Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:00,390 --> 00:00:00,479
That's where I'm leaving.
2
00:00:01,779 --> 00:00:04,780
I get that the chat GPT was
created so that it could be
3
00:00:04,780 --> 00:00:06,679
chain of thought prompting.
4
00:00:07,090 --> 00:00:07,720
I get that.
5
00:00:08,230 --> 00:00:13,700
However, chain of thought prompting
is based on single thought prompting
6
00:00:14,750 --> 00:00:16,130
and they just extended the model.
7
00:00:16,219 --> 00:00:18,390
So they're trying to
get you to that anyway.
8
00:00:18,510 --> 00:00:20,400
So I just tried to go there.
9
00:00:31,425 --> 00:00:33,055
Yes, so you can use ICP.
10
00:00:33,075 --> 00:00:36,275
Sorry, Mark asked, um, I can't
remember, read the questions.
11
00:00:36,765 --> 00:00:42,314
Um, so, uh, you can use the
ICP throughout the rest of the
12
00:00:42,324 --> 00:00:44,455
chat in the variable example.
13
00:00:44,455 --> 00:00:45,075
Yes, you can.
14
00:00:48,054 --> 00:00:51,705
Um, Harry, you just said by
using variables, so I'm not sure.
15
00:00:52,364 --> 00:00:53,044
Oh, that the,
16
00:00:56,794 --> 00:00:58,825
oh, that was the extension
of your earlier question.
17
00:00:59,425 --> 00:01:01,035
Um, I hope I answered that for you.
18
00:01:06,625 --> 00:01:07,095
All right.
19
00:01:07,545 --> 00:01:11,335
I think, is that the last question, Mark?
20
00:01:19,715 --> 00:01:20,865
Uh, you want to start over?
21
00:01:21,445 --> 00:01:22,355
Cecilia, you're lost.
22
00:01:22,595 --> 00:01:23,305
Would I lose you?
23
00:01:23,865 --> 00:01:24,045
I'm sorry.
24
00:01:24,155 --> 00:01:27,885
No, I was saying start back
in March, the beginning.
25
00:01:28,215 --> 00:01:31,345
Oh, you want to start over, over, over.
26
00:01:31,924 --> 00:01:32,284
Great.
27
00:01:32,395 --> 00:01:36,945
Um, I do see, I see we have a
question, um, from Nan in the Q&
28
00:01:36,945 --> 00:01:39,364
A about writing a marketing quiz.
29
00:01:40,060 --> 00:01:42,120
Need a question for a
quiz with four responses.
30
00:01:43,359 --> 00:01:43,590
Yeah.
31
00:01:43,590 --> 00:01:45,050
So Nan asked that earlier.
32
00:01:45,259 --> 00:01:46,300
I need
33
00:01:50,259 --> 00:01:54,620
to know the specific case and we
could probably sit and, and do that.
34
00:01:54,620 --> 00:02:00,139
And this is part of what, um, Jeff was
saying last week too, like the, one of
35
00:02:00,139 --> 00:02:02,680
the things that's going to happen is
there's going to be a new career for
36
00:02:02,680 --> 00:02:04,549
people who can write effective prompts.
37
00:02:09,300 --> 00:02:09,630
Right.
38
00:02:09,639 --> 00:02:13,660
So, um, then yes, we, so what we have.
39
00:02:14,825 --> 00:02:18,225
Uh, because it will need to be
extended from where you are.
40
00:02:18,535 --> 00:02:23,165
So, and do you want the entire quiz?
41
00:02:24,234 --> 00:02:29,335
Or just question need a question for
I really want the format in essence.
42
00:02:29,345 --> 00:02:32,784
So I've got a quiz.
43
00:02:33,134 --> 00:02:35,214
I want it to make up a quiz question.
44
00:02:35,635 --> 00:02:38,065
I wanted to make up the 4 responses.
45
00:02:38,505 --> 00:02:41,315
There's 4 categories or buckets.
46
00:02:42,055 --> 00:02:44,384
And so, therefore, the response.
47
00:02:44,790 --> 00:02:50,430
I want tied to an individual
bucket, but I want all four of the
48
00:02:50,440 --> 00:02:52,450
buckets represented in the question.
49
00:02:52,460 --> 00:02:57,900
What it tends to do is break
it up into here's a question.
50
00:02:58,180 --> 00:03:00,840
All responses go to this bucket.
51
00:03:01,199 --> 00:03:02,150
Here's another question.
52
00:03:02,150 --> 00:03:04,080
All the responses go to that bucket.
53
00:03:04,490 --> 00:03:06,210
And I want every question.
54
00:03:06,965 --> 00:03:13,335
Have each of the four responses
tied to each of the four buckets.
55
00:03:13,885 --> 00:03:14,815
Yeah, I gotcha.
56
00:03:14,825 --> 00:03:19,204
Embracing that, it just, I have to write
it and rewrite it, and I'm like, geez.
57
00:03:20,155 --> 00:03:23,655
So, it's going to get
confused there, okay?
58
00:03:23,935 --> 00:03:27,375
And the reason it's going to get confused
is, and I can guarantee, I haven't
59
00:03:27,375 --> 00:03:29,965
seen your prompt, but I'm going to
promise you one thing about your prompt.
60
00:03:30,274 --> 00:03:33,885
Your prompt is actually contradicting
itself in some places, and that's
61
00:03:33,885 --> 00:03:34,745
what's going to confuse it.
62
00:03:35,250 --> 00:03:35,610
Okay.
63
00:03:35,890 --> 00:03:37,340
Uh, and that's not anything personal.
64
00:03:37,440 --> 00:03:39,950
Um, Linda and I worked through a
prompt a couple months ago where
65
00:03:39,950 --> 00:03:41,090
she had the exact same thing.
66
00:03:41,090 --> 00:03:44,689
And to her, it was, Oh no, this
seemed like one, one thought.
67
00:03:44,690 --> 00:03:46,730
But then when you actually looked
at how the computer would look at
68
00:03:46,730 --> 00:03:48,369
it, it was started conflicting.
69
00:03:48,660 --> 00:03:49,010
Okay.
70
00:03:49,309 --> 00:03:53,199
Um, the thing that I will tell you
is an example is going to help you.
71
00:03:53,510 --> 00:04:00,859
So you're going to have to, so you're
going to ask it, you not what dropped
72
00:04:00,859 --> 00:04:05,899
your, did you drop your prompt on
my, um, form on the, in the, uh,
73
00:04:05,909 --> 00:04:09,029
in the Google doc, no, I don't.
74
00:04:09,475 --> 00:04:11,545
No, because all I saw was your handout.
75
00:04:11,585 --> 00:04:12,075
I didn't.
76
00:04:12,915 --> 00:04:16,915
Okay, so I finally got it.
77
00:04:16,945 --> 00:04:18,285
But now I'm like, how did I get it?
78
00:04:19,314 --> 00:04:23,054
Because I do this over and
over again, you know, I've got,
79
00:04:23,505 --> 00:04:25,004
because I do, I write quizzes.
80
00:04:25,625 --> 00:04:30,375
And so I know there's a way to
exactly write it and I just thought
81
00:04:30,375 --> 00:04:33,395
you might be able to help with
the language of it of the prompt.
82
00:04:36,455 --> 00:04:38,555
So, write down what you say.
83
00:04:39,655 --> 00:04:42,235
Okay, but but so hold on, but
you figured out the answer.
84
00:04:45,070 --> 00:04:48,390
Yes, several times I have, where
it has done it, but now I'm
85
00:04:48,390 --> 00:04:50,340
like, how did I, what did I say?
86
00:04:51,260 --> 00:04:52,130
How did I ask that?
87
00:04:52,570 --> 00:04:52,920
Okay.
88
00:04:53,300 --> 00:04:57,390
Do you have a version of when it
did it right that you can share?
89
00:04:57,399 --> 00:04:58,590
I probably can.
90
00:04:58,599 --> 00:04:59,009
Yes.
91
00:04:59,500 --> 00:04:59,770
Yeah.
92
00:05:00,200 --> 00:05:03,980
If you're willing to share that with me, I
can help you understand why I did it right
93
00:05:04,010 --> 00:05:08,490
and how to make it repeatable because
that's ultimately what we do because
94
00:05:08,490 --> 00:05:10,300
we represent so many different clients.
95
00:05:10,390 --> 00:05:13,670
We have to figure out
how to take a prompt.
96
00:05:14,060 --> 00:05:18,800
And make it in a way that it's,
it's going to repeat great answers,
97
00:05:18,960 --> 00:05:20,420
no matter who the client is.
98
00:05:20,950 --> 00:05:24,370
I can probably find that, just a second.
99
00:05:25,970 --> 00:05:28,880
So, if you may want to go on to
something else, let me look for a minute.
100
00:05:30,489 --> 00:05:32,879
Um, up, up, up, up, up, up, up.
101
00:05:33,460 --> 00:05:34,309
Questions, Mark?
102
00:05:36,340 --> 00:05:37,310
Uh, let's see.
103
00:05:37,310 --> 00:05:41,340
Oh, let me make sure I've unmuted.
104
00:05:41,400 --> 00:05:43,969
I actually asked a few and
I was muted the whole time.
105
00:05:43,969 --> 00:05:47,130
So anyways, uh, Stephanie has a question.
106
00:05:47,159 --> 00:05:50,860
I may have missed this one on, of the
trainings I missed while traveling,
107
00:05:50,870 --> 00:05:54,010
but have plugin recommendation
recommendations been made.
108
00:05:54,309 --> 00:05:57,770
I keep hearing about one that supposedly
makes it so chat GPT gives current
109
00:05:57,780 --> 00:05:59,760
info, but I don't know what it's called.
110
00:06:00,010 --> 00:06:03,510
So I'm guessing current info
would be, uh, full live info.
111
00:06:03,510 --> 00:06:03,840
Yeah.
112
00:06:04,210 --> 00:06:07,969
Yeah, so the, um, the ability to browse.
113
00:06:08,835 --> 00:06:10,905
Um, we'll get you to current info.
114
00:06:11,405 --> 00:06:17,265
Um, what's hysterical is, in case you
didn't know, Jasper now does that too.
115
00:06:17,975 --> 00:06:21,304
And they released it before,
ChatGPT, and they're Jasper Chat.
116
00:06:22,925 --> 00:06:27,284
Um, and so we'll still see how that
actually works and, and how you
117
00:06:27,365 --> 00:06:31,474
actually can use the data that it
gives you or how, how great it is.
118
00:06:32,025 --> 00:06:36,985
Um, the plugin I'm super excited
about is, uh, I'm gonna sound
119
00:06:36,985 --> 00:06:38,275
like a real old school nerd.
120
00:06:38,705 --> 00:06:44,164
Um, this APR plugin,
that's got me excited.
121
00:06:46,674 --> 00:06:48,575
Sorry, I missed the answer.
122
00:06:48,655 --> 00:06:51,044
Hatiba, did you say what it's called?
123
00:06:51,054 --> 00:06:57,664
Whatever plugin we need so it will look
for information from 2023 instead of 2021?
124
00:06:58,045 --> 00:07:02,075
So, that, that would be the browser plugin
that, that um, ChatGPT is releasing.
125
00:07:02,475 --> 00:07:03,015
Um.
126
00:07:03,075 --> 00:07:04,484
It's not available yet?
127
00:07:04,785 --> 00:07:05,305
It is not.
128
00:07:05,434 --> 00:07:06,005
At least.
129
00:07:06,495 --> 00:07:08,915
It's not widely available.
130
00:07:09,575 --> 00:07:10,675
Few people have it.
131
00:07:12,455 --> 00:07:14,005
I'm not one of those few people.
132
00:07:15,895 --> 00:07:20,575
James might be though, putting
you on the spot, buddy.
133
00:07:23,805 --> 00:07:24,205
It's funny.
134
00:07:24,205 --> 00:07:27,475
James always gets access to
everything like the day before me.
135
00:07:28,454 --> 00:07:29,585
And he's like, Oh, I got this.
136
00:07:29,585 --> 00:07:30,695
I'm like, yeah, I don't have it.
137
00:07:34,130 --> 00:07:37,909
Okay, so I did put that in
chat in question, the Q and A.
138
00:07:38,579 --> 00:07:43,140
So I think that is the one that
is going to get me the response.
139
00:07:43,189 --> 00:07:46,260
But then I gave you an
example of a question
140
00:07:49,730 --> 00:07:52,569
on what it produced with
the responses it produced.
141
00:07:55,409 --> 00:07:56,700
Is there a better way to ask that?
142
00:07:56,700 --> 00:07:56,729
Okay,
143
00:08:00,670 --> 00:08:01,110
so
144
00:08:06,690 --> 00:08:11,169
your prompt was, write a question
on challenges with business strategy
145
00:08:11,169 --> 00:08:14,969
and planning or branding and customer
journey or marketing and sales.
146
00:08:16,900 --> 00:08:19,619
I would rephrase that
whole sentence to start.
147
00:08:19,740 --> 00:08:24,180
Yeah, just tell me and I'll write it
down should be three responses for the
148
00:08:24,180 --> 00:08:29,390
question with tied to one of the child.
149
00:08:29,419 --> 00:08:32,839
But okay, so but you didn't
define you say tied to one of the
150
00:08:32,839 --> 00:08:36,189
challenge areas, but you didn't
define what the challenge areas are.
151
00:08:36,219 --> 00:08:40,069
Yeah, that's the business strategy
and planning, branding and customer
152
00:08:40,069 --> 00:08:42,190
journey, marketing and sales.
153
00:08:43,070 --> 00:08:44,830
Those are the challenge areas.
154
00:08:47,155 --> 00:08:51,085
Yeah, it looks like what you need to do is
separate all this into separate questions.
155
00:08:51,155 --> 00:08:53,335
I was afraid to put a comma in there.
156
00:08:53,345 --> 00:08:58,435
So you think I need to just
say there are three challenges?
157
00:08:58,935 --> 00:09:02,575
And yeah, and the three challenges
are this, this, this, and then
158
00:09:02,575 --> 00:09:06,175
I'll reference that to be able to
answer the question in those areas.
159
00:09:06,185 --> 00:09:09,095
But the whole thing is you should,
this should be like three different
160
00:09:09,095 --> 00:09:10,785
prompts is what I would do or four.
161
00:09:10,795 --> 00:09:11,205
Really?
162
00:09:11,915 --> 00:09:12,614
Oh, wait a minute.
163
00:09:13,145 --> 00:09:16,514
But I only want three
responses to the question.
164
00:09:17,050 --> 00:09:23,640
Yeah, but the way you're producing
it is just, um, clunky is the word.
165
00:09:23,640 --> 00:09:26,350
Yeah, that's why I'm asking
you to rewrite it for me.
166
00:09:27,390 --> 00:09:27,790
Okay.
167
00:09:27,900 --> 00:09:34,519
Um, so you, at the end of the day, you
want to, uh, a question for a challenge on
168
00:09:34,530 --> 00:09:38,300
business strategy, planning, or branding?
169
00:09:38,810 --> 00:09:39,580
No, that's what it.
170
00:09:40,730 --> 00:09:48,460
I want, I want a question with the
response going to one of those three.
171
00:09:49,059 --> 00:09:49,629
I got that.
172
00:09:49,910 --> 00:09:54,020
So before we get to, to that,
you're not giving it the question.
173
00:09:54,709 --> 00:09:57,150
You're asking it to figure
out the question for you.
174
00:09:57,269 --> 00:09:57,589
Correct?
175
00:09:57,980 --> 00:09:58,920
Yes.
176
00:09:59,630 --> 00:10:02,840
And you're then asking it to
figure out the response and
177
00:10:02,860 --> 00:10:04,400
which category it goes to.
178
00:10:04,935 --> 00:10:05,405
Yes.
179
00:10:05,875 --> 00:10:10,265
Okay, so from a logical perspective,
it can do that and it can do
180
00:10:10,265 --> 00:10:11,285
that in one prompt for you.
181
00:10:11,595 --> 00:10:16,274
Okay, the logical perspective is the
first thing is, hey, this is my topic.
182
00:10:17,815 --> 00:10:23,104
I'm looking for a question, just
one question, except I'm going to
183
00:10:23,105 --> 00:10:25,054
say 10 questions, but that's okay.
184
00:10:25,055 --> 00:10:25,365
Yeah.
185
00:10:25,800 --> 00:10:26,560
Start with one.
186
00:10:26,890 --> 00:10:27,350
Okay.
187
00:10:27,950 --> 00:10:29,010
Run it 10 times.
188
00:10:29,990 --> 00:10:30,500
Okay.
189
00:10:32,740 --> 00:10:33,730
This is my topic.
190
00:10:33,730 --> 00:10:37,360
I'm looking for a question
for this for a question.
191
00:10:39,310 --> 00:10:43,990
The question will have
four possible responses.
192
00:10:45,740 --> 00:10:51,310
The response categories should be,
and then give the name of the category
193
00:10:51,310 --> 00:10:54,270
and a description of the category.
194
00:10:58,140 --> 00:11:01,180
And I should say X, X and X, right?
195
00:11:03,315 --> 00:11:03,965
Define X.
196
00:11:05,585 --> 00:11:07,535
Well, X is the three challenges.
197
00:11:08,855 --> 00:11:09,275
Yes.
198
00:11:10,725 --> 00:11:11,535
Writing them out.
199
00:11:11,855 --> 00:11:14,585
The response category should be
branding and blah, blah, blah, blah.
200
00:11:15,505 --> 00:11:17,745
Should be X, so X, X, and X.
201
00:11:20,145 --> 00:11:23,075
Defining what X is in each case.
202
00:11:24,005 --> 00:11:24,625
Yes.
203
00:11:25,045 --> 00:11:26,325
Um, okay.
204
00:11:26,335 --> 00:11:27,775
And that will help.
205
00:11:28,435 --> 00:11:30,045
I'm trying to find
something else for you here.
206
00:11:30,775 --> 00:11:31,425
Um,
207
00:11:36,745 --> 00:11:37,745
for an actual prompt.
208
00:11:37,915 --> 00:11:39,875
And I want to be sure
there's no duplication.
209
00:11:40,225 --> 00:11:46,935
Because once in a while, it'll give me two
of the same one, and then the other two.
210
00:11:47,894 --> 00:11:49,105
And leave one out.
211
00:11:54,684 --> 00:11:57,045
And that's where now the example comes in.
212
00:11:57,045 --> 00:11:59,885
So, after you write
everything that I just said.
213
00:12:00,200 --> 00:12:05,040
Say an example would be and then tell
it question and give the question
214
00:12:05,970 --> 00:12:12,700
that answer one is and give an answer
and said this is this category answer
215
00:12:12,700 --> 00:12:18,910
to is this category answer three is
that category to be very specific in
216
00:12:18,910 --> 00:12:21,630
the response that that you give it.
217
00:12:24,564 --> 00:12:24,904
Does that make sense?
218
00:12:25,885 --> 00:12:27,645
Uh, yes, it does.
219
00:12:27,744 --> 00:12:29,095
Uh, but
220
00:12:33,545 --> 00:12:39,584
I'm afraid what it will do is not
really tie the response to the category,
221
00:12:40,655 --> 00:12:43,294
that response to that category.
222
00:12:43,824 --> 00:12:45,555
I can try it and see if it'll do it.
223
00:12:45,984 --> 00:12:50,775
And as long as I have an example, I think
I can just say, use this example, can't I?
224
00:12:52,315 --> 00:12:55,905
I'm going to say something in,
in, in absolute, absolute love.
225
00:12:55,994 --> 00:12:56,375
Okay.
226
00:12:56,885 --> 00:12:57,714
Um, but it may sound a
227
00:13:01,315 --> 00:13:01,585
Right.
228
00:13:01,615 --> 00:13:03,365
You said, I'm afraid it's
going to do something.
229
00:13:03,365 --> 00:13:05,605
Yeah, but we don't know what
it's going to just try it.
230
00:13:05,724 --> 00:13:06,935
If it does, we'll figure it out.
231
00:13:07,105 --> 00:13:07,505
Okay.
232
00:13:08,055 --> 00:13:10,565
I'm going to drop a prompt that
233
00:13:15,595 --> 00:13:16,255
may help you.
234
00:13:16,765 --> 00:13:17,225
Okay.
235
00:13:17,225 --> 00:13:18,475
You're putting it today.
236
00:13:18,950 --> 00:13:20,090
No, I'm going to put it in the chat.
237
00:13:20,460 --> 00:13:20,810
Yeah.
238
00:13:20,849 --> 00:13:21,329
Okay.
239
00:13:21,480 --> 00:13:23,700
If it doesn't help you, just ignore it.
240
00:13:23,990 --> 00:13:24,329
Okay.
241
00:13:25,520 --> 00:13:25,920
All right.
242
00:13:26,030 --> 00:13:34,269
Um, there anybody else you can have
that to, um, this prompt, what it does
243
00:13:34,270 --> 00:13:36,090
is it actually creates carousel posts.
244
00:13:36,520 --> 00:13:37,339
Is this the right one?
245
00:13:38,299 --> 00:13:39,610
Make sure I put the right one in here.
246
00:13:39,620 --> 00:13:40,570
I think I did.
247
00:13:40,720 --> 00:13:44,160
I think this is the one that creates
carousel posts that, that then
248
00:13:44,190 --> 00:13:46,680
creates, turns a carousel into a pole.
249
00:13:49,569 --> 00:13:50,759
Carousel into a pole.
250
00:13:50,760 --> 00:13:52,280
All right.
251
00:13:52,990 --> 00:13:53,439
It's,
252
00:13:56,600 --> 00:13:58,700
um, I don't think you
actually want that Indy.
253
00:14:00,540 --> 00:14:03,939
I think that would hurt your head
even more than it hurts mine.
254
00:14:05,989 --> 00:14:08,689
Um, actually, no, I think
I did drop the wrong one.
255
00:14:08,689 --> 00:14:13,100
And that one, I think
does just a carousel post.
256
00:14:13,730 --> 00:14:17,140
This one here.
257
00:14:20,430 --> 00:14:21,580
Here, take that one.
258
00:14:26,100 --> 00:14:26,460
Uh, let's see.
259
00:14:30,170 --> 00:14:30,560
Okay.
260
00:14:31,130 --> 00:14:31,590
Um.
261
00:14:31,630 --> 00:14:33,560
Actually, while you're trying
that out, you want to check
262
00:14:33,560 --> 00:14:35,200
on, uh, Stephanie's question?
263
00:14:35,860 --> 00:14:36,040
Sorry.
264
00:14:36,280 --> 00:14:36,610
Yes.
265
00:14:36,640 --> 00:14:37,139
Thank you.
266
00:14:39,090 --> 00:14:43,949
Uh, do we want to help ChatGPT by limiting
the number of words we use in our prompts?
267
00:14:44,060 --> 00:14:48,290
For example, would it help if instead of
typing the word and, we used an ampersand?
268
00:14:48,735 --> 00:14:50,055
Or does that not matter?
269
00:14:52,605 --> 00:14:58,925
So you're not helping chatGBT,
you're helping yourself with that.
270
00:14:59,235 --> 00:14:59,645
Okay?
271
00:14:59,715 --> 00:15:04,245
Because remember that the point
of it is, especially in 3.
272
00:15:04,245 --> 00:15:07,405
5 and 3, you're limited in
terms of the number of words.
273
00:15:09,354 --> 00:15:09,814
Right.
274
00:15:10,285 --> 00:15:13,854
Um, and really it's about characters
more than it is actual words.
275
00:15:13,854 --> 00:15:16,884
But, you know, as humans, we don't
think in characters we think in words.
276
00:15:17,405 --> 00:15:20,625
Um, and so it's an approximate
of about 4000 words.
277
00:15:21,555 --> 00:15:21,905
Right.
278
00:15:22,334 --> 00:15:28,429
Um, so that's not actually going
to when you do that to you.
279
00:15:29,480 --> 00:15:33,580
You limit the number of words so that
it can return more response to you.
280
00:15:33,840 --> 00:15:34,680
That's the bottom line.
281
00:15:35,610 --> 00:15:39,329
And and versus ampersand is not going
to make enough of a difference to care.
282
00:15:41,190 --> 00:15:45,360
Have you counted the words
in your, like, killer first
283
00:15:45,360 --> 00:15:47,080
prompt that's three pages long?
284
00:15:48,064 --> 00:15:48,594
I haven't.
285
00:15:48,874 --> 00:15:49,954
It just works every time.
286
00:15:57,094 --> 00:16:00,444
And believe me, I have some
prompts that don't work every time.
287
00:16:04,065 --> 00:16:07,144
I have, we uh, we did a prompt.
288
00:16:07,925 --> 00:16:10,255
So, real talk for a moment.
289
00:16:11,005 --> 00:16:14,314
One of the things that we're working
on right now is LinkedIn prospecting.
290
00:16:14,654 --> 00:16:17,365
And, anybody use LinkedIn Sales Navigator?
291
00:16:21,605 --> 00:16:30,494
The whole point of, of, A GPT model
is that an AI is that it takes a bunch
292
00:16:30,494 --> 00:16:35,255
of data and finds commonalities and
data that the human eye can't see.
293
00:16:35,829 --> 00:16:36,439
Just the whole point.
294
00:16:36,880 --> 00:16:41,310
And then it predicts what's, what
the next set of responses will be.
295
00:16:41,740 --> 00:16:42,080
Okay.
296
00:16:42,660 --> 00:16:48,519
So we got the bright idea in LinkedIn
Navigator, um, because we always just
297
00:16:48,520 --> 00:16:54,699
get stuck with the, um, the criteria for
Navigator to find the people that we want.
298
00:16:55,870 --> 00:16:57,020
And so we got the bright idea.
299
00:16:57,060 --> 00:17:03,575
Could we write a prompt that took
the profiles of Five LinkedIn
300
00:17:03,585 --> 00:17:10,744
navigator people that are our
ideal customer and then create the
301
00:17:12,145 --> 00:17:16,554
LinkedIn navigator search for those.
302
00:17:18,665 --> 00:17:20,345
Anybody interested in something like that?
303
00:17:23,815 --> 00:17:24,235
Yeah.
304
00:17:24,425 --> 00:17:25,775
We were super interested too.
305
00:17:26,124 --> 00:17:30,695
And we got it to the point
where it will only take two,
306
00:17:31,145 --> 00:17:32,365
it will only take two profiles.
307
00:17:32,755 --> 00:17:34,635
We go to three profiles and it just craps.
308
00:17:34,980 --> 00:17:38,860
Every time, but two profiles is not
enough to actually give you enough
309
00:17:38,860 --> 00:17:42,530
data to find anything worthwhile
that the human eye couldn't see.
310
00:17:45,460 --> 00:17:46,400
So we're still working on that.
311
00:17:46,400 --> 00:17:51,530
And if we get it done, I'll let you know,
let me rephrase when we get it done.
312
00:17:51,729 --> 00:17:52,320
I'll let you know,
313
00:17:57,670 --> 00:18:02,260
but that's kind of my point about why
prompt engineering is, is important
314
00:18:02,610 --> 00:18:05,580
because it allows us and why having
these conversations are important.
315
00:18:07,470 --> 00:18:12,830
Six weeks ago, we would have never
thought of that, but because we're using
316
00:18:12,830 --> 00:18:17,800
prompts to help us ideate our generic
content or not generic, general content
317
00:18:17,800 --> 00:18:21,409
for our clients now, and that's sped
up and given us so much time back.
318
00:18:21,649 --> 00:18:25,389
Now it's allowing us to solve
problems that we didn't even
319
00:18:25,399 --> 00:18:27,100
realize we could solve before.
320
00:18:29,740 --> 00:18:30,709
That's the beauty.
321
00:18:31,385 --> 00:18:32,675
Of what AI can do for us.
322
00:18:34,405 --> 00:18:34,504
Yes.
323
00:18:34,675 --> 00:18:36,965
Actually, I just got another
question from Michelle.
324
00:18:36,975 --> 00:18:38,985
I must have probably in
the chat or something.
325
00:18:39,385 --> 00:18:42,944
Uh, do you start every chat with
the master base prompts or do you
326
00:18:42,945 --> 00:18:45,965
start a new chat and tell it to
refer to the master base prompt
327
00:18:45,965 --> 00:18:47,115
chat that you've already saved?
328
00:18:48,075 --> 00:18:49,375
So that's a good question.
329
00:18:49,465 --> 00:18:51,984
Um, no, I don't start every
prompt with the master chat.
330
00:18:51,985 --> 00:18:55,345
The master chat is for when,
like how Jeff was doing when
331
00:18:55,345 --> 00:18:57,895
he had his different clients.
332
00:18:58,665 --> 00:19:03,905
And you have a chat that's
generating content for this client.
333
00:19:04,275 --> 00:19:04,955
That's when you do it.
334
00:19:04,965 --> 00:19:08,754
If you're just asking a
one off question, no need,
335
00:19:12,795 --> 00:19:14,324
no need to go through all
that because it's a lot.
336
00:19:14,354 --> 00:19:18,495
It takes, it's going to take a good
45 minutes to set it up correctly.
337
00:19:19,854 --> 00:19:20,255
No need.
338
00:19:21,805 --> 00:19:24,575
But if you're going to return to
this for the next eight weeks,
339
00:19:24,575 --> 00:19:26,405
then yeah, it's worth the time.
340
00:19:30,875 --> 00:19:31,035
All right.
341
00:19:31,125 --> 00:19:31,355
Let's see.
342
00:19:31,355 --> 00:19:32,275
We got Vicky too.
343
00:19:32,275 --> 00:19:34,275
Another question, Bard or ChatGPT.
344
00:19:34,675 --> 00:19:35,935
This space is moving so much.
345
00:19:36,310 --> 00:19:42,330
Uh, how the space is moving so much,
how much have you played with Bard
346
00:19:42,350 --> 00:19:44,610
and what and who is it better for?
347
00:19:45,500 --> 00:19:46,770
So that's a really great question.
348
00:19:46,770 --> 00:19:47,820
I'm going to answer it in this way.
349
00:19:48,200 --> 00:19:53,970
Um, so in case you hadn't noticed,
Jasper uses four different
350
00:19:54,219 --> 00:19:56,409
models to produce content.
351
00:19:57,509 --> 00:20:00,020
And if you actually listen
to them, there's actually
352
00:20:00,020 --> 00:20:01,500
five models that they use.
353
00:20:02,475 --> 00:20:04,625
If you're really, really listening, okay?
354
00:20:04,905 --> 00:20:05,795
Why is that?
355
00:20:06,055 --> 00:20:10,045
Because every single model does
something different and does
356
00:20:10,055 --> 00:20:11,755
something better than another one.
357
00:20:12,745 --> 00:20:20,074
So if, if you want to write in my
opinion, just straight writing, Bard wins.
358
00:20:21,764 --> 00:20:25,455
If you want ideation, chat, GPT wins.
359
00:20:27,885 --> 00:20:32,704
We're building an app right now
that is designed to help you with
360
00:20:33,054 --> 00:20:37,735
ideation of video content, basically
everything that we do at our agency,
361
00:20:38,125 --> 00:20:40,474
it's encapsulated inside of one app.
362
00:20:40,674 --> 00:20:41,885
And so we're going to be doing that.
363
00:20:41,885 --> 00:20:44,565
We're going to be using two
or three different models to
364
00:20:44,575 --> 00:20:46,645
help produce content because.
365
00:20:47,730 --> 00:20:51,510
Bard's going to do a better job
writing a video script, whereas chat
366
00:20:51,830 --> 00:20:58,199
GPT will do a better job writing
the, um, the, the, the title, right?
367
00:20:58,320 --> 00:20:58,870
And who knows?
368
00:20:58,900 --> 00:21:01,380
Anthropic may do something else
better than, than the others.
369
00:21:01,590 --> 00:21:04,320
And so we may use two or three
different things to pull together
370
00:21:04,320 --> 00:21:05,709
to create one piece of content.
371
00:21:07,980 --> 00:21:09,089
These are tools.
372
00:21:09,090 --> 00:21:10,210
They're not AI,
373
00:21:17,219 --> 00:21:19,150
like mid journey in your process?
374
00:21:19,170 --> 00:21:21,110
So prompt engineering and mid journey.
375
00:21:21,505 --> 00:21:27,835
I'm not, you know, and, and, um, honestly,
here's why I spend so much time in, um,
376
00:21:27,885 --> 00:21:31,285
written prompt response and engineering.
377
00:21:31,805 --> 00:21:34,555
And I know that world.
378
00:21:34,965 --> 00:21:41,834
And the reality of the fact
that I am visually a dunce.
379
00:21:44,190 --> 00:21:45,590
You just haven't practiced it.
380
00:21:45,630 --> 00:21:46,490
That's all it is.
381
00:21:46,920 --> 00:21:51,500
It's when I need some, I'm just going to
call Mark cause he's super good at it.
382
00:21:53,540 --> 00:21:55,940
I will say that the prompt
engineering definitely has an
383
00:21:55,949 --> 00:21:57,410
application within mid journey.
384
00:21:57,440 --> 00:22:02,380
The big difference between something like
chat, GPT and mid journey or any of the
385
00:22:02,380 --> 00:22:05,170
graphic kind of creators is there is some.
386
00:22:05,480 --> 00:22:10,220
Abstract aspects to it, like the
stylized function on mid journey.
387
00:22:10,520 --> 00:22:11,800
What the heck does that mean?
388
00:22:12,050 --> 00:22:16,070
You know, it's, uh, it's kind of
a term that's thrown around, but
389
00:22:16,100 --> 00:22:18,090
you can't really decide what it is.
390
00:22:18,360 --> 00:22:21,910
So, whereas you could be hyper
specific or at least a lot more
391
00:22:21,910 --> 00:22:25,810
specific with the chat GPT, it's
a little harder with mid journey.
392
00:22:25,810 --> 00:22:27,210
And a lot of those, because it's.
393
00:22:27,495 --> 00:22:29,155
It's an art platform, essentially.
394
00:22:29,165 --> 00:22:32,035
So you have to incorporate
that lack of science into it.
395
00:22:32,095 --> 00:22:35,075
But with that said, there is
a way to phrase information.
396
00:22:35,075 --> 00:22:37,895
There's a way to manipulate,
uh, you know, specific prompts.
397
00:22:38,345 --> 00:22:42,475
Uh, and it does have a few more of
those, uh, kind of tailored aspects
398
00:22:42,505 --> 00:22:46,644
like the stylized function, uh,
that you don't have on chat GPT.
399
00:22:47,915 --> 00:22:49,935
Can I share one last
thing, Mark, before we go?
400
00:22:50,850 --> 00:22:54,790
All right, so showed you
some a little bit abstract.
401
00:22:55,230 --> 00:22:55,600
Okay.
402
00:22:55,750 --> 00:22:59,550
Um, so here's my master prompt again,
uh, big thing that I changed this time
403
00:22:59,600 --> 00:23:03,389
is look at the, um, the expert, right?
404
00:23:03,549 --> 00:23:07,690
So my expert is an expert
in content marketing.
405
00:23:08,089 --> 00:23:09,670
Looks like Clark Kent.
406
00:23:10,274 --> 00:23:13,135
But has a friend, Atiba, who is Superman.
407
00:23:14,455 --> 00:23:20,445
They have run a content marketing agency
and currently are the president of digital
408
00:23:20,454 --> 00:23:23,014
marketer, educate an education company.
409
00:23:23,254 --> 00:23:27,485
Anybody know who that is, by the
way, just a random friend of mine.
410
00:23:29,185 --> 00:23:30,874
Um, the rest of this stayed the same.
411
00:23:30,955 --> 00:23:34,774
Then I asked it to produce a video
script about how to make money.
412
00:23:35,225 --> 00:23:36,995
raising chickens in Texas.
413
00:23:40,195 --> 00:23:46,345
Um, and it wrote a pretty decent,
goofy, silly little script.
414
00:23:46,655 --> 00:23:48,594
And he said, okay, that's
just another silly example.
415
00:23:48,605 --> 00:23:50,884
Let's get, get real though, T,
but we're not writing scripts
416
00:23:50,884 --> 00:23:51,855
about chickens in Texas.
417
00:23:51,855 --> 00:23:52,325
Okay, great.
418
00:23:52,624 --> 00:23:57,494
So what about a blog outline about the
customer journey, customer value journey?
419
00:23:57,785 --> 00:24:01,480
Well, he gave me a blog outline
and by the way, It knew that
420
00:24:01,879 --> 00:24:03,330
this should have eight stages.
421
00:24:03,510 --> 00:24:06,370
We're on the right track, because
it's not one of those four stage
422
00:24:06,370 --> 00:24:08,659
customer value journeys, right?
423
00:24:09,019 --> 00:24:10,449
So it gives me this blog outline.
424
00:24:10,499 --> 00:24:10,979
Okay, great.
425
00:24:11,079 --> 00:24:13,679
What about, um, something,
let's get a little SEO now.
426
00:24:13,699 --> 00:24:16,169
Let's get some, some keywords,
some, and semantic keywords.
427
00:24:16,169 --> 00:24:16,809
How does that work?
428
00:24:16,819 --> 00:24:20,229
Okay, so I'm looking for keywords and
semantic keywords, and the expert for
429
00:24:20,289 --> 00:24:23,399
a blog, and same blog title here, and
430
00:24:27,179 --> 00:24:28,429
it's going to give me some stuff as well.
431
00:24:33,290 --> 00:24:37,090
So you can absolutely use this
for very, very practical things.
432
00:24:37,710 --> 00:24:38,100
As well.
433
00:24:38,520 --> 00:24:39,430
That was my last example.
434
00:24:40,680 --> 00:24:41,180
Awesome.
435
00:24:41,190 --> 00:24:42,320
Well, thank you so much, Atiba.
436
00:24:42,320 --> 00:24:44,440
I think, uh, you know,
the whole format is huge.
437
00:24:44,500 --> 00:24:48,980
Um, people will definitely need to
rewatch this episode if you're not
438
00:24:48,980 --> 00:24:52,920
familiar with, uh, you know, prompt
engineering, but once you understand
439
00:24:52,920 --> 00:24:56,360
it, it makes a huge difference in
terms of how well you're able to
440
00:24:56,379 --> 00:25:00,130
consistently produce the results that
you're looking for, uh, with chat GPT.
441
00:25:00,139 --> 00:25:02,000
So Atiba, thank you.
442
00:25:02,060 --> 00:25:04,820
Uh, where can people find out more
about you and maybe get some more
443
00:25:04,820 --> 00:25:06,390
of that, uh, prompt magic going.
444
00:25:07,060 --> 00:25:07,380
Yeah.
445
00:25:07,380 --> 00:25:09,780
So listen, all seriousness,
I want to help you.
446
00:25:10,040 --> 00:25:10,340
Okay.
447
00:25:10,400 --> 00:25:11,370
I want to answer your questions.
448
00:25:11,370 --> 00:25:14,760
I know you're going to have a lot and
they're probably stuff that I've run into.
449
00:25:15,090 --> 00:25:17,410
Um, the best way to do
that is go to meet Atiba.
450
00:25:17,840 --> 00:25:19,619
That's A T I B I A.
451
00:25:20,140 --> 00:25:20,720
That's my name.
452
00:25:21,120 --> 00:25:22,090
Meet Atiba.
453
00:25:22,090 --> 00:25:22,340
com.
454
00:25:22,340 --> 00:25:24,050
That's going to take you to my LinkedIn.
455
00:25:24,110 --> 00:25:25,590
You're going to go
directly to my LinkedIn.
456
00:25:25,830 --> 00:25:28,750
Once you get there, connect
with me, send me a message.
457
00:25:29,314 --> 00:25:29,915
Let's talk.
458
00:25:30,935 --> 00:25:31,804
Drop me a prompt.
459
00:25:32,284 --> 00:25:32,945
Let me help you.
460
00:25:34,884 --> 00:25:35,334
Love it.
461
00:25:36,415 --> 00:25:37,465
Well, thank you so much, Dipa.
462
00:25:37,465 --> 00:25:40,855
I definitely met recommend, you know,
since this is fresh in your head, that you
463
00:25:40,855 --> 00:25:43,284
go ahead and, uh, try some of these out.
464
00:25:43,375 --> 00:25:45,895
Uh, that way you have them saved
in the chat and you can see if
465
00:25:45,895 --> 00:25:47,185
they work or, or they don't.
466
00:25:47,215 --> 00:25:51,235
But, uh, or you know, if you need
to rephrase, uh, but you know, at
467
00:25:51,235 --> 00:25:53,125
Dipa, like I said, excellent content.
468
00:25:53,185 --> 00:25:55,824
Uh, love that you continue to
develop it since the last time
469
00:25:55,824 --> 00:25:59,815
I heard it, and I am definitely
gonna start employing this as well.
470
00:25:59,815 --> 00:26:01,525
Maybe I'll make a version for.
471
00:26:01,880 --> 00:26:04,780
Uh, you know, mid journey or
those, uh, kind of visual aspects,
472
00:26:04,980 --> 00:26:07,890
uh, but it's all applicable, so
very much appreciate your time.
473
00:26:08,570 --> 00:26:09,490
Oh, my pleasure.
474
00:26:10,690 --> 00:26:10,930
Thank you.
475
00:26:10,930 --> 00:26:11,740
All right.
476
00:26:11,960 --> 00:26:14,480
So make sure if you
can drop your examples.
477
00:26:14,480 --> 00:26:17,980
We want to see your work, the show your
work discussion in the slack channel.
478
00:26:18,600 --> 00:26:21,179
Really appreciate if you
made some of those and maybe
479
00:26:21,180 --> 00:26:22,470
just summarize your results.
480
00:26:22,530 --> 00:26:25,430
See if this methodology really
improve what you were doing.
481
00:26:26,090 --> 00:26:29,474
We'd love to hear those case studies and
also your review of the session itself.
482
00:26:29,625 --> 00:26:32,295
Uh, as a reminder, this call
has been recorded and will be
483
00:26:32,305 --> 00:26:34,115
available within the next 24 hours.
484
00:26:34,125 --> 00:26:39,345
It's should be up, you know, instantly on
the Slack page, but, uh, within an hour,
485
00:26:39,444 --> 00:26:42,965
uh, probably no less, and then you could
rewatch it because you might need to a
486
00:26:42,965 --> 00:26:45,065
couple of times and pause, use the pause.
487
00:26:46,195 --> 00:26:46,795
All right.
488
00:26:46,825 --> 00:26:50,465
On Wednesday, we have
our podcasting session.
489
00:26:50,775 --> 00:26:54,895
So it's going to be Jeremy and he
has a bunch of successful podcasts.
490
00:26:54,895 --> 00:26:58,605
He helped podcasters and he actually
uses a variety of completely different
491
00:26:58,615 --> 00:27:01,124
tools that we haven't even discussed yet.
492
00:27:01,144 --> 00:27:03,095
So definitely don't miss Wednesday.
493
00:27:03,425 --> 00:27:07,545
You're going to learn a ton about
podcasting and about how to really
494
00:27:07,555 --> 00:27:11,265
simplify your podcast creation
process using Jeremy's techniques.
495
00:27:11,345 --> 00:27:14,225
So tune back in, in a couple of days.
496
00:27:14,890 --> 00:27:17,980
And have fun with chat GPT in the
meantime, really appreciate y'all.
38312
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.