WEBVTT

1
00:00:01.080 --> 00:00:03.000
<v Speaker 1>How'd you like to listen to dot net rocks with

2
00:00:03.040 --> 00:00:07.879
<v Speaker 1>no ads? Easy? Become a patron for just five dollars

3
00:00:07.919 --> 00:00:10.800
<v Speaker 1>a month. You get access to a private RSS feed

4
00:00:10.839 --> 00:00:14.279
<v Speaker 1>where all the shows have no ads. Twenty dollars a month,

5
00:00:14.279 --> 00:00:16.920
<v Speaker 1>we'll get you that and a special dot net Rocks

6
00:00:16.960 --> 00:00:21.000
<v Speaker 1>patron mug. Sign up now at Patreon dot dot NetRocks

7
00:00:21.120 --> 00:00:36.399
<v Speaker 1>dot com. Hey, welcome back to dot net rocks. I'm

8
00:00:36.479 --> 00:00:38.960
<v Speaker 1>Carl Franklin and I'materi Comp. You are here for your

9
00:00:39.039 --> 00:00:42.520
<v Speaker 1>dot net keeeking out, listening, pleasure and all that stuff,

10
00:00:42.640 --> 00:00:45.280
<v Speaker 1>all the things, all the things anything you want to

11
00:00:45.280 --> 00:00:46.560
<v Speaker 1>announce today, buddy.

12
00:00:46.520 --> 00:00:49.759
<v Speaker 2>No, Well let me I told you earlier. But yeah,

13
00:00:49.759 --> 00:00:52.479
<v Speaker 2>I know we got a puppy. Okay, because you know,

14
00:00:52.600 --> 00:00:55.640
<v Speaker 2>having a grandchild wasn't enough, we also need a puppy. Yeah,

15
00:00:55.759 --> 00:00:59.960
<v Speaker 2>so I've managed to tie this while she's at yoga.

16
00:01:00.079 --> 00:01:01.880
<v Speaker 2>Got to have the puppy asleep.

17
00:01:01.960 --> 00:01:04.959
<v Speaker 1>So wait, Manute, I thought you were swearing off dogs

18
00:01:05.400 --> 00:01:06.200
<v Speaker 1>after Zach.

19
00:01:06.640 --> 00:01:09.799
<v Speaker 2>Listen, I already had the perfect dog was seventeen years.

20
00:01:09.920 --> 00:01:11.799
<v Speaker 2>Don't need it down a dog. I didn't need that dog,

21
00:01:11.920 --> 00:01:14.680
<v Speaker 2>to be clear. But sometimes sometimes you're out numbered one

22
00:01:14.680 --> 00:01:23.719
<v Speaker 2>to one, you know, Oh that's great that it's really

23
00:01:23.760 --> 00:01:27.560
<v Speaker 2>got to be her dog this time. So I'm doing

24
00:01:27.599 --> 00:01:29.439
<v Speaker 2>the only logical thing I can do, which is good

25
00:01:29.439 --> 00:01:34.519
<v Speaker 2>to Australia for three weeks. Okay, I'm leaving on Thursday,

26
00:01:34.599 --> 00:01:36.680
<v Speaker 2>so I'm literally I'm gonna go away for three weeks

27
00:01:36.680 --> 00:01:37.840
<v Speaker 2>and hopefully.

28
00:01:37.560 --> 00:01:38.840
<v Speaker 1>What kind of puppy is it?

29
00:01:38.840 --> 00:01:41.920
<v Speaker 2>It's a it's a mix of Ausi Shepherd and border

30
00:01:42.000 --> 00:01:44.480
<v Speaker 2>collie and some poodle and some burnies, a little bit

31
00:01:44.480 --> 00:01:44.840
<v Speaker 2>of everything.

32
00:01:44.840 --> 00:01:46.840
<v Speaker 1>It's Oh my gosh, it's a cute little.

33
00:01:46.719 --> 00:01:48.040
<v Speaker 2>Dog, no two ways about it.

34
00:01:48.079 --> 00:01:50.120
<v Speaker 1>But you know, does it have an identity complex?

35
00:01:50.200 --> 00:01:52.599
<v Speaker 2>It's got springs and its legs is when it's gone.

36
00:01:52.680 --> 00:01:53.040
<v Speaker 1>Wow.

37
00:01:53.560 --> 00:01:56.120
<v Speaker 2>Okay, man, we're in the early stage needle teeth and

38
00:01:56.159 --> 00:01:58.760
<v Speaker 2>pee on the floor and bit by bit figuring it out.

39
00:01:58.920 --> 00:02:00.599
<v Speaker 2>I already took a tick off for her because she

40
00:02:00.640 --> 00:02:01.359
<v Speaker 2>was out in the lawn.

41
00:02:01.599 --> 00:02:07.120
<v Speaker 1>What's her name, Jojo short for Josephine Lily. Oh she

42
00:02:07.159 --> 00:02:09.439
<v Speaker 1>doesn't look like a deep fried potato wedge then.

43
00:02:09.439 --> 00:02:13.400
<v Speaker 2>No, not like some dogs, you know. Oh, she's a

44
00:02:13.400 --> 00:02:16.319
<v Speaker 2>cute little dog but cool. And she's got that French

45
00:02:16.360 --> 00:02:19.120
<v Speaker 2>twying tour so that hits the crazy name, right, anyway

46
00:02:19.240 --> 00:02:21.840
<v Speaker 2>I got, I got worse problems like, yeah, it makes her.

47
00:02:21.919 --> 00:02:23.960
<v Speaker 2>If it makes she who must be obeyed happy, then

48
00:02:24.080 --> 00:02:25.759
<v Speaker 2>I'm happy to do fantastic.

49
00:02:25.800 --> 00:02:28.360
<v Speaker 1>All right, Well, let's jump into it with a better

50
00:02:28.400 --> 00:02:28.960
<v Speaker 1>NO framework.

51
00:02:29.039 --> 00:02:37.759
<v Speaker 2>All right, what do you got?

52
00:02:37.840 --> 00:02:41.479
<v Speaker 1>All right? Well, in honor of our AI guest today, Vishwaesle,

53
00:02:41.759 --> 00:02:44.840
<v Speaker 1>who's been on the show several times before, many times,

54
00:02:45.439 --> 00:02:48.919
<v Speaker 1>I found a trending repo on GitHub. It's called krillin

55
00:02:49.080 --> 00:02:53.759
<v Speaker 1>ai k r I l l I n AI or

56
00:02:54.000 --> 00:02:57.960
<v Speaker 1>a one, depending on your point of reference. It's an

57
00:02:58.000 --> 00:03:02.039
<v Speaker 1>AI audio and video translation and dubbing tool. So let

58
00:03:02.039 --> 00:03:05.280
<v Speaker 1>me just read the paragraph here now, just does a caveat.

59
00:03:05.319 --> 00:03:07.719
<v Speaker 1>I have not downloaded it. I don't know if it's

60
00:03:07.719 --> 00:03:09.919
<v Speaker 1>any good, but it is trending, so that tells me

61
00:03:10.000 --> 00:03:13.240
<v Speaker 1>that people kind of like it. Crillin ai is an

62
00:03:13.240 --> 00:03:17.479
<v Speaker 1>all in one solution for effortless video localization and enhancement.

63
00:03:18.120 --> 00:03:22.759
<v Speaker 1>This minimalist yet powerful tool handles everything from translation, dubbing

64
00:03:22.840 --> 00:03:27.039
<v Speaker 1>to voice cloning. I see there's no the commas don't

65
00:03:27.080 --> 00:03:31.800
<v Speaker 1>work here. Translation comma dubbing to voice cloning comma. I

66
00:03:31.800 --> 00:03:36.000
<v Speaker 1>would say, everything from translation and dubbing to voice cloning.

67
00:03:36.080 --> 00:03:40.960
<v Speaker 1>Formatting seamlessly converting videos between landscape in portrait modes for

68
00:03:41.080 --> 00:03:47.439
<v Speaker 1>optimal display across all content platforms. YouTube TikTok, Billy Billy, Duian,

69
00:03:47.719 --> 00:03:52.400
<v Speaker 1>we chat channel, Red Note Kawai show. With its end

70
00:03:52.439 --> 00:03:56.400
<v Speaker 1>to end workflow, crillion Ai transforms raw footage into polished,

71
00:03:56.439 --> 00:04:01.520
<v Speaker 1>platform ready content and just a few clicks. So that's interesting.

72
00:04:01.560 --> 00:04:06.159
<v Speaker 1>You know, translation a localization anyway is one thing in

73
00:04:06.240 --> 00:04:11.280
<v Speaker 1>the world of software and web apps that we know

74
00:04:11.840 --> 00:04:18.360
<v Speaker 1>very well. But dubbing and you know, translating video that

75
00:04:18.519 --> 00:04:19.519
<v Speaker 1>has audio in it.

76
00:04:19.639 --> 00:04:21.680
<v Speaker 2>Well, the voice cloning one is the craziest one where

77
00:04:21.680 --> 00:04:25.600
<v Speaker 2>I take the voice of the person speaking and then

78
00:04:25.800 --> 00:04:27.480
<v Speaker 2>change their language, but it still.

79
00:04:27.279 --> 00:04:28.920
<v Speaker 1>Sounds like them change the language.

80
00:04:29.120 --> 00:04:31.560
<v Speaker 2>Yeah, that's nuts, but it's very jen Ai.

81
00:04:31.680 --> 00:04:34.079
<v Speaker 1>Yeah, it's nuts, but you know that's the stuff that

82
00:04:34.360 --> 00:04:36.959
<v Speaker 1>we get to see. This is the world we live

83
00:04:37.000 --> 00:04:38.759
<v Speaker 1>in now, so world we live in. So that's what

84
00:04:38.839 --> 00:04:40.600
<v Speaker 1>I got. Richard, who's talking to us.

85
00:04:40.480 --> 00:04:43.879
<v Speaker 2>Today, grabbed a comment off of show nineteen forty four

86
00:04:44.199 --> 00:04:46.199
<v Speaker 2>just a few weeks ago with our friend Jody Bershall,

87
00:04:46.279 --> 00:04:50.240
<v Speaker 2>doctor Jody Bernshall. Yeah's got a few comments on the show,

88
00:04:50.240 --> 00:04:52.519
<v Speaker 2>and this one's from Joshua hillar Up, one of our regulars.

89
00:04:52.560 --> 00:04:54.079
<v Speaker 2>I'm pretty sure already has a copy of Means to

90
00:04:54.120 --> 00:04:57.560
<v Speaker 2>go By, But you know, Joshua, thank you. And he said,

91
00:04:57.759 --> 00:05:00.800
<v Speaker 2>I'm thinking about the non deterministing aspects of LMS, and

92
00:05:00.839 --> 00:05:03.199
<v Speaker 2>what's frustrating is that there's been many decades of computer

93
00:05:03.240 --> 00:05:06.959
<v Speaker 2>science research on software correctness. It just never seems to

94
00:05:07.000 --> 00:05:10.000
<v Speaker 2>get used in the industry because it's too hard to learn.

95
00:05:10.079 --> 00:05:12.439
<v Speaker 2>If you did that in air quotes, too hard to learn.

96
00:05:13.279 --> 00:05:16.079
<v Speaker 2>LLLMS work really well at covering that hard work, and

97
00:05:16.120 --> 00:05:17.759
<v Speaker 2>I don't think it's as hard as people claim, at

98
00:05:17.839 --> 00:05:20.759
<v Speaker 2>least in the beginning. My hope is assuming enough money

99
00:05:20.759 --> 00:05:23.120
<v Speaker 2>put into developing these languages and tools to make the

100
00:05:23.199 --> 00:05:25.240
<v Speaker 2>use of that research. Now there's such an obvious use

101
00:05:25.279 --> 00:05:27.279
<v Speaker 2>case for it. And we probably should have talked about

102
00:05:27.319 --> 00:05:31.959
<v Speaker 2>this more with Jody too, Joshua, because she does come

103
00:05:32.040 --> 00:05:35.120
<v Speaker 2>from that I hate to say old school, but because

104
00:05:35.120 --> 00:05:38.199
<v Speaker 2>that would be like five years ago form of machine

105
00:05:38.279 --> 00:05:42.600
<v Speaker 2>learning where quality and accuracy, you know, validation was a

106
00:05:42.720 --> 00:05:44.079
<v Speaker 2>huge part of the job.

107
00:05:44.279 --> 00:05:47.000
<v Speaker 1>That's right. I remember talking to Seth Warez and he said,

108
00:05:47.079 --> 00:05:49.360
<v Speaker 1>ninety percent of my time is cleaning the data.

109
00:05:49.480 --> 00:05:53.839
<v Speaker 2>Yeah, to get to a meaningful quality. So there is

110
00:05:53.839 --> 00:05:56.560
<v Speaker 2>certainly some pressure on that, but we're we're bringing a

111
00:05:56.560 --> 00:06:00.519
<v Speaker 2>lot of people in without a lot of experience the space,

112
00:06:00.800 --> 00:06:03.120
<v Speaker 2>and they are not concerned about these things and they

113
00:06:03.120 --> 00:06:03.439
<v Speaker 2>should be.

114
00:06:03.600 --> 00:06:03.879
<v Speaker 3>M H.

115
00:06:04.480 --> 00:06:06.439
<v Speaker 2>So as usual, Josha, thank you so much for your

116
00:06:06.439 --> 00:06:08.560
<v Speaker 2>great comment, and a coffee of music. Cobi is on

117
00:06:08.600 --> 00:06:10.160
<v Speaker 2>its way to you. And if you'd like a copy music,

118
00:06:10.160 --> 00:06:11.759
<v Speaker 2>go bay rte a comment on the website at dot

119
00:06:11.800 --> 00:06:14.279
<v Speaker 2>netrongs dot com or on the facebooks. We publish every

120
00:06:14.279 --> 00:06:15.560
<v Speaker 2>show there and if you comment there and I've read

121
00:06:15.680 --> 00:06:17.439
<v Speaker 2>on the show, we'll send you a copy music O

122
00:06:17.519 --> 00:06:18.199
<v Speaker 2>bay music to.

123
00:06:18.240 --> 00:06:20.959
<v Speaker 1>Code by dot net. That is how you can find it.

124
00:06:20.959 --> 00:06:23.839
<v Speaker 1>It's still going strong. Track twenty two is available now

125
00:06:23.920 --> 00:06:25.920
<v Speaker 1>and of course you get the whole collection MP three

126
00:06:26.079 --> 00:06:32.720
<v Speaker 1>Flak or Wave. This is episode nineteen forty seven, and

127
00:06:32.839 --> 00:06:34.879
<v Speaker 1>so I can just give a little brief summary here

128
00:06:34.879 --> 00:06:37.439
<v Speaker 1>about what happened that year. It was a year of

129
00:06:37.480 --> 00:06:42.839
<v Speaker 1>significant global transformations. Of course, India and Pakistan gained independence

130
00:06:42.839 --> 00:06:46.279
<v Speaker 1>from British rule, and the Marshall Plan was initiated to

131
00:06:46.319 --> 00:06:50.879
<v Speaker 1>help rebuild war torn Europe. In the United States, Jackie

132
00:06:50.959 --> 00:06:55.639
<v Speaker 1>Robinson broke baseball's color barrier, and Chuck Yeger broke the

133
00:06:55.639 --> 00:06:59.959
<v Speaker 1>sound barrier. Also, the Truman Doctrine, which pledged US support

134
00:07:00.120 --> 00:07:05.000
<v Speaker 1>for nations threatened by communism, was established, which signaled the

135
00:07:05.040 --> 00:07:08.040
<v Speaker 1>beginning of the Cold War. You got anything to add?

136
00:07:08.839 --> 00:07:12.199
<v Speaker 2>Nineteen forty seven is the year the invention of the transistors.

137
00:07:12.360 --> 00:07:16.639
<v Speaker 2>That's bartying Britain and Shockley with the first point content

138
00:07:16.639 --> 00:07:19.120
<v Speaker 2>transi should have been talked about for years, but semiconductor

139
00:07:19.360 --> 00:07:22.240
<v Speaker 2>making pure material semi conducts were hard. A lot of

140
00:07:22.279 --> 00:07:25.439
<v Speaker 2>that came out of the war. And so what's funny

141
00:07:25.480 --> 00:07:27.079
<v Speaker 2>is reading some of the documentation at the time and

142
00:07:27.079 --> 00:07:28.279
<v Speaker 2>they weren't sure if it was actually going to be

143
00:07:28.319 --> 00:07:30.800
<v Speaker 2>all that useful. Interesting, you know, because vacuum tubes did

144
00:07:30.839 --> 00:07:33.120
<v Speaker 2>such a good job and this thing did not have

145
00:07:33.160 --> 00:07:36.120
<v Speaker 2>the potential the vacuum two did because the materials weren't

146
00:07:36.160 --> 00:07:38.120
<v Speaker 2>quite good enough. Yet they had no idea what was

147
00:07:38.160 --> 00:07:40.600
<v Speaker 2>about to happen. Huh No, but they you know, Shockley

148
00:07:40.600 --> 00:07:44.360
<v Speaker 2>would go on with Fairshire Semiconductor to help make the

149
00:07:44.360 --> 00:07:46.800
<v Speaker 2>originalized sees with Robert Noise and all those like. All

150
00:07:46.839 --> 00:07:49.560
<v Speaker 2>of that comes from there. But there's the beginning and

151
00:07:49.879 --> 00:07:53.759
<v Speaker 2>one other fallout of the war raytheon's radar range, the

152
00:07:53.839 --> 00:07:55.040
<v Speaker 2>first microwave oven.

153
00:07:55.279 --> 00:07:58.399
<v Speaker 1>Wow, yeah, radar range, that's what they called it.

154
00:07:58.480 --> 00:08:00.759
<v Speaker 2>They called it. They called it the radar range literally

155
00:08:00.800 --> 00:08:05.240
<v Speaker 2>because some of the early earlier technicians working on radar

156
00:08:05.360 --> 00:08:07.920
<v Speaker 2>noticed that the chocolate bars in their pockets would melt

157
00:08:07.920 --> 00:08:10.199
<v Speaker 2>when they got too close to the magnetrons.

158
00:08:10.399 --> 00:08:13.279
<v Speaker 1>Okay, so how safe was this thing? It doesn't sound

159
00:08:13.319 --> 00:08:14.360
<v Speaker 1>like it was very safe.

160
00:08:14.439 --> 00:08:18.879
<v Speaker 2>It's it can be is superheating the water, so it

161
00:08:18.920 --> 00:08:21.040
<v Speaker 2>will you will get water burns if you get too

162
00:08:21.079 --> 00:08:21.560
<v Speaker 2>close to it.

163
00:08:21.720 --> 00:08:25.519
<v Speaker 1>Yeah, right, And but radiation poisoning. Were they worried about that?

164
00:08:25.639 --> 00:08:28.759
<v Speaker 2>No? No, still, there's no I you know, ionizing radiation

165
00:08:28.839 --> 00:08:31.399
<v Speaker 2>is more complicated than this. This is just microwaves, just

166
00:08:31.519 --> 00:08:34.960
<v Speaker 2>like a bright light, and it can burn you because

167
00:08:35.000 --> 00:08:39.279
<v Speaker 2>it vibrates the water molecules, and those water moleoscules, once

168
00:08:39.320 --> 00:08:41.039
<v Speaker 2>they get to a certain temperature, are going to damage

169
00:08:41.039 --> 00:08:41.759
<v Speaker 2>the tissues they're in.

170
00:08:41.919 --> 00:08:44.799
<v Speaker 1>Okay, all right, let's bring Vishwaz back on dot net

171
00:08:44.879 --> 00:08:46.159
<v Speaker 1>rocks for the empteenth time.

172
00:08:46.519 --> 00:08:49.360
<v Speaker 2>It's at number seventeen, by the way I counted. Hey,

173
00:08:49.480 --> 00:08:52.519
<v Speaker 2>well that's umpteen, isn't it. That's umpteenth. Yeah, we're ext

174
00:08:52.759 --> 00:08:53.720
<v Speaker 2>the umpteeth category.

175
00:08:54.639 --> 00:08:58.000
<v Speaker 1>Bishwaslele serves as co founder and CEO at p wind

176
00:08:58.039 --> 00:09:01.919
<v Speaker 1>dot AI, A noted the industry speaker and author. Mister

177
00:09:02.000 --> 00:09:07.600
<v Speaker 1>Lealey is the Microsoft Regional Director for Washington, DC. Welcome back, Vishwas.

178
00:09:07.720 --> 00:09:10.799
<v Speaker 1>So it's new in the world of AI in vishwas Land.

179
00:09:11.080 --> 00:09:15.399
<v Speaker 3>Well, i've been. We talked to you last year, very

180
00:09:15.440 --> 00:09:21.440
<v Speaker 3>focused still on trying to grow this Jennai startup idea

181
00:09:21.480 --> 00:09:22.480
<v Speaker 3>that we started working.

182
00:09:22.519 --> 00:09:26.200
<v Speaker 2>Yeah, you left your longtime company to do this startup.

183
00:09:27.000 --> 00:09:30.600
<v Speaker 3>Yes, I left. I was there for thirty years the

184
00:09:30.639 --> 00:09:33.960
<v Speaker 3>previous company. How's it going last sixteen years? Is the CTO? Well,

185
00:09:34.000 --> 00:09:36.519
<v Speaker 3>it's going. It's going well. I mean, as you can

186
00:09:36.559 --> 00:09:39.559
<v Speaker 3>expect as a startup. World is all about good days

187
00:09:39.600 --> 00:09:42.200
<v Speaker 3>and bad days. But it has been very exciting a

188
00:09:42.200 --> 00:09:44.000
<v Speaker 3>lot of learning and we are growing.

189
00:09:44.159 --> 00:09:44.600
<v Speaker 1>That's cool.

190
00:09:44.639 --> 00:09:46.919
<v Speaker 2>Now. If I recall when we talked last time, you

191
00:09:46.960 --> 00:09:52.120
<v Speaker 2>were focused on generating responses to requests for proposal for

192
00:09:52.159 --> 00:09:55.679
<v Speaker 2>the RFPs. That's right, right, which in government land can

193
00:09:55.720 --> 00:09:58.320
<v Speaker 2>be absolutely massive, like hundreds of pages.

194
00:09:58.399 --> 00:10:01.440
<v Speaker 3>That's right, that's right, and that's what we have been

195
00:10:01.480 --> 00:10:07.279
<v Speaker 3>focused on. We call ourselves a thoughtful copilot. And I'll

196
00:10:07.480 --> 00:10:10.480
<v Speaker 3>explain the word thoughtful in a second. We call ourselves

197
00:10:10.559 --> 00:10:15.039
<v Speaker 3>thoughtful copilot for proposal writers. So what that means is

198
00:10:15.480 --> 00:10:18.759
<v Speaker 3>we will take your information. You're you know in the

199
00:10:18.879 --> 00:10:23.960
<v Speaker 3>years past you have responded to RFP documents that you've done.

200
00:10:24.320 --> 00:10:28.440
<v Speaker 3>You have competency documents, you have some fancy documents like

201
00:10:28.519 --> 00:10:32.600
<v Speaker 3>spars and for those who don't know this already, se

202
00:10:32.679 --> 00:10:35.960
<v Speaker 3>parts are documents that government agencies give you to validate

203
00:10:36.039 --> 00:10:39.519
<v Speaker 3>your experience. So, needless to say, you have a collection

204
00:10:39.639 --> 00:10:45.320
<v Speaker 3>of documents and now a new RFP comes along. And

205
00:10:45.399 --> 00:10:48.159
<v Speaker 3>these RFP documents can be, as you said, Richard, can

206
00:10:48.200 --> 00:10:51.279
<v Speaker 3>be really complex, can be fifteen hundred pages long with

207
00:10:51.320 --> 00:10:54.919
<v Speaker 3>different sections in them. So for example, they might be

208
00:10:54.960 --> 00:10:59.080
<v Speaker 3>a section which describes how should you respond to the RFP,

209
00:11:00.120 --> 00:11:04.519
<v Speaker 3>maybe a section which talks about what would be the

210
00:11:04.559 --> 00:11:08.600
<v Speaker 3>evaluation criteria for somebody looking at your RFB. And then

211
00:11:09.120 --> 00:11:11.440
<v Speaker 3>there may be another section which talks about all the

212
00:11:11.480 --> 00:11:12.559
<v Speaker 3>things that you must do.

213
00:11:12.879 --> 00:11:14.559
<v Speaker 1>So that's all the boring stuff.

214
00:11:14.799 --> 00:11:16.000
<v Speaker 3>Our job is other boring.

215
00:11:16.039 --> 00:11:18.720
<v Speaker 1>You Usually the stuff that you want to read last,

216
00:11:19.600 --> 00:11:20.639
<v Speaker 1>you have to read it first.

217
00:11:20.799 --> 00:11:24.919
<v Speaker 3>Yes, yes, and all this is part of something called

218
00:11:24.919 --> 00:11:28.519
<v Speaker 3>the Federal Acquisition regulation, which something came out many many

219
00:11:28.559 --> 00:11:33.440
<v Speaker 3>years ago, has different sections related to different parts of solicitation.

220
00:11:34.039 --> 00:11:38.679
<v Speaker 3>So what we specialize in is, now that we have

221
00:11:38.759 --> 00:11:44.039
<v Speaker 3>your knowledge repository built out, we deeply understand the solicitations

222
00:11:44.080 --> 00:11:47.519
<v Speaker 3>that comes in, and then we help you write a

223
00:11:47.639 --> 00:11:54.639
<v Speaker 3>draft quickly solely based on your information, so that we

224
00:11:54.679 --> 00:11:56.759
<v Speaker 3>can give you this first draft quickly and then you

225
00:11:56.799 --> 00:11:59.720
<v Speaker 3>can build on it. And there's a very interesting saying

226
00:11:59.759 --> 00:12:03.519
<v Speaker 3>in the proposal world that proposals are often one at

227
00:12:03.559 --> 00:12:07.279
<v Speaker 3>the end Richard that you know, you leave yourself enough

228
00:12:07.360 --> 00:12:10.879
<v Speaker 3>time to do some creative thinking, then you goos to

229
00:12:10.879 --> 00:12:16.080
<v Speaker 3>your competition, you do some innovative thinking. But the sad

230
00:12:16.120 --> 00:12:18.559
<v Speaker 3>reality of proposal writing is you never reach the end.

231
00:12:18.600 --> 00:12:20.840
<v Speaker 3>You spend all your time in the middle, sure, just

232
00:12:20.919 --> 00:12:24.639
<v Speaker 3>trying to get a good proposal out. So our value

233
00:12:24.639 --> 00:12:28.399
<v Speaker 3>proposition is very simple. Can we accelerate the initial stages

234
00:12:28.480 --> 00:12:31.559
<v Speaker 3>so that we give you more polishing and thinking time.

235
00:12:31.879 --> 00:12:36.840
<v Speaker 3>And that's ultimately what improves your probability of winning And

236
00:12:36.879 --> 00:12:40.240
<v Speaker 3>which is the name of per company, peven dot Ai.

237
00:12:40.279 --> 00:12:43.279
<v Speaker 1>The probability of winning. Mm hmm, that's really good.

238
00:12:43.720 --> 00:12:46.440
<v Speaker 2>Well, part of this again, we're calling the previous show

239
00:12:46.639 --> 00:12:49.240
<v Speaker 2>was being able to respond to more RFP so you

240
00:12:49.320 --> 00:12:53.080
<v Speaker 2>have more chances at work opportunities. The thing, of course,

241
00:12:53.080 --> 00:12:57.279
<v Speaker 2>has scared me is you're committing to stuff inside this

242
00:12:57.480 --> 00:13:00.399
<v Speaker 2>RFP yep. And so if the tool is already the

243
00:13:00.480 --> 00:13:03.080
<v Speaker 2>text for it, and it creates a commitment for you, you

244
00:13:03.039 --> 00:13:05.440
<v Speaker 2>can't deliver on like you could be in serious trouble.

245
00:13:05.519 --> 00:13:09.399
<v Speaker 1>I think that's why you said creates a rough draft, right, Yes,

246
00:13:09.559 --> 00:13:11.879
<v Speaker 1>you can't just like say, okay, here it is, send

247
00:13:11.960 --> 00:13:12.320
<v Speaker 1>it off.

248
00:13:12.960 --> 00:13:15.960
<v Speaker 3>See. Yeah, And that's that's the thing.

249
00:13:16.279 --> 00:13:18.639
<v Speaker 1>Yeah, you certainly have to know what you're saying.

250
00:13:18.879 --> 00:13:21.559
<v Speaker 3>Yeah, no, Carl, that's a very good, good catch there.

251
00:13:21.600 --> 00:13:23.919
<v Speaker 3>That's why I said draft. We're trying to improve the

252
00:13:24.000 --> 00:13:26.159
<v Speaker 3>quality of drafts so that you know, you can focus

253
00:13:26.200 --> 00:13:28.639
<v Speaker 3>on other things. But at the end of the day,

254
00:13:28.720 --> 00:13:31.879
<v Speaker 3>make no mistake, you're putting your name down on the proposal.

255
00:13:32.000 --> 00:13:33.519
<v Speaker 2>Sure, so you should read it.

256
00:13:34.240 --> 00:13:34.960
<v Speaker 3>You should read it.

257
00:13:35.240 --> 00:13:38.000
<v Speaker 1>So it's kind of like having a you know, a

258
00:13:38.200 --> 00:13:41.279
<v Speaker 1>manager under you or a secretary or somebody who knows

259
00:13:41.320 --> 00:13:43.639
<v Speaker 1>your business say hey, you can just say look through

260
00:13:43.679 --> 00:13:47.320
<v Speaker 1>this RFP and give me a rough draft and it

261
00:13:47.639 --> 00:13:51.480
<v Speaker 1>might have all the accurate information from your side, but

262
00:13:51.879 --> 00:13:54.080
<v Speaker 1>you know, you're the one that's got to commit to

263
00:13:54.360 --> 00:13:58.840
<v Speaker 1>what you're agreeing to. And so I guess my question

264
00:13:58.879 --> 00:14:00.559
<v Speaker 1>here is can you go back. I can have a

265
00:14:00.600 --> 00:14:05.799
<v Speaker 1>conversation with this bot if you will, and say, you know,

266
00:14:05.919 --> 00:14:10.679
<v Speaker 1>why did you why did you commit me to doing X?

267
00:14:11.519 --> 00:14:13.480
<v Speaker 1>You know, and have it give you an answer from

268
00:14:13.519 --> 00:14:14.080
<v Speaker 1>your data.

269
00:14:14.440 --> 00:14:19.200
<v Speaker 3>That's a that's a good point. We have an intermediate stage,

270
00:14:19.279 --> 00:14:24.200
<v Speaker 3>and this is the pattern patent should say that we filed.

271
00:14:24.279 --> 00:14:30.279
<v Speaker 3>We have a provisional patent. Yeah, so what's It's not

272
00:14:30.519 --> 00:14:35.320
<v Speaker 3>like the bot is just or the copilot in this

273
00:14:35.360 --> 00:14:37.519
<v Speaker 3>case of our proposal, copilot is just going to look

274
00:14:37.519 --> 00:14:40.799
<v Speaker 3>at your documents and just spit out one hundred page

275
00:14:40.840 --> 00:14:44.200
<v Speaker 3>document that it thinks that you should be doing. That's

276
00:14:44.240 --> 00:14:47.039
<v Speaker 3>a recipe for disaster because you go pick up things

277
00:14:47.320 --> 00:14:49.600
<v Speaker 3>that you don't want it to do. And there's a

278
00:14:49.720 --> 00:14:53.279
<v Speaker 3>very important threshold where you really have to save time

279
00:14:53.320 --> 00:14:55.200
<v Speaker 3>to people. If people say, hey, I have to first

280
00:14:55.240 --> 00:14:59.639
<v Speaker 3>read your silly forty documents that you generated and then

281
00:14:59.679 --> 00:15:01.720
<v Speaker 3>I have to rewrite it. Thank you, I'm not going

282
00:15:01.720 --> 00:15:03.879
<v Speaker 3>to use this tool. So there's a very important threshold

283
00:15:03.879 --> 00:15:07.639
<v Speaker 3>that you have to cross. So in our model. The

284
00:15:08.200 --> 00:15:11.240
<v Speaker 3>patent that we have filed is called object based writing.

285
00:15:11.799 --> 00:15:16.840
<v Speaker 3>Oh wow, okay, and what that means is and what

286
00:15:16.879 --> 00:15:21.200
<v Speaker 3>that means is that once let's say the r FP

287
00:15:21.279 --> 00:15:25.000
<v Speaker 3>aries and we have gone in and tried to analyze it,

288
00:15:25.840 --> 00:15:29.200
<v Speaker 3>and we create something called the flight plan. And why

289
00:15:29.240 --> 00:15:32.440
<v Speaker 3>are we calling it flight plan because we are the

290
00:15:32.480 --> 00:15:36.679
<v Speaker 3>copilot for proposal writers and in the aviation industry, obviously

291
00:15:36.759 --> 00:15:39.240
<v Speaker 3>there's a very important concept called flight plan that is

292
00:15:39.360 --> 00:15:42.799
<v Speaker 3>used for communication. So what we do is we try

293
00:15:42.840 --> 00:15:46.600
<v Speaker 3>to deeply using AI models, try to deeply understand the RFP,

294
00:15:46.879 --> 00:15:53.759
<v Speaker 3>understand the evaluation criteria, understand the instructions, and we manifest

295
00:15:53.879 --> 00:15:58.039
<v Speaker 3>that into a UI pattern called the flight plan. So

296
00:15:58.159 --> 00:16:01.000
<v Speaker 3>you go in and then you intera to the flight plan,

297
00:16:01.440 --> 00:16:05.799
<v Speaker 3>and this is where you go and say that I

298
00:16:05.879 --> 00:16:10.919
<v Speaker 3>want you to use this architecture. And let's just take

299
00:16:10.960 --> 00:16:14.000
<v Speaker 3>a concrete example that our listeners can follow along. Let's

300
00:16:14.000 --> 00:16:17.720
<v Speaker 3>say the RFP is about a records management solution, right,

301
00:16:18.399 --> 00:16:20.440
<v Speaker 3>and you may have done ten different types of records

302
00:16:20.440 --> 00:16:24.279
<v Speaker 3>management solution, maybe use SharePoint for that, maybe used some

303
00:16:24.679 --> 00:16:28.759
<v Speaker 3>purpose built records management solution things for that.

304
00:16:29.000 --> 00:16:33.440
<v Speaker 1>By the way, I'm sorry, yep, yep.

305
00:16:33.639 --> 00:16:36.240
<v Speaker 3>So if you had to do that. So once the

306
00:16:36.279 --> 00:16:39.519
<v Speaker 3>flight plan comes in, what we do is we say, hey,

307
00:16:40.759 --> 00:16:42.879
<v Speaker 3>we think that you have used these are three or

308
00:16:42.879 --> 00:16:45.960
<v Speaker 3>four architectural patterns to go after this kind of work.

309
00:16:47.519 --> 00:16:51.559
<v Speaker 3>Here's a suggestion, but please you need to update that

310
00:16:52.279 --> 00:16:56.440
<v Speaker 3>with maybe, like you said written Carl, SharePoint is not

311
00:16:56.480 --> 00:16:58.639
<v Speaker 3>the right solution. You want to do something else, so

312
00:16:58.720 --> 00:17:01.879
<v Speaker 3>replace that, And in that flight plan you tell us

313
00:17:01.919 --> 00:17:06.400
<v Speaker 3>that you know, I'm wanting to undertake this task using

314
00:17:06.519 --> 00:17:10.319
<v Speaker 3>this architectural pattern. And then you also in the flight

315
00:17:10.359 --> 00:17:14.880
<v Speaker 3>plan you get to tell people do you really understand

316
00:17:15.200 --> 00:17:17.680
<v Speaker 3>the pain points? Do you really understand the motivation of

317
00:17:17.720 --> 00:17:22.000
<v Speaker 3>the buyer? Why did they issue the RFP? And do

318
00:17:22.079 --> 00:17:24.720
<v Speaker 3>you why do you why do you think you're differentiated

319
00:17:24.759 --> 00:17:28.079
<v Speaker 3>than other competitors? If all your differentiation is or we

320
00:17:28.160 --> 00:17:31.359
<v Speaker 3>have all the certifications in place, well, every other competitor

321
00:17:31.400 --> 00:17:33.799
<v Speaker 3>is going to say that. So we force you to

322
00:17:33.920 --> 00:17:39.960
<v Speaker 3>think critically about the response and at a higher level.

323
00:17:40.039 --> 00:17:43.000
<v Speaker 1>So is it kind of like an outline that you

324
00:17:43.039 --> 00:17:46.880
<v Speaker 1>can interact with? It seems like it is. You you

325
00:17:46.920 --> 00:17:50.480
<v Speaker 1>have a model for a conversation with the AI. Yes,

326
00:17:50.920 --> 00:17:53.880
<v Speaker 1>so yes to this, no to this? What's about that?

327
00:17:54.160 --> 00:17:57.079
<v Speaker 3>Yes? And you know, so you're setting think of this

328
00:17:57.119 --> 00:18:00.200
<v Speaker 3>as that you're setting the vision for the response that

329
00:18:00.240 --> 00:18:03.880
<v Speaker 3>you want to generate. Right, you're talking about your competitors,

330
00:18:03.880 --> 00:18:06.000
<v Speaker 3>you're talking about your win themes, you're talking about your

331
00:18:06.039 --> 00:18:10.000
<v Speaker 3>pain points, you're talking about your solutioning strategy, and on

332
00:18:10.039 --> 00:18:12.079
<v Speaker 3>and and on. There are lots of data structures that

333
00:18:12.119 --> 00:18:16.720
<v Speaker 3>we capture, and then once we have that information, then

334
00:18:16.799 --> 00:18:20.559
<v Speaker 3>we try to in a thoughtful manner, try to infuse

335
00:18:21.279 --> 00:18:23.680
<v Speaker 3>what you gave us as a direction. Right, if your

336
00:18:23.720 --> 00:18:25.880
<v Speaker 3>capture team, if your salespeople have done a good job

337
00:18:26.200 --> 00:18:28.680
<v Speaker 3>and they weren't their salary, they probably on the golf

338
00:18:28.680 --> 00:18:32.200
<v Speaker 3>course realized that the key motivation for this RFP was

339
00:18:32.880 --> 00:18:35.240
<v Speaker 3>the pain point this organization is going through is the

340
00:18:35.319 --> 00:18:38.559
<v Speaker 3>last three upgrades were not there, and that key point

341
00:18:39.079 --> 00:18:41.599
<v Speaker 3>AI does not know about or would never know about.

342
00:18:42.000 --> 00:18:45.680
<v Speaker 3>And this will be your capture team. And then you

343
00:18:45.720 --> 00:18:49.079
<v Speaker 3>take that information, you have all of the data structures,

344
00:18:49.799 --> 00:18:52.880
<v Speaker 3>you have your knowledge repository, and I'll talk more about it.

345
00:18:54.480 --> 00:18:57.279
<v Speaker 3>We do a lot of work, and I very much

346
00:18:57.680 --> 00:19:00.599
<v Speaker 3>agree with what you were saying Card earlier about sets comment.

347
00:19:01.039 --> 00:19:06.319
<v Speaker 3>We do a lot of collation, classification, tagging of content

348
00:19:06.400 --> 00:19:09.440
<v Speaker 3>and cleaning of content. So now have you have your content,

349
00:19:09.559 --> 00:19:12.599
<v Speaker 3>We have your vision for how you want to respond,

350
00:19:13.400 --> 00:19:16.720
<v Speaker 3>and then we start drafting your content in a thoughtful manner.

351
00:19:17.319 --> 00:19:21.079
<v Speaker 3>And that drafting is done using best practices. And this

352
00:19:21.160 --> 00:19:24.359
<v Speaker 3>is where we are really fortunate to have Shipley. I

353
00:19:24.559 --> 00:19:27.079
<v Speaker 3>talked about this last time. Shipley is a fifty year

354
00:19:27.119 --> 00:19:30.960
<v Speaker 3>old company which is which taught people how to write

355
00:19:31.119 --> 00:19:34.480
<v Speaker 3>persuasive proposals. That's what they do. They teach classes, they

356
00:19:34.519 --> 00:19:38.519
<v Speaker 3>generate content. So now we have this information, we use

357
00:19:38.599 --> 00:19:42.880
<v Speaker 3>their best practices. And one example would be when you're

358
00:19:42.920 --> 00:19:46.799
<v Speaker 3>responding to an our RFP, be sure about customer centricity.

359
00:19:47.119 --> 00:19:50.599
<v Speaker 3>We talk about customer's problem, but speak to those problems

360
00:19:50.640 --> 00:19:53.640
<v Speaker 3>maybe in your terms without sort of taking ownership of

361
00:19:53.640 --> 00:19:56.480
<v Speaker 3>the problem. And as if you're teaching them right about

362
00:19:56.480 --> 00:20:01.160
<v Speaker 3>active voice, passive voice, and then very important those are

363
00:20:01.200 --> 00:20:05.440
<v Speaker 3>all very important. And then you start with the problem understanding.

364
00:20:05.599 --> 00:20:08.000
<v Speaker 3>Then you say where you have done this kind of work,

365
00:20:08.240 --> 00:20:10.799
<v Speaker 3>you do you have really good past performance about this.

366
00:20:11.440 --> 00:20:14.119
<v Speaker 3>So they are best practices of writing that come in.

367
00:20:14.559 --> 00:20:21.359
<v Speaker 3>And this is why it takes us minutes and hours

368
00:20:21.400 --> 00:20:25.440
<v Speaker 3>to generate the draft, right because you know, I was

369
00:20:25.480 --> 00:20:27.480
<v Speaker 3>joking with you last year when I was the show

370
00:20:27.920 --> 00:20:29.960
<v Speaker 3>that if you went to Chad Gypt and said, CHADGEPT,

371
00:20:30.079 --> 00:20:32.279
<v Speaker 3>this is a very important question. I'm going to ask you,

372
00:20:32.319 --> 00:20:34.920
<v Speaker 3>please think about it for five minutes before you respond.

373
00:20:35.759 --> 00:20:37.839
<v Speaker 3>Chad GPT does not know what to do with the

374
00:20:38.000 --> 00:20:40.920
<v Speaker 3>four minutes and fifty nine seconds, right, because it just

375
00:20:41.480 --> 00:20:44.240
<v Speaker 3>gave you the answer right away. Right in our case,

376
00:20:44.680 --> 00:20:46.319
<v Speaker 3>that's how it works. In our case, what we are

377
00:20:46.319 --> 00:20:48.920
<v Speaker 3>doing is, Oh, you have asked us to draft this information.

378
00:20:49.720 --> 00:20:53.440
<v Speaker 3>Let us try to Oh you told us this here, okay,

379
00:20:53.720 --> 00:20:58.039
<v Speaker 3>and your knowledge repository saying this and one other thing

380
00:20:58.680 --> 00:21:01.240
<v Speaker 3>that the comment that you read just a moment to

381
00:21:01.279 --> 00:21:04.720
<v Speaker 3>good Richard that if you tell the language model that

382
00:21:05.400 --> 00:21:08.000
<v Speaker 3>please take these ten things that I'm telling you and

383
00:21:08.119 --> 00:21:13.640
<v Speaker 3>infuse them and generate some content. Language model, maybe listen

384
00:21:13.680 --> 00:21:15.920
<v Speaker 3>to the first or second requirement and maybe the last

385
00:21:16.000 --> 00:21:17.960
<v Speaker 3>requirement and then forget everything in the middle.

386
00:21:18.359 --> 00:21:18.599
<v Speaker 2>Right.

387
00:21:19.640 --> 00:21:22.680
<v Speaker 3>So this is where the thoughtful copilot comes in. We

388
00:21:22.799 --> 00:21:25.960
<v Speaker 3>go step by step manner to generate the content.

389
00:21:26.160 --> 00:21:27.799
<v Speaker 2>I love it, but I appreciate that this is I

390
00:21:27.839 --> 00:21:32.480
<v Speaker 2>got to imagine when you've an experienced RFP person, you're

391
00:21:32.559 --> 00:21:36.240
<v Speaker 2>probably comparing the new RFP to past ones you've done.

392
00:21:36.680 --> 00:21:38.079
<v Speaker 2>It's got to be a certain amount of cut and

393
00:21:38.119 --> 00:21:41.839
<v Speaker 2>paste there at least referencing material, which means you tend

394
00:21:41.920 --> 00:21:44.440
<v Speaker 2>to try and solve the same problem over and over again,

395
00:21:45.440 --> 00:21:49.279
<v Speaker 2>rather than this customer centric like do you understand this

396
00:21:49.400 --> 00:21:52.640
<v Speaker 2>particular problem this time, which may or may not be

397
00:21:52.720 --> 00:21:57.000
<v Speaker 2>explicitly stated, and then make sure you're tuning the material

398
00:21:57.519 --> 00:21:59.880
<v Speaker 2>to that, even if it is from past material. This

399
00:22:00.200 --> 00:22:04.319
<v Speaker 2>is where the language model actually is super advantageous, because

400
00:22:04.359 --> 00:22:07.200
<v Speaker 2>you can train it on the past data and it

401
00:22:07.319 --> 00:22:12.359
<v Speaker 2>will generate original texts yep, presumably with the impetus of

402
00:22:12.440 --> 00:22:15.720
<v Speaker 2>the new customer problem attached to it. This is stuff

403
00:22:15.720 --> 00:22:17.920
<v Speaker 2>that's hard for people to do, but I think the

404
00:22:18.079 --> 00:22:19.480
<v Speaker 2>software be pretty good at it.

405
00:22:19.559 --> 00:22:22.720
<v Speaker 3>That's right. This is a very important point I in

406
00:22:22.759 --> 00:22:25.440
<v Speaker 3>my previous role we talked about. I was there for

407
00:22:25.480 --> 00:22:28.839
<v Speaker 3>a long time and I didn't write proposals, but I

408
00:22:28.880 --> 00:22:32.160
<v Speaker 3>often served as a technical smme for a certain section. Right, Hey,

409
00:22:32.160 --> 00:22:34.519
<v Speaker 3>this is the section we need to write about. How

410
00:22:34.559 --> 00:22:38.440
<v Speaker 3>should we write about and what would happen there is?

411
00:22:38.680 --> 00:22:41.440
<v Speaker 3>I would tend to talk about the projects that I

412
00:22:41.559 --> 00:22:43.880
<v Speaker 3>focused on, you know, even if they were not the

413
00:22:43.960 --> 00:22:50.279
<v Speaker 3>best fit. Right, because organizational memory influences how you respond

414
00:22:50.640 --> 00:22:53.599
<v Speaker 3>versus This is where the superpower of the language model

415
00:22:53.759 --> 00:22:57.920
<v Speaker 3>is that you have one hundred different past performance to

416
00:22:58.039 --> 00:23:01.519
<v Speaker 3>look for, and maybe the the ones I picked because

417
00:23:01.559 --> 00:23:03.400
<v Speaker 3>of my bias because that's what I've worked on and

418
00:23:03.400 --> 00:23:05.480
<v Speaker 3>I'm very proud of those, Maybe those are not the

419
00:23:05.480 --> 00:23:08.640
<v Speaker 3>best ones. Maybe you should put something else that has

420
00:23:09.119 --> 00:23:12.759
<v Speaker 3>better engagement to the problem at hand.

421
00:23:13.160 --> 00:23:13.799
<v Speaker 2>Right, So.

422
00:23:15.599 --> 00:23:19.599
<v Speaker 1>I can see the advantage of this because it's very specific.

423
00:23:19.640 --> 00:23:22.160
<v Speaker 1>But then again, you have to feed it your data.

424
00:23:22.279 --> 00:23:25.200
<v Speaker 1>What about the stuff that's built into office You know

425
00:23:25.279 --> 00:23:28.160
<v Speaker 1>that that knows like all of your documents and your

426
00:23:28.160 --> 00:23:31.960
<v Speaker 1>spreadsheets and your your files and your PDFs and all

427
00:23:32.000 --> 00:23:36.400
<v Speaker 1>that stuff. Is it too broad? Is that knowledge too

428
00:23:36.440 --> 00:23:40.440
<v Speaker 1>broad to feed an RFP into and say come out

429
00:23:40.480 --> 00:23:41.400
<v Speaker 1>with something meaningful.

430
00:23:41.519 --> 00:23:45.599
<v Speaker 3>Yes, that's a that's a great question. We we don't

431
00:23:45.640 --> 00:23:49.799
<v Speaker 3>get that question now much much much more, But previously

432
00:23:49.839 --> 00:23:51.440
<v Speaker 3>we used to get this question, why should I use

433
00:23:51.480 --> 00:23:54.519
<v Speaker 3>your copilot? We have the M through sixty five co pilot, right,

434
00:23:55.279 --> 00:23:57.079
<v Speaker 3>And the answer to that question is, if I can

435
00:23:57.200 --> 00:23:59.839
<v Speaker 3>even take a step back, you have general purpose Shared

436
00:24:00.319 --> 00:24:01.720
<v Speaker 3>chat GPT, claude.

437
00:24:01.440 --> 00:24:01.920
<v Speaker 1>What have you?

438
00:24:02.319 --> 00:24:06.240
<v Speaker 3>Right, and think of them as outside your firewall. Great tools.

439
00:24:06.319 --> 00:24:08.200
<v Speaker 3>I love them. I'm sure all of you have two

440
00:24:08.279 --> 00:24:10.920
<v Speaker 3>or three or more subscriptions because they are great at

441
00:24:11.440 --> 00:24:17.160
<v Speaker 3>synthesizing information, summarizing information. Just you're trying to write something

442
00:24:17.400 --> 00:24:22.640
<v Speaker 3>about a topic, it's great to collaborate with generate some content.

443
00:24:22.720 --> 00:24:25.079
<v Speaker 3>Of course, you have to think you ultimately you own

444
00:24:25.160 --> 00:24:29.279
<v Speaker 3>the content, and there can be inaccuracies, of course. So

445
00:24:29.359 --> 00:24:33.599
<v Speaker 3>that's outside the firewall tools. And I say that with

446
00:24:33.720 --> 00:24:38.039
<v Speaker 3>some hesitation, because only two weeks ago or three weeks ago,

447
00:24:38.400 --> 00:24:41.319
<v Speaker 3>chat gpt announced that, hey, in addition to outside stuff,

448
00:24:41.559 --> 00:24:43.720
<v Speaker 3>you can also point to a Google drive or something

449
00:24:43.799 --> 00:24:47.160
<v Speaker 3>like that and we'll start ingesting your content. So let's

450
00:24:47.160 --> 00:24:49.799
<v Speaker 3>just keep that aside for a moment. Let's just talk

451
00:24:49.839 --> 00:24:56.400
<v Speaker 3>about Claude and chat GPT. Great tools, but outside the

452
00:24:56.400 --> 00:24:59.000
<v Speaker 3>firewall tools. And then you have the office productivity tools

453
00:24:59.039 --> 00:25:02.440
<v Speaker 3>like and three sixty five Copilot an equivalent that are

454
00:25:02.440 --> 00:25:07.640
<v Speaker 3>built into, built into your enterprise. And they're great, right.

455
00:25:08.000 --> 00:25:10.880
<v Speaker 3>They know who you talk to a lot on email,

456
00:25:11.039 --> 00:25:13.400
<v Speaker 3>they know who the subject matter experts are. They have

457
00:25:13.400 --> 00:25:16.720
<v Speaker 3>a full access to your one edrive, what have you.

458
00:25:17.279 --> 00:25:21.799
<v Speaker 3>So they're great. But again they are general purpose, and

459
00:25:22.680 --> 00:25:26.200
<v Speaker 3>two important differences right. You can use them to write

460
00:25:26.200 --> 00:25:29.000
<v Speaker 3>an email to a customer whose irate. You can use

461
00:25:29.039 --> 00:25:31.359
<v Speaker 3>it to plan a party, a going away party for

462
00:25:31.480 --> 00:25:34.039
<v Speaker 3>your co worker. They do well, they will get all

463
00:25:34.079 --> 00:25:36.799
<v Speaker 3>these things right. You don't have to worry about copying

464
00:25:36.839 --> 00:25:40.039
<v Speaker 3>and pasting information because they have access to all the data.

465
00:25:40.559 --> 00:25:43.559
<v Speaker 3>There is security built in. They only get to information

466
00:25:43.640 --> 00:25:46.480
<v Speaker 3>that you have access to. All all great things with

467
00:25:46.559 --> 00:25:50.759
<v Speaker 3>those productivity tools. But when we talk about a domain

468
00:25:50.799 --> 00:25:54.440
<v Speaker 3>specific coal pilot like ours, there are more things that

469
00:25:54.519 --> 00:25:58.880
<v Speaker 3>need to be done. So I talked about having very

470
00:25:58.880 --> 00:26:01.880
<v Speaker 3>specific documents. We go to a customer and say, can

471
00:26:01.920 --> 00:26:04.799
<v Speaker 3>you please give us your past RFP response documents, and

472
00:26:04.839 --> 00:26:08.119
<v Speaker 3>maybe they have two thousands of those documents. We look

473
00:26:08.160 --> 00:26:12.720
<v Speaker 3>at those documents and we break them up into logical boundaries,

474
00:26:12.799 --> 00:26:16.240
<v Speaker 3>We classify them, we auto tag them, things like that.

475
00:26:16.400 --> 00:26:20.599
<v Speaker 3>We are very opinionated about what we are trying to

476
00:26:20.640 --> 00:26:23.720
<v Speaker 3>decipher from your proposal library content.

477
00:26:24.119 --> 00:26:28.079
<v Speaker 1>It's a specific data set rather than everything in your

478
00:26:28.200 --> 00:26:31.279
<v Speaker 1>enterprise exactly. You might not you know, you might not

479
00:26:31.359 --> 00:26:34.000
<v Speaker 1>want that email to your wife about the new dog.

480
00:26:35.000 --> 00:26:37.599
<v Speaker 1>In your response to the you.

481
00:26:37.559 --> 00:26:41.640
<v Speaker 3>Don't want that and no, Caul, that's absolutely right. And

482
00:26:41.680 --> 00:26:45.440
<v Speaker 3>there's one other sort of technical issue. Right, the general

483
00:26:45.440 --> 00:26:50.079
<v Speaker 3>purpose tools don't know exactly how to chunk these documents,

484
00:26:50.119 --> 00:26:52.759
<v Speaker 3>and often they chunk it at some page boundary or

485
00:26:52.799 --> 00:26:57.000
<v Speaker 3>some fixed word boundary, and we cannot do that. We

486
00:26:57.119 --> 00:27:00.880
<v Speaker 3>chunk them based on the logical sections the structure of

487
00:27:00.920 --> 00:27:03.799
<v Speaker 3>an RFP document, so that when we provide that as

488
00:27:03.839 --> 00:27:07.519
<v Speaker 3>a context to the language model, we provide the most

489
00:27:07.559 --> 00:27:11.000
<v Speaker 3>precise context. And it's all about context, right. Language models

490
00:27:11.000 --> 00:27:14.200
<v Speaker 3>can get confused easily, so we provide So that's one

491
00:27:14.240 --> 00:27:17.200
<v Speaker 3>big difference, right, all of the upfront work. If you

492
00:27:17.240 --> 00:27:20.519
<v Speaker 3>ask me where where we've done our most R and D.

493
00:27:21.480 --> 00:27:24.960
<v Speaker 3>We are fifty people strong now, so you're growing quite

494
00:27:24.960 --> 00:27:27.160
<v Speaker 3>a bit. So fifty to fifty two or fifty three

495
00:27:27.200 --> 00:27:34.920
<v Speaker 3>people and many data scientists awesome, awesome team of engineers, mlops, DevOps, whatnot,

496
00:27:35.000 --> 00:27:37.880
<v Speaker 3>all running on measure and of course data science engineers.

497
00:27:38.039 --> 00:27:41.440
<v Speaker 3>So one part of research is ingestion. How can we

498
00:27:41.519 --> 00:27:47.640
<v Speaker 3>be opinionated optimized ingestion? That's one part. And then also

499
00:27:47.759 --> 00:27:50.839
<v Speaker 3>how do you glean some metadata from these documents? That's

500
00:27:50.880 --> 00:27:55.160
<v Speaker 3>also important, right, because semantic search can break down if

501
00:27:55.160 --> 00:27:57.720
<v Speaker 3>you're trying to find very factual information. So how do

502
00:27:57.799 --> 00:28:03.200
<v Speaker 3>you extract the metadata things like that. That's one part

503
00:28:03.240 --> 00:28:05.039
<v Speaker 3>of R and D. The other part of R and

504
00:28:05.119 --> 00:28:09.000
<v Speaker 3>D is we talked about the flight plan. We talked

505
00:28:09.000 --> 00:28:11.160
<v Speaker 3>about how you get so much data from the user

506
00:28:11.240 --> 00:28:14.359
<v Speaker 3>about win themes and pain points and solutioning and all

507
00:28:14.400 --> 00:28:20.720
<v Speaker 3>of that. Right, how do you effectively generate prompts dynamically

508
00:28:21.519 --> 00:28:25.000
<v Speaker 3>so that you can generate quality content that adheres to

509
00:28:25.039 --> 00:28:30.160
<v Speaker 3>proposal writing best practices. So those two things together is

510
00:28:30.200 --> 00:28:33.200
<v Speaker 3>why there is a domain specific copilot, and people try

511
00:28:33.279 --> 00:28:35.359
<v Speaker 3>to do that. Initially, Hey, let me just upload the

512
00:28:35.440 --> 00:28:39.279
<v Speaker 3>RFP to the to the M three sixty five copilot

513
00:28:39.319 --> 00:28:42.240
<v Speaker 3>and say can you generate a response? And then in

514
00:28:42.279 --> 00:28:45.079
<v Speaker 3>some cases the response is limited. We are generating a

515
00:28:45.160 --> 00:28:47.039
<v Speaker 3>response which can be one hundred and sixty hundred and

516
00:28:47.039 --> 00:28:49.640
<v Speaker 3>fifty pages long. So, first of all, you can't do

517
00:28:49.759 --> 00:28:53.839
<v Speaker 3>that with a general purpose copilot. And secondly, how do

518
00:28:53.920 --> 00:28:56.799
<v Speaker 3>you without having to write all the prompts yourself? In

519
00:28:56.839 --> 00:28:59.359
<v Speaker 3>our system, the users never have to write a prompt

520
00:29:00.799 --> 00:29:04.799
<v Speaker 3>because the prompts are changing. The best practices for prompts

521
00:29:04.880 --> 00:29:08.920
<v Speaker 3>before the reasoning models came along, and the best practices

522
00:29:08.960 --> 00:29:11.519
<v Speaker 3>for prompting after using models are very different and you

523
00:29:11.519 --> 00:29:15.119
<v Speaker 3>can't expect your end users to keep learning new prompting techniques,

524
00:29:15.480 --> 00:29:20.119
<v Speaker 3>so we dynamically generate the prompts based on what is

525
00:29:20.160 --> 00:29:24.480
<v Speaker 3>in your knowledge repository. Right, So those are the two things.

526
00:29:24.519 --> 00:29:26.319
<v Speaker 3>Sorry for the long answer, but those are the two

527
00:29:26.359 --> 00:29:27.279
<v Speaker 3>things that are different.

528
00:29:27.640 --> 00:29:30.400
<v Speaker 1>No, that's okay. Yeah, that's really great. And this seems

529
00:29:30.440 --> 00:29:32.759
<v Speaker 1>like a good place to take a break, so we'll

530
00:29:32.759 --> 00:29:36.640
<v Speaker 1>be right back after these very important messages. Stay tuned.

531
00:29:38.359 --> 00:29:40.799
<v Speaker 1>Did you know you can lift and shift your dot

532
00:29:40.880 --> 00:29:45.000
<v Speaker 1>net framework apps to virtual machines in the cloud. Use

533
00:29:45.039 --> 00:29:49.359
<v Speaker 1>the elastic beanstock service to easily migrate to Amazon EC

534
00:29:49.519 --> 00:29:54.200
<v Speaker 1>two with little or no changes. Find out more aws

535
00:29:54.359 --> 00:30:02.759
<v Speaker 1>dot Amazon dot com, slash elastic Beanstock, and we're back.

536
00:30:02.839 --> 00:30:05.960
<v Speaker 1>It's dot net Rox. I'm Carl Franklin, that's Richie Campbell hey,

537
00:30:06.119 --> 00:30:10.920
<v Speaker 1>and that's vishwas Lele our friend. And just as a reminder,

538
00:30:10.960 --> 00:30:13.200
<v Speaker 1>if you don't want to hear these ads before, during,

539
00:30:13.359 --> 00:30:17.480
<v Speaker 1>and after the show, you can become a patron a

540
00:30:17.519 --> 00:30:20.680
<v Speaker 1>Patreon for five dollars a month. Go to Patreon dot

541
00:30:20.680 --> 00:30:22.599
<v Speaker 1>dot netroocks dot com. We'll give you a feed that

542
00:30:22.599 --> 00:30:25.640
<v Speaker 1>has no ads. You still have to hear me apologizing

543
00:30:25.759 --> 00:30:30.640
<v Speaker 1>for them. Okay, well, you know the thing, as you

544
00:30:30.640 --> 00:30:33.599
<v Speaker 1>were talking, it just kind of occurs to me that

545
00:30:34.240 --> 00:30:38.039
<v Speaker 1>what you're doing is you're creating a company around a

546
00:30:38.160 --> 00:30:43.240
<v Speaker 1>specific domain, right that where you know how to ingest

547
00:30:43.519 --> 00:30:45.640
<v Speaker 1>the documents, you know how to query, and you fine

548
00:30:45.680 --> 00:30:49.000
<v Speaker 1>tuned it. It's not like somebody is going to come

549
00:30:49.039 --> 00:30:51.039
<v Speaker 1>to you and say maybe they have, but as anybody

550
00:30:51.039 --> 00:30:52.640
<v Speaker 1>come to you and said, hey, you did such a

551
00:30:52.640 --> 00:30:56.319
<v Speaker 1>great job for this domain, can you make me a

552
00:30:56.400 --> 00:31:01.000
<v Speaker 1>company around this domain? And that's essentially what you've done

553
00:31:01.440 --> 00:31:04.400
<v Speaker 1>with just the starting with the idea of their domain.

554
00:31:05.000 --> 00:31:07.799
<v Speaker 1>And I imagine that's what a lot of our listeners

555
00:31:07.880 --> 00:31:10.039
<v Speaker 1>are trying to do with their own businesses and their

556
00:31:10.039 --> 00:31:11.200
<v Speaker 1>own domains, isn't it.

557
00:31:11.359 --> 00:31:15.000
<v Speaker 3>So that's an excellent question, Carl, That's an excellent question.

558
00:31:15.119 --> 00:31:19.359
<v Speaker 3>Let me my thinking has evolved over this question. I

559
00:31:19.799 --> 00:31:21.839
<v Speaker 3>think you had asked a similar question last year when

560
00:31:21.839 --> 00:31:25.000
<v Speaker 3>we talked, and my thinking has evolved. So, Number one,

561
00:31:25.880 --> 00:31:28.200
<v Speaker 3>I think the patterns that we have figured out in

562
00:31:28.279 --> 00:31:33.039
<v Speaker 3>terms of breaking down these documents in a domain specific manner,

563
00:31:33.720 --> 00:31:38.160
<v Speaker 3>generating these prompts dynamically, those patterns generally are applicable to

564
00:31:38.160 --> 00:31:41.519
<v Speaker 3>any business problem. So that's right. But what I've also

565
00:31:41.559 --> 00:31:45.400
<v Speaker 3>come to realize is in order to get true value

566
00:31:45.480 --> 00:31:49.240
<v Speaker 3>from jen AAI for any business process, any complex and

567
00:31:49.279 --> 00:31:51.920
<v Speaker 3>proposal writing is a complex business process. There are hundreds

568
00:31:51.960 --> 00:31:57.279
<v Speaker 3>and thousands of business processes. You really have to do

569
00:31:57.400 --> 00:32:00.599
<v Speaker 3>a lot of domain specific work in order to provide

570
00:32:00.680 --> 00:32:03.599
<v Speaker 3>value to the customers. It's not like you could take

571
00:32:03.640 --> 00:32:06.000
<v Speaker 3>these patterns. Well, you have to Let's say you went

572
00:32:06.039 --> 00:32:08.279
<v Speaker 3>to the financial sector, you went to the insurance sector,

573
00:32:08.680 --> 00:32:11.160
<v Speaker 3>You'd have to do a lot of domain analysis to

574
00:32:11.200 --> 00:32:14.839
<v Speaker 3>figure out what are the key entities, what should be

575
00:32:14.920 --> 00:32:18.480
<v Speaker 3>the metadata. You'd have to do a lot of work

576
00:32:19.000 --> 00:32:25.359
<v Speaker 3>to figure out the best practices, think about the prompt

577
00:32:25.519 --> 00:32:28.559
<v Speaker 3>generation engine. So it's just not a matter of taking

578
00:32:28.640 --> 00:32:31.480
<v Speaker 3>these patterns. Maybe the patterns supply at a higher level,

579
00:32:32.160 --> 00:32:35.200
<v Speaker 3>but it is the work that has gone into realizing

580
00:32:35.279 --> 00:32:38.160
<v Speaker 3>these patterns is where we have spent the last year in.

581
00:32:38.279 --> 00:32:40.240
<v Speaker 1>Right, because it seems like there's a lot of people

582
00:32:40.319 --> 00:32:43.519
<v Speaker 1>that are using RAG and it's kind of like what

583
00:32:43.519 --> 00:32:47.440
<v Speaker 1>you're doing here, But I don't think there from what

584
00:32:47.559 --> 00:32:50.920
<v Speaker 1>I understand, look at it, like as Richard likes to say,

585
00:32:50.920 --> 00:32:53.359
<v Speaker 1>it's in a squirt bottle. You know, we just want

586
00:32:53.440 --> 00:32:57.599
<v Speaker 1>to spray some RAG on our documents and be able

587
00:32:57.640 --> 00:33:00.000
<v Speaker 1>to query them and get what we want out of them.

588
00:33:00.640 --> 00:33:04.720
<v Speaker 1>And what you're talking about here is a lot more involved,

589
00:33:04.759 --> 00:33:07.759
<v Speaker 1>Like it's not just a RAG tool that you're using.

590
00:33:08.559 --> 00:33:12.039
<v Speaker 1>It's everything from the original document, how to break them down,

591
00:33:12.079 --> 00:33:13.400
<v Speaker 1>how to chunk them, how to put them in there,

592
00:33:13.480 --> 00:33:16.559
<v Speaker 1>the things to look for, the way to respond like

593
00:33:17.440 --> 00:33:22.200
<v Speaker 1>it's U And so I imagine you're we don't really

594
00:33:22.240 --> 00:33:25.480
<v Speaker 1>look in terms of accuracy because you're not saying you

595
00:33:25.480 --> 00:33:28.599
<v Speaker 1>know how many widgets are in BIN forty five right now,

596
00:33:30.240 --> 00:33:35.440
<v Speaker 1>You're not. You're really genuine generating a text response which

597
00:33:35.480 --> 00:33:37.839
<v Speaker 1>you ultimately have control over.

598
00:33:38.039 --> 00:33:42.279
<v Speaker 3>But accuracy is very important part for us. By the way, Carl,

599
00:33:42.599 --> 00:33:45.400
<v Speaker 3>responsible they is an important tenet for us, and it

600
00:33:45.559 --> 00:33:48.960
<v Speaker 3>manifests for us in many ways. And I'm really glad

601
00:33:49.000 --> 00:33:53.599
<v Speaker 3>that we tried to adhere or architect to these tenets

602
00:33:53.599 --> 00:33:55.319
<v Speaker 3>from the very beginning. And let me give you a

603
00:33:55.359 --> 00:33:59.480
<v Speaker 3>couple of examples. Right, so, every time we generate a

604
00:33:59.519 --> 00:34:04.200
<v Speaker 3>piece of text for you, the responsible AI tenant says

605
00:34:04.319 --> 00:34:07.119
<v Speaker 3>that you should try to be transparent with the user.

606
00:34:07.720 --> 00:34:10.079
<v Speaker 3>So you have to tell them exactly which document, which

607
00:34:10.159 --> 00:34:13.719
<v Speaker 3>paragraph did you source the content from. That's one. And

608
00:34:13.760 --> 00:34:18.719
<v Speaker 3>then ultimately we said, it's a shared responsibility model. It's

609
00:34:18.719 --> 00:34:22.559
<v Speaker 3>about the complementarity between the AI models and the human beings.

610
00:34:23.199 --> 00:34:27.679
<v Speaker 3>So how do you help the proposal writers get you

611
00:34:27.719 --> 00:34:30.840
<v Speaker 3>an accurate response sooner? So we generate something called the

612
00:34:30.880 --> 00:34:33.559
<v Speaker 3>hallucination report every time we generate a piece of text.

613
00:34:34.400 --> 00:34:38.079
<v Speaker 3>It and what the haalucination report is that every time

614
00:34:38.159 --> 00:34:43.039
<v Speaker 3>we write out some text, we try to extract any

615
00:34:43.159 --> 00:34:48.920
<v Speaker 3>assertions that you've made in that text or the AI

616
00:34:48.960 --> 00:34:51.960
<v Speaker 3>has made on your behalf, based on your knowledge repository.

617
00:34:53.000 --> 00:34:56.000
<v Speaker 3>And we said, you know, you're saying that you've done

618
00:34:56.440 --> 00:35:01.280
<v Speaker 3>these five thousand no cloud migration, but we really can't

619
00:35:01.320 --> 00:35:05.280
<v Speaker 3>find anything like this in our knowledge repository, right, which is.

620
00:35:05.280 --> 00:35:07.360
<v Speaker 2>A great thing for it to say when it can't

621
00:35:07.360 --> 00:35:09.559
<v Speaker 2>find something, rather than make something up.

622
00:35:09.639 --> 00:35:12.199
<v Speaker 3>Yeah, that's right. And we know that the sales team

623
00:35:12.760 --> 00:35:15.360
<v Speaker 3>tends to sometimes take a creative license with some things.

624
00:35:15.360 --> 00:35:19.719
<v Speaker 3>Maybe they combine to projects. Right, So it's not saying

625
00:35:19.719 --> 00:35:23.480
<v Speaker 3>this is wrong, it is saying that it will it

626
00:35:23.519 --> 00:35:26.920
<v Speaker 3>will serve you well to take this statement. We can't

627
00:35:26.960 --> 00:35:30.719
<v Speaker 3>find an explicit reference to the statement in or repository.

628
00:35:31.079 --> 00:35:33.800
<v Speaker 3>Can you come back and sort of take a look,

629
00:35:33.840 --> 00:35:36.199
<v Speaker 3>and maybe you can approve that risk and say, no,

630
00:35:36.480 --> 00:35:41.519
<v Speaker 3>we are taking these two projects in and we're saying

631
00:35:41.599 --> 00:35:44.800
<v Speaker 3>that overall we have done these kinds of migrations for

632
00:35:44.960 --> 00:35:49.639
<v Speaker 3>this aggregated agency, and that's how we are making this assertion.

633
00:35:49.880 --> 00:35:51.760
<v Speaker 3>That's fine, you can approve that risk.

634
00:35:51.880 --> 00:35:54.199
<v Speaker 1>Yeah, it may be an accurate inference or it may

635
00:35:54.199 --> 00:35:55.960
<v Speaker 1>be completely wacky.

636
00:35:55.599 --> 00:35:57.159
<v Speaker 2>But at least if you have the references, you can

637
00:35:57.159 --> 00:35:59.119
<v Speaker 2>go evacuate it yourself if you want, Yeah.

638
00:35:58.920 --> 00:36:00.559
<v Speaker 3>You can. You can go back and read. And the

639
00:36:00.639 --> 00:36:02.159
<v Speaker 3>third thing.

640
00:36:02.119 --> 00:36:04.159
<v Speaker 2>That we also do and argue the interpretation.

641
00:36:04.199 --> 00:36:06.280
<v Speaker 3>Third thing that we also do is something called the

642
00:36:06.320 --> 00:36:10.480
<v Speaker 3>completion report. Right, So the RFP document was forty to

643
00:36:10.480 --> 00:36:15.360
<v Speaker 3>fifty pages long. It had instructions, it had evaluation criteria,

644
00:36:15.400 --> 00:36:19.360
<v Speaker 3>it had many many requirements, and it's a very important

645
00:36:19.599 --> 00:36:22.599
<v Speaker 3>aspect of responding that you're compliant. You're answering all the

646
00:36:22.679 --> 00:36:23.960
<v Speaker 3>questions that you were asked to do.

647
00:36:24.079 --> 00:36:26.119
<v Speaker 2>Yeah, you didn't miss any you didn't miss any.

648
00:36:26.480 --> 00:36:30.159
<v Speaker 3>So we again try to generate a compliance matrix for

649
00:36:30.199 --> 00:36:33.559
<v Speaker 3>you and say, look, these are the things that were

650
00:36:33.599 --> 00:36:36.960
<v Speaker 3>asked in the RFP. But again, this is a very

651
00:36:37.000 --> 00:36:41.320
<v Speaker 3>important part you have to go and validate that yourself,

652
00:36:41.360 --> 00:36:45.280
<v Speaker 3>because language models can be inaccurate at times. So it's

653
00:36:45.320 --> 00:36:48.719
<v Speaker 3>a very much an assistive technology, and we are not

654
00:36:48.800 --> 00:36:52.760
<v Speaker 3>quite getting it to autonomous anytime soon. That press up

655
00:36:52.800 --> 00:36:55.719
<v Speaker 3>button proposal comes out that you're ready to submit.

656
00:36:55.400 --> 00:36:57.159
<v Speaker 2>But it also occurs to me that again this is

657
00:36:57.199 --> 00:36:59.320
<v Speaker 2>something it's good at that it could lead you to

658
00:37:00.119 --> 00:37:04.320
<v Speaker 2>cerve responses or lack of response to a requirement, the

659
00:37:04.360 --> 00:37:09.000
<v Speaker 2>same way that a generative AI image recognized er may

660
00:37:09.159 --> 00:37:12.119
<v Speaker 2>point a radiologist to a particular spot on a picture

661
00:37:12.159 --> 00:37:15.239
<v Speaker 2>and say this looks anomalous yep, and encourage them to

662
00:37:15.239 --> 00:37:18.800
<v Speaker 2>look in the right corners. Given all the guidance you're

663
00:37:18.800 --> 00:37:22.280
<v Speaker 2>providing here, which I really appreciate, right that the flight

664
00:37:22.360 --> 00:37:26.840
<v Speaker 2>plan approached the prompt generation to make sure it's accurate

665
00:37:26.880 --> 00:37:30.519
<v Speaker 2>and focus on the right material with the references. Does

666
00:37:30.559 --> 00:37:33.599
<v Speaker 2>the language model actually matter? Like you talked about open

667
00:37:33.679 --> 00:37:37.559
<v Speaker 2>AI last year, Now there's been many more models released.

668
00:37:37.599 --> 00:37:40.199
<v Speaker 2>I mean cloud was always around, but deep seeks appeared

669
00:37:40.280 --> 00:37:44.039
<v Speaker 2>like does any of those make a difference given this

670
00:37:44.400 --> 00:37:45.559
<v Speaker 2>strict set of guidance.

671
00:37:46.280 --> 00:37:51.960
<v Speaker 3>That's a great question, So let me answer that using

672
00:37:52.639 --> 00:37:56.199
<v Speaker 3>two important points. Right turns out that these rf peace

673
00:37:56.280 --> 00:37:59.599
<v Speaker 3>can also have sensitive information, and you need to have

674
00:38:00.760 --> 00:38:05.199
<v Speaker 3>things like CMMC two standards where you are explicitly telling

675
00:38:05.239 --> 00:38:09.119
<v Speaker 3>the government that this information is not just public RFP.

676
00:38:09.280 --> 00:38:13.880
<v Speaker 3>So think about you're going after some RFP that talks

677
00:38:13.880 --> 00:38:17.159
<v Speaker 3>about some kind of things weapon system and even the

678
00:38:17.280 --> 00:38:22.199
<v Speaker 3>RFPs can have what is known as a controlled unclassified information.

679
00:38:22.920 --> 00:38:28.280
<v Speaker 3>So in order to support and show that you're handling

680
00:38:28.320 --> 00:38:34.639
<v Speaker 3>that information correctly, you need to show to the auditors

681
00:38:35.599 --> 00:38:40.079
<v Speaker 3>where your packets have traversed in that system. And then

682
00:38:40.199 --> 00:38:44.880
<v Speaker 3>ultimately where did you send this data and did let's

683
00:38:44.880 --> 00:38:47.320
<v Speaker 3>say you sent it to the external system like language model.

684
00:38:47.840 --> 00:38:52.199
<v Speaker 3>Did that language model itself have a security classification and

685
00:38:52.239 --> 00:38:55.559
<v Speaker 3>it is giving you guarantees about not logging that data

686
00:38:55.599 --> 00:38:57.719
<v Speaker 3>beyond the metadata and things like that.

687
00:38:57.559 --> 00:39:01.039
<v Speaker 2>Right, yeah, and the sovereignty where did that they actually go?

688
00:39:01.559 --> 00:39:01.920
<v Speaker 3>Yes?

689
00:39:02.320 --> 00:39:04.400
<v Speaker 2>Now, I mean this makes a strong case for running

690
00:39:04.360 --> 00:39:05.239
<v Speaker 2>as a local model.

691
00:39:05.800 --> 00:39:11.079
<v Speaker 3>Well, that's true, we use but you know the same time,

692
00:39:11.119 --> 00:39:13.280
<v Speaker 3>these RFPs are very complex, so we want the best

693
00:39:13.320 --> 00:39:14.840
<v Speaker 3>comprehension that is available.

694
00:39:15.239 --> 00:39:19.039
<v Speaker 2>You want a trillion parameters, you need want trills.

695
00:39:18.400 --> 00:39:21.639
<v Speaker 3>I need a trillion parameters, right, So what we do

696
00:39:21.719 --> 00:39:26.159
<v Speaker 3>is platforms like asure opening. I give you that guarantee

697
00:39:26.199 --> 00:39:29.320
<v Speaker 3>and you can actually show to people how your network,

698
00:39:30.760 --> 00:39:33.480
<v Speaker 3>how do your packets from all the way from incoming

699
00:39:33.599 --> 00:39:38.199
<v Speaker 3>RFP to how the response generation traversed a certain network

700
00:39:38.320 --> 00:39:42.679
<v Speaker 3>path that the auditors can say, yep, we certify, we're

701
00:39:42.719 --> 00:39:45.119
<v Speaker 3>okay with that, that these packets are fine. So that's one.

702
00:39:45.159 --> 00:39:47.679
<v Speaker 3>So it's not just a matter of hey, let me

703
00:39:47.800 --> 00:39:51.519
<v Speaker 3>just go send this data packet to somewhere else unless

704
00:39:51.519 --> 00:39:55.000
<v Speaker 3>they have a classification. So that's one one important consideration

705
00:39:55.079 --> 00:39:55.400
<v Speaker 3>for us.

706
00:39:55.440 --> 00:39:58.320
<v Speaker 2>So just narrow is your choices of models based on

707
00:39:58.519 --> 00:40:00.920
<v Speaker 2>whether or not they're going to clear see see two.

708
00:40:01.119 --> 00:40:05.000
<v Speaker 3>Yes, that's one. And secondly, Richard, the other thing that

709
00:40:05.320 --> 00:40:10.320
<v Speaker 3>we've realized is that these models have a personality. So

710
00:40:10.679 --> 00:40:13.760
<v Speaker 3>just because they speak English doesn't mean you can just swap.

711
00:40:13.440 --> 00:40:17.440
<v Speaker 2>Now anthropomorphic of you Vishwa's goodness, Yeah, you've pushed.

712
00:40:17.199 --> 00:40:19.599
<v Speaker 1>Richard's answer promorphic button there.

713
00:40:19.760 --> 00:40:23.719
<v Speaker 3>Yes, so these models have a personality against say saying that,

714
00:40:24.239 --> 00:40:27.239
<v Speaker 3>And so I find this interesting when people say, hey,

715
00:40:27.280 --> 00:40:29.480
<v Speaker 3>these are models are all English pays, so you can

716
00:40:29.559 --> 00:40:32.239
<v Speaker 3>just switch one and see which one works. When you

717
00:40:32.280 --> 00:40:36.000
<v Speaker 3>are generating hundreds and hundreds of pages of prompts. As

718
00:40:36.079 --> 00:40:39.039
<v Speaker 3>we do, it is really important for us to understand

719
00:40:39.079 --> 00:40:43.079
<v Speaker 3>the personality of the model, and we can change the model,

720
00:40:43.119 --> 00:40:44.880
<v Speaker 3>and in fact, we change the models all the time.

721
00:40:44.880 --> 00:40:48.239
<v Speaker 3>When we went from four to four turbo and so on,

722
00:40:48.320 --> 00:40:51.280
<v Speaker 3>and now we're using oh one and three. Every time

723
00:40:51.280 --> 00:40:53.480
<v Speaker 3>we change a model, we have to do extensive testing

724
00:40:53.920 --> 00:40:56.639
<v Speaker 3>to make sure our prompting layer works well. But at

725
00:40:56.719 --> 00:40:59.920
<v Speaker 3>least these models are a certain family. Part of these models,

726
00:41:00.159 --> 00:41:01.800
<v Speaker 3>just switching to us different models.

727
00:41:01.519 --> 00:41:03.760
<v Speaker 2>You've all described you're only talking about open ai models

728
00:41:03.760 --> 00:41:04.199
<v Speaker 2>there so far.

729
00:41:04.280 --> 00:41:09.159
<v Speaker 3>Yes, we're talking about OpenAI models, so that's the other part.

730
00:41:10.679 --> 00:41:15.159
<v Speaker 3>So those two important considerations have gone in into deciding

731
00:41:15.280 --> 00:41:18.960
<v Speaker 3>which models we go against. We're thankful to open ai

732
00:41:19.119 --> 00:41:21.960
<v Speaker 3>and Azure open Ai that their models have generally kept up.

733
00:41:22.360 --> 00:41:25.239
<v Speaker 3>It's not like they're not they're the ones who came

734
00:41:25.239 --> 00:41:27.679
<v Speaker 3>out with the reasoning models. Of course, reasoning models are

735
00:41:27.679 --> 00:41:30.760
<v Speaker 3>available on other platforms as well now, but they've kept

736
00:41:30.920 --> 00:41:35.119
<v Speaker 3>up with the advancements that are happening. So we're pretty

737
00:41:35.119 --> 00:41:39.440
<v Speaker 3>happy with where we are. But we constantly run tests

738
00:41:40.159 --> 00:41:43.039
<v Speaker 3>to see how other models would do.

739
00:41:43.400 --> 00:41:46.920
<v Speaker 2>Now and you mentioned already the difference between using a

740
00:41:46.960 --> 00:41:49.320
<v Speaker 2>model that doesn't have a reasoning feature, and I'm doing

741
00:41:49.360 --> 00:41:52.760
<v Speaker 2>air quotes yep, because I read the Anthropic paper where

742
00:41:52.760 --> 00:41:55.840
<v Speaker 2>they talked about the fact that the whole reasoning behavior

743
00:41:56.400 --> 00:42:00.159
<v Speaker 2>is a post back or behavior that the result to

744
00:42:00.239 --> 00:42:04.119
<v Speaker 2>the prompt generated and then analyzed after the fact by

745
00:42:04.199 --> 00:42:08.960
<v Speaker 2>the tool to generate the quote unquote reasoning. Right.

746
00:42:09.039 --> 00:42:14.440
<v Speaker 3>So the idea here is that I'm trying to generate

747
00:42:14.440 --> 00:42:17.920
<v Speaker 3>a response to a certain section. Sure, and either I

748
00:42:17.960 --> 00:42:21.119
<v Speaker 3>can just in a non reasoning model, I would just say, hey,

749
00:42:21.159 --> 00:42:24.000
<v Speaker 3>generate an answer, and we'll just go through a certain

750
00:42:24.119 --> 00:42:29.280
<v Speaker 3>chain and just start generating a response immediately. But the

751
00:42:29.320 --> 00:42:33.679
<v Speaker 3>reasoning model, it just tries to develop a plan and say, Okay,

752
00:42:34.280 --> 00:42:37.280
<v Speaker 3>you're asking to generate this response. I could use this

753
00:42:37.440 --> 00:42:41.480
<v Speaker 3>example versus this example. Let's try with this example, go

754
00:42:41.559 --> 00:42:44.599
<v Speaker 3>halfway through and realize that there's not enough meat in

755
00:42:44.639 --> 00:42:47.079
<v Speaker 3>this Let's just go back and switch the example. That's

756
00:42:47.119 --> 00:42:48.480
<v Speaker 3>what reasoning is all about, right.

757
00:42:48.519 --> 00:42:51.079
<v Speaker 2>Yeah, that's what it implies. But what the Anthropic paper

758
00:42:51.119 --> 00:42:53.119
<v Speaker 2>says is that they're actually doing that after the fact.

759
00:42:53.280 --> 00:42:55.679
<v Speaker 2>They already have the statement they want to say, and

760
00:42:55.719 --> 00:42:59.159
<v Speaker 2>then they take their statement apart and fill in the

761
00:42:59.159 --> 00:43:01.639
<v Speaker 2>pieces to show how they quote reasoned it.

762
00:43:01.639 --> 00:43:03.760
<v Speaker 1>Yes, more like justification than reasoning.

763
00:43:04.239 --> 00:43:07.719
<v Speaker 2>You showed me the equation. I knew the answer, and

764
00:43:07.760 --> 00:43:11.400
<v Speaker 2>now I write out quote my work even though I've

765
00:43:11.400 --> 00:43:13.320
<v Speaker 2>already got the answer. I'm just trying to fill it

766
00:43:13.320 --> 00:43:14.679
<v Speaker 2>in to make you feel better because you asked me

767
00:43:14.679 --> 00:43:15.280
<v Speaker 2>to show your work.

768
00:43:15.480 --> 00:43:15.679
<v Speaker 1>Yeah.

769
00:43:15.719 --> 00:43:18.760
<v Speaker 3>No, that's the anthropic paper, no question about it. But

770
00:43:19.599 --> 00:43:24.159
<v Speaker 3>we are adding on top of that reasoning layer. We say, hey,

771
00:43:24.400 --> 00:43:26.920
<v Speaker 3>which past performance do you want to use? How should

772
00:43:26.920 --> 00:43:29.199
<v Speaker 3>you be writing about it? Things like that.

773
00:43:29.599 --> 00:43:31.840
<v Speaker 2>Yeah, and I'm not going to say anything bad about

774
00:43:31.840 --> 00:43:34.280
<v Speaker 2>the fact that it goes and poll's references because you

775
00:43:34.400 --> 00:43:37.039
<v Speaker 2>need those. That's all the quality stuff for there.

776
00:43:37.800 --> 00:43:41.599
<v Speaker 1>Yep, that's fishs. Last time we talked, we've got on

777
00:43:41.639 --> 00:43:45.880
<v Speaker 1>the subject of how you think jen Ai and AI

778
00:43:45.960 --> 00:43:49.599
<v Speaker 1>in general is going to affect the lives of average

779
00:43:49.639 --> 00:43:54.079
<v Speaker 1>developers like us. Has your thoughts on that changed in

780
00:43:54.119 --> 00:43:54.760
<v Speaker 1>the last year.

781
00:43:55.920 --> 00:44:02.480
<v Speaker 3>My thoughts have not changed. I think developers who will

782
00:44:02.519 --> 00:44:05.519
<v Speaker 3>greatly benefit from tools like that. It is not a panacea.

783
00:44:05.639 --> 00:44:07.880
<v Speaker 3>You can't just say hey, I'm going to give you

784
00:44:07.920 --> 00:44:13.039
<v Speaker 3>these things and go code me something. I think it

785
00:44:13.119 --> 00:44:16.960
<v Speaker 3>puts developers who have been thoughtful, who have worked on

786
00:44:17.000 --> 00:44:21.159
<v Speaker 3>the craft who understand the edge case as well, who

787
00:44:21.199 --> 00:44:25.000
<v Speaker 3>are able to critically look at the code that the

788
00:44:25.599 --> 00:44:29.679
<v Speaker 3>lllms are generating. They're in a very good position because

789
00:44:29.679 --> 00:44:32.400
<v Speaker 3>they can really get that acceleration at the same time

790
00:44:32.440 --> 00:44:36.119
<v Speaker 3>they're critically analyzing what's being generated for them. I think

791
00:44:36.159 --> 00:44:39.000
<v Speaker 3>it's a real challenge for people who are beginning because

792
00:44:39.719 --> 00:44:42.199
<v Speaker 3>it can very superficially tell you that it is working,

793
00:44:42.599 --> 00:44:44.880
<v Speaker 3>but it may not actually be working exactly the way

794
00:44:44.880 --> 00:44:45.760
<v Speaker 3>you want it to, or.

795
00:44:47.119 --> 00:44:50.920
<v Speaker 1>The AI might give you a solution which is more complex,

796
00:44:51.000 --> 00:44:53.079
<v Speaker 1>and you're building and rolling your own thing when there's

797
00:44:53.119 --> 00:44:55.880
<v Speaker 1>already something available that does it, and it's not going

798
00:44:55.960 --> 00:44:58.639
<v Speaker 1>to tell you that. And I've had this experience and

799
00:44:58.679 --> 00:45:00.880
<v Speaker 1>you go back and you say, hey, can I just

800
00:45:01.000 --> 00:45:04.639
<v Speaker 1>use X? And it says, oh, yes, absolutely.

801
00:45:04.159 --> 00:45:04.679
<v Speaker 3>Yes, Yeah.

802
00:45:04.719 --> 00:45:07.320
<v Speaker 1>Well why didn't you tell me that before? Are you idiot? Right?

803
00:45:07.440 --> 00:45:07.719
<v Speaker 2>Yeah?

804
00:45:07.760 --> 00:45:11.559
<v Speaker 1>So to your point, somebody who doesn't know about you know,

805
00:45:11.719 --> 00:45:14.920
<v Speaker 1>tool X or tool why isn't going to find out

806
00:45:15.000 --> 00:45:18.000
<v Speaker 1>that it gave you the answer that you wanted, which

807
00:45:18.039 --> 00:45:21.639
<v Speaker 1>is how do I build this? It didn't say you

808
00:45:21.639 --> 00:45:25.079
<v Speaker 1>didn't say how do I solve this problem? And if

809
00:45:25.119 --> 00:45:27.679
<v Speaker 1>you did that, you might have gotten a different answer.

810
00:45:27.760 --> 00:45:30.719
<v Speaker 3>Well, that's that's very important. It's also important to do

811
00:45:30.800 --> 00:45:34.440
<v Speaker 3>it incrementally and iteratively so that, yeah, you don't just

812
00:45:34.480 --> 00:45:36.360
<v Speaker 3>get two hundred lines of code, you have no idea

813
00:45:36.360 --> 00:45:38.199
<v Speaker 3>and you run a test and you think it's fine.

814
00:45:38.719 --> 00:45:42.159
<v Speaker 3>But if you do it incrementally, all of the basics

815
00:45:42.159 --> 00:45:45.559
<v Speaker 3>of getting this right. Can I refactor this, can I

816
00:45:45.639 --> 00:45:49.639
<v Speaker 3>get can can this piece be optimized? Using this? Yeah,

817
00:45:49.719 --> 00:45:53.599
<v Speaker 3>it's accelerating that immensely, and so.

818
00:45:53.719 --> 00:45:56.400
<v Speaker 2>You know, it's funny you're describing exactly what you say

819
00:45:56.480 --> 00:46:02.079
<v Speaker 2>p wind does for RFP that experienced RFP builder respond.

820
00:46:02.119 --> 00:46:05.480
<v Speaker 2>Builders can use this tool to accelerate the behavior. But

821
00:46:05.920 --> 00:46:10.360
<v Speaker 2>it is an interaction the tools pulling resources from past

822
00:46:10.480 --> 00:46:16.800
<v Speaker 2>work and suggesting options that then you could iterate on incrementally,

823
00:46:16.960 --> 00:46:20.000
<v Speaker 2>piece by piece, so that you know, when we talked

824
00:46:20.000 --> 00:46:23.360
<v Speaker 2>a year ago this was about making RFPs faster. Now

825
00:46:23.400 --> 00:46:27.599
<v Speaker 2>you're really talking about higher quality and better tuned to

826
00:46:27.760 --> 00:46:29.280
<v Speaker 2>the demands of the new RFP.

827
00:46:29.920 --> 00:46:33.079
<v Speaker 3>Definitely, definitely, and the quality. We are reaching a point

828
00:46:33.079 --> 00:46:35.519
<v Speaker 3>to where people say I can spot judge it PT

829
00:46:35.840 --> 00:46:38.360
<v Speaker 3>generated text from a mile right, people see that I

830
00:46:38.360 --> 00:46:39.440
<v Speaker 3>don't know if there's.

831
00:46:39.119 --> 00:46:42.679
<v Speaker 2>Well AI slop is now in the vernacular for a reason.

832
00:46:42.760 --> 00:46:45.920
<v Speaker 2>There's a lot of bad generative AI slop out there.

833
00:46:46.039 --> 00:46:48.840
<v Speaker 1>I can definitely tell when images are AI created because

834
00:46:48.840 --> 00:46:53.039
<v Speaker 1>they're so slick, you know, and people have made.

835
00:46:52.880 --> 00:46:54.039
<v Speaker 2>A half he even fingers.

836
00:46:54.559 --> 00:46:59.119
<v Speaker 1>Yeah, people have made a I don't know, hobby or

837
00:46:59.159 --> 00:47:04.599
<v Speaker 1>maybe a career out of generating. You know, the most peaceful,

838
00:47:04.719 --> 00:47:10.280
<v Speaker 1>sublime picturesque spot with a house by a brook and

839
00:47:10.400 --> 00:47:13.079
<v Speaker 1>you know this and that, and they just post it

840
00:47:13.119 --> 00:47:19.000
<v Speaker 1>on Facebook and say a beautiful place right with no contacts,

841
00:47:19.039 --> 00:47:21.760
<v Speaker 1>with no you know, people are like, wow, where is that? Well,

842
00:47:21.760 --> 00:47:25.920
<v Speaker 1>it's amazing, right, Yeah, it just doesn't exist. And I

843
00:47:25.920 --> 00:47:27.519
<v Speaker 1>could spot those pictures a mile away.

844
00:47:27.719 --> 00:47:30.360
<v Speaker 2>Let me tell you, as a conference organizer, I know

845
00:47:30.400 --> 00:47:33.519
<v Speaker 2>when you use chat GPT to write your abstract, abstract

846
00:47:34.119 --> 00:47:37.320
<v Speaker 2>at your abstract because they are all the same.

847
00:47:37.480 --> 00:47:37.719
<v Speaker 3>Yeah.

848
00:47:37.760 --> 00:47:41.679
<v Speaker 2>I got a thousand abstracts in and four hundred of

849
00:47:41.760 --> 00:47:44.960
<v Speaker 2>them start with in a world. Yeah right, like come on.

850
00:47:46.320 --> 00:47:51.320
<v Speaker 3>Yeah and b. Because we're so focused on the quality

851
00:47:51.360 --> 00:47:58.360
<v Speaker 3>of writing, we explicitly look for these things where language

852
00:47:58.400 --> 00:48:03.639
<v Speaker 3>models are trying to quote unquote write the perfect text

853
00:48:03.679 --> 00:48:05.719
<v Speaker 3>because you know, you've given them ten things to write

854
00:48:05.760 --> 00:48:09.599
<v Speaker 3>and they find the best way possible to pack that

855
00:48:09.679 --> 00:48:12.679
<v Speaker 3>information and sort of present it. The problem is it

856
00:48:12.760 --> 00:48:15.599
<v Speaker 3>is very onerous on a reader when you're packing it

857
00:48:15.679 --> 00:48:20.719
<v Speaker 3>so much information right, and then overuse of cliches, making

858
00:48:20.760 --> 00:48:24.159
<v Speaker 3>statements without sort of providing background information. These are all

859
00:48:24.239 --> 00:48:32.320
<v Speaker 3>common sense of LLLM generated writing, and we take explicit

860
00:48:32.400 --> 00:48:36.159
<v Speaker 3>steps in our engine to either correct this mistake or

861
00:48:36.239 --> 00:48:40.000
<v Speaker 3>constantly remind the model to slow it down to make

862
00:48:40.039 --> 00:48:43.159
<v Speaker 3>it readable, to improve the quality. These are all things

863
00:48:43.320 --> 00:48:45.800
<v Speaker 3>that are works in progress. A lot more work to

864
00:48:45.840 --> 00:48:48.159
<v Speaker 3>be done there, but those are the kinds of things

865
00:48:48.199 --> 00:48:51.880
<v Speaker 3>that we're thinking about. Goes back to all of these

866
00:48:51.920 --> 00:48:57.079
<v Speaker 3>things are needed to have a real impact on solving

867
00:48:57.079 --> 00:49:00.199
<v Speaker 3>a business problem. When you think about this, it's not

868
00:49:00.280 --> 00:49:02.000
<v Speaker 3>just a matter of taking this and saying, Okay, I'm

869
00:49:02.039 --> 00:49:05.320
<v Speaker 3>going to go start generating financial reports tomorrow. There'll be

870
00:49:05.360 --> 00:49:07.280
<v Speaker 3>a lot of work that needed to go in.

871
00:49:07.440 --> 00:49:09.920
<v Speaker 1>As a programmer, you kind of think of yourself as

872
00:49:09.960 --> 00:49:13.400
<v Speaker 1>a senior programmer slash manager, somebody who can write code

873
00:49:14.000 --> 00:49:17.880
<v Speaker 1>but chooses to offload the boring stuff to a junior programmer.

874
00:49:18.679 --> 00:49:23.400
<v Speaker 1>And it's all about the prompts, you know, It's all

875
00:49:23.400 --> 00:49:26.119
<v Speaker 1>about what you ask it to do. And I've had

876
00:49:26.159 --> 00:49:28.719
<v Speaker 1>the experience of chatchypt anyway where I said, you know,

877
00:49:28.719 --> 00:49:31.119
<v Speaker 1>I'm trying to do this, and it might be about programming,

878
00:49:31.159 --> 00:49:34.360
<v Speaker 1>it might not, and it will say, oh, well there's

879
00:49:34.480 --> 00:49:37.320
<v Speaker 1>currently no way to do this and blah blah blah,

880
00:49:37.360 --> 00:49:41.679
<v Speaker 1>this is not possible, and or maybe it gives you

881
00:49:41.719 --> 00:49:44.519
<v Speaker 1>some suggestions that are just stupid, like is it turned on?

882
00:49:44.760 --> 00:49:48.960
<v Speaker 1>You know, that kind of stuff, And then you can say, well,

883
00:49:49.199 --> 00:49:51.400
<v Speaker 1>is any can you check the internet to see if

884
00:49:51.440 --> 00:49:54.199
<v Speaker 1>anyone else is having this problem? And that is the

885
00:49:54.239 --> 00:49:58.119
<v Speaker 1>most powerful prompt you know. If you're not satisfied with

886
00:49:58.119 --> 00:50:00.880
<v Speaker 1>the answer it gives you just say, hey, goog google

887
00:50:00.960 --> 00:50:04.119
<v Speaker 1>it or whatever you know, and it will come back

888
00:50:04.199 --> 00:50:08.039
<v Speaker 1>with sometimes with yes, there's a somebody's having this product.

889
00:50:08.079 --> 00:50:10.039
<v Speaker 1>It seems like this is a common problem and this

890
00:50:10.159 --> 00:50:14.239
<v Speaker 1>is what this people, these people did to overcome it, right, absolutely,

891
00:50:14.519 --> 00:50:16.639
<v Speaker 1>So it's it's all about the prompts and it's all

892
00:50:16.639 --> 00:50:20.559
<v Speaker 1>about thinking in that sort of manager senior programmer to

893
00:50:20.639 --> 00:50:22.599
<v Speaker 1>junior programmer mindset.

894
00:50:22.719 --> 00:50:26.159
<v Speaker 2>Yep. But back to you. You know the p win tool.

895
00:50:26.400 --> 00:50:30.840
<v Speaker 2>You're mostly writing prompts with the tool to then run

896
00:50:30.920 --> 00:50:33.880
<v Speaker 2>them to get results for the operator, that's right, that's right,

897
00:50:33.880 --> 00:50:37.199
<v Speaker 2>And because there is a repetitive piece to this of

898
00:50:37.719 --> 00:50:42.000
<v Speaker 2>setting the restrictions and making sure the context is correct.

899
00:50:42.079 --> 00:50:44.280
<v Speaker 2>Like I got to imagine there's a couple of big

900
00:50:44.360 --> 00:50:48.119
<v Speaker 2>paragraphs at the top of every prompt just to make

901
00:50:48.159 --> 00:50:51.960
<v Speaker 2>sure it stays in the constraint, and then specifics for

902
00:50:52.480 --> 00:50:55.199
<v Speaker 2>the section you're in in the RFP.

903
00:50:55.320 --> 00:50:58.119
<v Speaker 3>YEP, there's some systems prompts that go in and every

904
00:50:58.199 --> 00:51:00.760
<v Speaker 3>time to sort of keep.

905
00:51:00.559 --> 00:51:03.920
<v Speaker 2>And it occurred to me, you know, thinking about this

906
00:51:04.000 --> 00:51:06.519
<v Speaker 2>problem space and thinking about in our reactions to AI

907
00:51:06.639 --> 00:51:08.679
<v Speaker 2>SLOP and you know, detechnics and so forth. It's like,

908
00:51:09.000 --> 00:51:12.039
<v Speaker 2>if you think this pattern matching software is awesome, try

909
00:51:12.079 --> 00:51:17.639
<v Speaker 2>a human because humans are really good at finding patterns, especially,

910
00:51:17.679 --> 00:51:20.679
<v Speaker 2>and that's what they see. There's certain patterns to what

911
00:51:20.760 --> 00:51:24.280
<v Speaker 2>a lot of low quality l M tools generate that

912
00:51:24.679 --> 00:51:27.800
<v Speaker 2>you immediately perceived. And it's now starting to shift our

913
00:51:27.880 --> 00:51:31.599
<v Speaker 2>minds where it's now repulsive. Yeah, and we're in a

914
00:51:31.599 --> 00:51:34.960
<v Speaker 2>funny place, but it's there's some good advice in here

915
00:51:35.000 --> 00:51:37.039
<v Speaker 2>visual so I really appreciate it. Like a year later,

916
00:51:37.519 --> 00:51:41.400
<v Speaker 2>you're speaking very differently about the product you're making and

917
00:51:41.480 --> 00:51:43.960
<v Speaker 2>the tool and the way to use these tools like

918
00:51:44.480 --> 00:51:47.440
<v Speaker 2>it shows that it's the evolution that's going on here.

919
00:51:47.519 --> 00:51:50.239
<v Speaker 3>Yeah, I know, not Richard and call that's that's certainly true.

920
00:51:50.440 --> 00:51:54.800
<v Speaker 3>Learned a lot in this process of awesome technology. There's

921
00:51:54.840 --> 00:51:57.280
<v Speaker 3>no question about it. I think we'll be it's the

922
00:51:57.320 --> 00:52:01.079
<v Speaker 3>next super cycle, as Gartner Le likes to call. They said,

923
00:52:01.199 --> 00:52:04.519
<v Speaker 3>you know, every tech super cyclist twenty years. The last

924
00:52:04.519 --> 00:52:07.239
<v Speaker 3>one started in two thousand, but digital and the Internet

925
00:52:07.719 --> 00:52:10.039
<v Speaker 3>and we are at the We're at the intersection of

926
00:52:10.079 --> 00:52:12.360
<v Speaker 3>the previous one and launching into the gen AI.

927
00:52:12.840 --> 00:52:15.239
<v Speaker 2>Yeah. Yeah, this has been I felt like this is

928
00:52:15.239 --> 00:52:16.760
<v Speaker 2>a fundamental shift in U acts.

929
00:52:16.960 --> 00:52:18.320
<v Speaker 3>It's a fundamental shift.

930
00:52:18.480 --> 00:52:20.800
<v Speaker 1>The way we interact with our equipment is about to change.

931
00:52:20.840 --> 00:52:23.320
<v Speaker 1>But I think this generation isn't going to be twenty years.

932
00:52:23.320 --> 00:52:25.880
<v Speaker 1>It's probably gonna be more like five or six or ten.

933
00:52:26.239 --> 00:52:28.519
<v Speaker 3>True's that's that's so.

934
00:52:28.559 --> 00:52:30.280
<v Speaker 1>Much has happened in the last.

935
00:52:30.239 --> 00:52:32.159
<v Speaker 2>A lot happened in the first few years of the

936
00:52:32.159 --> 00:52:34.559
<v Speaker 2>twenty first century as Internet came out of the dot

937
00:52:34.599 --> 00:52:37.360
<v Speaker 2>com boom, and you know, we shifted to mobile.

938
00:52:37.400 --> 00:52:39.719
<v Speaker 1>It's not like we've been going slow so far, no,

939
00:52:39.840 --> 00:52:41.480
<v Speaker 1>but it does seem to be accelerating.

940
00:52:42.760 --> 00:52:45.519
<v Speaker 3>I think, Yeah, I know, it seems to be accelerating.

941
00:52:45.559 --> 00:52:48.480
<v Speaker 3>But also I would say that there is some platauing,

942
00:52:48.719 --> 00:52:51.599
<v Speaker 3>which you may see counterintuitive when I say that plat

943
00:52:51.599 --> 00:52:56.159
<v Speaker 3>doing because GBT five was not released. They were going

944
00:52:56.199 --> 00:52:59.440
<v Speaker 3>to release GPT five. Right, Just a bigger and bigger

945
00:52:59.480 --> 00:53:02.599
<v Speaker 3>model with more data is not leading to better results.

946
00:53:02.840 --> 00:53:06.159
<v Speaker 2>Yeah, the last few years we've pretty much consumed the

947
00:53:06.199 --> 00:53:10.119
<v Speaker 2>whole Internet into tokenization. There isn't more Internet to grab,

948
00:53:10.559 --> 00:53:13.920
<v Speaker 2>so that that's not an exponential function, Like we're kind

949
00:53:13.920 --> 00:53:17.639
<v Speaker 2>of addicted to the exponential function, but it only existed

950
00:53:17.679 --> 00:53:21.239
<v Speaker 2>because a small group of people worked extremely hard to

951
00:53:21.280 --> 00:53:25.480
<v Speaker 2>increase the density of silicon substrates. That's the only thing

952
00:53:26.280 --> 00:53:29.400
<v Speaker 2>they you know, most everything else doesn't work that way,

953
00:53:29.519 --> 00:53:32.599
<v Speaker 2>and this doesn't because there's only so much data. And

954
00:53:32.639 --> 00:53:36.639
<v Speaker 2>it's very clear that bringing in more data generated by

955
00:53:36.719 --> 00:53:39.519
<v Speaker 2>AI for this is like taking a photocopy of a photocopy.

956
00:53:39.960 --> 00:53:42.320
<v Speaker 2>It's degenerative, it's not useful data.

957
00:53:43.320 --> 00:53:44.960
<v Speaker 1>Well, I can't wait to talk to you next year

958
00:53:44.960 --> 00:53:47.760
<v Speaker 1>to see what's new and see what else you've learned. Yeah,

959
00:53:47.800 --> 00:53:51.199
<v Speaker 1>it's fantastic. Thank you, Vishwaz. It's always very talking to you.

960
00:53:51.360 --> 00:53:53.880
<v Speaker 3>Always a pleasure to be on this show. Thank you

961
00:53:53.960 --> 00:53:55.159
<v Speaker 3>for inviting me again.

962
00:53:55.679 --> 00:53:57.679
<v Speaker 1>Well, thank you and thanks for listening, and we'll talk

963
00:53:57.679 --> 00:54:20.960
<v Speaker 1>to you next time on dot net rocks. Dot net

964
00:54:21.079 --> 00:54:24.000
<v Speaker 1>Rocks is brought to you by Franklin's Net and produced

965
00:54:24.000 --> 00:54:27.840
<v Speaker 1>by Pop Studios, a full service audio, video and post

966
00:54:27.840 --> 00:54:32.000
<v Speaker 1>production facility located physically in New London, Connecticut, and of

967
00:54:32.039 --> 00:54:36.519
<v Speaker 1>course in the cloud online at pwop dot com.

968
00:54:36.719 --> 00:54:38.880
<v Speaker 4>Visit our website at d O T N E t

969
00:54:39.079 --> 00:54:43.119
<v Speaker 4>R O c k S dot com for RSS feeds, downloads,

970
00:54:43.280 --> 00:54:46.960
<v Speaker 4>mobile apps, comments, and access to the full archives going

971
00:54:47.000 --> 00:54:50.400
<v Speaker 4>back to show number one, recorded in September two thousand

972
00:54:50.400 --> 00:54:50.679
<v Speaker 4>and two.

973
00:54:51.280 --> 00:54:53.639
<v Speaker 1>And make sure you check out our sponsors. They keep

974
00:54:53.719 --> 00:54:56.880
<v Speaker 1>us in business. Now go write some code. See you

975
00:54:56.920 --> 00:55:03.920
<v Speaker 1>next time you got and Daddy see a summer time

976
00:55:05.199 --> 00:55:09.519
<v Speaker 1>that means his home, then my Texas in line vegetable