can give those tasks to an agent or to Claude or whatever. And it can do that, but you still have all these other things to
257
00:22:24.934 --> 00:22:32.374
form that into something that automates the business process, which actually provides a value for now, at least. Mhmm. So,
258
00:22:33.255 --> 00:22:36.294
you know, that that's a good way to think about it, I think,
259
00:22:36.615 --> 00:22:41.340
what this guy said on a podcast. But let's see if that holds true in a year. Yeah.
260
00:22:42.860 --> 00:22:45.179
Yeah. For sure. And going further,
261
00:22:45.500 --> 00:22:48.780
the idea of an LLM running in, say,
262
00:22:49.020 --> 00:22:50.059
a robot.
263
00:22:50.220 --> 00:22:59.794
I don't have any experience with these humanoid robots that are under development now, but I have little doubt that the day of the domestic robot
264
00:22:59.795 --> 00:23:01.075
is in our future.
265
00:23:01.715 --> 00:23:07.315
And I kind of think that I I I'm I'm a fan of that myself. I think it's pretty cool.
266
00:23:07.555 --> 00:23:19.970
Again, you could take these things in any direction, and it would be the humans behind them that are doing the operating that are thinking of nefarious things. But I'm thinking of stuff like folding my clothes for me. You
267
00:23:20.049 --> 00:23:21.650
know? Again, delegating
268
00:23:21.650 --> 00:23:22.530
tasks
269
00:23:23.035 --> 00:23:28.394
and freeing me up to use the full capacity of my brain to ideate
270
00:23:28.395 --> 00:23:34.075
and to add value and to help and to be kind and do all of the human stuff
271
00:23:34.315 --> 00:23:37.035
and delegate scut work and tasks
272
00:23:37.290 --> 00:23:38.809
to AI agents.
273
00:23:39.850 --> 00:23:42.970
Yeah. Yeah. Definitely. Embodied
274
00:23:42.970 --> 00:23:50.250
physical AI that's absolutely coming. Mhmm. Mhmm. Yeah. And then let's see how that goes. Like, would you trust that with your daughter?
275
00:23:50.650 --> 00:23:52.010
Like a a humanoid AI?
276
00:23:54.195 --> 00:23:55.315
Yeah. Exactly.
277
00:23:55.635 --> 00:23:57.154
Exactly. I don't know.
278
00:23:57.635 --> 00:24:00.674
Maybe maybe after a few years.
I don't know. Mhmm.
279
00:24:00.995 --> 00:24:03.794
Yeah. Exactly. I mean, the v one
280
00:24:04.035 --> 00:24:11.159
issue is pretty universal, isn't it? Yeah. You you you need to iron out the warts and and get relatively
281
00:24:11.799 --> 00:24:12.679
stable.
282
00:24:12.840 --> 00:24:13.480
Okay.
283
00:24:14.280 --> 00:24:14.919
Yeah.
284
00:24:15.400 --> 00:24:16.359
So the
285
00:24:16.840 --> 00:24:25.865
main, thing that you produce now for Pluralsight is courses. Right? So educational courses about all sorts of things. Like I'm looking at your Pluralsight
286
00:24:25.865 --> 00:24:28.745
author page here and it says currently
287
00:24:28.905 --> 00:24:30.345
179
288
00:24:30.345 --> 00:24:33.785
courses and I'm sure there's a bunch of them that have been retired as well.
289
00:24:35.100 --> 00:24:45.820
Right. That's a lot a lot of material that you have been that you have created and you still continue to create, which is incredible because that means people can learn and then they can scale
290
00:24:46.380 --> 00:24:49.179
what what they do. I think that's great. So
291
00:24:49.945 --> 00:24:51.945
how does using AI
292
00:24:53.945 --> 00:24:55.945
change how you teach?
293
00:24:56.185 --> 00:24:56.825
Mhmm.
294
00:24:57.625 --> 00:24:59.465
Well, the rapid development
295
00:24:59.545 --> 00:25:01.465
has been a watershed.
296
00:25:01.465 --> 00:25:06.090
I mean, for example, the courses that I'm doing now are on Kubernetes,
297
00:25:06.090 --> 00:25:09.929
particularly the certified Kubernetes administrator certification.
298
00:25:10.490 --> 00:25:13.850
And that's a lab exam, so it's entirely practical. And
299
00:25:14.730 --> 00:25:16.010
creating
300
00:25:16.010 --> 00:25:19.450
demos is something I love doing as an instructional designer.
301
00:25:20.095 --> 00:25:36.669
It's it's actually more delightful now because I'm able to include the AI and the planning of these demos, and it consistently gives me, I think, banger ideas that I might have taken a lot longer to think about on my own. Or maybe in some cases, wouldn't have thought about them
302
00:25:37.070 --> 00:25:41.149
across the board. So the quality of my sample code,
303
00:25:41.310 --> 00:25:43.149
the quality of my demos
304
00:25:43.230 --> 00:25:44.830
has definitely increased,
305
00:25:45.405 --> 00:25:49.485
and it's not a question of complexity for the sake of complexity.
306
00:25:49.565 --> 00:25:54.605
Why? Because I put that down in my guardrails, human in the loop. You know? But
307
00:25:55.005 --> 00:25:57.005
the quality is is,
308
00:25:57.529 --> 00:26:11.850
again, it's it's really nice. I I tend to work quickly anyway. I'm I'm fortunate in in that I can learn pretty quickly. And and generally speaking, knock on wood, I'm able to avoid the analysis paralysis
309
00:26:11.850 --> 00:26:16.125
that hits some fellow authors that are in my life where
310
00:26:16.285 --> 00:26:22.205
you get hung up on perfection. I'm so grateful that that I've been able to sidestep that so far.
311
00:26:22.765 --> 00:26:23.325
So,
312
00:26:23.565 --> 00:26:26.765
yeah, it just potentially makes me even faster,
313
00:26:26.765 --> 00:26:30.830
and and to do these things in parallel with AI is really helpful.
314
00:26:31.710 --> 00:26:35.230
Yeah. And do you also use it in course production?
315
00:26:35.550 --> 00:26:39.950
So, I don't know, voice cloning, video editing, stuff like that. Mhmm.
316
00:26:40.615 --> 00:26:46.774
I've experimented with that stuff. Just the other day, I got turned on to a GitHub project that
317
00:26:47.015 --> 00:26:50.294
offers an MCP interface into Camtasia.
318
00:26:50.294 --> 00:26:51.095
Camtasia's
319
00:26:51.095 --> 00:26:55.249
been my video editor of choice for couple dozen years now.
320
00:26:55.809 --> 00:27:10.384
And I thought, wow. That's cool. I could turn the agent towards my raw video and and see what it can do. So that's on my bench to take a look at, and I'm happy to share that project with you after we're done recording, Barry, if you're interested. Out of curiosity,
321
00:27:10.784 --> 00:27:12.465
are you still on Camtasia,
322
00:27:12.465 --> 00:27:21.664
or do you use ScreenFlow or Premiere? What do you use for No. Still Camtasia. Nice. Still Camtasia. Okay. Yeah. And and it it has improved a lot over the last years.
323
00:27:22.150 --> 00:27:28.549
Oh, yeah. Exactly. There was a period of time where it felt like the camp the TechSmith engineering teams
324
00:27:28.950 --> 00:27:31.110
were not only ignoring feedback,
325
00:27:31.110 --> 00:27:32.230
but actively
326
00:27:32.309 --> 00:27:34.710
bugging their software. I know that sounds critical.
327
00:27:35.395 --> 00:27:41.315
But they've got something good, a lot better going on now in terms of transparency and effectiveness.
328
00:27:41.635 --> 00:27:43.874
But to get back to your original question,
329
00:27:44.434 --> 00:27:46.915
no. I mean, I I I experimented
330
00:27:46.915 --> 00:27:52.450
with the voice cloning a little bit, but I'm I'm really not comfortable with that because
331
00:27:52.610 --> 00:27:56.289
I think some of my best value as an instructor is,
332
00:27:57.250 --> 00:28:01.010
I I inject my passion and personality into my training.
333
00:28:01.490 --> 00:28:02.610
And until recently,
334
00:28:02.985 --> 00:28:04.825
I never used transcripts.
335
00:28:04.825 --> 00:28:06.905
Now I I am using transcripts
336
00:28:06.905 --> 00:28:10.585
a lot more, not during demos, but during the PowerPoint stuff.
337
00:28:10.985 --> 00:28:17.225
I hope that I worry a little bit, frankly, that I'm coming across more robotic. I always
338
00:28:17.550 --> 00:28:25.230
prided myself thinking, well, if I'm not using a transcript, I'm it's like a live classroom, so there's a built in spontaneity
339
00:28:25.230 --> 00:28:28.110
there. And that's true. And a built in energy,
340
00:28:28.670 --> 00:28:30.510
and you run the risk of missing stuff.
341
00:28:31.345 --> 00:28:36.544
Now I I use the transcripts because it's easier. I'm not missing stuff,
342
00:28:36.945 --> 00:28:41.024
but I worry about the human factor. And that's also why
343
00:28:41.345 --> 00:28:47.440
I'm not a fan of voice cloning or video cloning in my instructional stuff at this point.
344
00:28:48.720 --> 00:28:49.999
Yeah. Agree.
345
00:28:50.559 --> 00:28:53.440
I I've always used transcriptions.
346
00:28:53.679 --> 00:28:54.239
So
347
00:28:54.480 --> 00:28:58.080
what that means for the listener, when we create a Pluralsight
348
00:28:58.080 --> 00:29:10.695
course, what I always do is when I, for instance, present a couple of slides, I write down everything that I'm gonna say upfront. And then I'm gonna I re read that, I record it, and then I stitch it together with the video. Mhmm.
349
00:29:11.175 --> 00:29:20.960
Mhmm. Some people are very good at not having to do that. They can just do it off the cuff. Like Tim, for instance, he can do that, which is amazing. And that's a talent to do that.
350
00:29:21.280 --> 00:29:37.815
But, yeah, I I use that myself as well. And I think when you do use voice cloning or something, people sniff it out. People feel it. And then they're like, this is AI. No. Thanks. I I don't like it. It just feels wrong or something. I don't know. Yeah. There really is.
351
00:29:39.750 --> 00:29:41.350
There's a sterility.
352
00:29:41.430 --> 00:29:42.150
There's
353
00:29:43.430 --> 00:29:46.630
off would be about the most technical term.
354
00:29:48.150 --> 00:29:48.790
Yeah.
355
00:29:49.110 --> 00:29:53.190
Yeah. The like, the uncanny valley. That's kinda what it is. Like, it's not.
356
00:29:54.465 --> 00:29:55.825
Yep. Do you
357
00:29:56.225 --> 00:29:57.424
as you see
358
00:29:57.745 --> 00:30:01.904
users consuming your courses and you can see the analytics and stuff as well,
359
00:30:02.385 --> 00:30:07.265
do you still see that people have the attention span and
360
00:30:06.820 --> 00:30:12.660
the willingness to actually sit down and go for a course of, let's say, two hours to learn something?
361
00:30:15.940 --> 00:30:18.740
Let me see. I need to ponder that for a second.
362
00:30:19.380 --> 00:30:19.700
Yes.
363
00:30:20.255 --> 00:30:24.575
But I think more than anything else, it's the subject matter.
364
00:30:27.615 --> 00:30:28.735
Pluralsight,
365
00:30:28.735 --> 00:30:30.575
I think it's pretty reflective
366
00:30:30.575 --> 00:30:37.260
across the world with technical training. The notion is of, generally speaking, shorter form content,
367
00:30:37.820 --> 00:30:43.260
atomizing content so learners can dip in and dip out however they want to.
368
00:30:44.300 --> 00:30:52.854
You know, that's all well and good. It can be taken to too much of an extreme, but, again, I think content is king more than anything else.
369
00:30:53.095 --> 00:30:57.494
For instance, I've I've had a lot of viewership
370
00:30:57.895 --> 00:30:59.735
on leading
371
00:30:59.735 -->
00:31:04.135
edge, bleeding edge stuff, like if I'm teaching Claude Code, for example.
372
00:31:04.710 --> 00:31:11.109
Yep. That people seem to be, for some reason, willing to sit down with a lot longer than maybe
373
00:31:11.350 --> 00:31:13.429
me teaching SQL Server.
374
00:31:13.830 --> 00:31:15.590
So, I mean, the instructor
375
00:31:15.590 --> 00:31:21.335
factors in there, but I think more than anything else, it's the relevancy and currency of the content
376
00:31:21.895 --> 00:31:25.735
and how that relates to the learner. They may be under guidance
377
00:31:25.975 --> 00:31:32.054
under strict guidance. You get smart on this Claude code business, or you're out of here. Or they might think themselves.
378
00:31:32.809 --> 00:31:35.610
If I don't get on top of this stuff, I'm
379
00:31:36.490 --> 00:31:37.290
limiting
380
00:31:37.290 --> 00:31:39.210
my career advancement.
381
00:31:39.210 --> 00:31:39.690
So
382
00:31:41.530 --> 00:31:42.410
that'll
383
00:31:43.530 --> 00:31:45.625
Okay. And so,
384
00:31:45.785 --> 00:31:57.145
just as a as a sidestep here, I've avoided teaching things about Claude code, for instance, because it changes so extremely rapidly. How do you deal with that? Like, with the UI changes, for instance? Right.
385
00:31:58.220 --> 00:32:19.625
That's a good question. One thing I always make sure to call it out, and it can't be called out too many times. I'll say it right in the recorded training for Pete's sake. I'll say, now please understand, and I'll repeat this. What you're seeing on your screen right now when you compare it to mine may be very different. We're talking about rapid development,
386
00:32:19.625 --> 00:32:24.265
rapid iteration. We're talking about companies competing and trying to get ahead.
387
00:32:24.970 --> 00:32:27.210
So focus on the underlying
388
00:32:27.450 --> 00:32:28.490
80%.
389
00:32:28.490 --> 00:32:32.490
Why are we doing these things? What goals are we looking to achieve?
390
00:32:32.810 --> 00:32:35.610
Don't get hung up on the specific invocation
391
00:32:35.610 --> 00:32:39.050
operator or the UI element because they're those are gonna change.
392
00:32:40.825 --> 00:32:51.065
Yeah. Yeah. Exactly. That's also what I usually try to do. Yeah. And learners thank me for that as well. I've had quite a few learners thank me for that heads up because,
393
00:32:51.225 --> 00:32:52.825
you know, it's a way to avoid
394
00:32:53.130 --> 00:33:03.850
stall out and somebody rage quitting your course. And and that goes to what I said a few minutes ago about somebody having a negative experience with AI and just saying, ah,
395
00:33:04.410 --> 00:33:07.370
the heck with the whole thing. I don't need that AI stuff.
396
00:33:08.835 --> 00:33:16.674
Yeah. Exactly. That works the same with courses as well. Hey. This button isn't even there. What is what is he talking about? I'll I'll quit this course. Yeah.
397
00:33:17.315 --> 00:33:18.114
Same thing.
398
00:33:18.515 --> 00:33:19.315
Mhmm. Okay.
399
00:33:20.850 --> 00:33:23.730
So maybe as a final question.
400
00:33:24.770 --> 00:33:30.769
Looking I'm for an answer and I don't have it myself. Like I have two kids, they're six and
401
00:33:32.210 --> 00:33:33.009
10.
402
00:33:33.650 --> 00:33:34.610
I forget almost.
403
00:33:36.315 --> 00:33:41.514
A year ago, I would say, You should learn software development or something
404
00:33:42.315 --> 00:33:44.075
in IT. You'll be fine.
405
00:33:44.395 --> 00:33:47.995
Maybe there's a lot less work or something, you can be an architect or whatever.
406
00:33:48.520 --> 00:33:50.519
Now I'm not so sure anymore.
407
00:33:50.920 --> 00:33:51.880
What
408
00:33:51.880 --> 00:33:54.759
would you recommend that people go and study?
409
00:33:56.440 --> 00:34:01.480
Oh, gosh. At the sound at the risk of sounding like I'm spouting a cliche,
410
00:34:02.515 --> 00:34:09.555
what I the guidance I offer to those who ask and the guidance that I give, I have one 16 year old daughter,
411
00:34:10.195 --> 00:34:10.755
is
412
00:34:11.795 --> 00:34:17.710
what my grandfather told me when I was a young boy. And he said, Timmy, if you find a job
413
00:34:18.029 --> 00:34:18.750
that
414
00:34:19.309 --> 00:34:37.115
delights you he didn't use the word delight, but makes you happy, you're good at it, and it's something that you would do even if you weren't getting paid for it, then you found your professional calling. And that always struck with me, and I'm grateful that I found that in the merging of technology and adult education.
415
00:34:37.915 --> 00:34:42.075
So what I advise is people to really self inventory
416
00:34:42.450 --> 00:34:47.170
and think about what you're most passionate about professionally or personally
417
00:34:47.570 --> 00:34:55.890
and see how that lines up with your aptitude. Of course, you'll wanna have aptitude as well for it. But Yeah. Passion and aptitude,
418
00:34:55.890 --> 00:34:57.810
find where that nexus is,
419
00:34:58.985 --> 00:35:02.905
and evaluate that as a potential career path.
420
00:35:03.545 --> 00:35:08.425
And whether that's in the humanities or the sciences or the arts,
421
00:35:08.985 --> 00:35:12.025
whatever, but for me, and I'm just speaking for myself,
422
00:35:13.940 --> 00:35:22.180
man, I don't wanna be in a position where I'm watching the clock because when you think of how much your life you spend on the in the job,
423
00:35:22.900 --> 00:35:25.619
I need to do something that's personally fulfilling.
424
00:35:26.325 --> 00:35:27.365
Not everybody's
425
00:35:27.365 --> 00:35:30.405
privileged enough to have that. I respect,
426
00:35:30.405 --> 00:35:36.005
and I wanna put that out there as well. But if you are privileged enough to have that choice,
427
00:35:37.685 --> 00:35:40.020
consider it. Passion and aptitude.
428
00:35:41.220 --> 00:35:43.780
That's beautiful. Yeah. I like that a lot.
429
00:35:44.500 --> 00:35:46.260
Alright. Thank you very much.
430
00:35:46.660 --> 00:35:48.660
This was delightful.
431
00:35:48.820 --> 00:35:55.085
You're welcome, Barry. Always great to chat with you. I absolutely love your instructional content. Always have.
432
00:35:55.645 --> 00:35:58.685
Oh, thank you. Yeah. Same here. Big fan. Thanks.
433
00:35:59.405 --> 00:35:59.885
Alright.