1
00:00:02,480 --> 00:00:03,000
Hi guys.

2
00:00:03,000 --> 00:00:03,920
Welcome to this session.

3
00:00:03,920 --> 00:00:06,320
So in this session we'll talk about prompt priming.

4
00:00:06,640 --> 00:00:12,360
So prompt priming is a concept which refers to the practice of providing some initial input to the model

5
00:00:12,400 --> 00:00:16,160
to the ChatGPT tool before generating any kind of response.

6
00:00:16,160 --> 00:00:23,920
So this initial input really helps to guide the tool towards generating a response that is more relevant

7
00:00:23,920 --> 00:00:25,480
and customized to you.

8
00:00:25,920 --> 00:00:28,040
So the user's intended input.

9
00:00:28,040 --> 00:00:34,400
So it is very crucial and important that whenever we are giving prompts to ChatGPT tool, we are giving

10
00:00:34,400 --> 00:00:40,440
some context, some context, some background of what exactly what kind of information you are looking

11
00:00:40,440 --> 00:00:40,800
for.

12
00:00:41,080 --> 00:00:46,840
Like for example, without priming, let's say I'm saying where should I go on my next vacation?

13
00:00:47,480 --> 00:00:50,560
Now this is something very it's super generic.

14
00:00:50,760 --> 00:00:58,360
Now ChatGPT will find it extremely generic as a input given and will give a very generic response to

15
00:00:58,400 --> 00:00:58,760
it.

16
00:00:58,800 --> 00:01:02,520
It will give me all kinds of places around the world, okay.

17
00:01:02,560 --> 00:01:04,130
And information about that.

18
00:01:04,490 --> 00:01:05,690
But now think about it.

19
00:01:05,690 --> 00:01:07,970
If I give some context behind it.

20
00:01:08,010 --> 00:01:08,490
Okay.

21
00:01:08,530 --> 00:01:11,850
So let's say I'm saying I would like to go on my next vacation.

22
00:01:11,850 --> 00:01:14,730
I'm going on a trip with my wife and kids.

23
00:01:14,730 --> 00:01:16,490
The location should be tropical.

24
00:01:16,770 --> 00:01:18,410
We would love to go to a beach.

25
00:01:18,450 --> 00:01:24,850
I would like a direct flight from my place to LAX, and I have a travel budget of $5,000.

26
00:01:25,210 --> 00:01:27,450
Where should I go on my next vacation?

27
00:01:28,250 --> 00:01:29,490
So now what happens?

28
00:01:29,690 --> 00:01:31,210
I have given some context.

29
00:01:31,210 --> 00:01:37,730
I have given some scenarios, specific things which I am looking for, my interests, my likes and dislikes,

30
00:01:37,930 --> 00:01:39,810
all that have given context of.

31
00:01:40,090 --> 00:01:46,890
And now because of this, the prompt will be the response will be far better, much more relevant and

32
00:01:46,890 --> 00:01:49,650
customized to my particular need.

33
00:01:49,890 --> 00:01:53,210
So this is what we refer to as prompt priming.

34
00:01:53,530 --> 00:01:55,010
Let's look at one more example.

35
00:01:55,610 --> 00:02:02,370
Let's say I'm saying please create three potential titles of my new online course that teaches people

36
00:02:02,410 --> 00:02:03,530
how to use AI.

37
00:02:04,210 --> 00:02:11,850
Now this is again super generic Because ChatGPT is going to give me all kinds of titles possible, which

38
00:02:11,890 --> 00:02:13,010
serves this purpose.

39
00:02:13,850 --> 00:02:18,650
But now, if I give some context where I'm saying that, please create three potential titles for my

40
00:02:18,650 --> 00:02:21,410
new online course that teaches people how to use AI.

41
00:02:21,850 --> 00:02:25,530
Here is an example of some my recent course titles.

42
00:02:25,570 --> 00:02:29,210
Please emulate the style and the written format of these.

43
00:02:29,450 --> 00:02:31,290
So let's say I'm giving some context.

44
00:02:31,290 --> 00:02:33,210
My current courses names are.

45
00:02:33,250 --> 00:02:34,850
Video editing Masterclass.

46
00:02:34,930 --> 00:02:38,730
Edit your videos like a pro cinematography masterclass.

47
00:02:38,730 --> 00:02:40,410
The complete videography guide.

48
00:02:40,570 --> 00:02:45,650
So now when I give some context like this, the outputs will be far better.

49
00:02:45,970 --> 00:02:52,490
The tool will emulate the writing style or in this particular examples which I have shared and will

50
00:02:52,490 --> 00:02:54,290
give me responses based on that.

51
00:02:54,890 --> 00:02:59,890
So this is how you have to keep this in mind, that whenever you are giving a prompt to ChatGPT, we

52
00:02:59,890 --> 00:03:07,290
have to give context information with it as well so that you get the most specific desired response

53
00:03:07,290 --> 00:03:07,970
out of it.