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 --> 00:00:17.679
<v Speaker 1>We'll get you that and a special dot NetRocks patron mug.

6
00:00:18.160 --> 00:00:34.000
<v Speaker 1>Sign up now at Patreon dot dot NetRocks dot com.

7
00:00:34.119 --> 00:00:38.000
<v Speaker 2>Hey guess what. It's dot net Rocks Steve Sanderson Edition.

8
00:00:38.159 --> 00:00:41.240
<v Speaker 2>I'm Carl Franklin, the amateur Campbell And uh, what can

9
00:00:41.280 --> 00:00:42.799
<v Speaker 2>we say? Richard New Year?

10
00:00:43.039 --> 00:00:46.840
<v Speaker 3>We're you're making a show and checking it twice? Oh wait, no,

11
00:00:47.039 --> 00:00:48.920
<v Speaker 3>Christmas is over? Yeah?

12
00:00:49.320 --> 00:00:52.159
<v Speaker 2>Uh all right, Well we got a lot of sort

13
00:00:52.200 --> 00:00:55.439
<v Speaker 2>of pre show ramble to do, so let's get right

14
00:00:55.479 --> 00:01:05.879
<v Speaker 2>into a better no framework awesome. Well I don't have

15
00:01:05.920 --> 00:01:09.040
<v Speaker 2>a framework piece or anything per se, but I do

16
00:01:09.159 --> 00:01:13.400
<v Speaker 2>have some news about Blazer Train and Blazer Puzzle. So

17
00:01:13.879 --> 00:01:17.920
<v Speaker 2>Blazer Train I have done sparsely since we started the

18
00:01:17.959 --> 00:01:23.680
<v Speaker 2>Blazer Puzzle, just focusing on redoing old things. But I've

19
00:01:23.719 --> 00:01:26.480
<v Speaker 2>started a series on Blazer Train now that's going to

20
00:01:26.560 --> 00:01:30.159
<v Speaker 2>be weekly or every other week on What's New and

21
00:01:30.200 --> 00:01:33.920
<v Speaker 2>Dot at nine. So the first one is published maybe

22
00:01:34.079 --> 00:01:35.879
<v Speaker 2>even the second one by the time this comes out,

23
00:01:36.480 --> 00:01:38.879
<v Speaker 2>and the Blazer Puzzle is going to be a little

24
00:01:38.920 --> 00:01:42.400
<v Speaker 2>different than usual. Typically, what we've done with the Blazer

25
00:01:42.439 --> 00:01:45.680
<v Speaker 2>puzzles we give a problem and we say, okay, take

26
00:01:45.719 --> 00:01:48.319
<v Speaker 2>the week or a few days and find a solution

27
00:01:48.400 --> 00:01:50.439
<v Speaker 2>and email us the solution. Then we pick a winner

28
00:01:50.480 --> 00:01:54.159
<v Speaker 2>from all the right answers. And we're not doing that anymore.

29
00:01:54.680 --> 00:01:57.040
<v Speaker 2>We're going to give you a problem and then we're

30
00:01:57.079 --> 00:02:00.799
<v Speaker 2>going to take a little pause, give people a chance

31
00:02:00.840 --> 00:02:04.480
<v Speaker 2>to duck out or press the pause button on the video,

32
00:02:04.920 --> 00:02:07.239
<v Speaker 2>and then we're going to give the solution. So no

33
00:02:07.319 --> 00:02:11.560
<v Speaker 2>more winners, no more mugs, no more don't post this

34
00:02:11.639 --> 00:02:14.080
<v Speaker 2>on social media. We want you to engage with us more.

35
00:02:14.400 --> 00:02:16.719
<v Speaker 2>So it's kind of fun. It's more fun.

36
00:02:17.000 --> 00:02:17.680
<v Speaker 3>That's cool, man.

37
00:02:17.800 --> 00:02:20.599
<v Speaker 2>Yeah, So that's what I got. Just some updates from

38
00:02:20.639 --> 00:02:27.360
<v Speaker 2>my Blazer videos. And also we should probably just briefly

39
00:02:27.400 --> 00:02:29.800
<v Speaker 2>go over some things that happened in nineteen thirty six.

40
00:02:30.000 --> 00:02:31.680
<v Speaker 3>This is episode ninety thirty six.

41
00:02:32.120 --> 00:02:34.639
<v Speaker 2>Yeah, since it's episode nineteen thirty six and I want

42
00:02:34.639 --> 00:02:37.599
<v Speaker 2>to be labor stuff and we don't want to take

43
00:02:37.599 --> 00:02:39.719
<v Speaker 2>too much time. But there are a few important things

44
00:02:39.759 --> 00:02:44.000
<v Speaker 2>that happened. Of course, you know, Nazi Germany just kind

45
00:02:44.039 --> 00:02:48.599
<v Speaker 2>of ratcheted up in general. So there's a whole bunch

46
00:02:48.680 --> 00:02:53.319
<v Speaker 2>of things. But on February fourth, Keynes John Maynard Keynes

47
00:02:53.400 --> 00:02:58.360
<v Speaker 2>published The General Theory of Employment Interest in Money, a

48
00:02:58.479 --> 00:03:04.879
<v Speaker 2>revolutionary economic work that fundamentally transformed modern modern macroeconomic thought

49
00:03:05.759 --> 00:03:10.319
<v Speaker 2>and policymaking. Everybody knows about Keynesy and economics now. On

50
00:03:10.400 --> 00:03:15.360
<v Speaker 2>February nineteenth, Marion Anderson performed at the White House, significant

51
00:03:16.199 --> 00:03:19.000
<v Speaker 2>in the context of racial segregation, would later be remembered

52
00:03:19.000 --> 00:03:22.759
<v Speaker 2>as a pivotal, pivotal moment in the civil rights movement.

53
00:03:23.960 --> 00:03:27.800
<v Speaker 2>March first, the first p seventeen bomber was delivered on

54
00:03:27.919 --> 00:03:34.360
<v Speaker 2>March seventeenth, Saint Patrick's Day Flood in Pittsburgh, Terrible, terrible flood.

55
00:03:36.199 --> 00:03:41.520
<v Speaker 2>April thirteenth. Hitler appears on Time magazine cover. May seventh,

56
00:03:41.560 --> 00:03:47.520
<v Speaker 2>Italian annexation of Ethiopia, and they continued to do a

57
00:03:47.520 --> 00:03:54.120
<v Speaker 2>lot of damage in Ethiopia, the Italian military in On

58
00:03:54.159 --> 00:03:59.479
<v Speaker 2>May twenty eighth, Alan Turing submitted the groundbreaking paper on computability.

59
00:04:00.919 --> 00:04:05.199
<v Speaker 2>And he's a hero among us developers, of course, in

60
00:04:05.240 --> 00:04:09.960
<v Speaker 2>mathematicians everywhere, and you know, do you have anything else

61
00:04:10.000 --> 00:04:11.719
<v Speaker 2>you want to add? I mean, there's tons of things

62
00:04:11.719 --> 00:04:14.199
<v Speaker 2>that happened, but sure, well you know, I stick towards

63
00:04:14.240 --> 00:04:17.120
<v Speaker 2>the Zion stuff. So in nineteen thirty six was the

64
00:04:17.240 --> 00:04:21.800
<v Speaker 2>year that the last thylacine died, also known as the

65
00:04:21.839 --> 00:04:25.399
<v Speaker 2>Tasmanian tiger. Although it was more wolf like than anything else.

66
00:04:25.839 --> 00:04:29.240
<v Speaker 2>It had been hunted because they believed it had been

67
00:04:29.279 --> 00:04:31.399
<v Speaker 2>hunted for bounty because they believed it was killing sheep.

68
00:04:31.439 --> 00:04:34.360
<v Speaker 2>Turned out to not be true. The last one died

69
00:04:34.439 --> 00:04:38.439
<v Speaker 2>of neglect in the Tasmanian zoo. This is strictly a

70
00:04:38.480 --> 00:04:43.399
<v Speaker 2>Tasmanian animal, and coincidentally, there is an organization working hard

71
00:04:43.480 --> 00:04:48.800
<v Speaker 2>to de extinct the thylaccene. Wow like Jurassic Park style or.

72
00:04:48.920 --> 00:04:52.319
<v Speaker 3>Well, no, his Jurassic Park is fiction.

73
00:04:53.759 --> 00:04:55.279
<v Speaker 2>No, no, of course, but you know what I mean

74
00:04:55.399 --> 00:04:56.360
<v Speaker 2>to cloning DNA.

75
00:04:56.480 --> 00:05:00.920
<v Speaker 3>But in Jurassic Park's approach was to find DNA of

76
00:05:00.959 --> 00:05:04.600
<v Speaker 3>the dinosaurs and then fill in the gaps of amphibian DNA,

77
00:05:04.639 --> 00:05:07.439
<v Speaker 3>which is you know, again it's kind of fictional. What

78
00:05:07.480 --> 00:05:10.560
<v Speaker 3>they're actually doing, these folks are doing, is they are

79
00:05:10.720 --> 00:05:15.160
<v Speaker 3>finding the closest living genetic relative because they have good

80
00:05:15.199 --> 00:05:19.120
<v Speaker 3>genetic material for the thylacine, and then they are changing

81
00:05:19.199 --> 00:05:22.600
<v Speaker 3>that DNA to match the thylacine. Okay, but they're also

82
00:05:22.680 --> 00:05:25.000
<v Speaker 3>working closely with Tasmani itself, like if they're going to

83
00:05:25.079 --> 00:05:26.839
<v Speaker 3>does it make sense to reinduce it all that sort

84
00:05:26.879 --> 00:05:29.439
<v Speaker 3>of thing, and there's a strong will to bring that

85
00:05:29.480 --> 00:05:32.360
<v Speaker 3>animal back. It'll actually helps stabilize the ecosystem in Tasmania.

86
00:05:32.439 --> 00:05:35.439
<v Speaker 3>Now that the thylacine has been gone for some ninety years,

87
00:05:36.399 --> 00:05:38.319
<v Speaker 3>Tasmani has been stuffing air effects for not having a

88
00:05:38.319 --> 00:05:41.600
<v Speaker 3>top tier predator, and so there's an idea that bringing

89
00:05:41.639 --> 00:05:43.040
<v Speaker 3>back the thylascene would help.

90
00:05:43.199 --> 00:05:45.360
<v Speaker 2>See you get a mini geek out in every dot

91
00:05:45.439 --> 00:05:46.240
<v Speaker 2>net Rocks show.

92
00:05:46.360 --> 00:05:48.439
<v Speaker 3>There you go. I mean, I've been keeping notes on

93
00:05:48.519 --> 00:05:50.600
<v Speaker 3>de extinction for the mammoth and a few others and

94
00:05:50.639 --> 00:05:52.000
<v Speaker 3>so forth. The thilastine has been one of them, and

95
00:05:52.000 --> 00:05:53.759
<v Speaker 3>it just happens to be that nineteen thirty six was

96
00:05:53.759 --> 00:05:55.360
<v Speaker 3>the year that the last thyloscene died.

97
00:05:55.560 --> 00:05:57.480
<v Speaker 2>Wow, well, who's talking to us today?

98
00:05:57.560 --> 00:06:00.720
<v Speaker 3>Richard Graudy comment off of show nineteen twenty two, the

99
00:06:00.759 --> 00:06:02.920
<v Speaker 3>one we did with our friend Dan Roth and the

100
00:06:02.959 --> 00:06:06.160
<v Speaker 3>Fall of twenty four talking about Blazer and dot net nine.

101
00:06:06.879 --> 00:06:09.759
<v Speaker 3>And this comment seemed particularly relevant to our conversation today

102
00:06:09.800 --> 00:06:11.800
<v Speaker 3>because it's from Brent from Atlanta, who said it was Grelway.

103
00:06:11.800 --> 00:06:13.360
<v Speaker 3>Was great to hear from Dan. He binds me of

104
00:06:13.399 --> 00:06:15.439
<v Speaker 3>a brilliant co worker of mine who just retired from

105
00:06:15.480 --> 00:06:20.519
<v Speaker 3>Mongo dB. I'd love to know if coding llm's running

106
00:06:20.560 --> 00:06:23.600
<v Speaker 3>locally like the Quinn two point five coder, will be

107
00:06:23.639 --> 00:06:26.480
<v Speaker 3>easily integrated individual studio. I'm looking to enhance my Blazer

108
00:06:26.519 --> 00:06:28.800
<v Speaker 3>coding with such tools without having to pay for Copilot,

109
00:06:29.120 --> 00:06:31.480
<v Speaker 3>which is preferred to be in verie to Quinn. Anyway,

110
00:06:32.120 --> 00:06:38.000
<v Speaker 3>I love the show. Well, hey get out copilot now free,

111
00:06:38.480 --> 00:06:41.399
<v Speaker 3>So so much for paying for that. B All the

112
00:06:41.399 --> 00:06:44.879
<v Speaker 3>copilots now have options for different back ends you can

113
00:06:44.959 --> 00:06:47.399
<v Speaker 3>run on, so you know, the default is the open

114
00:06:47.439 --> 00:06:49.759
<v Speaker 3>AI one, but if you want to switch to a

115
00:06:49.879 --> 00:06:52.920
<v Speaker 3>LAMA or cloud or anything like that, you can do that. Yeah.

116
00:06:52.959 --> 00:06:54.360
<v Speaker 3>Absolutely so there.

117
00:06:54.399 --> 00:06:56.360
<v Speaker 2>Just as in a side I was talking to the

118
00:06:56.360 --> 00:06:59.160
<v Speaker 2>guys at dev Express and they have a control now

119
00:06:59.639 --> 00:07:02.519
<v Speaker 2>that tracks all of that stuff away and just gives

120
00:07:02.560 --> 00:07:07.120
<v Speaker 2>you like an input box and you can connect it

121
00:07:07.120 --> 00:07:10.160
<v Speaker 2>to wherever you want without any kind of nasty pain.

122
00:07:10.439 --> 00:07:13.199
<v Speaker 3>Nice. Yeah, so yeah, all good things happening, good things,

123
00:07:13.240 --> 00:07:15.480
<v Speaker 3>and so Brent, thank you so much for your comment.

124
00:07:15.639 --> 00:07:17.040
<v Speaker 3>Copy of music Cobuy is on its way to you.

125
00:07:17.079 --> 00:07:18.680
<v Speaker 3>And if you'd like copy of music Cooba, I write

126
00:07:18.680 --> 00:07:20.560
<v Speaker 3>a comment on the website at dotn at Rocks dot

127
00:07:20.560 --> 00:07:22.639
<v Speaker 3>com or on the facebooks. We publish every show there

128
00:07:22.639 --> 00:07:24.079
<v Speaker 3>and if you comment there, we're read it on the show.

129
00:07:24.279 --> 00:07:25.560
<v Speaker 3>We'll send you copy of music Goba.

130
00:07:25.680 --> 00:07:27.680
<v Speaker 2>And you can follow us on other social media. We've

131
00:07:27.680 --> 00:07:30.879
<v Speaker 2>been on ex Twitter forever. We're on mastadon and on

132
00:07:30.959 --> 00:07:36.160
<v Speaker 2>blue Sky, and I believe Richard's also on threads. I

133
00:07:36.199 --> 00:07:38.639
<v Speaker 2>have a Thread's account, but I don't watch it, and

134
00:07:38.720 --> 00:07:40.639
<v Speaker 2>you know, but you can find us out there.

135
00:07:40.879 --> 00:07:42.720
<v Speaker 3>Yep, we're out there. Blue Sky seems to do the

136
00:07:42.720 --> 00:07:43.600
<v Speaker 3>fun one of these days.

137
00:07:43.680 --> 00:07:47.360
<v Speaker 2>Yeah, just some variation of at Carl Franklin at rich Campbell.

138
00:07:48.399 --> 00:07:53.680
<v Speaker 2>So let's bring back our friend Steve Sanderson. This is

139
00:07:53.720 --> 00:07:57.079
<v Speaker 2>a very humble bio that Steve wrote for us. He's

140
00:07:57.079 --> 00:07:59.439
<v Speaker 2>a developer on the dot net team at Microsoft. He

141
00:07:59.519 --> 00:08:02.680
<v Speaker 2>focused as I'm making dot net better for application developers

142
00:08:02.680 --> 00:08:05.720
<v Speaker 2>with a focus on AI and the web. Yeah, he's

143
00:08:05.759 --> 00:08:07.680
<v Speaker 2>done a few things, a couple of things here and there,

144
00:08:07.800 --> 00:08:09.560
<v Speaker 2>not really mentioning in the bio.

145
00:08:10.319 --> 00:08:13.439
<v Speaker 4>Welcome back, Steve, Hello, thank you for bringing me back.

146
00:08:13.879 --> 00:08:14.600
<v Speaker 2>Good to have you.

147
00:08:14.800 --> 00:08:17.720
<v Speaker 3>Yeah, absolutely, man, And you know I always lead this

148
00:08:17.759 --> 00:08:19.560
<v Speaker 3>off the same way. What are you working on?

149
00:08:20.680 --> 00:08:21.680
<v Speaker 4>What am I working on?

150
00:08:23.199 --> 00:08:23.480
<v Speaker 3>Well?

151
00:08:23.560 --> 00:08:26.000
<v Speaker 4>I think, like quite a lot of us, I've started

152
00:08:26.040 --> 00:08:29.800
<v Speaker 4>to focus on the AI side of software.

153
00:08:29.879 --> 00:08:30.920
<v Speaker 2>Oh wow, recently.

154
00:08:32.240 --> 00:08:35.600
<v Speaker 4>Yeah. I think it's a really big opportunity, and there's

155
00:08:35.600 --> 00:08:37.440
<v Speaker 4>many different ways you can think about what it is.

156
00:08:37.519 --> 00:08:39.720
<v Speaker 4>Like on one level, it's like a tool that can

157
00:08:39.759 --> 00:08:41.799
<v Speaker 4>help you write your code, or it's just like a

158
00:08:41.879 --> 00:08:45.000
<v Speaker 4>chat interface or things like that. I think all those

159
00:08:45.039 --> 00:08:47.679
<v Speaker 4>things are fine, but that's not what I'm personally drawn

160
00:08:47.799 --> 00:08:51.399
<v Speaker 4>to as like an area where we can exploit opportunities.

161
00:08:52.000 --> 00:08:55.000
<v Speaker 4>Maybe it's my background, but I feel really drawn to

162
00:08:55.080 --> 00:08:59.600
<v Speaker 4>doing things around applications and doing things for application developers,

163
00:08:59.600 --> 00:09:02.120
<v Speaker 4>and I think about the you know, the many many

164
00:09:02.120 --> 00:09:05.480
<v Speaker 4>people I know who working companies that are producing software

165
00:09:05.919 --> 00:09:09.679
<v Speaker 4>for their customers or for their employees, and things like

166
00:09:10.320 --> 00:09:13.240
<v Speaker 4>how do you actually use AI within that to make

167
00:09:13.279 --> 00:09:15.720
<v Speaker 4>better software? How can you make your software have better

168
00:09:15.759 --> 00:09:18.200
<v Speaker 4>features than it would have had before?

169
00:09:18.279 --> 00:09:21.639
<v Speaker 3>Well, and when you were thinking about that, like I

170
00:09:21.679 --> 00:09:23.720
<v Speaker 3>remember you thinking about trying to make it easier to

171
00:09:23.720 --> 00:09:27.279
<v Speaker 3>put data on web pages, and that made knockout. Yeah. So,

172
00:09:28.320 --> 00:09:30.320
<v Speaker 3>and then you were thinking about how to make it

173
00:09:30.360 --> 00:09:32.279
<v Speaker 3>easier to use c sharp on web pages, and that

174
00:09:32.360 --> 00:09:34.120
<v Speaker 3>made Blazer. So I kind of like it when you're

175
00:09:34.120 --> 00:09:35.919
<v Speaker 3>thinking about things, Steve, good things happening.

176
00:09:37.000 --> 00:09:40.279
<v Speaker 2>I remember last year you did a demo at one

177
00:09:40.279 --> 00:09:42.720
<v Speaker 2>of the Dona comps or something like that. You did

178
00:09:42.720 --> 00:09:46.840
<v Speaker 2>a demo of some AI in AI chat wired up

179
00:09:46.840 --> 00:09:51.360
<v Speaker 2>to data. Yeah, it was in Blazer and it was

180
00:09:51.480 --> 00:09:54.440
<v Speaker 2>just mind blowing. So you've been doing it for a while.

181
00:09:54.639 --> 00:09:57.960
<v Speaker 4>Yeah, that was our e shop support demo. I'm sure

182
00:09:57.960 --> 00:10:01.200
<v Speaker 4>we can add a link to that. Yeah. That was

183
00:10:01.879 --> 00:10:05.919
<v Speaker 4>some exploration around this of what you get when you

184
00:10:05.919 --> 00:10:10.799
<v Speaker 4>put Blazer and AI and typical application business app scenarios together.

185
00:10:11.200 --> 00:10:14.039
<v Speaker 4>And that's an exploration of like a customer support scenario

186
00:10:14.080 --> 00:10:17.720
<v Speaker 4>where people are submitting inquiries and there's some AI that

187
00:10:17.799 --> 00:10:22.480
<v Speaker 4>automatically classifies them as different types of thing, and then

188
00:10:22.600 --> 00:10:26.399
<v Speaker 4>the staff who's trying to deal with customer support gets

189
00:10:27.000 --> 00:10:30.559
<v Speaker 4>like a chat assistant that's able to look through corporate

190
00:10:30.639 --> 00:10:34.480
<v Speaker 4>or enterprise data to provide suggested answers. Fills it out,

191
00:10:34.720 --> 00:10:38.559
<v Speaker 4>you know, rates the customer's satisfaction automatically, all that kind

192
00:10:38.600 --> 00:10:40.960
<v Speaker 4>of state thing, and it just represents a whole own

193
00:10:40.960 --> 00:10:43.559
<v Speaker 4>of scenarios that we think people would probably actually have.

194
00:10:43.759 --> 00:10:45.720
<v Speaker 2>Yeah, I'm looking forward to the day when I can

195
00:10:45.759 --> 00:10:52.279
<v Speaker 2>replace my report criteria selection UI with just a chat box. Yeah,

196
00:10:52.320 --> 00:10:55.240
<v Speaker 2>and you probably can do that already and I can actually,

197
00:10:56.200 --> 00:10:59.039
<v Speaker 2>but you know, it's going to take a little bit

198
00:10:59.080 --> 00:11:01.639
<v Speaker 2>of a paradigm shift for users to want to go

199
00:11:01.720 --> 00:11:04.759
<v Speaker 2>for that perhaps, But you know, nobody's saying you can't

200
00:11:04.799 --> 00:11:05.639
<v Speaker 2>offer it as an option.

201
00:11:05.799 --> 00:11:08.720
<v Speaker 4>Yeah, totally. And you mentioned chat as an interface there.

202
00:11:08.759 --> 00:11:12.639
<v Speaker 4>I think chat is clearly something that people strongly associate

203
00:11:12.679 --> 00:11:15.879
<v Speaker 4>with AI, and it's a thing that we didn't really

204
00:11:15.919 --> 00:11:18.879
<v Speaker 4>have as a form of UI before AI came along,

205
00:11:18.919 --> 00:11:21.120
<v Speaker 4>and so that's kind of exciting and cool. But I

206
00:11:21.159 --> 00:11:23.519
<v Speaker 4>also whenever I talk about this, I really try to

207
00:11:24.159 --> 00:11:27.039
<v Speaker 4>emphasize the fact that chat is not the only way

208
00:11:27.200 --> 00:11:30.799
<v Speaker 4>to benefit from AI, And personally, in a lot of cases,

209
00:11:30.840 --> 00:11:34.000
<v Speaker 4>I don't actually like typing into chat boxes like it.

210
00:11:34.240 --> 00:11:38.159
<v Speaker 4>When I'm using my computer to do something productive, my

211
00:11:38.240 --> 00:11:40.080
<v Speaker 4>mind is focused on the task and I don't really

212
00:11:40.120 --> 00:11:43.440
<v Speaker 4>want to be like explaining stuff in English to the computer. Yeah,

213
00:11:43.720 --> 00:11:46.559
<v Speaker 4>and so I think a lot of the time when

214
00:11:46.559 --> 00:11:48.559
<v Speaker 4>we think about how we can add AI to our

215
00:11:48.600 --> 00:11:53.159
<v Speaker 4>applications and produce genuinely more productive apps, it's about using

216
00:11:53.200 --> 00:11:56.480
<v Speaker 4>AI on the back end just sort of like almost

217
00:11:56.559 --> 00:11:59.879
<v Speaker 4>like secretly, without involving the user. It's just predicting what

218
00:12:00.039 --> 00:12:02.159
<v Speaker 4>they want and doing parts of the job for them

219
00:12:02.200 --> 00:12:05.120
<v Speaker 4>ahead of the time so they don't have to do it.

220
00:12:05.120 --> 00:12:07.519
<v Speaker 2>It does bring to mind a couple of really good

221
00:12:07.759 --> 00:12:11.399
<v Speaker 2>text interfaces where you're writing and then things are helping you.

222
00:12:12.399 --> 00:12:15.960
<v Speaker 2>Obviously get ub copilot and go back to intelligence and

223
00:12:16.000 --> 00:12:20.159
<v Speaker 2>statement completion and see sharp or even writing queries in

224
00:12:20.519 --> 00:12:23.720
<v Speaker 2>SQL management studio, you know when you say select star

225
00:12:23.840 --> 00:12:26.639
<v Speaker 2>from and you get dropped down. You know, you could

226
00:12:26.679 --> 00:12:29.600
<v Speaker 2>implement that in a chatbot where you could say I

227
00:12:29.639 --> 00:12:32.919
<v Speaker 2>want to see all the reports of type and then

228
00:12:33.679 --> 00:12:39.600
<v Speaker 2>you know, transaction type, whatever, whatever type of reports. You know,

229
00:12:39.679 --> 00:12:43.559
<v Speaker 2>those things will probably come in the in the AI

230
00:12:43.840 --> 00:12:45.600
<v Speaker 2>front end chat boxes.

231
00:12:45.720 --> 00:12:48.879
<v Speaker 4>I'm sure they will. Yeah. And another good example of

232
00:12:48.879 --> 00:12:53.080
<v Speaker 4>that is, of course, as you already mentioned, visual studio Copilot.

233
00:12:53.840 --> 00:12:56.200
<v Speaker 4>And one thing that I really love about that is

234
00:12:57.320 --> 00:12:59.720
<v Speaker 4>the fact that I don't have to explain to it

235
00:13:00.080 --> 00:13:02.080
<v Speaker 4>what I want it to do, Like it's there while

236
00:13:02.120 --> 00:13:06.480
<v Speaker 4>I'm writing code and producing sensible suggestions for me without

237
00:13:06.480 --> 00:13:09.080
<v Speaker 4>me stopping to say I need to do X. It's

238
00:13:09.159 --> 00:13:11.679
<v Speaker 4>just you know, inferring that from what I've already typed

239
00:13:11.720 --> 00:13:12.799
<v Speaker 4>in code, which is I've.

240
00:13:12.600 --> 00:13:14.720
<v Speaker 3>Seen this happen in Excel. I don't know if you've

241
00:13:14.720 --> 00:13:16.960
<v Speaker 3>played with Excel lately if you have that stuff turned on.

242
00:13:17.080 --> 00:13:20.279
<v Speaker 3>But if if you're doing a pattern of entry into

243
00:13:21.080 --> 00:13:24.000
<v Speaker 3>a series of a column of cells, it starts pre

244
00:13:24.120 --> 00:13:26.399
<v Speaker 3>populating it with the next one it thinks you want,

245
00:13:26.799 --> 00:13:29.159
<v Speaker 3>and it's I mean, the easy one is like one, two, three,

246
00:13:29.279 --> 00:13:32.799
<v Speaker 3>but you know, first of each month, it's figured that

247
00:13:32.840 --> 00:13:37.399
<v Speaker 3>one out, Like you're exactly right. It's not doing it

248
00:13:37.399 --> 00:13:39.320
<v Speaker 3>for you. You're not telling it what to do. It's

249
00:13:39.360 --> 00:13:42.440
<v Speaker 3>just looking at what you're doing and then shortcutting instead

250
00:13:42.440 --> 00:13:43.799
<v Speaker 3>of me having to type it out. Now I'm just

251
00:13:43.879 --> 00:13:47.480
<v Speaker 3>like tab yep, I'll keep that, tah that and so forth.

252
00:13:47.519 --> 00:13:49.960
<v Speaker 3>Like that's really subtle and clever.

253
00:13:49.919 --> 00:13:52.840
<v Speaker 2>And it doesn't have a lobotomy like Clippy. But it's

254
00:13:52.879 --> 00:13:56.080
<v Speaker 2>the you know, tried to it's trying to solve the

255
00:13:56.159 --> 00:13:59.960
<v Speaker 2>same problem. Really, I mean, it's the whole idea of clippy,

256
00:14:00.519 --> 00:14:01.759
<v Speaker 2>you know, without a lobotomy.

257
00:14:03.440 --> 00:14:06.759
<v Speaker 3>Well, when we've had smart populating and forms and things

258
00:14:06.840 --> 00:14:09.440
<v Speaker 3>like our browsers know our addresses and so if you

259
00:14:09.639 --> 00:14:11.759
<v Speaker 3>looks like you're starting a type of address, it finds

260
00:14:11.799 --> 00:14:13.320
<v Speaker 3>the rest of the boxes and fills them all in

261
00:14:13.360 --> 00:14:17.919
<v Speaker 3>for you. Like that kind of thing, and actually address

262
00:14:17.960 --> 00:14:19.320
<v Speaker 3>fill in is one of those ones I think people

263
00:14:19.320 --> 00:14:20.720
<v Speaker 3>have worked really hard on where it's like, hey, when

264
00:14:20.799 --> 00:14:23.080
<v Speaker 3>you seeing your postcode, okay, well now I know your

265
00:14:23.080 --> 00:14:24.320
<v Speaker 3>city in state right, Like.

266
00:14:24.440 --> 00:14:26.879
<v Speaker 2>The country and postcode sort of reverse.

267
00:14:26.559 --> 00:14:29.840
<v Speaker 3>The thing up. But now I start thinking about forms

268
00:14:29.879 --> 00:14:33.240
<v Speaker 3>over data, Like I'm really interested in the machine learning

269
00:14:33.279 --> 00:14:36.679
<v Speaker 3>models that study a user's workflow and start to tailor

270
00:14:36.759 --> 00:14:40.000
<v Speaker 3>their behavior to that user. Like if you do the

271
00:14:40.080 --> 00:14:42.480
<v Speaker 3>same thing every day in this app, how do I

272
00:14:42.600 --> 00:14:44.000
<v Speaker 3>make it quicker for you?

273
00:14:44.279 --> 00:14:48.000
<v Speaker 4>Yeah, that's an interesting area. People have started speculating like

274
00:14:48.240 --> 00:14:51.720
<v Speaker 4>about really far off futuristic things which are interesting. I

275
00:14:52.039 --> 00:14:55.240
<v Speaker 4>don't know what the sort of short term thing is here,

276
00:14:55.399 --> 00:15:00.399
<v Speaker 4>Like there's already products and demos out there of AI

277
00:15:00.480 --> 00:15:04.879
<v Speaker 4>systems that generate a UI on demand, so you know,

278
00:15:04.919 --> 00:15:07.519
<v Speaker 4>while a user is doing some task, there isn't a

279
00:15:07.519 --> 00:15:10.559
<v Speaker 4>pre defined set of textboxers, a pre defined set of

280
00:15:10.559 --> 00:15:14.759
<v Speaker 4>wizard steps or whatever. But some AI is being asked

281
00:15:14.279 --> 00:15:16.840
<v Speaker 4>to make up a UI on the fly based on

282
00:15:16.879 --> 00:15:19.759
<v Speaker 4>what the user appears to be doing. That's tailored towards

283
00:15:19.799 --> 00:15:22.559
<v Speaker 4>that task, And I think that's pretty much still a

284
00:15:22.759 --> 00:15:26.000
<v Speaker 4>sort of proof of concept level right now. I doubt

285
00:15:26.000 --> 00:15:29.159
<v Speaker 4>that anyone's completely relying on that to ship and app with,

286
00:15:29.360 --> 00:15:32.360
<v Speaker 4>but it's conceivable that, you know, five years from now,

287
00:15:32.960 --> 00:15:36.519
<v Speaker 4>the way we interact with computers will be much more

288
00:15:36.559 --> 00:15:39.360
<v Speaker 4>sort of generated on demand for us rather than pre defined.

289
00:15:39.559 --> 00:15:41.480
<v Speaker 2>Is that one of a good example of what you

290
00:15:41.559 --> 00:15:45.200
<v Speaker 2>mean by AI working on the back end without you know,

291
00:15:45.480 --> 00:15:48.000
<v Speaker 2>you really noticing it all that much, or were you

292
00:15:48.039 --> 00:15:49.080
<v Speaker 2>thinking of something else.

293
00:15:49.320 --> 00:15:52.559
<v Speaker 4>I was thinking a much simpler thing. So the dynamically

294
00:15:52.559 --> 00:15:55.480
<v Speaker 4>make up a UI as the user is working is

295
00:15:55.519 --> 00:15:58.600
<v Speaker 4>like super sci fi futuristic stuff, which by which I

296
00:15:58.639 --> 00:16:00.639
<v Speaker 4>mean like it's not going to be several months away.

297
00:16:00.720 --> 00:16:02.919
<v Speaker 3>But like you know with the pets of AI.

298
00:16:04.720 --> 00:16:09.399
<v Speaker 4>But no, what I meant was something like really straightforward

299
00:16:09.440 --> 00:16:11.799
<v Speaker 4>stuff that you can code up in in ten minutes.

300
00:16:12.759 --> 00:16:16.799
<v Speaker 4>So the kind of like core features that you can

301
00:16:16.840 --> 00:16:20.840
<v Speaker 4>do with AI, stuff like being able to automatically classify text,

302
00:16:21.000 --> 00:16:25.639
<v Speaker 4>automatically extracting structured data from fuzzy inputs, whether that's plain

303
00:16:25.679 --> 00:16:31.279
<v Speaker 4>text or images, ability to summarize, translate, ability to detect

304
00:16:31.519 --> 00:16:35.759
<v Speaker 4>anomalies in data, the ability to score user sentiment. All

305
00:16:35.799 --> 00:16:38.559
<v Speaker 4>these kinds of things you can do programmatically on the

306
00:16:38.559 --> 00:16:41.399
<v Speaker 4>back end of your application and then use that to

307
00:16:42.559 --> 00:16:46.440
<v Speaker 4>you know, trigger workflows automatically. Like some message comes in

308
00:16:46.480 --> 00:16:49.720
<v Speaker 4>and it appears to be a complaint, Well you can automatically,

309
00:16:50.200 --> 00:16:52.480
<v Speaker 4>you know, send a message to the person who deals

310
00:16:52.519 --> 00:16:55.720
<v Speaker 4>with complaints or something like that. Or you get something

311
00:16:55.759 --> 00:17:00.360
<v Speaker 4>that you know, you get a large amount of text

312
00:17:00.559 --> 00:17:03.720
<v Speaker 4>in from something and you can summarize it down to

313
00:17:03.759 --> 00:17:07.599
<v Speaker 4>one sentence to display as like the heading within a

314
00:17:07.599 --> 00:17:09.880
<v Speaker 4>table or something like that. You know, there's so many

315
00:17:09.920 --> 00:17:14.799
<v Speaker 4>ways that you can use AI systems programmatically to make

316
00:17:14.799 --> 00:17:17.160
<v Speaker 4>your application just feel that bit more intelligent.

317
00:17:17.400 --> 00:17:19.559
<v Speaker 2>It sounds like pattern matching on steroids.

318
00:17:19.680 --> 00:17:20.799
<v Speaker 4>Yeah, in in some ways, you.

319
00:17:20.799 --> 00:17:22.680
<v Speaker 2>Know the things that we loved pattern matching for.

320
00:17:23.160 --> 00:17:26.839
<v Speaker 4>Well, arguably at the lowest level, that's what language models are.

321
00:17:27.000 --> 00:17:31.039
<v Speaker 3>Yeah. Yeah, it is all pattern managing matching tokens effectively, but.

322
00:17:31.000 --> 00:17:33.240
<v Speaker 2>It's not stuff that you necessarily have to do in

323
00:17:33.319 --> 00:17:36.759
<v Speaker 2>raw code. You know, absolutely the language has a pattern

324
00:17:36.759 --> 00:17:38.160
<v Speaker 2>matching feature and you're using that.

325
00:17:38.640 --> 00:17:42.039
<v Speaker 4>Yeah. Yeah, there are tons of application features that people

326
00:17:42.440 --> 00:17:46.240
<v Speaker 4>could be using quite easily and cheaply, especially in terms

327
00:17:46.279 --> 00:17:49.359
<v Speaker 4>of the amount of developer effort. Something like semantic search,

328
00:17:49.400 --> 00:17:52.359
<v Speaker 4>for example, Like the naming makes it sound kind of

329
00:17:52.720 --> 00:17:55.079
<v Speaker 4>fancy and advanced or something like that, but it's really not.

330
00:17:55.559 --> 00:17:57.720
<v Speaker 4>You know, you could you can take any search feature

331
00:17:57.759 --> 00:18:01.000
<v Speaker 4>that you've got today and upgrade it to be semantic search,

332
00:18:01.359 --> 00:18:04.200
<v Speaker 4>like within an afternoon, and at least at a sort

333
00:18:04.240 --> 00:18:06.400
<v Speaker 4>of prototype level, and see whether or not that's going

334
00:18:06.440 --> 00:18:09.440
<v Speaker 4>to benefit your application, so that users don't need to

335
00:18:09.480 --> 00:18:11.920
<v Speaker 4>type things correctly and they don't need to phrase things

336
00:18:11.960 --> 00:18:14.240
<v Speaker 4>in a particular way, but it just sort of smartly

337
00:18:14.279 --> 00:18:16.240
<v Speaker 4>works out what they're trying to search for.

338
00:18:16.400 --> 00:18:18.960
<v Speaker 3>Well. Semantic search to me seems like one of those

339
00:18:19.119 --> 00:18:23.000
<v Speaker 3>buzzword phrases of a promise of a better future, right,

340
00:18:23.039 --> 00:18:26.599
<v Speaker 3>I mean, we've been arguing about semantic search since the

341
00:18:26.680 --> 00:18:29.799
<v Speaker 3>web was invented, right. Even Tim Berner's lead was like,

342
00:18:29.839 --> 00:18:31.519
<v Speaker 3>this is what this is all about. It's just a

343
00:18:31.599 --> 00:18:34.079
<v Speaker 3>question of or we finally got and we finally had

344
00:18:34.079 --> 00:18:37.759
<v Speaker 3>a set of tools that can do it consistently take

345
00:18:37.799 --> 00:18:40.880
<v Speaker 3>the semantical information around it and say you make a

346
00:18:40.960 --> 00:18:42.119
<v Speaker 3>more informed search.

347
00:18:42.359 --> 00:18:44.640
<v Speaker 4>Well, I personally think that when it comes to just

348
00:18:45.319 --> 00:18:47.720
<v Speaker 4>using embedding models, which are one of the two main

349
00:18:47.799 --> 00:18:53.519
<v Speaker 4>types of language models that people use today, to take

350
00:18:53.680 --> 00:18:57.839
<v Speaker 4>things like document titles or text from documents, convert them

351
00:18:57.839 --> 00:19:00.519
<v Speaker 4>into embeddings and then be able to search through those

352
00:19:01.640 --> 00:19:05.160
<v Speaker 4>in a way that matches on meaning rather than exact

353
00:19:05.279 --> 00:19:09.000
<v Speaker 4>string matches is a very straightforward thing to achieve, Like,

354
00:19:09.039 --> 00:19:11.720
<v Speaker 4>it's a really well trodden path by now, We've got

355
00:19:12.279 --> 00:19:15.960
<v Speaker 4>so many cheap ways of doing it that I think

356
00:19:16.000 --> 00:19:18.680
<v Speaker 4>that most people who have got any kind of application

357
00:19:19.359 --> 00:19:21.039
<v Speaker 4>and do as any kind of search feature ought to

358
00:19:21.039 --> 00:19:22.000
<v Speaker 4>be thinking about doing that.

359
00:19:22.119 --> 00:19:24.400
<v Speaker 2>We think about it this way, like you make a

360
00:19:24.480 --> 00:19:29.599
<v Speaker 2>document a PDF document of rules that your software must follow, right,

361
00:19:29.640 --> 00:19:34.119
<v Speaker 2>and then just set the AI on it and say, Okay,

362
00:19:34.640 --> 00:19:37.599
<v Speaker 2>don't let me break the rules in my software. Okay,

363
00:19:39.400 --> 00:19:41.400
<v Speaker 2>there's a there's a sci fi for you.

364
00:19:42.039 --> 00:19:44.759
<v Speaker 4>Yeah, it's it's a scary thing. So, I mean, AI

365
00:19:45.079 --> 00:19:48.200
<v Speaker 4>has so much promise, right, But at the same time,

366
00:19:48.559 --> 00:19:53.200
<v Speaker 4>it also kind of violates many of the assumptions that

367
00:19:53.240 --> 00:19:56.039
<v Speaker 4>we've had about how software should work, like, particularly when

368
00:19:56.119 --> 00:19:59.519
<v Speaker 4>you talk about rules that can't be violated or anything

369
00:19:59.519 --> 00:20:01.680
<v Speaker 4>to do with security. You know, as soon as you

370
00:20:01.720 --> 00:20:04.960
<v Speaker 4>bring AI into it and have a language model making

371
00:20:05.000 --> 00:20:07.880
<v Speaker 4>decisions about what a user kind of can't do, everything

372
00:20:07.880 --> 00:20:10.920
<v Speaker 4>becomes so fuzzy. Like you tell the language model a

373
00:20:10.920 --> 00:20:13.200
<v Speaker 4>certain user should or shouldn't be allowed to do something,

374
00:20:13.839 --> 00:20:15.680
<v Speaker 4>but if that user says that they want to do

375
00:20:15.720 --> 00:20:17.640
<v Speaker 4>it persuasively enough, then it might just let them do

376
00:20:17.720 --> 00:20:18.240
<v Speaker 4>it anyway.

377
00:20:18.680 --> 00:20:22.000
<v Speaker 3>Persuading software, I said in air quotes.

378
00:20:22.039 --> 00:20:24.440
<v Speaker 2>But what I would do in that situation is I

379
00:20:24.440 --> 00:20:27.519
<v Speaker 2>would want a tool that says, Okay, here's the document

380
00:20:27.559 --> 00:20:31.039
<v Speaker 2>of rules and business rules. Right, not necessarily you know,

381
00:20:31.160 --> 00:20:34.759
<v Speaker 2>thou shalt not or whatever, but and then say, and

382
00:20:34.839 --> 00:20:39.119
<v Speaker 2>here's my code and here's my rules. Now generate some

383
00:20:39.240 --> 00:20:41.559
<v Speaker 2>code from me that I can where I can plug

384
00:20:41.599 --> 00:20:43.720
<v Speaker 2>the holes. Yeah, okay, you know, and then I can

385
00:20:44.000 --> 00:20:46.200
<v Speaker 2>look at I can do that once, and then I

386
00:20:46.240 --> 00:20:48.839
<v Speaker 2>can look at that code those things and see if

387
00:20:48.880 --> 00:20:51.720
<v Speaker 2>they if that's a good idea to implement them. But

388
00:20:52.240 --> 00:20:53.960
<v Speaker 2>you know, that's how I want to use AI. I

389
00:20:54.000 --> 00:20:56.960
<v Speaker 2>wanted to either generate some code or give me some

390
00:20:57.000 --> 00:21:00.119
<v Speaker 2>suggestions and they'll let me write the final you know,

391
00:21:00.240 --> 00:21:02.720
<v Speaker 2>do the final cut and paste or whatever and testing.

392
00:21:02.799 --> 00:21:05.599
<v Speaker 4>Yeah, I think that's reasonable. So that's using GAI as

393
00:21:05.599 --> 00:21:09.119
<v Speaker 4>a coding assistant, which is definitely a very very valuable

394
00:21:09.319 --> 00:21:11.680
<v Speaker 4>part of the whole thing. And a lot of people

395
00:21:11.680 --> 00:21:15.319
<v Speaker 4>are doing that and that's great. There are limitations to that,

396
00:21:15.599 --> 00:21:20.000
<v Speaker 4>you know, one of them is ultimately it might still

397
00:21:20.039 --> 00:21:22.359
<v Speaker 4>get it wrong and you may or may not actually

398
00:21:22.440 --> 00:21:24.200
<v Speaker 4>spark the fact that it's got it wrong. Like, there

399
00:21:24.200 --> 00:21:28.440
<v Speaker 4>could still be bugs, especially subtle security bugs. It's not magic.

400
00:21:29.640 --> 00:21:35.400
<v Speaker 4>And secondly, if you're constrained to only using GAI at

401
00:21:35.400 --> 00:21:38.599
<v Speaker 4>development time and not at run time, then that constrains

402
00:21:38.599 --> 00:21:41.960
<v Speaker 4>the sorts of features that you can ship. So I

403
00:21:41.960 --> 00:21:44.240
<v Speaker 4>don't think it's like the ultimate or only solution, but

404
00:21:44.279 --> 00:21:47.480
<v Speaker 4>it's definitely a valuable and valid way of thinking about

405
00:21:47.839 --> 00:21:49.279
<v Speaker 4>things in a lot of cases.

406
00:21:49.279 --> 00:21:51.880
<v Speaker 2>Right, And I you know, just as an example, what

407
00:21:51.960 --> 00:21:54.519
<v Speaker 2>I talked about is just an evolution of what we're

408
00:21:54.519 --> 00:21:58.680
<v Speaker 2>already doing now with you know, Copilot and all of

409
00:21:58.720 --> 00:22:02.119
<v Speaker 2>that stuff. Yeah, so I can see those things happening,

410
00:22:02.200 --> 00:22:06.000
<v Speaker 2>you know, more discrete tools for helping us shore up

411
00:22:06.079 --> 00:22:10.799
<v Speaker 2>our code. Static code analysis another great way to use AI.

412
00:22:11.880 --> 00:22:15.920
<v Speaker 2>But yeah, I would, I would be skeptical to Here's

413
00:22:16.000 --> 00:22:19.440
<v Speaker 2>here's something that Jeff Fritz and I were thinking about,

414
00:22:20.960 --> 00:22:25.279
<v Speaker 2>and it's not necessarily AI, but it's calling translation services

415
00:22:25.279 --> 00:22:28.200
<v Speaker 2>on the fly so that somebody you don't have to

416
00:22:28.279 --> 00:22:34.000
<v Speaker 2>actually do different language versions of your application. You could

417
00:22:34.039 --> 00:22:37.279
<v Speaker 2>just you know, you're in Japan, you bring up everything

418
00:22:37.279 --> 00:22:39.799
<v Speaker 2>in Japanese and it goes and does a translation. But

419
00:22:39.880 --> 00:22:44.359
<v Speaker 2>now you're relying on that translation to be accurate in

420
00:22:44.400 --> 00:22:47.599
<v Speaker 2>real time. Not only that, but you're racking up all

421
00:22:47.680 --> 00:22:51.599
<v Speaker 2>the API calls that you're doing. So another idea would

422
00:22:51.640 --> 00:22:56.240
<v Speaker 2>be to just take a tool that would generate all

423
00:22:56.279 --> 00:23:01.319
<v Speaker 2>the text and all the resources in every language and

424
00:23:01.359 --> 00:23:04.400
<v Speaker 2>then boom, now you've got some Now you can actually

425
00:23:04.440 --> 00:23:05.039
<v Speaker 2>test it.

426
00:23:04.960 --> 00:23:06.480
<v Speaker 4>And I'm sure and a lot of people are doing

427
00:23:06.519 --> 00:23:07.480
<v Speaker 4>that absolutely.

428
00:23:08.200 --> 00:23:11.599
<v Speaker 3>Yeah. Yeah. The language tokenisation strategy that llm's brought to

429
00:23:11.640 --> 00:23:13.519
<v Speaker 3>the table made translation.

430
00:23:13.319 --> 00:23:15.519
<v Speaker 2>A lot easier, yeah, and more accurate.

431
00:23:15.680 --> 00:23:17.559
<v Speaker 3>And it does seem to be more accurate as well.

432
00:23:17.799 --> 00:23:22.000
<v Speaker 4>Yeah. Well, modern large language models entirely come out of

433
00:23:22.440 --> 00:23:25.240
<v Speaker 4>machine translation. That's where this whole thing started, you know,

434
00:23:25.319 --> 00:23:30.920
<v Speaker 4>building mL models that could translate between human languages, and

435
00:23:31.000 --> 00:23:34.599
<v Speaker 4>the way that that was very successful through transformers became

436
00:23:35.240 --> 00:23:36.519
<v Speaker 4>you know what we have today.

437
00:23:36.839 --> 00:23:40.319
<v Speaker 3>Sort of the key ingredient to what began the path

438
00:23:40.319 --> 00:23:44.119
<v Speaker 3>towards GPT was it's the translation problem first, and it's

439
00:23:44.160 --> 00:23:46.759
<v Speaker 3>just yeah, it's one of its superpowers. And what I

440
00:23:46.799 --> 00:23:48.680
<v Speaker 3>like about it is, for the most part, we haven't noticed.

441
00:23:48.759 --> 00:23:51.200
<v Speaker 3>It's just that every all translations seem to be better

442
00:23:51.480 --> 00:23:54.920
<v Speaker 3>and cheaper and more prevalent, just showing up in more places.

443
00:23:55.039 --> 00:23:55.200
<v Speaker 1>Yeah.

444
00:23:55.200 --> 00:23:55.559
<v Speaker 3>Absolute.

445
00:23:55.559 --> 00:23:57.160
<v Speaker 4>In fact, it was just today that I don't know

446
00:23:57.160 --> 00:24:00.200
<v Speaker 4>if you saw VLC the media player. The oper was

447
00:24:00.240 --> 00:24:04.759
<v Speaker 4>media Player as a shipped to feature this morning, which

448
00:24:04.880 --> 00:24:10.359
<v Speaker 4>adds automatic subtitles to what you're watching, is controversial because

449
00:24:10.359 --> 00:24:12.079
<v Speaker 4>people are not sure if the quality is good enough.

450
00:24:12.119 --> 00:24:14.480
<v Speaker 4>But yeah, you're right, it is showing up all over

451
00:24:14.480 --> 00:24:14.839
<v Speaker 4>the place.

452
00:24:15.079 --> 00:24:20.519
<v Speaker 2>So how likely are you to use a chat bot

453
00:24:20.599 --> 00:24:24.920
<v Speaker 2>on a website that pretends to be a representative of

454
00:24:24.960 --> 00:24:25.839
<v Speaker 2>the company. Oh?

455
00:24:25.920 --> 00:24:30.240
<v Speaker 4>Usually, I mean I'm usually my general feeling when encountering

456
00:24:30.279 --> 00:24:33.000
<v Speaker 4>something like that is oh no, what have they done?

457
00:24:33.480 --> 00:24:38.920
<v Speaker 4>But I did have one example of a time quite

458
00:24:38.960 --> 00:24:40.680
<v Speaker 4>recently where I had to use a chat butt and

459
00:24:40.680 --> 00:24:43.640
<v Speaker 4>it actually worked, and I was amazed, Wow, I had

460
00:24:44.880 --> 00:24:47.160
<v Speaker 4>made a booking with like Expedia or something. I think

461
00:24:47.160 --> 00:24:50.279
<v Speaker 4>it was Expedia, and I couldn't find my booking number anywhere.

462
00:24:50.319 --> 00:24:52.200
<v Speaker 4>Like I went to every single email, there was no

463
00:24:52.240 --> 00:24:55.119
<v Speaker 4>booking number in anything I could find. I tried to

464
00:24:55.119 --> 00:24:57.640
<v Speaker 4>contact customer services. It was AI. I thought, oh, this

465
00:24:57.720 --> 00:24:59.640
<v Speaker 4>is stupid, this is never going to work. And I

466
00:24:59.640 --> 00:25:01.960
<v Speaker 4>asked it the question and it said, like what's your

467
00:25:02.039 --> 00:25:03.480
<v Speaker 4>name and where you're going and stuff, and then it

468
00:25:03.920 --> 00:25:06.279
<v Speaker 4>just immediately came back and said, this is your booking number,

469
00:25:06.799 --> 00:25:10.160
<v Speaker 4>and it was awesome and it was correct. Yeah of course,

470
00:25:10.640 --> 00:25:11.240
<v Speaker 4>yeah wow.

471
00:25:11.400 --> 00:25:13.839
<v Speaker 3>And from there, like you then searched on that or

472
00:25:13.960 --> 00:25:16.400
<v Speaker 3>you know, opened something up like validated it elsewhere.

473
00:25:16.640 --> 00:25:18.240
<v Speaker 4>Yeah, well it took it gave me a link to

474
00:25:18.759 --> 00:25:22.079
<v Speaker 4>something that I hadn't been able to find previously.

475
00:25:22.240 --> 00:25:25.400
<v Speaker 2>Do you do you think that chat bots should be

476
00:25:25.440 --> 00:25:28.240
<v Speaker 2>required to tell you that they are a bot and

477
00:25:28.279 --> 00:25:30.160
<v Speaker 2>you're not actually speaking to a real person.

478
00:25:30.319 --> 00:25:32.519
<v Speaker 4>I don't know. I mean within context, it can be

479
00:25:32.559 --> 00:25:34.759
<v Speaker 4>really obvious. Like if if it's literally a chat you

480
00:25:34.839 --> 00:25:37.279
<v Speaker 4>I and there's a little icon of a robot and

481
00:25:37.400 --> 00:25:39.599
<v Speaker 4>it says like assistant bot is his name, then you're

482
00:25:39.599 --> 00:25:41.440
<v Speaker 4>not going to think it's a person. Yeah, it would

483
00:25:41.440 --> 00:25:42.920
<v Speaker 4>be a terrible person.

484
00:25:43.240 --> 00:25:46.680
<v Speaker 2>I've asked bots before and they have said, no, I'm

485
00:25:46.680 --> 00:25:48.920
<v Speaker 2>not a bot, but I knew it was.

486
00:25:50.799 --> 00:25:53.279
<v Speaker 3>And you asked him to respond to you and iamic pentameter.

487
00:25:53.839 --> 00:25:57.559
<v Speaker 4>Yeah, and then you do the the voidkamp test or something.

488
00:25:57.640 --> 00:26:00.759
<v Speaker 2>Is that Okay, well I'm interested in that, but we

489
00:26:00.799 --> 00:26:02.359
<v Speaker 2>probably shouldn't go down that rabbit.

490
00:26:05.480 --> 00:26:10.880
<v Speaker 3>Yeah, definitely trouble. I am thinking in terms of how

491
00:26:10.920 --> 00:26:15.519
<v Speaker 3>we use generative AI models to understand the user's interaction

492
00:26:15.599 --> 00:26:19.400
<v Speaker 3>with the app. I've been doing some work with some

493
00:26:19.480 --> 00:26:22.240
<v Speaker 3>neuroscience companies and they do a lot of additional instrumentation

494
00:26:22.319 --> 00:26:23.920
<v Speaker 3>on people. And one of the things they've said is like,

495
00:26:24.559 --> 00:26:27.519
<v Speaker 3>facial expressions are not a good way to measure someone's

496
00:26:27.559 --> 00:26:30.759
<v Speaker 3>response to things, and they're very cultural, they're very personal

497
00:26:30.799 --> 00:26:34.599
<v Speaker 3>individuals and so forth. But if you take that camera

498
00:26:34.680 --> 00:26:37.160
<v Speaker 3>and zoom in on a point of skin close enough,

499
00:26:37.640 --> 00:26:42.960
<v Speaker 3>you can actually see heart rate, and heart rate is neutral.

500
00:26:43.200 --> 00:26:46.240
<v Speaker 3>Like the fact that now you can measure that person's

501
00:26:46.240 --> 00:26:48.279
<v Speaker 3>heart rate relative to one step to another inside of

502
00:26:48.319 --> 00:26:50.440
<v Speaker 3>a piece of software and say is a heart rate

503
00:26:50.480 --> 00:26:53.880
<v Speaker 3>increasing or decreasing and that is a better indicator of

504
00:26:54.559 --> 00:26:56.359
<v Speaker 3>frustration or But.

505
00:26:56.440 --> 00:26:58.920
<v Speaker 2>You have to have a baseline though you have to

506
00:26:58.960 --> 00:27:01.039
<v Speaker 2>know it when they're not excited.

507
00:27:01.799 --> 00:27:04.359
<v Speaker 3>Yeah, yeah, I think it's very personal, right that you

508
00:27:04.839 --> 00:27:08.680
<v Speaker 3>could put someone through some paces and their cases. They

509
00:27:08.759 --> 00:27:12.720
<v Speaker 3>do initial testing for a kind of surveying, and so

510
00:27:12.759 --> 00:27:14.480
<v Speaker 3>they sort of look at what your measurements look like

511
00:27:14.519 --> 00:27:16.319
<v Speaker 3>on that and then go into more important ones and

512
00:27:16.359 --> 00:27:17.279
<v Speaker 3>see right through reaction.

513
00:27:17.480 --> 00:27:20.319
<v Speaker 4>Yeah, well that's interesting. It possibly gets us into some

514
00:27:20.559 --> 00:27:24.559
<v Speaker 4>ethical and maybe even legal issues. Like so, you know

515
00:27:24.640 --> 00:27:30.480
<v Speaker 4>a lot of recruitment takes place through AI these days,

516
00:27:30.480 --> 00:27:33.799
<v Speaker 4>and people are often when applying for jobs as to

517
00:27:33.799 --> 00:27:37.079
<v Speaker 4>do video interviews that kind of like an AI video

518
00:27:37.680 --> 00:27:41.440
<v Speaker 4>AI assessed video interview. You know, you could it would

519
00:27:41.480 --> 00:27:44.440
<v Speaker 4>be really straightforward then to be using a technique like

520
00:27:44.480 --> 00:27:46.960
<v Speaker 4>that to try and assess do we think this person's

521
00:27:47.000 --> 00:27:49.799
<v Speaker 4>really being honest about what they're saying on that? But

522
00:27:50.599 --> 00:27:54.480
<v Speaker 4>if you're going to make decisions about someone on that basis,

523
00:27:55.279 --> 00:27:58.440
<v Speaker 4>then you know, as a software developer, engineer and manager

524
00:27:58.960 --> 00:28:01.240
<v Speaker 4>thinking about implement feature like that, you've got to think

525
00:28:01.359 --> 00:28:04.839
<v Speaker 4>very carefully about how reliable you can make this and

526
00:28:04.880 --> 00:28:07.440
<v Speaker 4>what the ethics of doing that really are.

527
00:28:07.480 --> 00:28:10.599
<v Speaker 2>Because humans have trigger words, right that may not have

528
00:28:10.640 --> 00:28:13.039
<v Speaker 2>anything to do with what you're talking about But you

529
00:28:13.160 --> 00:28:16.279
<v Speaker 2>use a word or something and some of you know,

530
00:28:16.599 --> 00:28:18.839
<v Speaker 2>the heart rate will go up and they'll start sweating.

531
00:28:19.319 --> 00:28:21.000
<v Speaker 2>But has nothing to do with the context.

532
00:28:21.160 --> 00:28:24.640
<v Speaker 3>Well, we've all interviewed developers. It turns out that doing

533
00:28:25.079 --> 00:28:28.160
<v Speaker 3>being interviewed as a developer increases your heart rate. Yeah,

534
00:28:29.480 --> 00:28:32.319
<v Speaker 3>they're not comfortable, the vast majority of the market. It's

535
00:28:32.319 --> 00:28:34.400
<v Speaker 3>almost strange to find someone who is comfortable.

536
00:28:34.720 --> 00:28:36.319
<v Speaker 4>Yeah, that's even more suspicious.

537
00:28:36.480 --> 00:28:39.359
<v Speaker 3>Yeah, what's wrong with that, psychopath? Why are you happy

538
00:28:39.519 --> 00:28:41.640
<v Speaker 3>being interviewed? There's something wrong here.

539
00:28:43.799 --> 00:28:47.880
<v Speaker 2>There's no laughing in development, laughing in interviews.

540
00:28:48.000 --> 00:28:50.079
<v Speaker 3>Nothing's fun. This is not fun.

541
00:28:51.319 --> 00:28:54.200
<v Speaker 2>We'll be right back with more with Steve Sanderson after this.

542
00:28:55.519 --> 00:28:58.240
<v Speaker 2>Did you know that you can work with AWS directly

543
00:28:58.279 --> 00:29:04.240
<v Speaker 2>from your ide AWS provides toolkits for visual studio, visual studio, code,

544
00:29:04.519 --> 00:29:08.599
<v Speaker 2>and jet brains rider Learn more at AWS dot Amazon

545
00:29:08.640 --> 00:29:15.839
<v Speaker 2>dot com, slash net slash tools. And we're back. It's

546
00:29:15.839 --> 00:29:18.359
<v Speaker 2>dot net Rocks. I'm Carl Franklin, that's Richard Campbell hey,

547
00:29:18.519 --> 00:29:22.839
<v Speaker 2>and that is mister Blazer himself, Steve Sanderson. We're talking

548
00:29:22.839 --> 00:29:29.759
<v Speaker 2>about AI, his latest passion. We kind of stopped and uh,

549
00:29:30.279 --> 00:29:32.440
<v Speaker 2>let's open up the floor for a new topic. What's

550
00:29:32.480 --> 00:29:35.680
<v Speaker 2>what's something else that you're thinking about AI wise.

551
00:29:35.519 --> 00:29:38.839
<v Speaker 4>Steve Well, I guess the main area is what do

552
00:29:38.880 --> 00:29:42.720
<v Speaker 4>we actually do practically in order to give better tools

553
00:29:43.000 --> 00:29:45.359
<v Speaker 4>and capabilities to dot net developers. You know, I'm on

554
00:29:45.359 --> 00:29:48.880
<v Speaker 4>the dot net team. That's that's what my jobs. And

555
00:29:48.960 --> 00:29:50.799
<v Speaker 4>so the main thing that we're looking at doing at

556
00:29:50.799 --> 00:29:55.799
<v Speaker 4>the moment is producing a new set of standard abstractions

557
00:29:55.839 --> 00:29:58.960
<v Speaker 4>for AI features in dot Net. This is a pattern

558
00:29:59.079 --> 00:30:01.240
<v Speaker 4>that you know we've we've used in all sorts of

559
00:30:01.240 --> 00:30:04.319
<v Speaker 4>other things. So you know, we've got packages like Microsoft

560
00:30:04.400 --> 00:30:09.160
<v Speaker 4>Extensions Dependency Injection. You'll know we've got Microsoft Extensions Logging

561
00:30:09.279 --> 00:30:11.799
<v Speaker 4>and all sorts of other Microsoft Extensions things that contain

562
00:30:12.640 --> 00:30:17.119
<v Speaker 4>standard representations of common features. So we're following that same pattern.

563
00:30:17.240 --> 00:30:19.920
<v Speaker 4>We're going to have already shipped a preview of a

564
00:30:19.960 --> 00:30:24.279
<v Speaker 4>package called Microsoft Extensions AI, and that contains some new

565
00:30:24.359 --> 00:30:28.519
<v Speaker 4>standard representations for things like language models which we call

566
00:30:28.519 --> 00:30:32.759
<v Speaker 4>i CHET client and embedding models or I Embedding Generator

567
00:30:32.799 --> 00:30:35.240
<v Speaker 4>as we call it, and all kinds of other standard

568
00:30:35.319 --> 00:30:38.640
<v Speaker 4>types and helpers that you can use when you want

569
00:30:38.680 --> 00:30:41.559
<v Speaker 4>to add some AI features into your application. And then

570
00:30:41.559 --> 00:30:44.680
<v Speaker 4>there are implementations for all of these with many different

571
00:30:45.680 --> 00:30:48.680
<v Speaker 4>implementations provided. So we've got the obvious ones like open

572
00:30:48.720 --> 00:30:52.119
<v Speaker 4>AI as your open AI. We've got ones for Olama,

573
00:30:52.359 --> 00:30:57.359
<v Speaker 4>there's ones for Gemini, ones for Anthropic. You know, all

574
00:30:57.440 --> 00:31:00.480
<v Speaker 4>kinds of different implementations.

575
00:31:00.279 --> 00:31:03.839
<v Speaker 2>So both cloudy and local implementations of LLMS.

576
00:31:03.400 --> 00:31:07.200
<v Speaker 4>YEP absolutely and then all from us as well. The

577
00:31:07.240 --> 00:31:11.400
<v Speaker 4>intention is that this is a shared community effort, so

578
00:31:11.440 --> 00:31:14.759
<v Speaker 4>we've been working with external projects like the Alama Sharp

579
00:31:14.799 --> 00:31:17.880
<v Speaker 4>project and others to make sure that they've all got

580
00:31:17.960 --> 00:31:21.200
<v Speaker 4>implementations of these same interfaces. And the payoff for all

581
00:31:21.279 --> 00:31:24.640
<v Speaker 4>this for dot net developers is that you have one

582
00:31:24.839 --> 00:31:28.759
<v Speaker 4>common program model that you can use whichever AI back

583
00:31:28.880 --> 00:31:31.480
<v Speaker 4>end you want to work with. And it's hopefully quite

584
00:31:31.480 --> 00:31:34.480
<v Speaker 4>a well thought out one because you know, we've had

585
00:31:34.599 --> 00:31:37.359
<v Speaker 4>people dedicated to thinking about this for months and it's

586
00:31:37.440 --> 00:31:40.200
<v Speaker 4>very flexible and you can plug in your own behaviors

587
00:31:40.240 --> 00:31:43.240
<v Speaker 4>at different stages in the pipeline and combine things and

588
00:31:43.279 --> 00:31:45.119
<v Speaker 4>you know, do all the stuff that you will want

589
00:31:45.119 --> 00:31:47.279
<v Speaker 4>to do, and yeah, we want to be able to

590
00:31:47.279 --> 00:31:48.599
<v Speaker 4>build an ecosystem around that.

591
00:31:48.680 --> 00:31:52.559
<v Speaker 2>Are all these providers committed to adhering to the interfaces

592
00:31:52.559 --> 00:31:55.160
<v Speaker 2>that you have or is it up to you doing

593
00:31:55.160 --> 00:31:58.119
<v Speaker 2>the implementation to adjust if their APIs change.

594
00:31:58.480 --> 00:32:00.920
<v Speaker 4>So yeah, So let's take an example. So we'll say

595
00:32:01.359 --> 00:32:04.279
<v Speaker 4>the Alarma on for example. If people don't know, Olama

596
00:32:04.400 --> 00:32:06.319
<v Speaker 4>is some software that you can run locally on your

597
00:32:06.559 --> 00:32:09.400
<v Speaker 4>developer machine as a way of using things like language

598
00:32:09.400 --> 00:32:11.720
<v Speaker 4>models locally. You probably wouldn't use it in production, but

599
00:32:11.759 --> 00:32:15.720
<v Speaker 4>it's great for development, Okay. So there are there are

600
00:32:15.720 --> 00:32:18.240
<v Speaker 4>a bunch of different client packages for that for dot net.

601
00:32:18.480 --> 00:32:21.359
<v Speaker 4>So Alarma sharp is the most well known one, and

602
00:32:21.480 --> 00:32:24.279
<v Speaker 4>you can use it's APIs directly, just like it's straight

603
00:32:24.359 --> 00:32:27.559
<v Speaker 4>concrete APIs a newer Alarma client or whatever it is,

604
00:32:27.880 --> 00:32:30.240
<v Speaker 4>and use it directly. But then that code's not interoperable

605
00:32:30.240 --> 00:32:33.640
<v Speaker 4>with anything else. So what you can do is use

606
00:32:33.759 --> 00:32:36.519
<v Speaker 4>the iChat client implementation that it provides. So you would

607
00:32:36.559 --> 00:32:40.160
<v Speaker 4>say something like Newolarma client dot dot, and then at

608
00:32:40.160 --> 00:32:42.279
<v Speaker 4>the end you put dot as chat client and that

609
00:32:42.359 --> 00:32:45.160
<v Speaker 4>gives you back and in an object that implements this

610
00:32:45.240 --> 00:32:47.799
<v Speaker 4>iChat client interface. And now you can use that in

611
00:32:47.839 --> 00:32:50.240
<v Speaker 4>the same way as every other AI service.

612
00:32:50.440 --> 00:32:55.839
<v Speaker 2>So it's really Olama's responsibility to implement Yeah, iChat client,

613
00:32:55.920 --> 00:32:57.960
<v Speaker 2>it is totally, which is the dot Net interface.

614
00:32:58.079 --> 00:33:00.240
<v Speaker 4>Yeah, that's right, in the same way that Sarah log

615
00:33:00.240 --> 00:33:03.960
<v Speaker 4>implements IE logging. And you know, that's what the whole

616
00:33:04.000 --> 00:33:06.839
<v Speaker 4>point of having these standard interfaces is that everyone can

617
00:33:06.920 --> 00:33:09.079
<v Speaker 4>make them work in whatever way makes sense to them.

618
00:33:09.240 --> 00:33:11.799
<v Speaker 2>Yeah, and I'm wondering, like, how would that evolve.

619
00:33:12.799 --> 00:33:16.400
<v Speaker 4>Well, yeah, so it evolves in that the industry itself

620
00:33:16.480 --> 00:33:19.720
<v Speaker 4>is evolving and we're getting new types of AI services

621
00:33:19.759 --> 00:33:21.960
<v Speaker 4>coming out. A good example of that at the moment

622
00:33:22.039 --> 00:33:24.960
<v Speaker 4>are the real time APIs. So at the moment, most

623
00:33:25.000 --> 00:33:27.200
<v Speaker 4>of our interactions with language models are a sort of

624
00:33:27.599 --> 00:33:29.920
<v Speaker 4>request response pattern where we send a bunch of text

625
00:33:29.920 --> 00:33:31.880
<v Speaker 4>to them and they come back with a bunch of text.

626
00:33:31.960 --> 00:33:36.519
<v Speaker 4>But there's a different paradigm that's emerging called real time

627
00:33:36.559 --> 00:33:40.079
<v Speaker 4>at the moment, where it's a bidirectional communication channel a

628
00:33:40.119 --> 00:33:42.799
<v Speaker 4>bit like a web socket or you know, just straight

629
00:33:42.880 --> 00:33:46.000
<v Speaker 4>TCP socket connection where you can just sort of fire

630
00:33:46.200 --> 00:33:49.319
<v Speaker 4>a load of bites across the wire to the AI

631
00:33:49.400 --> 00:33:51.599
<v Speaker 4>system and it can send bites back to you at

632
00:33:51.640 --> 00:33:54.920
<v Speaker 4>any time in any order, like overlapping or whatever, and

633
00:33:54.960 --> 00:33:57.319
<v Speaker 4>those bites could represent text, or they could be audio

634
00:33:57.400 --> 00:34:00.759
<v Speaker 4>data or images or whatever in either direction. So that's

635
00:34:00.839 --> 00:34:06.079
<v Speaker 4>the real time API, and our standard abstraction I chat

636
00:34:06.079 --> 00:34:09.519
<v Speaker 4>client doesn't represent that today. It represents the request responds

637
00:34:09.599 --> 00:34:13.639
<v Speaker 4>text based pattern. So, as you alluded to, we have

638
00:34:13.679 --> 00:34:16.360
<v Speaker 4>to evolve as time goes on. We will add further

639
00:34:16.400 --> 00:34:20.519
<v Speaker 4>abstractions to represent other AI patterns when they become common

640
00:34:20.760 --> 00:34:22.039
<v Speaker 4>across multiple providers.

641
00:34:22.519 --> 00:34:26.679
<v Speaker 2>And these providers keep contexts too, right well, they can

642
00:34:26.760 --> 00:34:28.079
<v Speaker 2>do so that they can.

643
00:34:28.760 --> 00:34:32.159
<v Speaker 4>The classic way of interacting with the language model is stateless.

644
00:34:32.320 --> 00:34:35.079
<v Speaker 4>So if you're having a conversation in a chatbot where

645
00:34:35.119 --> 00:34:36.840
<v Speaker 4>you say A and it says B, and U say

646
00:34:36.920 --> 00:34:39.920
<v Speaker 4>C and it says D. When you sen want to

647
00:34:39.960 --> 00:34:41.880
<v Speaker 4>send the message E, you don't just send E to it.

648
00:34:41.920 --> 00:34:46.000
<v Speaker 4>You also send abcd like that because it hasn't remembered

649
00:34:46.000 --> 00:34:49.119
<v Speaker 4>any of the conversation, so you literally have to repeat

650
00:34:49.159 --> 00:34:52.159
<v Speaker 4>the entire conversation. Now, the app developer doesn't think about

651
00:34:52.199 --> 00:34:54.800
<v Speaker 4>that now, because that's like inside the libraries. But that's

652
00:34:54.840 --> 00:34:55.840
<v Speaker 4>what's happening on the wire.

653
00:34:55.960 --> 00:34:59.400
<v Speaker 2>Okay, So we've been spoiled by chat GPT. In other words,

654
00:34:59.559 --> 00:35:02.559
<v Speaker 2>it's it's doing that context stuff under the hood and

655
00:35:02.599 --> 00:35:04.320
<v Speaker 2>we don't we don't have to worry about it.

656
00:35:04.400 --> 00:35:07.000
<v Speaker 4>Yeah, the WebUI does that and to be honest, they

657
00:35:07.000 --> 00:35:10.760
<v Speaker 4>probably do some service side caching of the conversations as well,

658
00:35:10.800 --> 00:35:13.079
<v Speaker 4>but that's you know, that would be specific to them.

659
00:35:13.199 --> 00:35:16.920
<v Speaker 3>Yeah, okay, interesting I've been I've got an open AI

660
00:35:17.039 --> 00:35:21.559
<v Speaker 3>interface into my Home Assistant implementation, and essentially what it

661
00:35:21.599 --> 00:35:26.119
<v Speaker 3>does is prefixes whatever my request is with the model

662
00:35:26.199 --> 00:35:29.360
<v Speaker 3>of the house as part of the prompt. So it's

663
00:35:29.480 --> 00:35:32.559
<v Speaker 3>essentially saying, here's what's in the house, now, what would

664
00:35:32.599 --> 00:35:35.360
<v Speaker 3>you do with this sentence? And then it comes back

665
00:35:35.400 --> 00:35:37.239
<v Speaker 3>with us, you know, so I can say things like

666
00:35:38.159 --> 00:35:40.599
<v Speaker 3>turn on all the outdoor lights, turn off the lights

667
00:35:40.599 --> 00:35:42.519
<v Speaker 3>in the garage, and turn off the lights in the garage,

668
00:35:42.920 --> 00:35:45.639
<v Speaker 3>and it will change those statements. It really translates that

669
00:35:45.800 --> 00:35:48.760
<v Speaker 3>into it's this switch that's which they know does all

670
00:35:48.760 --> 00:35:54.239
<v Speaker 3>the things. Yeah, but it is literally manufacturing the context

671
00:35:54.400 --> 00:35:56.119
<v Speaker 3>each time you make a request.

672
00:35:56.719 --> 00:35:57.800
<v Speaker 4>Yeah, that is right.

673
00:35:57.960 --> 00:35:58.199
<v Speaker 3>Yeah.

674
00:35:58.239 --> 00:35:59.800
<v Speaker 2>When's Alexa going to catch up to this?

675
00:36:00.079 --> 00:36:00.400
<v Speaker 1>Hmmm?

676
00:36:01.159 --> 00:36:04.519
<v Speaker 3>Yeah. I don't envy those folks. The yellms have sort

677
00:36:04.559 --> 00:36:07.119
<v Speaker 3>of caught them with their pants down, both the Google

678
00:36:07.159 --> 00:36:11.519
<v Speaker 3>Home folks and they and the Amazon folks. They've got

679
00:36:11.599 --> 00:36:12.880
<v Speaker 3>you respond right.

680
00:36:12.719 --> 00:36:14.920
<v Speaker 2>But they didn't They wanted to kill the product, didn't They.

681
00:36:14.960 --> 00:36:17.760
<v Speaker 3>Well, the product was losing money, losing lots of money,

682
00:36:17.920 --> 00:36:21.159
<v Speaker 3>like the you know, the purpose behind those the Amazon

683
00:36:21.159 --> 00:36:24.519
<v Speaker 3>device was to sell stuff on Amazon Sales tool, except

684
00:36:24.519 --> 00:36:27.280
<v Speaker 3>that nobody did that right because it correctly became a

685
00:36:27.360 --> 00:36:30.119
<v Speaker 3>joke about walking into the room and ordering you know,

686
00:36:30.639 --> 00:36:33.840
<v Speaker 3>a ton of soap on someone, right like or having

687
00:36:33.840 --> 00:36:36.119
<v Speaker 3>your children order stuff because they saw you do it.

688
00:36:36.679 --> 00:36:39.159
<v Speaker 3>So nobody did that part. And they sold all that

689
00:36:39.239 --> 00:36:41.320
<v Speaker 3>gear for cost. So it was a few years ago

690
00:36:41.360 --> 00:36:43.159
<v Speaker 3>they said, hey, we're cutting these teams way back, like

691
00:36:43.239 --> 00:36:44.400
<v Speaker 3>we spent billions on them.

692
00:36:44.440 --> 00:36:47.400
<v Speaker 2>Has anybody heard about anything that they're working on in

693
00:36:47.440 --> 00:36:48.000
<v Speaker 2>the back end?

694
00:36:48.239 --> 00:36:51.599
<v Speaker 3>They clearly are. Yeah, I mean that they haven't.

695
00:36:51.639 --> 00:36:52.239
<v Speaker 2>They have to be.

696
00:36:52.320 --> 00:36:55.400
<v Speaker 3>They have to be. The same time, they had just

697
00:36:55.440 --> 00:36:58.159
<v Speaker 3>cut their teams and within months of Amazon saying that

698
00:36:58.199 --> 00:37:01.119
<v Speaker 3>Google did the same thing for their devices as well.

699
00:37:01.480 --> 00:37:04.119
<v Speaker 2>Well. That that brings me to the next question, Steve,

700
00:37:04.159 --> 00:37:06.320
<v Speaker 2>do you have an iPhone? I do, yep. And what

701
00:37:06.360 --> 00:37:07.920
<v Speaker 2>do you think of Apple Intelligence?

702
00:37:08.239 --> 00:37:10.559
<v Speaker 4>Oh, I don't have one that's that new, you say, I.

703
00:37:10.480 --> 00:37:14.559
<v Speaker 2>Do, and I don't think it's very intelligent. I would

704
00:37:14.599 --> 00:37:17.440
<v Speaker 2>thought I was going to get an upgrade to sirikay

705
00:37:18.039 --> 00:37:21.400
<v Speaker 2>that hasn't happened. And I have, you know, my Apple

706
00:37:21.440 --> 00:37:24.760
<v Speaker 2>car play, so anytime I ask it something that's Siri ye,

707
00:37:25.039 --> 00:37:27.199
<v Speaker 2>and I'll ask it stuff and it's just as dumb

708
00:37:27.239 --> 00:37:30.239
<v Speaker 2>as it was before. Yeah, so I don't see Apple Intelligence.

709
00:37:30.239 --> 00:37:32.239
<v Speaker 4>I mean, I'd be happy with even if the basic

710
00:37:32.320 --> 00:37:35.360
<v Speaker 4>SERI worked. Like I tell my phone to like set

711
00:37:35.360 --> 00:37:37.079
<v Speaker 4>a reminder or something and it just gives me a

712
00:37:37.119 --> 00:37:38.519
<v Speaker 4>spinner and that's it.

713
00:37:38.599 --> 00:37:39.000
<v Speaker 2>Wow.

714
00:37:39.119 --> 00:37:44.840
<v Speaker 3>So yeah, this is very unusual of Apple. But the

715
00:37:44.880 --> 00:37:48.840
<v Speaker 3>best guess that the Apple you know, Digerati have said

716
00:37:48.960 --> 00:37:51.719
<v Speaker 3>is that Apple was afraid last year if they didn't

717
00:37:51.719 --> 00:37:55.119
<v Speaker 3>say something about AI at WWDC because they only do

718
00:37:55.159 --> 00:37:57.320
<v Speaker 3>one show here, if they waited till this year would

719
00:37:57.320 --> 00:38:00.920
<v Speaker 3>be too late, so they basically pre aound something like normally,

720
00:38:00.960 --> 00:38:03.360
<v Speaker 3>Apple already has all this stuff worked out, talks about

721
00:38:03.360 --> 00:38:05.760
<v Speaker 3>it in the show and its releases on schedule. But

722
00:38:05.800 --> 00:38:08.760
<v Speaker 3>that is not what happened with Apple Intelligence. They came

723
00:38:08.840 --> 00:38:11.440
<v Speaker 3>up with a term, they pitched it at the show,

724
00:38:11.719 --> 00:38:13.360
<v Speaker 3>and then they immediately pushed it back.

725
00:38:13.599 --> 00:38:15.239
<v Speaker 2>Yeah, No, that was weird.

726
00:38:15.679 --> 00:38:17.559
<v Speaker 4>I don't even know if it's shipped globally. Yeah, I

727
00:38:17.559 --> 00:38:19.320
<v Speaker 4>don't know if it's available in the UK. I haven't

728
00:38:19.360 --> 00:38:20.440
<v Speaker 4>heard anyone talk about it.

729
00:38:20.679 --> 00:38:25.079
<v Speaker 3>Yeah, it's it is. I think you're seeing the closest

730
00:38:25.079 --> 00:38:28.000
<v Speaker 3>thing to Apple being scared that they're missing the boat

731
00:38:28.079 --> 00:38:31.440
<v Speaker 3>on this thing and they're behaving oddly because we would

732
00:38:31.519 --> 00:38:34.199
<v Speaker 3>expect them. And again, I don't use Apple products, but

733
00:38:34.280 --> 00:38:37.559
<v Speaker 3>I've lived alongside them long enough to know if Apple

734
00:38:37.599 --> 00:38:39.679
<v Speaker 3>says they're going to do something, they generally just do

735
00:38:39.760 --> 00:38:44.280
<v Speaker 3>it and have a good plan. And that's not happening here. Yeah,

736
00:38:44.360 --> 00:38:46.800
<v Speaker 3>it's an odd time, but I do think we're all

737
00:38:46.840 --> 00:38:49.320
<v Speaker 3>feeling around for the right thing to do in this space.

738
00:38:49.360 --> 00:38:52.159
<v Speaker 3>Like I'm excited that you guys are building tools because

739
00:38:52.159 --> 00:38:54.519
<v Speaker 3>that gives me a standard way to interact with it

740
00:38:54.559 --> 00:38:56.400
<v Speaker 3>in my apps. No, like for me as a dot

741
00:38:56.400 --> 00:39:01.400
<v Speaker 3>net developer. Thanks like the extensions all I understand Right

742
00:39:01.639 --> 00:39:03.559
<v Speaker 3>when I need this, I go, I go to new Get,

743
00:39:03.599 --> 00:39:06.239
<v Speaker 3>I bring it in in and off I go. So

744
00:39:06.360 --> 00:39:08.880
<v Speaker 3>it's a way to sort of create a common approach

745
00:39:08.920 --> 00:39:13.280
<v Speaker 3>to integrating stuff into yourself. Yeah, absolutely, So. Just I

746
00:39:13.320 --> 00:39:15.599
<v Speaker 3>grab the blog post that I'll put in the show

747
00:39:15.639 --> 00:39:17.320
<v Speaker 3>notes because it does give you sort of a walk

748
00:39:17.360 --> 00:39:19.679
<v Speaker 3>through of this. And it's just that you talked about

749
00:39:19.719 --> 00:39:21.920
<v Speaker 3>open AI. You talked about, was it.

750
00:39:22.000 --> 00:39:24.480
<v Speaker 2>Lama O Lama O Lama olama, And.

751
00:39:24.480 --> 00:39:26.519
<v Speaker 3>Then there's the inference engine.

752
00:39:26.800 --> 00:39:28.719
<v Speaker 4>The inference I'm not sure.

753
00:39:29.079 --> 00:39:33.000
<v Speaker 3>As you as your AI inference Yeah.

754
00:39:32.679 --> 00:39:35.440
<v Speaker 4>Oh right, yeah, sorry, as your AI inference. Yeah, that's right.

755
00:39:35.480 --> 00:39:38.679
<v Speaker 4>That's that's almost like the cloud version of OLAMA. That's

756
00:39:38.719 --> 00:39:40.679
<v Speaker 4>a very simple mental model for it. It's a way

757
00:39:40.719 --> 00:39:43.599
<v Speaker 4>of running any kind of model that you want to

758
00:39:43.639 --> 00:39:46.599
<v Speaker 4>provide from us or once from a standard catalog in

759
00:39:47.440 --> 00:39:51.320
<v Speaker 4>a hosted service, as opposed to say, like as your

760
00:39:51.360 --> 00:39:54.199
<v Speaker 4>open air, which is literally just open AI models and

761
00:39:54.320 --> 00:39:57.400
<v Speaker 4>doesn't include other things like the LAMA models.

762
00:39:57.280 --> 00:40:01.360
<v Speaker 3>Because at the same time, as you AI has opened

763
00:40:01.400 --> 00:40:03.440
<v Speaker 3>up to many more models, and just open AI you

764
00:40:03.440 --> 00:40:04.519
<v Speaker 3>have all theseries.

765
00:40:04.639 --> 00:40:05.639
<v Speaker 4>That's correct, I.

766
00:40:05.559 --> 00:40:07.360
<v Speaker 3>Mentioned to the listener at the beginning of the show.

767
00:40:07.519 --> 00:40:09.239
<v Speaker 4>Yeah, yeah, I think in a lot of cases that's

768
00:40:09.280 --> 00:40:11.800
<v Speaker 4>going to be a much easier way of running a

769
00:40:11.800 --> 00:40:14.800
<v Speaker 4>wider range of models in production than you know, setting

770
00:40:14.840 --> 00:40:21.280
<v Speaker 4>up your own like containers and serving model output from that.

771
00:40:21.199 --> 00:40:24.960
<v Speaker 4>That's quite hard business to do because you know, these

772
00:40:25.039 --> 00:40:26.760
<v Speaker 4>things only work well if they're running on the right

773
00:40:26.840 --> 00:40:30.519
<v Speaker 4>kind of GPU hardware, and that can be expensive, and

774
00:40:30.840 --> 00:40:33.360
<v Speaker 4>you know, you really don't want to be managing all

775
00:40:33.400 --> 00:40:33.840
<v Speaker 4>of that stuff.

776
00:40:33.840 --> 00:40:36.199
<v Speaker 3>If you can avoid that stuff is plumbing, right. You

777
00:40:36.400 --> 00:40:39.239
<v Speaker 3>just want to be able to send your your thing

778
00:40:39.239 --> 00:40:42.480
<v Speaker 3>out over an API and get a useful response back. Yeah, done,

779
00:40:42.480 --> 00:40:46.239
<v Speaker 3>it's just another API. No magic. Please just let my API,

780
00:40:46.639 --> 00:40:50.480
<v Speaker 3>that my API call work exactly. You're creating a cloud dependency.

781
00:40:50.519 --> 00:40:52.360
<v Speaker 3>But that's not that weird. Like there seems to be

782
00:40:52.360 --> 00:40:57.840
<v Speaker 3>a big push to run more of these models on prem.

783
00:40:58.320 --> 00:41:00.840
<v Speaker 3>While we're recording this, I think C is still going

784
00:41:00.880 --> 00:41:03.519
<v Speaker 3>on the Consumer Electronic Show, and Nvidia made this announcement

785
00:41:03.559 --> 00:41:07.800
<v Speaker 3>about this three thousand dollars supercomputer running what they called

786
00:41:08.719 --> 00:41:14.119
<v Speaker 3>the Grace Blackwell chip set. But they're saying, for three

787
00:41:14.119 --> 00:41:18.280
<v Speaker 3>thousand bucks, you will run a two hundred billion parameter

788
00:41:18.800 --> 00:41:19.639
<v Speaker 3>model on prem.

789
00:41:19.920 --> 00:41:22.360
<v Speaker 4>Oh it's funny, isn't it the way this competition works.

790
00:41:22.400 --> 00:41:25.920
<v Speaker 4>So yeah, the current status quo is that you use

791
00:41:25.960 --> 00:41:30.920
<v Speaker 4>a combination of Nvideo provided hardware and then the software

792
00:41:30.960 --> 00:41:35.119
<v Speaker 4>from open A or another tech giant, Microsoft or Google.

793
00:41:35.639 --> 00:41:39.320
<v Speaker 4>And so we've got Nvidea trying to commoditize the tech

794
00:41:39.719 --> 00:41:43.079
<v Speaker 4>the other tech giants the model providers by saying, oh no,

795
00:41:43.159 --> 00:41:45.199
<v Speaker 4>you just need our hardware. You don't need any cloud.

796
00:41:45.440 --> 00:41:47.800
<v Speaker 4>And then you've got the tech giants trying to commoditize

797
00:41:47.880 --> 00:41:50.079
<v Speaker 4>n video by saying, oh, we've got our own custom silicon,

798
00:41:50.320 --> 00:41:52.800
<v Speaker 4>you don't need Nvidia. Yeah.

799
00:41:53.679 --> 00:41:55.840
<v Speaker 3>Fun well, happily buying each other's products too.

800
00:41:56.039 --> 00:41:58.679
<v Speaker 4>Yeah, see who's going to win.

801
00:41:58.920 --> 00:42:02.320
<v Speaker 3>This is co oppetition, But it did what impressed me, Like,

802
00:42:03.199 --> 00:42:05.639
<v Speaker 3>GPT three is one hundred and seventy five billion parameters.

803
00:42:05.639 --> 00:42:08.400
<v Speaker 3>So in a matter of four years, we've gone from

804
00:42:09.159 --> 00:42:13.280
<v Speaker 3>a cloud problem that Mark Rosinovich talked about building the

805
00:42:13.280 --> 00:42:16.119
<v Speaker 3>fifth largest supercomputer in the world to build that model

806
00:42:16.159 --> 00:42:18.840
<v Speaker 3>back in the day, to something for three grand I

807
00:42:18.840 --> 00:42:21.159
<v Speaker 3>could sit on my desk. In theory it was CES,

808
00:42:21.239 --> 00:42:23.039
<v Speaker 3>which is basically a concept show.

809
00:42:23.000 --> 00:42:26.519
<v Speaker 2>Right, and the stock continues to get by them. Yeah.

810
00:42:27.280 --> 00:42:29.480
<v Speaker 4>Yeah, it's amazing enough us that grows. In fact, just

811
00:42:29.559 --> 00:42:34.559
<v Speaker 4>yesterday I was experimenting with what's the biggest language model

812
00:42:34.559 --> 00:42:37.199
<v Speaker 4>that I can train on my laptop in like one minute?

813
00:42:37.920 --> 00:42:39.719
<v Speaker 4>I thought it was going to be nothing like I thought.

814
00:42:40.119 --> 00:42:42.840
<v Speaker 4>You know, it takes months of GPU time to make

815
00:42:42.880 --> 00:42:45.719
<v Speaker 4>a sensible language model, Like in one minute, it's not

816
00:42:45.760 --> 00:42:48.360
<v Speaker 4>even going to produce words that you can read. Sure,

817
00:42:49.559 --> 00:42:53.480
<v Speaker 4>it turns out you can produce something sort of if

818
00:42:53.480 --> 00:42:57.920
<v Speaker 4>you take a GPT that sorry, GPT two, an implementation

819
00:42:58.039 --> 00:43:01.000
<v Speaker 4>of that on a single GPU on my laptop, I

820
00:43:01.039 --> 00:43:06.280
<v Speaker 4>can get something that produces pretty intelligible sentences within one

821
00:43:06.320 --> 00:43:07.199
<v Speaker 4>minute of training.

822
00:43:07.639 --> 00:43:07.800
<v Speaker 3>Wo.

823
00:43:08.440 --> 00:43:12.159
<v Speaker 4>So yeah, it's crazy how how quickly we've come on

824
00:43:12.280 --> 00:43:15.760
<v Speaker 4>from you know, it being a you know, industry defining

825
00:43:15.800 --> 00:43:21.039
<v Speaker 4>problem to produce anything like the English language to being

826
00:43:21.079 --> 00:43:22.039
<v Speaker 4>really quite straightforward.

827
00:43:23.159 --> 00:43:25.760
<v Speaker 3>You know, they're used to be an XKCD graphic about

828
00:43:25.800 --> 00:43:28.679
<v Speaker 3>identifying birds in a picture, being needing a team in

829
00:43:28.800 --> 00:43:31.920
<v Speaker 3>years of work, and now we expect our phone when

830
00:43:31.960 --> 00:43:36.719
<v Speaker 3>we take a photo, like I've got the new Android phone,

831
00:43:36.760 --> 00:43:39.960
<v Speaker 3>the Pixel nine, and one of its features in Gemini

832
00:43:40.039 --> 00:43:41.880
<v Speaker 3>is when you take a photo, it writes a caption

833
00:43:41.920 --> 00:43:46.559
<v Speaker 3>of what's in the book, and that's included, Like just prettful?

834
00:43:47.119 --> 00:43:48.400
<v Speaker 4>Is that on device that.

835
00:43:48.639 --> 00:43:50.639
<v Speaker 3>The apparently it's on device. I suspect there's a round

836
00:43:50.679 --> 00:43:53.000
<v Speaker 3>trip to the cloud involved. Okay, pretty sure?

837
00:43:53.079 --> 00:43:54.800
<v Speaker 2>What I what I want to do when I keep

838
00:43:54.840 --> 00:43:56.480
<v Speaker 2>threatening my wife, I'm going to do this is to

839
00:43:56.559 --> 00:44:00.320
<v Speaker 2>take the ten thousand photos that have accumulated since I

840
00:44:00.360 --> 00:44:03.800
<v Speaker 2>started saving them and upload them to a cloud service

841
00:44:03.880 --> 00:44:07.039
<v Speaker 2>and have it identify what's in the photos, and then

842
00:44:07.239 --> 00:44:10.159
<v Speaker 2>create a database that I can search so that I

843
00:44:10.199 --> 00:44:13.800
<v Speaker 2>can say, you know, a picture of Richard Campbell with

844
00:44:13.880 --> 00:44:17.360
<v Speaker 2>a glass of whiskey, and nine thousand of those ten

845
00:44:17.400 --> 00:44:20.079
<v Speaker 2>thousand photos come up and.

846
00:44:20.280 --> 00:44:23.840
<v Speaker 3>List Yeah, it's just in state from me.

847
00:44:24.800 --> 00:44:27.800
<v Speaker 2>Yeah. I think that's another little science fiction any thing too.

848
00:44:27.840 --> 00:44:30.119
<v Speaker 2>But I mean you can sort of do that now.

849
00:44:30.280 --> 00:44:32.079
<v Speaker 4>But oh you can totally do that now.

850
00:44:32.159 --> 00:44:33.719
<v Speaker 2>Yeah, maybe not.

851
00:44:34.400 --> 00:44:37.159
<v Speaker 4>You could even just have it generate those pictures even

852
00:44:37.159 --> 00:44:38.000
<v Speaker 4>if they didn't exist.

853
00:44:38.079 --> 00:44:38.840
<v Speaker 2>Well, there you go.

854
00:44:39.199 --> 00:44:41.079
<v Speaker 3>There is that. Yeah, you don't have enough pictures me

855
00:44:41.119 --> 00:44:43.039
<v Speaker 3>holding a glass of whiskey. You can make them.

856
00:44:44.119 --> 00:44:45.800
<v Speaker 2>By the way, I still haven't been able to send

857
00:44:45.840 --> 00:44:49.920
<v Speaker 2>you a Christmas present because your mail system is borked. Richard.

858
00:44:50.000 --> 00:44:52.599
<v Speaker 3>Well, we had a six week strike, yeah, and it

859
00:44:52.760 --> 00:44:54.440
<v Speaker 3>kind of made a mess of absolutely Ever.

860
00:44:54.760 --> 00:44:57.079
<v Speaker 2>Is it back in business now or yeah.

861
00:44:56.920 --> 00:45:00.239
<v Speaker 3>The strike has been stopped till the spring, so a

862
00:45:00.280 --> 00:45:04.280
<v Speaker 3>window now, Okay, that's right done. They never resolved anything.

863
00:45:04.280 --> 00:45:06.039
<v Speaker 3>They just kicked it down the road to this.

864
00:45:06.320 --> 00:45:09.199
<v Speaker 2>Steve, do you have your hands in Blazer much these days?

865
00:45:09.400 --> 00:45:09.639
<v Speaker 3>Yeah?

866
00:45:09.679 --> 00:45:12.719
<v Speaker 4>So definitely not as much as before, because you know,

867
00:45:12.719 --> 00:45:17.719
<v Speaker 4>I've my focus is broadened and spread out. But yes,

868
00:45:17.719 --> 00:45:20.800
<v Speaker 4>I'm still very involved in the Blazer team. You know,

869
00:45:20.840 --> 00:45:25.280
<v Speaker 4>I've probably liked ten Blazer meetings a week and yeah,

870
00:45:25.320 --> 00:45:29.400
<v Speaker 4>so that we're working towards clarifying a dot net ten plan.

871
00:45:29.559 --> 00:45:31.400
<v Speaker 4>At the moment for Blazer, we've got a whole bunch

872
00:45:31.480 --> 00:45:33.880
<v Speaker 4>of meetings going on around that.

873
00:45:34.199 --> 00:45:36.559
<v Speaker 3>It's crazy to think about. Dot net ten just gives

874
00:45:36.559 --> 00:45:39.079
<v Speaker 3>me chills. Man. Yeah, I guess it's only a couple

875
00:45:39.159 --> 00:45:41.239
<v Speaker 3>months ago. You ship dot net nine, So I guess

876
00:45:41.239 --> 00:45:42.840
<v Speaker 3>that's only fair. There's going to be another one.

877
00:45:42.960 --> 00:45:44.599
<v Speaker 4>Yeah, I know what you mean. It's a bit like

878
00:45:44.639 --> 00:45:47.679
<v Speaker 4>browser versions, like you know, Chrome one hundred and fifty

879
00:45:47.760 --> 00:45:52.440
<v Speaker 4>five or whatever by now. Yeah, time goes on. So yeah,

880
00:45:52.440 --> 00:45:55.079
<v Speaker 4>the Blazer team is We're actually all gathering in person

881
00:45:55.400 --> 00:45:57.480
<v Speaker 4>next week, which is going to be fun to see everyone,

882
00:45:57.719 --> 00:46:00.559
<v Speaker 4>and we will try and dig in to a lot

883
00:46:00.559 --> 00:46:03.719
<v Speaker 4>of this planning and working out what we want. I

884
00:46:03.719 --> 00:46:05.960
<v Speaker 4>think one of the big themes that we'll focus on

885
00:46:06.079 --> 00:46:10.079
<v Speaker 4>in dot net ten is the most core scenario of

886
00:46:10.119 --> 00:46:15.599
<v Speaker 4>Blazer usage, which is Blazer server and what we can

887
00:46:15.679 --> 00:46:19.840
<v Speaker 4>do to make that as bulletproof as possible. Like one

888
00:46:19.880 --> 00:46:21.960
<v Speaker 4>of the key things that people have struggled with Blazer

889
00:46:21.960 --> 00:46:24.239
<v Speaker 4>server from the beginning is the fact that you have

890
00:46:24.280 --> 00:46:26.920
<v Speaker 4>to have this constant connection. And yes, we've always had

891
00:46:26.920 --> 00:46:29.800
<v Speaker 4>a sort of reconnection mechanism, but it's always been a

892
00:46:29.800 --> 00:46:33.480
<v Speaker 4>little bit you know, suboptimal and like does it really work,

893
00:46:33.519 --> 00:46:35.559
<v Speaker 4>And even when it works, it's a little bit like

894
00:46:35.679 --> 00:46:38.079
<v Speaker 4>jarring to the end user and can result in them

895
00:46:38.119 --> 00:46:41.519
<v Speaker 4>losing some state. So what can we do to make

896
00:46:41.599 --> 00:46:45.239
<v Speaker 4>it as practical as possible for a Blazer app developer

897
00:46:45.559 --> 00:46:49.280
<v Speaker 4>to have a really bulletproof experience for the user so

898
00:46:49.280 --> 00:46:51.159
<v Speaker 4>that whether or not the connection is lost, the user

899
00:46:51.199 --> 00:46:52.559
<v Speaker 4>does not lose state.

900
00:46:52.639 --> 00:46:55.039
<v Speaker 2>Well, you certainly laid the foundation really well in dot

901
00:46:55.199 --> 00:46:57.679
<v Speaker 2>at nine. I mean even right out of the box,

902
00:46:57.760 --> 00:47:01.599
<v Speaker 2>the experience is, yeah, your code kind of freezes for

903
00:47:01.639 --> 00:47:04.320
<v Speaker 2>a bit, Yeah, but it usually comes back.

904
00:47:04.920 --> 00:47:06.880
<v Speaker 4>Yeah, Yeah, that's right. We did improve it a lot

905
00:47:06.880 --> 00:47:09.519
<v Speaker 4>in nine. In prior to nine, it used to be

906
00:47:09.559 --> 00:47:12.239
<v Speaker 4>a pretty awful user experience, if I'm honest, where it

907
00:47:12.280 --> 00:47:14.679
<v Speaker 4>would just sort of make it the user's problem to

908
00:47:15.400 --> 00:47:19.119
<v Speaker 4>work out whether to reload. You know, it wasn't great.

909
00:47:19.519 --> 00:47:22.440
<v Speaker 4>And in nine it's a lot more prone to like

910
00:47:22.480 --> 00:47:25.079
<v Speaker 4>figure out the problem and solve it. Itself, but that's

911
00:47:25.119 --> 00:47:30.320
<v Speaker 4>still not bulletproof. You can still lose data because it's

912
00:47:30.320 --> 00:47:32.199
<v Speaker 4>stored in the server memory, and if the server's gone,

913
00:47:32.239 --> 00:47:34.199
<v Speaker 4>well it's gone, Like what else do you expect to happen?

914
00:47:34.719 --> 00:47:39.440
<v Speaker 4>So we want to create mechanisms by which you can

915
00:47:40.639 --> 00:47:44.920
<v Speaker 4>persist that state in a way that's independent of maintaining

916
00:47:44.920 --> 00:47:45.840
<v Speaker 4>the connection to the server.

917
00:47:46.280 --> 00:47:50.679
<v Speaker 2>At nine, there are also laser improvements for auto mode.

918
00:47:51.280 --> 00:47:53.840
<v Speaker 2>In general, it didn't really work all that well for

919
00:47:53.960 --> 00:47:56.599
<v Speaker 2>me before in dot Net eight and before, and in

920
00:47:56.760 --> 00:47:58.880
<v Speaker 2>nine it seems to really work well.

921
00:47:59.079 --> 00:48:01.679
<v Speaker 4>Yeah, so when an eight first shift, we unfortunately had

922
00:48:01.760 --> 00:48:04.199
<v Speaker 4>quite a bad bug with the automotive that basically meant

923
00:48:04.239 --> 00:48:07.119
<v Speaker 4>it was never going to work, which was terrible, and

924
00:48:07.159 --> 00:48:08.920
<v Speaker 4>we patched it almost straight away, but are still a

925
00:48:08.920 --> 00:48:12.840
<v Speaker 4>lot of people got this very bad first impression of that,

926
00:48:14.280 --> 00:48:17.239
<v Speaker 4>and even then it was you know, still had constraints

927
00:48:17.280 --> 00:48:20.400
<v Speaker 4>and limitations, and so yeah, we really wanted to improve

928
00:48:20.440 --> 00:48:22.199
<v Speaker 4>that a lot in nine, make sure that not only

929
00:48:22.239 --> 00:48:24.280
<v Speaker 4>did it really work this time, but it actually works

930
00:48:24.320 --> 00:48:26.400
<v Speaker 4>well in practical situations.

931
00:48:25.840 --> 00:48:28.639
<v Speaker 2>And that seems to be with along with some state

932
00:48:28.719 --> 00:48:33.000
<v Speaker 2>management and you know, shifting state from server to client

933
00:48:33.039 --> 00:48:34.960
<v Speaker 2>when we go to web assembly. That kind of stuff

934
00:48:35.480 --> 00:48:38.320
<v Speaker 2>seems to be a really good pattern. I think now

935
00:48:38.960 --> 00:48:41.639
<v Speaker 2>that I would actually recommend it, you know, because you

936
00:48:41.679 --> 00:48:45.960
<v Speaker 2>get the startup snappiness of server, but then you get

937
00:48:46.000 --> 00:48:50.039
<v Speaker 2>the you know, the independence of web assembly.

938
00:48:50.199 --> 00:48:53.840
<v Speaker 4>I absolutely agree with you that if your application is

939
00:48:53.880 --> 00:48:55.519
<v Speaker 4>built in the right way and the developer knows what

940
00:48:55.559 --> 00:48:57.920
<v Speaker 4>they're doing, then you can make it work really great.

941
00:48:57.960 --> 00:49:00.719
<v Speaker 4>And that's that's excellent. But we kind of want to

942
00:49:00.800 --> 00:49:02.920
<v Speaker 4>raise the bar from that from Dottnut time. We want

943
00:49:02.920 --> 00:49:04.760
<v Speaker 4>to make it so that you don't have to be

944
00:49:04.800 --> 00:49:08.760
<v Speaker 4>someone who writes your code in a sort of elaborate

945
00:49:08.800 --> 00:49:11.239
<v Speaker 4>and carefully thought out manner. You don't have to be

946
00:49:11.239 --> 00:49:13.719
<v Speaker 4>an expert, but rather just the natural way of building

947
00:49:13.760 --> 00:49:17.079
<v Speaker 4>your code in a simple, obvious manner. We'll just have

948
00:49:17.119 --> 00:49:21.239
<v Speaker 4>all those benefits just innately. That's really how we want

949
00:49:21.239 --> 00:49:22.960
<v Speaker 4>to raise the bar and improve things.

950
00:49:22.920 --> 00:49:25.760
<v Speaker 2>Right, so we can still use server, because using server

951
00:49:25.880 --> 00:49:28.440
<v Speaker 2>is just by itself a huge benefit because you don't

952
00:49:28.480 --> 00:49:30.159
<v Speaker 2>have to have an API layer and you don't have

953
00:49:30.239 --> 00:49:33.880
<v Speaker 2>to extra security precautions and things like that.

954
00:49:34.280 --> 00:49:37.440
<v Speaker 4>Yeah, it's very very straightforwards. I really enjoy whenever I

955
00:49:37.440 --> 00:49:39.440
<v Speaker 4>get to write a bit of playser server code because

956
00:49:39.480 --> 00:49:43.440
<v Speaker 4>it just bypasses so many of the boring boilerplate tasks

957
00:49:43.480 --> 00:49:45.960
<v Speaker 4>that you have in web development and just means you

958
00:49:46.039 --> 00:49:48.599
<v Speaker 4>just get something running very quickly and it just works.

959
00:49:48.760 --> 00:49:51.360
<v Speaker 2>Well, I'm excited. Let me know when I'll have FILS.

960
00:49:51.119 --> 00:49:54.559
<v Speaker 3>A long way from those experiments you showed in twenty sixteen. Friend,

961
00:49:54.639 --> 00:49:55.199
<v Speaker 3>my goodness.

962
00:49:55.360 --> 00:49:58.960
<v Speaker 4>Oh yeah, yeah, yes, indeed.

963
00:49:59.679 --> 00:50:00.840
<v Speaker 3>Yeah.

964
00:50:01.199 --> 00:50:02.519
<v Speaker 2>Is that the best talk you ever gave?

965
00:50:02.559 --> 00:50:06.000
<v Speaker 4>Or well, it's definitely fun. It was really cool.

966
00:50:06.039 --> 00:50:09.159
<v Speaker 3>Actually to do that, you hurt David Fowler's head and

967
00:50:09.159 --> 00:50:11.679
<v Speaker 3>that's not easy to do. Yeah, yeah, that's true.

968
00:50:12.000 --> 00:50:12.920
<v Speaker 2>Yeah, very cool.

969
00:50:13.039 --> 00:50:15.360
<v Speaker 3>It was a great time. It's good. It was cool

970
00:50:15.400 --> 00:50:18.239
<v Speaker 3>to be in the room. Definitely, moment, definitely.

971
00:50:18.280 --> 00:50:20.199
<v Speaker 2>Well, I'm looking forward to it, and I guess you

972
00:50:20.239 --> 00:50:22.079
<v Speaker 2>know the repos and open books so you can just

973
00:50:22.119 --> 00:50:25.440
<v Speaker 2>go check the progress and are the early bits out

974
00:50:25.480 --> 00:50:26.119
<v Speaker 2>there yet for.

975
00:50:26.320 --> 00:50:28.880
<v Speaker 4>At ten, No, not at all, because we haven't even

976
00:50:28.880 --> 00:50:32.760
<v Speaker 4>decided what's going to go into it. Sometimes we start

977
00:50:32.800 --> 00:50:36.440
<v Speaker 4>our planning a little bit earlier, but we were intentional

978
00:50:36.760 --> 00:50:39.119
<v Speaker 4>as a team to wait a little bit longer. I'd

979
00:50:39.199 --> 00:50:42.159
<v Speaker 4>let things settle a little bit more, be more thoughtful

980
00:50:42.159 --> 00:50:47.559
<v Speaker 4>about collecting feedback and about like creating clear consensus about

981
00:50:47.280 --> 00:50:51.440
<v Speaker 4>what would be wanted in this particular release. So yeah,

982
00:50:51.440 --> 00:50:53.920
<v Speaker 4>that's why it's it's brought us into January before we've

983
00:50:54.840 --> 00:50:55.840
<v Speaker 4>got a nailed down plan.

984
00:50:56.440 --> 00:50:59.360
<v Speaker 2>Excellent, awesome, Well we're coming to the end here. Is

985
00:50:59.360 --> 00:51:00.960
<v Speaker 2>there anything else you want to talk about before we

986
00:51:00.960 --> 00:51:01.480
<v Speaker 2>wrap it up?

987
00:51:01.639 --> 00:51:03.280
<v Speaker 4>Not specifically for me, all right?

988
00:51:03.480 --> 00:51:05.400
<v Speaker 2>Best place in your neighborhood for fish and chips?

989
00:51:05.639 --> 00:51:09.199
<v Speaker 4>Fish and chips? Wow, I don't know. Probably got a

990
00:51:09.239 --> 00:51:12.960
<v Speaker 4>couple of local chippies, but yeah, it's not really my thing,

991
00:51:14.159 --> 00:51:14.559
<v Speaker 4>not really.

992
00:51:14.639 --> 00:51:14.960
<v Speaker 2>Okay.

993
00:51:15.239 --> 00:51:17.800
<v Speaker 3>You in the South of England is that fish and

994
00:51:17.880 --> 00:51:19.679
<v Speaker 3>chip country?

995
00:51:19.719 --> 00:51:20.119
<v Speaker 1>It is?

996
00:51:20.280 --> 00:51:22.159
<v Speaker 3>It is you eat?

997
00:51:22.679 --> 00:51:25.679
<v Speaker 2>You must be going for a chicken teaka masala then

998
00:51:25.760 --> 00:51:26.480
<v Speaker 2>or something.

999
00:51:27.199 --> 00:51:29.199
<v Speaker 3>Better it's more for you, yeah, for sure.

1000
00:51:29.239 --> 00:51:31.719
<v Speaker 2>And where's your where's your favorite place in Bristol?

1001
00:51:32.280 --> 00:51:35.280
<v Speaker 4>Oh, in Bristol, We've got a really good one called

1002
00:51:35.400 --> 00:51:37.800
<v Speaker 4>Urban tand or just a good tip for the for

1003
00:51:37.840 --> 00:51:42.320
<v Speaker 4>the locals. Yeah, that's that's sort of classic in my area.

1004
00:51:42.400 --> 00:51:44.440
<v Speaker 2>Well, Steve, it's always great to talk to you, of course,

1005
00:51:44.639 --> 00:51:47.360
<v Speaker 2>and we'll be speaking to you more, you know, when

1006
00:51:47.800 --> 00:51:52.559
<v Speaker 2>things around dot ten get awesome. Ye okay, thanks again

1007
00:51:52.639 --> 00:52:14.119
<v Speaker 2>and we'll talk to you next time on dot net rocks.

1008
00:52:16.480 --> 00:52:19.159
<v Speaker 2>Dot net Rocks is brought to you by Franklin's Net

1009
00:52:19.280 --> 00:52:23.239
<v Speaker 2>and produced by Pop Studios, a full service audio, video

1010
00:52:23.320 --> 00:52:27.400
<v Speaker 2>and post production facility located physically in New London, Connecticut,

1011
00:52:27.639 --> 00:52:32.440
<v Speaker 2>and of course in the cloud online at pwop dot com.

1012
00:52:32.639 --> 00:52:34.760
<v Speaker 5>Visit our website at d O T N E t

1013
00:52:35.000 --> 00:52:39.039
<v Speaker 5>R O c k S dot com for RSS feeds, downloads,

1014
00:52:39.199 --> 00:52:42.880
<v Speaker 5>mobile apps, comments, and access to the full archives going

1015
00:52:42.920 --> 00:52:46.159
<v Speaker 5>back to show number one, recorded in September two.

1016
00:52:45.960 --> 00:52:48.960
<v Speaker 2>Thousand and two. And make sure you check out our sponsors.

1017
00:52:49.119 --> 00:52:52.119
<v Speaker 2>They keep us in business. Now, go write some code.

1018
00:52:52.480 --> 00:52:53.239
<v Speaker 2>See you next time.

1019
00:52:54.159 --> 00:52:59.440
<v Speaker 5>You got javans

1020
00:53:01.119 --> 00:53:04.960
<v Speaker 2>That means home, then my Texas in line d