WEBVTT

1
00:00:01.080 --> 00:00:02.960
<v Speaker 1>How'd you like to listen to dot net rocks with

2
00:00:03.040 --> 00:00:07.839
<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
00:00:10.800 --> 00:00:14.039
<v Speaker 1>where all the shows have no ads. Twenty dollars a

5
00:00:14.039 --> 00:00:16.559
<v Speaker 1>month will get you that and a special dot net

6
00:00:16.640 --> 00:00:20.399
<v Speaker 1>Rocks patron mug. Sign up now at Patreon dot dot

7
00:00:20.440 --> 00:00:36.640
<v Speaker 1>NetRocks dot com. Hey, and welcome back to dot net rocks.

8
00:00:36.679 --> 00:00:40.159
<v Speaker 1>I'm Carl Franklin, an amateur camp This is episode number

9
00:00:40.159 --> 00:00:44.079
<v Speaker 1>two thousand and five. Here we are, so, I guess

10
00:00:44.079 --> 00:00:47.520
<v Speaker 1>we should start with what happened in two thousand and five?

11
00:00:49.280 --> 00:00:50.679
<v Speaker 2>You want to start? Where do you want to go?

12
00:00:50.719 --> 00:00:51.799
<v Speaker 2>I got a bunch of weird things.

13
00:00:51.880 --> 00:00:54.079
<v Speaker 1>Yeah, I'll save all the good stuff for you. But

14
00:00:54.719 --> 00:00:57.000
<v Speaker 1>there's some, you know, not so good things that happen

15
00:00:57.039 --> 00:01:01.600
<v Speaker 1>in two thousand and five, like Hurricane Katrina. Oh right, yeah,

16
00:01:01.719 --> 00:01:05.719
<v Speaker 1>I was down in New Orleans after Katrina for jazz

17
00:01:05.719 --> 00:01:13.000
<v Speaker 1>Fest and Robert Plant and what's her name? Alison Krause

18
00:01:13.519 --> 00:01:15.319
<v Speaker 1>came out and did when the levee.

19
00:01:15.000 --> 00:01:17.719
<v Speaker 2>Breaks a little on the nose but okay.

20
00:01:17.439 --> 00:01:22.480
<v Speaker 1>And also I remember going to a bar where they

21
00:01:22.680 --> 00:01:30.480
<v Speaker 1>said it was a makeshift hospital during Katrina and on

22
00:01:30.640 --> 00:01:33.560
<v Speaker 1>the you know, people would lay on the bar and

23
00:01:33.760 --> 00:01:36.519
<v Speaker 1>doctors would come in and work on them. Sure, all right,

24
00:01:37.000 --> 00:01:42.879
<v Speaker 1>Iraq war, bad war? In Iraqi elections. John Paul the

25
00:01:42.920 --> 00:01:46.120
<v Speaker 1>Second died in two thousand and five. Pope Benedict became

26
00:01:46.400 --> 00:01:51.680
<v Speaker 1>Pope Well. German Cardinal Joseph Ratzinger became Pope Benedict, and

27
00:01:51.719 --> 00:01:52.879
<v Speaker 1>he was a sixteen.

28
00:01:52.920 --> 00:01:55.439
<v Speaker 2>He was a close confident of John Paul's.

29
00:01:55.439 --> 00:01:59.480
<v Speaker 1>I recall, yeah, the London July seven terrorist bombings.

30
00:02:00.120 --> 00:02:00.319
<v Speaker 3>MS.

31
00:02:00.319 --> 00:02:01.840
<v Speaker 1>Were you around when that happened.

32
00:02:02.280 --> 00:02:06.560
<v Speaker 3>I was in London when that happened. I was Yeah,

33
00:02:06.599 --> 00:02:11.400
<v Speaker 3>that hit very close to home. Well glad you're still here. Yeah,

34
00:02:11.479 --> 00:02:11.879
<v Speaker 3>me too.

35
00:02:13.120 --> 00:02:16.400
<v Speaker 1>Sodom Hussein's trial begin, Well, we know how that'll go. Yeah,

36
00:02:16.400 --> 00:02:21.879
<v Speaker 1>we know. The spoiler alert didn't go well for him.

37
00:02:22.000 --> 00:02:25.039
<v Speaker 1>Terry Schiavo the right to Die case. Remember the legal

38
00:02:25.080 --> 00:02:29.599
<v Speaker 1>and ethical battle over removing the feeding tubes from Terry's chabo. Yeah, yeah,

39
00:02:29.800 --> 00:02:34.599
<v Speaker 1>national debate about end of life decisions, government intervention, family rights.

40
00:02:36.120 --> 00:02:42.360
<v Speaker 1>Record breaking Atlantic hurricane season, not just Katrina, but Rita Wilma,

41
00:02:43.560 --> 00:02:48.919
<v Speaker 1>just one of the worst hurricane seasons. UH Israel withdrew

42
00:02:48.960 --> 00:02:51.360
<v Speaker 1>from Gaza. Things were looking up.

43
00:02:51.360 --> 00:02:53.120
<v Speaker 2>There, we're gonna be elections only one.

44
00:02:53.400 --> 00:02:59.759
<v Speaker 1>Yeah, and Angela Merkle became Chancellor of Germany, first female

45
00:02:59.800 --> 00:03:03.479
<v Speaker 1>chamer beginning a leadership era that would shape European politics

46
00:03:03.520 --> 00:03:09.280
<v Speaker 1>for more than fifteen years. Some honorable mentions. Michael Jackson

47
00:03:09.400 --> 00:03:16.439
<v Speaker 1>was acquitted, Prince Charles married Camilla Parker Bowels. French and

48
00:03:16.560 --> 00:03:20.599
<v Speaker 1>Dutch rejection of the EU Constitution. Let's talk bad about

49
00:03:20.639 --> 00:03:21.240
<v Speaker 1>the French and.

50
00:03:21.199 --> 00:03:24.520
<v Speaker 2>The Dutch, right Arguably the moment the E that's the

51
00:03:24.520 --> 00:03:25.439
<v Speaker 2>moment the EU broke.

52
00:03:25.719 --> 00:03:29.120
<v Speaker 1>Yeah, in Pakistan there was an earthquake that killed tens

53
00:03:29.280 --> 00:03:34.800
<v Speaker 1>of thousands of people. In high oil and gasoline prices worldwide,

54
00:03:34.919 --> 00:03:38.240
<v Speaker 1>I'm not so sure that they were as high as

55
00:03:38.280 --> 00:03:41.080
<v Speaker 1>they are now. I don't know, probably not. Yeah.

56
00:03:41.159 --> 00:03:41.280
<v Speaker 2>No.

57
00:03:41.599 --> 00:03:44.120
<v Speaker 3>Also, I got married in two thousand and five. Yeah,

58
00:03:44.319 --> 00:03:49.879
<v Speaker 3>ah wow, which nearly made it to twenty years. Yeah,

59
00:03:49.960 --> 00:03:53.400
<v Speaker 3>but you know, most of them were good and it

60
00:03:53.479 --> 00:03:57.599
<v Speaker 3>was it's amicably dissolved, good, good, good.

61
00:03:57.639 --> 00:04:01.520
<v Speaker 2>Some lovely progeny. As I recall, I do have two.

62
00:04:01.919 --> 00:04:04.759
<v Speaker 3>I have two of the most amazing kids anybody could

63
00:04:04.840 --> 00:04:09.680
<v Speaker 3>hope for. Yeah, that's just apps. I mean, they are special,

64
00:04:09.840 --> 00:04:13.080
<v Speaker 3>they are and yeah, I'll never say that, but my

65
00:04:13.199 --> 00:04:16.439
<v Speaker 3>kids are awesome, all right.

66
00:04:16.560 --> 00:04:19.199
<v Speaker 1>So Top ten grossing movies from two thousand and five.

67
00:04:19.279 --> 00:04:25.360
<v Speaker 1>Number ten Hitch, number nine, Batman Begins, so many Batman's,

68
00:04:25.959 --> 00:04:33.519
<v Speaker 1>I'm Batman, Charlie and the Chocolate Factory, Mister and Missus Smith, Madagascar,

69
00:04:34.319 --> 00:04:40.519
<v Speaker 1>King Kong War, The World's The Chronicles of Narnia, Lying

70
00:04:40.560 --> 00:04:44.560
<v Speaker 1>the Witch and the Wardrobe, Number two, Star Wars Episode three,

71
00:04:44.680 --> 00:04:49.800
<v Speaker 1>Revenge of the Sith, and number one Harry Potter and

72
00:04:49.800 --> 00:04:53.519
<v Speaker 1>the Goblet of Fire, grossing eight hundred and ninety five

73
00:04:53.879 --> 00:04:55.519
<v Speaker 1>point nine million dollars.

74
00:04:55.959 --> 00:04:57.759
<v Speaker 3>I'll see. If I could only keep one of those,

75
00:04:57.800 --> 00:05:01.240
<v Speaker 3>I'd go with Madagascar like that one was a great

76
00:05:02.560 --> 00:05:03.879
<v Speaker 3>Winds just killed.

77
00:05:03.959 --> 00:05:09.360
<v Speaker 1>Yeah, yeah. Richard, Space and Tech, I guess this was

78
00:05:09.360 --> 00:05:10.879
<v Speaker 1>a pretty good year for space. Huh.

79
00:05:11.040 --> 00:05:14.199
<v Speaker 2>Well, uh, this is the year that Airbus reveals the

80
00:05:14.240 --> 00:05:18.000
<v Speaker 2>A three eighty find the building an airplane bigger than

81
00:05:18.000 --> 00:05:22.519
<v Speaker 2>seven forty seven, and they kind of botched it because, actually, music,

82
00:05:22.800 --> 00:05:26.000
<v Speaker 2>they'll take far longer to build than planned. Deep down,

83
00:05:26.040 --> 00:05:29.680
<v Speaker 2>if you're into aeronautics, they had they knew, they expected

84
00:05:29.680 --> 00:05:32.639
<v Speaker 2>that they would build stretch versions of the A three eighty, right,

85
00:05:32.680 --> 00:05:34.360
<v Speaker 2>they only ever built the one model the eight, but

86
00:05:34.399 --> 00:05:36.519
<v Speaker 2>they were planning on building stretch models, and so in

87
00:05:36.560 --> 00:05:39.360
<v Speaker 2>anticipation of that, they overbuilt the wing so that it

88
00:05:39.399 --> 00:05:41.360
<v Speaker 2>would be able to handle the stretch versions, and that

89
00:05:41.439 --> 00:05:44.759
<v Speaker 2>there are for by making the main version, the initial

90
00:05:44.839 --> 00:05:48.079
<v Speaker 2>version less efficient than it could be. Okay, that, combined

91
00:05:48.120 --> 00:05:51.399
<v Speaker 2>with the general failure of spoken hub flying systems, this

92
00:05:51.519 --> 00:05:54.120
<v Speaker 2>method of using big airports that everybody flies into and

93
00:05:54.160 --> 00:05:56.839
<v Speaker 2>everybody flies out of, meant the A three eighty was

94
00:05:56.879 --> 00:06:00.319
<v Speaker 2>the wrong airplane for modern times. And so build a

95
00:06:00.399 --> 00:06:02.040
<v Speaker 2>less than two hundred of them, and then they'll shut

96
00:06:02.160 --> 00:06:04.279
<v Speaker 2>on the line and it'll be a major financial loser.

97
00:06:04.160 --> 00:06:04.600
<v Speaker 3>For air US.

98
00:06:04.639 --> 00:06:08.120
<v Speaker 1>I don't remember any of that. I just Airbus built

99
00:06:08.199 --> 00:06:10.680
<v Speaker 1>other planes since then, right, Oh yeah, No.

100
00:06:11.040 --> 00:06:13.680
<v Speaker 2>Arguably the A three twenty is the most successful airplane

101
00:06:13.680 --> 00:06:15.959
<v Speaker 2>out there. You know, he's neck connect with the seven

102
00:06:16.000 --> 00:06:18.120
<v Speaker 2>thirty seven. But I can go nuts on aerospace, as

103
00:06:18.120 --> 00:06:21.920
<v Speaker 2>you well know. Yeah, let's keep going on, I would argue.

104
00:06:21.920 --> 00:06:23.439
<v Speaker 2>One of the most interesting things happened this year. The

105
00:06:23.519 --> 00:06:26.800
<v Speaker 2>year was the DARPA Grand Challenge. This was the beginning

106
00:06:26.800 --> 00:06:31.759
<v Speaker 2>of automated driving, and when Stanford's stan Lee vehicle completed

107
00:06:31.800 --> 00:06:34.160
<v Speaker 2>the challenge successfully, they had it they'd been running for

108
00:06:34.160 --> 00:06:35.079
<v Speaker 2>a couple of years at that point.

109
00:06:35.199 --> 00:06:37.079
<v Speaker 1>That was the best show I ever watched on the

110
00:06:37.120 --> 00:06:37.959
<v Speaker 1>Discovery Channel.

111
00:06:38.079 --> 00:06:40.720
<v Speaker 2>Yeah, it was great, And here we are twenty years later,

112
00:06:41.000 --> 00:06:43.639
<v Speaker 2>still trying to figure it out. All right. On the

113
00:06:43.639 --> 00:06:48.000
<v Speaker 2>space side, January is a crazy month. It starts with

114
00:06:49.120 --> 00:06:54.000
<v Speaker 2>a group of astronomers identifying a Cooper object they called

115
00:06:54.120 --> 00:06:56.920
<v Speaker 2>Aras at the time, when they identified it, they thought

116
00:06:56.920 --> 00:07:01.720
<v Speaker 2>it was larger than Pluto and kicked off the cascade

117
00:07:01.959 --> 00:07:04.519
<v Speaker 2>that results in Pluto being demoted as a planet. Right,

118
00:07:04.600 --> 00:07:07.240
<v Speaker 2>So the issue being here, now that they found Arison,

119
00:07:07.240 --> 00:07:09.199
<v Speaker 2>they're pretty sure there's other objects of that size. They'll

120
00:07:09.240 --> 00:07:12.160
<v Speaker 2>laterally find them, things like said and so forth. Initially

121
00:07:12.199 --> 00:07:14.160
<v Speaker 2>they say, okay, well there's ten plants in Solar system.

122
00:07:14.199 --> 00:07:16.519
<v Speaker 2>Then there might be eleven or twelve or thirteen, but

123
00:07:16.560 --> 00:07:20.800
<v Speaker 2>they're different from the main nine or the main eight.

124
00:07:20.879 --> 00:07:22.160
<v Speaker 1>But they do or at the Sun.

125
00:07:22.000 --> 00:07:23.639
<v Speaker 2>Right all or at the Sun. So they had to

126
00:07:23.959 --> 00:07:25.959
<v Speaker 2>The reality is there was no definition for a planet

127
00:07:25.959 --> 00:07:26.560
<v Speaker 2>at the time.

128
00:07:26.839 --> 00:07:29.800
<v Speaker 1>Right right. I remember Neil de grass Tyson was one

129
00:07:29.800 --> 00:07:31.959
<v Speaker 1>of the guys who put the nail on the coffin

130
00:07:32.000 --> 00:07:33.160
<v Speaker 1>of Pluto as a planet.

131
00:07:33.519 --> 00:07:36.279
<v Speaker 3>That's actually how Neil Degrass Tyson became famous.

132
00:07:36.399 --> 00:07:36.560
<v Speaker 1>Yeah.

133
00:07:36.639 --> 00:07:38.639
<v Speaker 2>Yeah, it was support of this argument. The problem is

134
00:07:38.639 --> 00:07:42.040
<v Speaker 2>that the definition is weak orbiting the Sun, fine is

135
00:07:42.120 --> 00:07:45.839
<v Speaker 2>round or has hydrostatic equilibrium aka enough gravity pull itself

136
00:07:45.879 --> 00:07:49.480
<v Speaker 2>into shape. Fine, here's the one they added to make

137
00:07:49.519 --> 00:07:53.439
<v Speaker 2>it planet has quote cleared its orbit.

138
00:07:53.800 --> 00:07:54.399
<v Speaker 1>What does that mean?

139
00:07:54.560 --> 00:07:58.040
<v Speaker 3>So that's exactly so it sucked up everything which is

140
00:07:58.160 --> 00:08:01.399
<v Speaker 3>in its orbital path itself.

141
00:08:01.519 --> 00:08:03.920
<v Speaker 2>Yeah, to be clear, no planet has actually done that.

142
00:08:04.199 --> 00:08:08.480
<v Speaker 2>Every planet has both Trojan and Apollo asteroids following in

143
00:08:08.560 --> 00:08:11.079
<v Speaker 2>its orbit. But one would argue that is clear that

144
00:08:11.160 --> 00:08:15.759
<v Speaker 2>they are on the same orbital path, just in gravitational equilibrium,

145
00:08:15.759 --> 00:08:19.560
<v Speaker 2>so they never get to the planet. You know, Pluto

146
00:08:20.199 --> 00:08:23.600
<v Speaker 2>isn't on the plane of the elliptic, it doesn't actually

147
00:08:23.720 --> 00:08:27.120
<v Speaker 2>orbit flat with the other eight planets. It also crosses

148
00:08:27.199 --> 00:08:30.600
<v Speaker 2>Neptune's orbit like it's a different object. Now. At the

149
00:08:30.639 --> 00:08:33.399
<v Speaker 2>same time, they also had Serres, which is the probably

150
00:08:33.399 --> 00:08:36.039
<v Speaker 2>the remains of a planet that existed between Mars and

151
00:08:36.080 --> 00:08:38.440
<v Speaker 2>Jupiter and was torn apart, and it's a planetary core,

152
00:08:38.879 --> 00:08:41.039
<v Speaker 2>so they considered they called that a dwarf planet as well.

153
00:08:41.200 --> 00:08:44.519
<v Speaker 2>Was originally called an asteroid, even though it's huge, and

154
00:08:44.559 --> 00:08:47.639
<v Speaker 2>now they had ris as well, also not on the

155
00:08:47.679 --> 00:08:52.360
<v Speaker 2>planet ecliptic also, you know, doing some crossing and asymmetry,

156
00:08:52.799 --> 00:08:55.039
<v Speaker 2>and so the dwarf planet category sort of picks all

157
00:08:55.080 --> 00:08:57.200
<v Speaker 2>those Cooper objects up.

158
00:08:57.399 --> 00:09:00.120
<v Speaker 1>I remember being blown away by the images of Pluto.

159
00:09:00.559 --> 00:09:02.240
<v Speaker 1>That was a voyager.

160
00:09:02.440 --> 00:09:05.440
<v Speaker 2>Oh when new Horizons gets there, new Horizons.

161
00:09:05.480 --> 00:09:05.720
<v Speaker 1>Yeah.

162
00:09:05.799 --> 00:09:10.440
<v Speaker 3>Yeah. My favorite thing about that whole sort of dwarf

163
00:09:10.480 --> 00:09:13.960
<v Speaker 3>planet drama is that Eris is named after the Greek

164
00:09:14.000 --> 00:09:19.639
<v Speaker 3>goddess of mischief and discord and chaos, which is very appropriate.

165
00:09:20.120 --> 00:09:25.440
<v Speaker 3>Completely through the whole astronomical establishment into disorder for years, you.

166
00:09:25.480 --> 00:09:27.600
<v Speaker 2>Got people wound up and still wound up. There's a

167
00:09:27.639 --> 00:09:29.399
<v Speaker 2>movement again to make Pluto a planet.

168
00:09:29.519 --> 00:09:32.759
<v Speaker 1>Yes, so Hailarius. That's right, it's not over yet. I

169
00:09:32.840 --> 00:09:33.720
<v Speaker 1>recently heard that.

170
00:09:34.039 --> 00:09:36.200
<v Speaker 2>Yeah, all right, well let's move on. That's a fun one.

171
00:09:36.320 --> 00:09:39.840
<v Speaker 2>Also in January, the Huygens probe off of Cassini lands

172
00:09:39.840 --> 00:09:42.240
<v Speaker 2>on Titan and gives us our first images of the

173
00:09:42.240 --> 00:09:45.159
<v Speaker 2>surface of Titan because it has a very thick hydro

174
00:09:45.399 --> 00:09:49.960
<v Speaker 2>chemical atmosphere methane and methane primarily, and we can see

175
00:09:50.120 --> 00:09:54.159
<v Speaker 2>as it's descending and sends back these photos erosion patterns,

176
00:09:54.200 --> 00:09:57.399
<v Speaker 2>just not erosion caused by water. Water is frozen solid there,

177
00:09:57.440 --> 00:10:02.879
<v Speaker 2>it's like rock there. This is done by hydrochemicals, by

178
00:10:02.879 --> 00:10:05.919
<v Speaker 2>things like ethane raining out of the sky and eroding

179
00:10:06.240 --> 00:10:11.600
<v Speaker 2>the terrain. So amazing pictures. Great accomplishment there, and also

180
00:10:11.720 --> 00:10:17.720
<v Speaker 2>in January. We're still in January the Deep and Impact experiments.

181
00:10:17.759 --> 00:10:21.039
<v Speaker 2>This launched off a Delta two to impact on the

182
00:10:21.080 --> 00:10:23.840
<v Speaker 2>Temple one comet as it went by, so they get

183
00:10:23.840 --> 00:10:26.799
<v Speaker 2>there by July. It was a very quick intercept, but

184
00:10:26.919 --> 00:10:28.559
<v Speaker 2>mission will go a little bit wrong. They will have

185
00:10:28.639 --> 00:10:31.159
<v Speaker 2>the impactor, but the sensors will be overwhelmed by the debris.

186
00:10:31.200 --> 00:10:33.200
<v Speaker 2>It'll kick up far more than expected.

187
00:10:33.399 --> 00:10:34.000
<v Speaker 1>I remember that.

188
00:10:34.159 --> 00:10:36.639
<v Speaker 2>But the Stardust mission that's already up there, that's been

189
00:10:36.639 --> 00:10:39.000
<v Speaker 2>doing collections off of other comets, will be able to

190
00:10:39.000 --> 00:10:41.480
<v Speaker 2>do a pass on Temple one's debris cloud as well

191
00:10:41.519 --> 00:10:44.080
<v Speaker 2>and get material that way, so they'll recover from.

192
00:10:43.960 --> 00:10:46.200
<v Speaker 1>You want to land on the head of the comet,

193
00:10:46.320 --> 00:10:47.080
<v Speaker 1>not the tail.

194
00:10:47.919 --> 00:10:49.879
<v Speaker 2>Well this they only sent an impactor in it. The

195
00:10:49.919 --> 00:10:52.519
<v Speaker 2>idea was to kick up debris to try and measure

196
00:10:52.919 --> 00:10:55.000
<v Speaker 2>the contents and actually collect some of that de breach.

197
00:10:55.000 --> 00:10:58.080
<v Speaker 2>It didn't work out. Finally for space There was only

198
00:10:58.120 --> 00:11:01.960
<v Speaker 2>one flight of a shuttle after the Columbia disaster in

199
00:11:01.960 --> 00:11:03.559
<v Speaker 2>two thousand and three. There were no flights in two

200
00:11:03.600 --> 00:11:05.360
<v Speaker 2>thousand and four. There's one in two thousand and five.

201
00:11:05.399 --> 00:11:06.759
<v Speaker 2>It was supposed to be the return of flight. It

202
00:11:06.799 --> 00:11:10.080
<v Speaker 2>was the Discovery Shuttle bringing supplies to the space station

203
00:11:10.200 --> 00:11:14.879
<v Speaker 2>that brought up the Rafello, the MPLM European capsule that

204
00:11:14.919 --> 00:11:16.600
<v Speaker 2>they would take out of the cargo bay of the

205
00:11:16.639 --> 00:11:18.639
<v Speaker 2>shuttle and dock to the station to leave it there

206
00:11:18.679 --> 00:11:21.480
<v Speaker 2>that they could refill it with garbage and or experiments

207
00:11:21.480 --> 00:11:25.399
<v Speaker 2>and bring it back. There will be enough problems with Discovery,

208
00:11:25.879 --> 00:11:28.960
<v Speaker 2>including damages to its tiles, that they will not fly

209
00:11:29.039 --> 00:11:32.519
<v Speaker 2>again that entire year. They'll have to do further corrections.

210
00:11:32.519 --> 00:11:34.240
<v Speaker 2>This is when they add the additional arm to be

211
00:11:34.279 --> 00:11:38.039
<v Speaker 2>able to inspect the hull, and that'll be later. This

212
00:11:38.080 --> 00:11:39.840
<v Speaker 2>one they did of they because they went to the

213
00:11:39.879 --> 00:11:42.919
<v Speaker 2>space station. They did the inspection by pulling Discovery off

214
00:11:42.960 --> 00:11:44.960
<v Speaker 2>of the space station and flipping the shuttle over so

215
00:11:44.960 --> 00:11:47.759
<v Speaker 2>they could photograph it and saw some problems. So the

216
00:11:48.200 --> 00:11:50.799
<v Speaker 2>issues of the tile system are becoming more and more apparent,

217
00:11:50.840 --> 00:11:52.759
<v Speaker 2>and it will ultimately result in the end of the

218
00:11:52.759 --> 00:11:57.919
<v Speaker 2>Shuttle program. On the computing side, in the Microsoft lands,

219
00:11:57.960 --> 00:12:02.360
<v Speaker 2>we get XP National sixty four bit, the first sixty

220
00:12:02.399 --> 00:12:04.159
<v Speaker 2>four bit version of Windows.

221
00:12:05.000 --> 00:12:08.240
<v Speaker 1>I ran it, yeah, I remember that show. Yeah, we

222
00:12:08.279 --> 00:12:11.919
<v Speaker 1>did on sixty four bit, and that also prompted the

223
00:12:11.960 --> 00:12:15.679
<v Speaker 1>sixty four bit question yeah, which we end our conference

224
00:12:16.200 --> 00:12:16.639
<v Speaker 1>shows with.

225
00:12:16.799 --> 00:12:21.039
<v Speaker 2>It also goes alongside dot net two and Studio two

226
00:12:21.080 --> 00:12:23.519
<v Speaker 2>thousand and five, which includes sixty four bit support, except

227
00:12:23.559 --> 00:12:26.759
<v Speaker 2>that they had law offered the option as compile any,

228
00:12:26.879 --> 00:12:29.200
<v Speaker 2>which really meant running thirty two bit and crash in

229
00:12:29.240 --> 00:12:29.879
<v Speaker 2>sixty four bit.

230
00:12:30.159 --> 00:12:32.200
<v Speaker 1>Yep, I remember.

231
00:12:34.799 --> 00:12:37.159
<v Speaker 2>Any wrong? We did that show. Don't do it any

232
00:12:37.200 --> 00:12:39.279
<v Speaker 2>If you're not sure you're going to run in sixty

233
00:12:39.279 --> 00:12:41.360
<v Speaker 2>four bit, set it to thirty two bid. Oh you

234
00:12:41.440 --> 00:12:44.120
<v Speaker 2>will be sad. And really the only thing you were

235
00:12:44.120 --> 00:12:46.000
<v Speaker 2>getting was do you get more than two gigs of

236
00:12:46.039 --> 00:12:46.759
<v Speaker 2>address space?

237
00:12:46.879 --> 00:12:47.080
<v Speaker 1>Right?

238
00:12:47.159 --> 00:12:49.159
<v Speaker 2>And I think I said this on the show at

239
00:12:49.159 --> 00:12:50.440
<v Speaker 2>the time. If you need more than two gigs of

240
00:12:50.440 --> 00:12:56.759
<v Speaker 2>address space, what do you do? Do you doing, especially

241
00:12:56.759 --> 00:12:59.279
<v Speaker 2>for a web page? I want to run. I want

242
00:12:59.320 --> 00:13:01.840
<v Speaker 2>to run is sixty four bit moode. It's like more

243
00:13:01.879 --> 00:13:03.440
<v Speaker 2>than two gigs for a web page?

244
00:13:03.679 --> 00:13:04.279
<v Speaker 1>What do you doing?

245
00:13:05.639 --> 00:13:06.919
<v Speaker 3>Like a tudy stories.

246
00:13:06.639 --> 00:13:09.399
<v Speaker 2>Coming out of the dot com bust last year. In

247
00:13:09.399 --> 00:13:12.120
<v Speaker 2>two thousand and four, we had YouTube going public because

248
00:13:12.159 --> 00:13:15.080
<v Speaker 2>the SEC required they had too many shareholders, so they

249
00:13:15.159 --> 00:13:19.080
<v Speaker 2>start making some our Google goes public and this is

250
00:13:19.120 --> 00:13:22.000
<v Speaker 2>when YouTube is founded and the first YouTube video called

251
00:13:22.120 --> 00:13:24.440
<v Speaker 2>Me at the Zoo is published. This is before you know,

252
00:13:24.480 --> 00:13:27.840
<v Speaker 2>Google hasn't bought them yet, right, but they will. But

253
00:13:28.120 --> 00:13:31.320
<v Speaker 2>my Google does launch Google Maps in two thousand and five. Yeah,

254
00:13:31.360 --> 00:13:33.679
<v Speaker 2>and a little bit on the hardware side, Microsoft launches

255
00:13:33.720 --> 00:13:36.639
<v Speaker 2>the Xbox three sixty, the weirdo version of Xbox that

256
00:13:36.679 --> 00:13:40.960
<v Speaker 2>all the game developers hated. The first r duinos are sold,

257
00:13:41.000 --> 00:13:44.200
<v Speaker 2>and this really begins this wave even before Raspberry Pie

258
00:13:44.200 --> 00:13:46.919
<v Speaker 2>and things of the little micro controller you can program

259
00:13:46.919 --> 00:13:50.919
<v Speaker 2>and do cool computer things. Yeah, and Lenovo buys IBM

260
00:13:51.000 --> 00:13:53.799
<v Speaker 2>think padline and becomes you know, today, I think the

261
00:13:53.840 --> 00:13:57.000
<v Speaker 2>coolest laptop maker on the planet, not that I want one,

262
00:13:57.120 --> 00:13:58.960
<v Speaker 2>but they do cool stuff.

263
00:13:59.000 --> 00:14:01.480
<v Speaker 1>The think pads where coveted. Yeah.

264
00:14:01.840 --> 00:14:05.039
<v Speaker 3>The coolest maker on the planet that is an Apple.

265
00:14:05.240 --> 00:14:06.159
<v Speaker 3>Let's put it that way.

266
00:14:06.799 --> 00:14:08.799
<v Speaker 2>The Apple doesn't make a lot of machines. They make

267
00:14:08.799 --> 00:14:11.519
<v Speaker 2>the highest quality machines, like by far. But when I

268
00:14:11.519 --> 00:14:14.159
<v Speaker 2>say cool, I mean like you never know what logos

269
00:14:14.440 --> 00:14:16.799
<v Speaker 2>Leno was gonna do. Is like this one has two screens,

270
00:14:16.840 --> 00:14:20.080
<v Speaker 2>this one has three screens, this one full. Yes, yes,

271
00:14:20.559 --> 00:14:25.720
<v Speaker 2>it becomes right like they're nuts. Yes, all right, standing down.

272
00:14:26.159 --> 00:14:29.799
<v Speaker 2>They make it. They make a dedicated knock for teams

273
00:14:29.879 --> 00:14:36.559
<v Speaker 2>because everybody hates themselves, Like I don't know it all right,

274
00:14:36.600 --> 00:14:38.320
<v Speaker 2>that's all I got, thanks.

275
00:14:38.039 --> 00:14:43.120
<v Speaker 1>For Okay, before we talk to MS. Let's do better.

276
00:14:43.159 --> 00:14:44.679
<v Speaker 1>No framework, roll.

277
00:14:44.519 --> 00:14:53.799
<v Speaker 2>It awesome man, you got.

278
00:14:54.360 --> 00:15:00.000
<v Speaker 1>So there's this project on GitHub called Sophia Script for Windows.

279
00:15:00.240 --> 00:15:01.039
<v Speaker 2>Oh what is that?

280
00:15:01.080 --> 00:15:04.679
<v Speaker 1>And basically it's a PowerShell module for fine tuning Windows

281
00:15:04.720 --> 00:15:09.039
<v Speaker 1>on GitHub. It's got one hundred and fifty unique functions

282
00:15:09.080 --> 00:15:13.759
<v Speaker 1>to configure Windows using Microsoft's officially documented ways without without

283
00:15:13.799 --> 00:15:18.840
<v Speaker 1>harming your system. Okay, And there is now or there

284
00:15:18.960 --> 00:15:22.799
<v Speaker 1>was recently a Windows version of this. So this is

285
00:15:22.919 --> 00:15:27.879
<v Speaker 1>Sofia app in the Sofia community. So they say, it's

286
00:15:27.919 --> 00:15:32.480
<v Speaker 1>the next chapter of the Sofia script project. And this

287
00:15:32.559 --> 00:15:34.840
<v Speaker 1>is a free, open source app for fine tuning Windows

288
00:15:34.879 --> 00:15:38.879
<v Speaker 1>ten and Windows eleven. Offers a modern UI UX with

289
00:15:39.000 --> 00:15:41.960
<v Speaker 1>more than one hundred and thirty unique tweaks and shows

290
00:15:41.960 --> 00:15:46.240
<v Speaker 1>how Windows can be configured without making any harm to Windows.

291
00:15:47.039 --> 00:15:49.799
<v Speaker 1>So I haven't used it, but there's you can install

292
00:15:49.799 --> 00:15:53.279
<v Speaker 1>it with Chocolate Scoop and beta versions you can just

293
00:15:54.120 --> 00:15:59.279
<v Speaker 1>you know, expand them and run them and yeah, it's

294
00:15:59.320 --> 00:16:00.000
<v Speaker 1>this is good stuf.

295
00:16:00.440 --> 00:16:03.759
<v Speaker 2>Yeah, sure, you know. Over my other life on Windows Weekly,

296
00:16:03.919 --> 00:16:06.919
<v Speaker 2>Paul the Rod has been working steadily on how do

297
00:16:06.960 --> 00:16:09.840
<v Speaker 2>you make Windows eleven not suck? Yeah, right, like just

298
00:16:09.919 --> 00:16:14.039
<v Speaker 2>turning removing stuff and getting the base configuration down, you know.

299
00:16:14.559 --> 00:16:16.360
<v Speaker 2>And if you don't want to deal with one drive,

300
00:16:16.440 --> 00:16:18.879
<v Speaker 2>here's how to actually make it go away without nagging you.

301
00:16:18.919 --> 00:16:20.759
<v Speaker 2>If you don't want a Microsoft account, here's how you

302
00:16:20.879 --> 00:16:22.840
<v Speaker 2>actually can figure it. But this looks like a tool

303
00:16:22.919 --> 00:16:24.320
<v Speaker 2>just make your life a lot easier for that sort

304
00:16:24.320 --> 00:16:24.559
<v Speaker 2>of thing.

305
00:16:24.720 --> 00:16:27.480
<v Speaker 1>Yep. There's one feature that I'm going to check to

306
00:16:27.519 --> 00:16:34.399
<v Speaker 1>see if it has, and that is this persistent the

307
00:16:34.480 --> 00:16:38.960
<v Speaker 1>first persistent feature quote unquote that anytime you're in file

308
00:16:39.039 --> 00:16:41.799
<v Speaker 1>Explorer and you've got wave files and MP three files

309
00:16:41.840 --> 00:16:48.440
<v Speaker 1>and stuff, it insists on using the music format for

310
00:16:48.799 --> 00:16:52.320
<v Speaker 1>the fields that it shows rather than regular documents. And

311
00:16:52.360 --> 00:16:57.000
<v Speaker 1>I don't care about artists and album and contributing artists

312
00:16:57.039 --> 00:16:59.960
<v Speaker 1>and you know, all this stuff. I want to see

313
00:17:00.159 --> 00:17:03.919
<v Speaker 1>the file sized, because I'm you know, I deal with files.

314
00:17:04.240 --> 00:17:06.039
<v Speaker 2>Yeah, I don't care about how big the file is.

315
00:17:06.119 --> 00:17:07.920
<v Speaker 1>And it's and you turn it off and you turn

316
00:17:08.000 --> 00:17:11.960
<v Speaker 1>it and it comes back, and it's just really really aggravating.

317
00:17:12.200 --> 00:17:14.240
<v Speaker 1>I just want that feature out of Windows. So I'm

318
00:17:14.279 --> 00:17:18.200
<v Speaker 1>gonna look for that. Stop fighting me, right, That's that's

319
00:17:18.599 --> 00:17:20.720
<v Speaker 1>what I'm talking about. Who's talking to us?

320
00:17:20.839 --> 00:17:23.839
<v Speaker 2>Richard grabbing camming off the show nineteen sixteen. You know,

321
00:17:23.960 --> 00:17:28.359
<v Speaker 2>back in the World War One days done with one

322
00:17:28.440 --> 00:17:32.559
<v Speaker 2>Rendel called how simple is as simple as possible? Because

323
00:17:33.039 --> 00:17:37.599
<v Speaker 2>we get good show names, generated a ton of comments.

324
00:17:37.640 --> 00:17:40.680
<v Speaker 2>Of course, this is when we were talking primarily about

325
00:17:40.720 --> 00:17:44.920
<v Speaker 2>things like is our micro services essential? Like what are

326
00:17:44.920 --> 00:17:46.880
<v Speaker 2>better ways to build software? How do you keep this

327
00:17:47.119 --> 00:17:48.960
<v Speaker 2>just as complicated as it needs to be? In no

328
00:17:49.000 --> 00:17:51.559
<v Speaker 2>more than that? And just got a ton of comments

329
00:17:51.559 --> 00:17:53.720
<v Speaker 2>off of this show. Yeah, and I'm gonna grab this

330
00:17:53.720 --> 00:17:57.920
<v Speaker 2>one from Robin Osborne who says, thanks so much. When

331
00:17:57.920 --> 00:18:00.920
<v Speaker 2>I'm really doubting myself during the decade long tsunami of

332
00:18:01.119 --> 00:18:05.480
<v Speaker 2>JavaScript all the things, and I'm thinking, surely this isn't

333
00:18:05.480 --> 00:18:09.079
<v Speaker 2>the best approach. Am I wrong? Do I just not

334
00:18:09.160 --> 00:18:12.160
<v Speaker 2>understand something that everybody else gets. It's a load off

335
00:18:12.160 --> 00:18:14.279
<v Speaker 2>my chest to hear people I respect in the industry

336
00:18:14.279 --> 00:18:18.400
<v Speaker 2>talking about lovely things like HTMX and referencing Alex Russell's

337
00:18:18.400 --> 00:18:22.319
<v Speaker 2>great articles. I love Polly, I love twelve factor back

338
00:18:22.319 --> 00:18:25.079
<v Speaker 2>in the day. I love making things as simple as possible,

339
00:18:25.119 --> 00:18:27.640
<v Speaker 2>simple to build, simple to maintain, and still for the

340
00:18:27.720 --> 00:18:32.039
<v Speaker 2>end user. Gagny and kiss for the win. Shit, I'm

341
00:18:32.039 --> 00:18:34.599
<v Speaker 2>not going to argue with that. How about kiss? You mean,

342
00:18:34.759 --> 00:18:35.400
<v Speaker 2>keep it simple?

343
00:18:35.400 --> 00:18:35.799
<v Speaker 3>Stupid?

344
00:18:36.160 --> 00:18:37.920
<v Speaker 2>Yeah, I don't know where you want to go, but

345
00:18:38.279 --> 00:18:40.960
<v Speaker 2>you know what ramin where on board. You obviously heard

346
00:18:41.000 --> 00:18:42.759
<v Speaker 2>it on that show and probably hear more of that

347
00:18:42.799 --> 00:18:44.599
<v Speaker 2>today too. So thank you so much for your comment.

348
00:18:44.799 --> 00:18:46.519
<v Speaker 2>A copy of music Coby. It's on its way to you.

349
00:18:46.519 --> 00:18:47.880
<v Speaker 2>And if you'd like a copy of music Cobe, I

350
00:18:47.920 --> 00:18:49.720
<v Speaker 2>write a comment on the website at dot at Rocks

351
00:18:49.759 --> 00:18:51.880
<v Speaker 2>dot com or on the facebooks we publish every show

352
00:18:51.880 --> 00:18:53.160
<v Speaker 2>there and even comment there when I read it on

353
00:18:53.200 --> 00:18:55.480
<v Speaker 2>the show, we'll send you copy of music Cobayah.

354
00:18:55.599 --> 00:18:57.640
<v Speaker 1>Music to Koba, of course, is a project I started

355
00:18:57.640 --> 00:19:00.440
<v Speaker 1>a long time ago to create twenty five minute music

356
00:19:00.599 --> 00:19:03.200
<v Speaker 1>tracks that can slip into the background and help you

357
00:19:03.240 --> 00:19:07.079
<v Speaker 1>focus and it's been wildly popular. Now we have twenty

358
00:19:07.079 --> 00:19:11.440
<v Speaker 1>two tracks. Twenty three is coming, I promise, and music

359
00:19:11.519 --> 00:19:13.119
<v Speaker 1>too by dot net if you want to get it

360
00:19:14.720 --> 00:19:20.440
<v Speaker 1>in MP three, wave and FLACK versions. Okay, let's bring

361
00:19:20.480 --> 00:19:24.920
<v Speaker 1>back ms Rendel. Ms has been writing code since childhood,

362
00:19:25.000 --> 00:19:28.640
<v Speaker 1>getting paid for it since her teens, and inflicting opinions

363
00:19:28.680 --> 00:19:33.319
<v Speaker 1>on conference audiences for the last fifteen years. The former

364
00:19:33.440 --> 00:19:36.559
<v Speaker 1>CTO with deep roots in dot net, c sharp APIs

365
00:19:36.640 --> 00:19:40.680
<v Speaker 1>performance engineering and system architecture. She's now working in financial

366
00:19:40.720 --> 00:19:44.920
<v Speaker 1>technology by day, then spending her spare time building ambitious, weird,

367
00:19:45.279 --> 00:19:49.440
<v Speaker 1>and occasionally beautiful things at the intersection of ar AI

368
00:19:49.680 --> 00:19:52.039
<v Speaker 1>and human connection. Welcome back with MS.

369
00:19:52.279 --> 00:19:53.880
<v Speaker 3>Hey, Hey, thank you for having me.

370
00:19:53.920 --> 00:19:59.279
<v Speaker 1>Thanks for participating in the intro. Yeah, fun, Yeah, I'm

371
00:19:59.279 --> 00:20:01.319
<v Speaker 1>sure since the ast time we talked, you've got a

372
00:20:01.359 --> 00:20:02.640
<v Speaker 1>lot of things on your mind.

373
00:20:03.319 --> 00:20:11.200
<v Speaker 3>It's been a wild couple of years. Yeah, yeah, I

374
00:20:11.400 --> 00:20:15.880
<v Speaker 3>just I've continued trying to keep things as simple as possible.

375
00:20:15.920 --> 00:20:20.160
<v Speaker 3>There's a bit of a movement has kind of popped

376
00:20:20.240 --> 00:20:23.039
<v Speaker 3>up in the last couple of years. Actually, Chris Woodruff,

377
00:20:23.160 --> 00:20:28.440
<v Speaker 3>who I know, you guys know, has been doing a

378
00:20:28.480 --> 00:20:33.079
<v Speaker 3>lot of writing sort of around the simplicity first approach.

379
00:20:33.160 --> 00:20:38.079
<v Speaker 3>She's a big advocate of that. There's the use what

380
00:20:38.200 --> 00:20:42.839
<v Speaker 3>works initiative, which is sort of the whole buy don't

381
00:20:42.880 --> 00:20:47.480
<v Speaker 3>build kind of trying to suggest to people that just

382
00:20:47.559 --> 00:20:51.720
<v Speaker 3>because an open source project is asking for commercial support money,

383
00:20:51.839 --> 00:20:53.920
<v Speaker 3>that's not a good reason to go off and build

384
00:20:53.960 --> 00:20:59.920
<v Speaker 3>your own messaging stack or warth authentication stack or whatever it.

385
00:21:01.400 --> 00:21:04.000
<v Speaker 2>We wrote this code not because it was easy, but

386
00:21:04.079 --> 00:21:05.519
<v Speaker 2>because we thought it was easy.

387
00:21:06.720 --> 00:21:09.079
<v Speaker 3>Yes, we wrote this code because we thought it would

388
00:21:09.079 --> 00:21:10.519
<v Speaker 3>save us five thousand dollars.

389
00:21:10.519 --> 00:21:14.400
<v Speaker 1>And I think it's a trap of modern AI development,

390
00:21:14.759 --> 00:21:18.519
<v Speaker 1>which we're all finding ourselves doing some somewhat, is that

391
00:21:19.079 --> 00:21:22.480
<v Speaker 1>you think, you know, oh, I'll just I need this,

392
00:21:22.720 --> 00:21:26.720
<v Speaker 1>I'll just have my AI write it. Where the first

393
00:21:26.799 --> 00:21:29.559
<v Speaker 1>question should be does it exist? You know?

394
00:21:29.880 --> 00:21:30.119
<v Speaker 2>Yes?

395
00:21:30.359 --> 00:21:33.680
<v Speaker 3>And that's literally in my prompt that I use for

396
00:21:34.079 --> 00:21:38.359
<v Speaker 3>exploring new ideas, there's a sort of thing very near

397
00:21:38.400 --> 00:21:41.759
<v Speaker 3>the top saying if something exists, let's just use it,

398
00:21:41.799 --> 00:21:42.920
<v Speaker 3>tell me about it.

399
00:21:42.839 --> 00:21:45.319
<v Speaker 1>It kind of reminds me of the days when you know,

400
00:21:45.480 --> 00:21:49.480
<v Speaker 1>everybody wanted to build an iPhone app, an Android app,

401
00:21:50.359 --> 00:21:54.799
<v Speaker 1>and they come to you with ideas. You know, hey,

402
00:21:54.880 --> 00:21:57.400
<v Speaker 1>I got this great idea for an app, I'll tell

403
00:21:57.440 --> 00:22:01.759
<v Speaker 1>you what you build it it will split the yes,

404
00:22:01.920 --> 00:22:06.279
<v Speaker 1>okay question number First of all, no, in question for you?

405
00:22:06.440 --> 00:22:08.599
<v Speaker 1>Does it exist? Did you love to see if it exists?

406
00:22:08.599 --> 00:22:10.119
<v Speaker 1>In the apisode? Oh no, I didn't do that.

407
00:22:10.240 --> 00:22:15.559
<v Speaker 2>All right, Well, yeah, where do you exists? Bet? It does?

408
00:22:15.680 --> 00:22:18.480
<v Speaker 3>So anyway, I'm building something that definitely exists.

409
00:22:19.440 --> 00:22:21.359
<v Speaker 2>Nice, but I wanted to talk.

410
00:22:21.200 --> 00:22:23.119
<v Speaker 3>To you guys about it anyway because I am Actually

411
00:22:23.279 --> 00:22:27.559
<v Speaker 3>it's been a while since I built something kind of big,

412
00:22:29.039 --> 00:22:34.400
<v Speaker 3>and in dot net there's been a bunch of sort

413
00:22:34.400 --> 00:22:38.759
<v Speaker 3>of interesting projects, but they weren't really they were either

414
00:22:38.839 --> 00:22:40.759
<v Speaker 3>kind of closed source and I wasn't allowed to talk

415
00:22:40.759 --> 00:22:45.799
<v Speaker 3>about them, or they were outside the dot net ecosystem.

416
00:22:46.279 --> 00:22:48.680
<v Speaker 3>But yeah, I've actually I've been working on a thing

417
00:22:49.519 --> 00:22:53.359
<v Speaker 3>and it's in dot net, and I thought you guys

418
00:22:53.359 --> 00:22:54.200
<v Speaker 3>would be interested.

419
00:22:54.519 --> 00:22:56.000
<v Speaker 2>All right, tell us about it.

420
00:22:56.039 --> 00:22:59.039
<v Speaker 1>Well, you don't need to tell us about it. We

421
00:22:59.119 --> 00:23:01.119
<v Speaker 1>can just talk about something else if you like.

422
00:23:03.160 --> 00:23:09.039
<v Speaker 3>No, So, I'm building my own coding agent harness. Oh thing,

423
00:23:11.240 --> 00:23:15.279
<v Speaker 3>So like clawed code or codex or open code or

424
00:23:15.519 --> 00:23:20.599
<v Speaker 3>pie or any of the millions of different ones that

425
00:23:20.720 --> 00:23:21.480
<v Speaker 3>are out there.

426
00:23:22.160 --> 00:23:23.720
<v Speaker 1>I got to tell you before you go any further.

427
00:23:23.839 --> 00:23:26.759
<v Speaker 1>I tried that and it I was tearing my hair

428
00:23:26.799 --> 00:23:28.880
<v Speaker 1>out so much that I just gave up.

429
00:23:28.920 --> 00:23:29.799
<v Speaker 3>It's going quite well.

430
00:23:29.839 --> 00:23:30.759
<v Speaker 1>It's not easy.

431
00:23:31.400 --> 00:23:34.240
<v Speaker 3>It's not easy, and there's a lot of things that

432
00:23:34.720 --> 00:23:37.000
<v Speaker 3>sort of pop up along the way where you kind

433
00:23:37.000 --> 00:23:39.000
<v Speaker 3>of go, oh, I didn't think of that. Oh that's interesting.

434
00:23:39.200 --> 00:23:45.039
<v Speaker 3>Oh yeah, I suppose that is, but yeah, no. Doing

435
00:23:45.079 --> 00:23:50.519
<v Speaker 3>it in dot net and c sharp is provide some

436
00:23:50.640 --> 00:23:55.240
<v Speaker 3>interesting opportunities that I was kind of like, well, if

437
00:23:55.279 --> 00:23:58.119
<v Speaker 3>I was using dot Net, then I could use new

438
00:23:58.160 --> 00:24:03.920
<v Speaker 3>get to distribute extensions. I would have kind of very

439
00:24:04.039 --> 00:24:07.519
<v Speaker 3>firm interface boundaries, and I could have an abstractions and

440
00:24:07.559 --> 00:24:10.880
<v Speaker 3>an extensions package with different kinds of extension, and people

441
00:24:10.880 --> 00:24:16.960
<v Speaker 3>could extend around those. And there's a phenomenal first party

442
00:24:17.079 --> 00:24:23.039
<v Speaker 3>ecosystem around building AI tools and agents with dot net,

443
00:24:23.079 --> 00:24:26.000
<v Speaker 3>because you've got like Microsoft dot Extensions, dot Ai, You've

444
00:24:26.000 --> 00:24:30.599
<v Speaker 3>got Semantic Kernel, you've got the Multi Agent framework. These

445
00:24:30.640 --> 00:24:35.079
<v Speaker 3>are all things that are being built and supported by

446
00:24:35.119 --> 00:24:38.200
<v Speaker 3>somebody else, which takes a lot of the sort of

447
00:24:38.359 --> 00:24:40.079
<v Speaker 3>more complicated bits of effort.

448
00:24:41.440 --> 00:24:41.640
<v Speaker 2>You know.

449
00:24:41.759 --> 00:24:46.880
<v Speaker 3>Just talking about providers, you've got sort of three anthropic

450
00:24:47.119 --> 00:24:52.960
<v Speaker 3>open AI and Gemini and then you've got like local

451
00:24:53.000 --> 00:25:00.240
<v Speaker 3>providers like Olama, Lama, cpp LM Studio, OMLX and all

452
00:25:00.279 --> 00:25:02.079
<v Speaker 3>the other things that are out there that are like

453
00:25:02.160 --> 00:25:06.319
<v Speaker 3>open Ai compatible, like deep seek and Kimmi and GLM

454
00:25:06.359 --> 00:25:10.720
<v Speaker 3>and all these different things, and there are either pre

455
00:25:10.880 --> 00:25:14.599
<v Speaker 3>existing rappers for them. You know, there's a Anthropic ship,

456
00:25:14.759 --> 00:25:19.680
<v Speaker 3>an implementation of I Chat client which is in the

457
00:25:19.680 --> 00:25:25.200
<v Speaker 3>Microsoft Extensions project. There's an Alarma sharp out there which

458
00:25:25.440 --> 00:25:28.240
<v Speaker 3>interacts with Alarm. So yeah, there's all these sorts of things,

459
00:25:28.279 --> 00:25:30.400
<v Speaker 3>and so it makes a lot of the building of

460
00:25:30.440 --> 00:25:35.720
<v Speaker 3>this thing more like lego and sticking sort of pre

461
00:25:35.839 --> 00:25:39.519
<v Speaker 3>built bricks together, which really really helps.

462
00:25:42.279 --> 00:25:44.759
<v Speaker 2>So, yeah, do we need another one?

463
00:25:44.920 --> 00:25:49.680
<v Speaker 3>Yes, yes we do. I do. I definitely do.

464
00:25:50.680 --> 00:25:52.480
<v Speaker 1>You find all these other ones are lacking.

465
00:25:53.400 --> 00:25:56.839
<v Speaker 3>So my sort of daily driver and the thing I've

466
00:25:56.839 --> 00:25:58.720
<v Speaker 3>been using at work for the last year is Claude

467
00:25:58.759 --> 00:26:02.799
<v Speaker 3>Coat and claud Coke is amazing. But it works with

468
00:26:02.880 --> 00:26:09.079
<v Speaker 3>Claude and you can do sort of interesting hacky setting

469
00:26:09.079 --> 00:26:13.400
<v Speaker 3>anthropic environment variables and get it to work with other engines,

470
00:26:13.519 --> 00:26:18.519
<v Speaker 3>especially when they have an anthropic compatible API. But we

471
00:26:18.640 --> 00:26:24.319
<v Speaker 3>are approaching the rug pull. Yeah, the point where in

472
00:26:24.400 --> 00:26:27.720
<v Speaker 3>the same way that Uber went right, We've destroyed the competition.

473
00:26:27.880 --> 00:26:32.359
<v Speaker 3>Now we can rack the prices up. The vcs are

474
00:26:32.400 --> 00:26:35.960
<v Speaker 3>kind of like going, it's probably time that we start

475
00:26:36.039 --> 00:26:41.200
<v Speaker 3>charging what it actually costs and make it profitable. And

476
00:26:42.559 --> 00:26:45.880
<v Speaker 3>there are multiple outcomes that could happen from that.

477
00:26:47.680 --> 00:26:47.880
<v Speaker 1>Yeah.

478
00:26:48.079 --> 00:26:49.519
<v Speaker 2>I mean, I'm going to wrestle with this being a

479
00:26:49.599 --> 00:26:51.480
<v Speaker 2>rug pull so much as a reality check.

480
00:26:52.440 --> 00:26:54.240
<v Speaker 3>Yes, yeah, okay, yeah, No, definitely.

481
00:26:54.279 --> 00:26:56.640
<v Speaker 2>It's is like, hey, this stuff costs more money than

482
00:26:56.640 --> 00:26:59.039
<v Speaker 2>you were charging, so how much is it really.

483
00:26:58.799 --> 00:27:00.640
<v Speaker 1>Well, it depends on what side you're looking at. If

484
00:27:00.640 --> 00:27:04.079
<v Speaker 1>you're looking at the LM providers, it's a reality check.

485
00:27:04.119 --> 00:27:07.079
<v Speaker 1>If you're looking at users, it's a rugbull. Yeah, no

486
00:27:07.119 --> 00:27:07.720
<v Speaker 1>doubt about it.

487
00:27:07.759 --> 00:27:10.079
<v Speaker 3>I mean that's certainly for a lot of the less

488
00:27:10.160 --> 00:27:16.240
<v Speaker 3>technical users who don't understand the constraints and limits and

489
00:27:17.200 --> 00:27:18.279
<v Speaker 3>energy use and everything.

490
00:27:18.599 --> 00:27:20.440
<v Speaker 1>I just want to tell you what I'm doing. I'm

491
00:27:20.519 --> 00:27:25.519
<v Speaker 1>using GitHub copilot Cli against a local machine that's running Olama,

492
00:27:26.119 --> 00:27:28.119
<v Speaker 1>and I found a couple of models that work really

493
00:27:28.160 --> 00:27:33.240
<v Speaker 1>really well. Which ones so that so Quinn yep, Quinn

494
00:27:33.240 --> 00:27:37.359
<v Speaker 1>three point six latest is the best? Yes, and even

495
00:27:37.440 --> 00:27:43.440
<v Speaker 1>two point five thirty three thirty two billion yea Quin coder. Yeah,

496
00:27:44.240 --> 00:27:48.000
<v Speaker 1>works works the best, that's the second best. And then

497
00:27:48.440 --> 00:27:50.720
<v Speaker 1>we did this on code with Ai dot com. The

498
00:27:50.799 --> 00:27:55.799
<v Speaker 1>last two episodes were local language model roundups, and I

499
00:27:55.839 --> 00:27:58.519
<v Speaker 1>did and I tested a bunch of them with against

500
00:27:58.559 --> 00:28:01.759
<v Speaker 1>my Olama machine, and those two are the only ones

501
00:28:01.759 --> 00:28:03.359
<v Speaker 1>that I would use going.

502
00:28:03.119 --> 00:28:08.119
<v Speaker 3>For I've been using Gemma four. I tested at the

503
00:28:09.200 --> 00:28:16.559
<v Speaker 3>thirty one billion parameter and it's good. Quinn is better

504
00:28:16.559 --> 00:28:21.799
<v Speaker 3>for coding, yeah, but Gemma four I'm using for a

505
00:28:21.839 --> 00:28:23.680
<v Speaker 3>project that I'm not ready to tell you about it

506
00:28:23.839 --> 00:28:28.839
<v Speaker 3>but because I don't want to. It's it's in stealth

507
00:28:29.319 --> 00:28:31.839
<v Speaker 3>and at some point somebody's going to give me sacks

508
00:28:31.839 --> 00:28:35.799
<v Speaker 3>of money to actually productize it. Still, this is kind

509
00:28:35.799 --> 00:28:40.319
<v Speaker 3>of at the core of that. But yes, I think

510
00:28:42.440 --> 00:28:47.519
<v Speaker 3>I don't know whether sort of the big funded cloud

511
00:28:47.720 --> 00:28:52.240
<v Speaker 3>LM providers and Thropic and open AI, it's it's kind

512
00:28:52.319 --> 00:28:58.240
<v Speaker 3>of questionable whether they even survive because they're a real

513
00:28:58.359 --> 00:29:02.759
<v Speaker 3>questions especially, I mean, you Knowthos. Was Mythos held back

514
00:29:02.920 --> 00:29:09.799
<v Speaker 3>because it was exposing sort of vulnerabilities in ten thousand

515
00:29:10.200 --> 00:29:13.839
<v Speaker 3>two power fundamental internet projects? Or was it held back

516
00:29:13.920 --> 00:29:18.640
<v Speaker 3>because the compute capacity did not exist to run it?

517
00:29:19.039 --> 00:29:20.720
<v Speaker 1>Yeah? Yeah, it's pretty big, you know, and.

518
00:29:21.119 --> 00:29:25.640
<v Speaker 3>Thropic of basically least Colossus one and two off SpaceX

519
00:29:25.680 --> 00:29:30.960
<v Speaker 3>now to try and run this stuff. But you know,

520
00:29:31.000 --> 00:29:34.440
<v Speaker 3>I keep seeing analysis that these we're expecting to build

521
00:29:34.839 --> 00:29:40.160
<v Speaker 3>hundreds of gigawatts of capacity per year, but we're actually

522
00:29:40.160 --> 00:29:42.079
<v Speaker 3>building tens of gigawatts if we're lucky.

523
00:29:42.519 --> 00:29:45.519
<v Speaker 2>So well he did. Yeah, it turns out you can't

524
00:29:45.599 --> 00:29:48.240
<v Speaker 2>just build power plants over night. It's not that quick. Yeah,

525
00:29:48.400 --> 00:29:49.559
<v Speaker 2>you know, as the guy who does a bunch of

526
00:29:49.599 --> 00:29:52.640
<v Speaker 2>talks about power, it's like, hey, pretty much the fastest

527
00:29:52.640 --> 00:29:55.960
<v Speaker 2>you can build one power plants about five years. Yeah,

528
00:29:56.000 --> 00:29:58.400
<v Speaker 2>and this thing hasn't been going on for five years.

529
00:29:58.400 --> 00:30:00.359
<v Speaker 2>So how many power plants do you think we've so

530
00:30:00.480 --> 00:30:01.000
<v Speaker 2>far forward?

531
00:30:01.960 --> 00:30:04.240
<v Speaker 3>One of my favorite things about the power plants was,

532
00:30:05.400 --> 00:30:08.039
<v Speaker 3>I think it was Hank Green on YouTube did a video.

533
00:30:08.519 --> 00:30:13.839
<v Speaker 3>There's lots of old shutdown coal power stations which have

534
00:30:13.920 --> 00:30:16.279
<v Speaker 3>got all the everything that they need to be turned

535
00:30:16.279 --> 00:30:19.359
<v Speaker 3>into small nuclear power stations. You could just stick a

536
00:30:19.400 --> 00:30:22.400
<v Speaker 3>reactor core in there. The reason they can't do it,

537
00:30:22.440 --> 00:30:27.240
<v Speaker 3>certainly in the United States, is that they're already radioactive

538
00:30:27.359 --> 00:30:31.359
<v Speaker 3>to a level that exceeds EPA regulations. For how radioactive

539
00:30:31.359 --> 00:30:36.000
<v Speaker 3>and nuclear power station can be just from burning coal. Wow,

540
00:30:36.319 --> 00:30:40.680
<v Speaker 3>which is it's lovely. Yeah, Trump plants to refire these

541
00:30:40.960 --> 00:30:48.359
<v Speaker 3>coal plants. Yeah, I mean that's also crazy. Yeah, but yes,

542
00:30:49.640 --> 00:30:54.720
<v Speaker 3>I kind of see a potential future where you've got

543
00:30:54.720 --> 00:30:59.319
<v Speaker 3>to exist in between the cloud llms and the on

544
00:30:59.519 --> 00:31:07.640
<v Speaker 3>device things by providing like custom training. So a customer

545
00:31:07.680 --> 00:31:10.079
<v Speaker 3>comes to you and goes, I want coding agents that

546
00:31:10.119 --> 00:31:13.240
<v Speaker 3>I can run locally that all I care about is

547
00:31:13.279 --> 00:31:19.039
<v Speaker 3>dot Net and typescript and you know, React. And you

548
00:31:19.119 --> 00:31:21.839
<v Speaker 3>either get like a completely ground up trained thing, or

549
00:31:21.920 --> 00:31:26.039
<v Speaker 3>you get a fine tuned trained thing training and fine

550
00:31:26.079 --> 00:31:26.960
<v Speaker 3>tuning models.

551
00:31:28.039 --> 00:31:28.799
<v Speaker 1>I think so too.

552
00:31:28.920 --> 00:31:33.440
<v Speaker 3>A it's compute expensive, and B it's it's not easy,

553
00:31:33.519 --> 00:31:37.039
<v Speaker 3>it's not sort of straightforward. It's a it's a skin.

554
00:31:37.039 --> 00:31:39.079
<v Speaker 1>Well you know. The other the other option is to

555
00:31:39.119 --> 00:31:43.319
<v Speaker 1>take something that does know, you know, c sharp, typescript,

556
00:31:43.559 --> 00:31:45.559
<v Speaker 1>all of those, but also knows a lot of other

557
00:31:45.640 --> 00:31:48.119
<v Speaker 1>stuff and just pare it down to what you need

558
00:31:48.160 --> 00:31:51.559
<v Speaker 1>it for. The distillations kind of like stubbing out when

559
00:31:51.559 --> 00:31:53.960
<v Speaker 1>you're compiling, you know, stub out the stuff that you

560
00:31:54.000 --> 00:31:54.960
<v Speaker 1>don't want to link in.

561
00:31:55.200 --> 00:32:00.480
<v Speaker 3>Yeah, and so yeah, I want something that I can

562
00:32:01.200 --> 00:32:05.119
<v Speaker 3>make work with Claude or Gemini, or I can make

563
00:32:05.160 --> 00:32:07.839
<v Speaker 3>it work with OMLX running a local thing, or I

564
00:32:07.839 --> 00:32:12.519
<v Speaker 3>can make it work with Olama running on a DGX

565
00:32:12.559 --> 00:32:19.240
<v Speaker 3>Spark sitting in my house. And yeah, so, and I

566
00:32:19.279 --> 00:32:21.680
<v Speaker 3>wanted something that I had more control over. I looked

567
00:32:21.680 --> 00:32:24.119
<v Speaker 3>at the source code for the Pie Coding Agent, which

568
00:32:24.160 --> 00:32:29.240
<v Speaker 3>is the closest thing, and it's written in typescript, which,

569
00:32:29.680 --> 00:32:34.319
<v Speaker 3>apart from anything else, means you have to have Node installed.

570
00:32:35.039 --> 00:32:37.720
<v Speaker 3>And I have a long history of railing against the

571
00:32:37.799 --> 00:32:42.880
<v Speaker 3>need to install mode and so yeah, and I thought

572
00:32:42.880 --> 00:32:46.400
<v Speaker 3>I would I would sort of build my own Pie

573
00:32:46.440 --> 00:32:50.559
<v Speaker 3>inspired thing in C sharp. And it's so nice to

574
00:32:50.559 --> 00:32:52.960
<v Speaker 3>be back in c sharp and to have the agent

575
00:32:53.119 --> 00:32:58.920
<v Speaker 3>generating code that I fully understand and can refactor with

576
00:32:59.039 --> 00:33:04.640
<v Speaker 3>kind of sharper and those sorts of things. And so yeah,

577
00:33:05.160 --> 00:33:08.119
<v Speaker 3>it's uh, it's it's out well, it's not quite out

578
00:33:08.119 --> 00:33:09.839
<v Speaker 3>there yet. I haven't done a proper launch, but it's

579
00:33:09.839 --> 00:33:18.039
<v Speaker 3>public on GitHub at demonic ai with an A and

580
00:33:18.079 --> 00:33:21.880
<v Speaker 3>then the demon d m o N dash core.

581
00:33:25.839 --> 00:33:27.599
<v Speaker 1>And will add that to the list.

582
00:33:28.640 --> 00:33:30.799
<v Speaker 3>Yeah, I'll send you the I think I sent you

583
00:33:30.839 --> 00:33:35.599
<v Speaker 3>the link in the pre show thing. And yeah, the

584
00:33:35.599 --> 00:33:40.440
<v Speaker 3>core of it runs as a separate process, and it's

585
00:33:40.480 --> 00:33:47.400
<v Speaker 3>it's a Jason RPC server, so you I'm currently building

586
00:33:47.400 --> 00:33:50.920
<v Speaker 3>a terminal client for it, like a net console app,

587
00:33:51.240 --> 00:33:54.720
<v Speaker 3>but there's going to be an Avalonia app, and it

588
00:33:54.799 --> 00:33:58.839
<v Speaker 3>is also going to be there will be another thing,

589
00:33:59.440 --> 00:34:04.440
<v Speaker 3>which is a public gRPC server that exposes it over

590
00:34:04.519 --> 00:34:09.000
<v Speaker 3>gRPC so you can talk to it from your phone.

591
00:34:09.559 --> 00:34:16.800
<v Speaker 3>And yeah, but the things I'm kind of excited about.

592
00:34:16.800 --> 00:34:18.920
<v Speaker 3>So dot net means I can compile it as a

593
00:34:18.920 --> 00:34:24.480
<v Speaker 3>standalone thing, so people don't have to necessarily have the

594
00:34:24.519 --> 00:34:26.840
<v Speaker 3>dot Net SDK installed, although if you have the dot

595
00:34:26.840 --> 00:34:29.400
<v Speaker 3>Net SDK installed, you'll also just be able to do

596
00:34:29.400 --> 00:34:35.760
<v Speaker 3>dot netool installed demon and it will be distributed that

597
00:34:35.840 --> 00:34:43.920
<v Speaker 3>way as well. And I've borrowed so the process isolation

598
00:34:44.079 --> 00:34:49.880
<v Speaker 3>thing is is cool. It's using Microsoft Extensions AI, which

599
00:34:49.920 --> 00:34:52.400
<v Speaker 3>means there's a bunch of stuff out there that I

600
00:34:52.440 --> 00:34:59.280
<v Speaker 3>can already import and wrap quite lightly. I've borrowed the

601
00:34:59.519 --> 00:35:02.920
<v Speaker 3>session system from Pie, so you have a tree of

602
00:35:03.000 --> 00:35:07.199
<v Speaker 3>sessions and when you spawn a subagent, it kind of

603
00:35:07.199 --> 00:35:11.079
<v Speaker 3>creates a fork from the current session, and so you

604
00:35:11.159 --> 00:35:12.559
<v Speaker 3>end up with a tree. I don't know if you've

605
00:35:12.559 --> 00:35:14.960
<v Speaker 3>looked at pie at all. But it has this concept

606
00:35:15.000 --> 00:35:19.039
<v Speaker 3>of sessions as trees with sub sessions and sub sub

607
00:35:19.079 --> 00:35:21.480
<v Speaker 3>sessions and all that sort of thing. It's really quite clever.

608
00:35:22.679 --> 00:35:24.920
<v Speaker 3>And they're all just files in the directory.

609
00:35:24.800 --> 00:35:28.719
<v Speaker 1>Course, so you're basically persisting the history in all the

610
00:35:28.800 --> 00:35:32.639
<v Speaker 1>context around that is in MD files, yeah, yeh.

611
00:35:32.599 --> 00:35:37.719
<v Speaker 3>MD files and JSONL files. And then and this is

612
00:35:37.760 --> 00:35:42.880
<v Speaker 3>the bit that I'm sort of I think is my

613
00:35:42.880 --> 00:35:47.360
<v Speaker 3>my value proposition is the extension model. So you can

614
00:35:47.360 --> 00:35:50.760
<v Speaker 3>create an extension. You have a new Get package that

615
00:35:50.840 --> 00:35:55.079
<v Speaker 3>you can get, and you build your extension based on that,

616
00:35:55.840 --> 00:35:58.599
<v Speaker 3>and then you publish it to new get with a

617
00:35:58.639 --> 00:36:03.760
<v Speaker 3>tag of DMA nash extension and with the source code available.

618
00:36:04.719 --> 00:36:08.440
<v Speaker 3>And then Nougat is already one of the more secure

619
00:36:09.760 --> 00:36:16.039
<v Speaker 3>package platforms out there, whereas you know, NPM has been

620
00:36:16.079 --> 00:36:19.559
<v Speaker 3>having some disasters lately, and PI has its share of

621
00:36:19.639 --> 00:36:24.679
<v Speaker 3>issues and everything else. New get is pretty secure. And

622
00:36:24.719 --> 00:36:27.960
<v Speaker 3>if you publish it as source available and you get

623
00:36:27.960 --> 00:36:33.960
<v Speaker 3>the new package that goes alongside the new package, then

624
00:36:35.559 --> 00:36:39.400
<v Speaker 3>you install it using the agent. So you go, hey,

625
00:36:39.400 --> 00:36:41.480
<v Speaker 3>I'm going to install an extension, and it goes off

626
00:36:41.480 --> 00:36:43.280
<v Speaker 3>and it gets it and it gets the source code

627
00:36:43.320 --> 00:36:47.719
<v Speaker 3>and it scans the source code for vulnerabilities before it

628
00:36:47.760 --> 00:36:50.280
<v Speaker 3>allows you to load the package. So if someone tries

629
00:36:50.360 --> 00:36:53.400
<v Speaker 3>to distribute a package that's got a Bitcoin minor or

630
00:36:53.440 --> 00:36:56.519
<v Speaker 3>something that's going to extract all your bank details and

631
00:36:56.559 --> 00:37:02.480
<v Speaker 3>credit cards, it's got a built in secure scam before

632
00:37:02.519 --> 00:37:03.280
<v Speaker 3>it does anything.

633
00:37:04.840 --> 00:37:06.599
<v Speaker 1>How far along are you with this project?

634
00:37:06.960 --> 00:37:15.199
<v Speaker 3>It's working, I can use it to build itself. And yeah,

635
00:37:15.320 --> 00:37:20.639
<v Speaker 3>I'm expecting it's as we're recording this. It's NDC Copenhagen

636
00:37:20.679 --> 00:37:23.320
<v Speaker 3>next week, and I'm expecting to be making a lot

637
00:37:23.360 --> 00:37:26.079
<v Speaker 3>of noise about it at NDC Copenhagen and trying to

638
00:37:26.360 --> 00:37:31.440
<v Speaker 3>persuade people to give it a look. But yes, and

639
00:37:31.480 --> 00:37:36.599
<v Speaker 3>then the sort of the much much bigger thing, the

640
00:37:36.639 --> 00:37:41.440
<v Speaker 3>startup that's being built on top of it, once the

641
00:37:41.480 --> 00:37:44.880
<v Speaker 3>core of this is done, should progress fairly quickly as well.

642
00:37:44.880 --> 00:37:50.320
<v Speaker 3>And that's not only kind of personal AI and playing

643
00:37:50.360 --> 00:37:54.239
<v Speaker 3>in the kind of open claw and Hermes space. It's

644
00:37:54.280 --> 00:38:00.119
<v Speaker 3>also adorable, okay, And I'm going to bring adorability and

645
00:38:00.400 --> 00:38:01.840
<v Speaker 3>beauty to.

646
00:38:01.840 --> 00:38:04.079
<v Speaker 1>The manifest itself.

647
00:38:04.320 --> 00:38:09.159
<v Speaker 3>Actually at the moment, as a bird, oh.

648
00:38:09.119 --> 00:38:12.440
<v Speaker 1>Bird bird, is it an avatar you interact with or

649
00:38:12.480 --> 00:38:13.519
<v Speaker 1>is it just I will.

650
00:38:13.360 --> 00:38:16.079
<v Speaker 3>Go I will come back and tell you more about

651
00:38:16.119 --> 00:38:21.119
<v Speaker 3>it at another stage. But it is, it is. It's

652
00:38:21.199 --> 00:38:23.559
<v Speaker 3>leveraging a lot of the things that I've been working

653
00:38:23.599 --> 00:38:26.119
<v Speaker 3>with over the last couple of years and bringing them together.

654
00:38:26.239 --> 00:38:28.480
<v Speaker 1>I can smell the smoke and see the wheels turning

655
00:38:28.480 --> 00:38:29.559
<v Speaker 1>in the brain of yours.

656
00:38:29.599 --> 00:38:33.519
<v Speaker 3>Oh but no, I've been I've got kind of like

657
00:38:34.159 --> 00:38:36.719
<v Speaker 3>a proof of concept app installed on my phone that

658
00:38:36.920 --> 00:38:39.840
<v Speaker 3>is really incredibly simple that is already blowing people away.

659
00:38:39.880 --> 00:38:43.000
<v Speaker 3>They're kind of go, oh, that's really that's amazing. And

660
00:38:43.039 --> 00:38:46.159
<v Speaker 3>then yeah, well, hooking it up to aiye is just

661
00:38:46.159 --> 00:38:47.719
<v Speaker 3>going to do very interesting things.

662
00:38:48.000 --> 00:38:49.679
<v Speaker 1>I think this is a good time to take a break,

663
00:38:49.719 --> 00:38:52.960
<v Speaker 1>so we'll be right back after these very important messages.

664
00:38:53.000 --> 00:38:59.360
<v Speaker 1>Don't go away, and we're back. It's darting at rocks.

665
00:38:59.360 --> 00:39:02.280
<v Speaker 1>I'm Carl Frank, and that's my friend Richard Campbell, and

666
00:39:02.320 --> 00:39:06.679
<v Speaker 1>that's our friend M's Randall. Hello, talking about some new stuff,

667
00:39:07.559 --> 00:39:12.360
<v Speaker 1>a new way to interact with your local language model

668
00:39:12.480 --> 00:39:14.559
<v Speaker 1>or your large language model.

669
00:39:14.840 --> 00:39:18.559
<v Speaker 2>Yep, yep, I am circling back on this whole. Aren't

670
00:39:18.559 --> 00:39:20.239
<v Speaker 2>we going to get to a place where you have

671
00:39:20.280 --> 00:39:24.000
<v Speaker 2>an LM associated with an application that can modify the application.

672
00:39:24.280 --> 00:39:26.719
<v Speaker 3>Yes, I mean that's that's one of the things with

673
00:39:26.800 --> 00:39:30.800
<v Speaker 3>this is especially the LLLM can briefly extend itself by

674
00:39:30.800 --> 00:39:36.199
<v Speaker 3>writing a CSX script, which you can you know, distributing

675
00:39:36.199 --> 00:39:39.880
<v Speaker 3>the Rosslyn things. We can compile that, load it into

676
00:39:39.920 --> 00:39:43.599
<v Speaker 3>an assembly context. That becomes a temporary extension, and then

677
00:39:43.639 --> 00:39:48.079
<v Speaker 3>there's actually a built in promote command, right that then

678
00:39:48.719 --> 00:39:52.079
<v Speaker 3>converts that into an actual sort of dot Net project

679
00:39:52.119 --> 00:39:54.480
<v Speaker 3>with a cs pro file and ne get packaging and

680
00:39:54.519 --> 00:39:55.079
<v Speaker 3>everything else.

681
00:39:55.119 --> 00:39:58.400
<v Speaker 1>In the work Vanilla was doing was extension. He was

682
00:39:58.480 --> 00:40:02.400
<v Speaker 1>using squad dash to to modify a squad dash.

683
00:40:02.760 --> 00:40:10.920
<v Speaker 3>Yes, and there are there's there are platforms out there

684
00:40:11.280 --> 00:40:14.840
<v Speaker 3>where it is literally this, you know, create a new

685
00:40:14.880 --> 00:40:17.440
<v Speaker 3>application and it just starts and it's an empty screen

686
00:40:17.480 --> 00:40:23.000
<v Speaker 3>on your iPhone or your desktop browser or whatever, and

687
00:40:23.039 --> 00:40:26.760
<v Speaker 3>you literally start telling, hey, application, this is what I

688
00:40:26.800 --> 00:40:28.320
<v Speaker 3>want you to be, this is what I want you

689
00:40:28.360 --> 00:40:33.960
<v Speaker 3>to do. And yeah, it kind of builds itself from

690
00:40:34.000 --> 00:40:37.079
<v Speaker 3>the inside out, and if you want a new feature

691
00:40:37.119 --> 00:40:39.199
<v Speaker 3>at any point, you can just go, hey, come back

692
00:40:39.199 --> 00:40:41.480
<v Speaker 3>and I need you to add a new feature, right,

693
00:40:42.239 --> 00:40:47.199
<v Speaker 3>And I think that is there's that level of things

694
00:40:47.960 --> 00:40:50.119
<v Speaker 3>where it's kind of like build an application so that

695
00:40:50.199 --> 00:40:53.840
<v Speaker 3>I can track my to do list or whatever. And

696
00:40:53.880 --> 00:40:56.639
<v Speaker 3>then there's the point at which, and this is kind

697
00:40:56.679 --> 00:41:00.159
<v Speaker 3>of one of the things that's very heavily on my

698
00:41:00.280 --> 00:41:08.320
<v Speaker 3>mind is we have ways of interacting with agents that

699
00:41:11.679 --> 00:41:15.360
<v Speaker 3>the idea of having an actual application with a specific

700
00:41:15.519 --> 00:41:20.400
<v Speaker 3>user interface will just be silly. Why would you do that?

701
00:41:21.679 --> 00:41:25.000
<v Speaker 2>Well, yeah, text boxes and buttons and things seem silly.

702
00:41:25.079 --> 00:41:28.239
<v Speaker 2>The screen will be used to present information.

703
00:41:28.280 --> 00:41:33.800
<v Speaker 3>Yeah, sort of. ALI is generating infographics and charts and

704
00:41:34.480 --> 00:41:37.559
<v Speaker 3>pictorial representations so we can all forget to learn how

705
00:41:37.599 --> 00:41:41.199
<v Speaker 3>to read and all these sorts of things.

706
00:41:41.400 --> 00:41:44.199
<v Speaker 2>Look, the line goes up to the right, this is good.

707
00:41:44.239 --> 00:41:47.039
<v Speaker 2>You should get a raise. Or the line is going down,

708
00:41:47.239 --> 00:41:48.440
<v Speaker 2>you are going to be down.

709
00:41:51.800 --> 00:41:54.880
<v Speaker 3>So yes, the Onion did a good story a couple

710
00:41:54.920 --> 00:42:03.079
<v Speaker 3>of weeks ago about high schoolers lacking objectssistance skills, which

711
00:42:03.119 --> 00:42:08.599
<v Speaker 3>is something that toddlers developed about eighteen months. So yes,

712
00:42:09.920 --> 00:42:13.960
<v Speaker 3>But yeah, know that the bigger idea I think is,

713
00:42:14.119 --> 00:42:16.960
<v Speaker 3>and and this is the kind of core of having

714
00:42:17.000 --> 00:42:25.239
<v Speaker 3>this as a standalone thing with an STDO RPC interface

715
00:42:26.239 --> 00:42:31.320
<v Speaker 3>is does it need an avaloniar application, does it need

716
00:42:31.320 --> 00:42:34.360
<v Speaker 3>a command line application, or can it sort of just

717
00:42:34.519 --> 00:42:37.800
<v Speaker 3>run as a server somewhere and I can talk to

718
00:42:37.840 --> 00:42:41.440
<v Speaker 3>it using my phone and my AirPods and that sort

719
00:42:41.480 --> 00:42:45.119
<v Speaker 3>of thing just persistently, and it can run locally. I

720
00:42:45.159 --> 00:42:47.039
<v Speaker 3>can run it in my house, I can access it

721
00:42:47.079 --> 00:42:50.440
<v Speaker 3>over tail scale or a cloud flare tunnel or something,

722
00:42:51.159 --> 00:42:55.239
<v Speaker 3>and it can keep all my data locally. To me, yeah,

723
00:42:55.239 --> 00:42:58.320
<v Speaker 3>that's important on my own sort of you know, And

724
00:42:58.320 --> 00:43:00.239
<v Speaker 3>that's I mean to me, that is a huge thing.

725
00:43:00.800 --> 00:43:07.960
<v Speaker 3>That is, it's very much. I don't want to send

726
00:43:08.079 --> 00:43:11.119
<v Speaker 3>every email email I get, and every Apple message I

727
00:43:11.159 --> 00:43:16.159
<v Speaker 3>get and and all these different things through a hosted

728
00:43:16.199 --> 00:43:20.039
<v Speaker 3>cloud model. It would be much better if I could

729
00:43:20.280 --> 00:43:21.119
<v Speaker 3>run them locally.

730
00:43:21.599 --> 00:43:24.719
<v Speaker 1>And so I'm with you, and I think that the

731
00:43:24.760 --> 00:43:29.360
<v Speaker 1>future is, you know, big machines running locally that are

732
00:43:29.400 --> 00:43:33.760
<v Speaker 1>running some you know OLAM or some kind of local

733
00:43:35.000 --> 00:43:40.840
<v Speaker 1>model host and because that's the big thing, right for

734
00:43:41.280 --> 00:43:44.000
<v Speaker 1>the expense can be absorbed by big companies. I mean,

735
00:43:44.079 --> 00:43:46.400
<v Speaker 1>but you know, guys like us don't want to be

736
00:43:46.400 --> 00:43:49.199
<v Speaker 1>paying a couple of thousand dollars a month for large

737
00:43:49.280 --> 00:43:55.239
<v Speaker 1>language model access. But but you know, privacy is a

738
00:43:55.239 --> 00:43:56.599
<v Speaker 1>big problem.

739
00:43:56.960 --> 00:44:01.920
<v Speaker 3>Privacy is a really big thing. And you know, I

740
00:44:01.960 --> 00:44:08.199
<v Speaker 3>can see a business model where actually, what we're selling

741
00:44:08.280 --> 00:44:13.079
<v Speaker 3>is like an appliance in the same way that people

742
00:44:13.079 --> 00:44:16.920
<v Speaker 3>would buy an Alexa or whatever they called those things,

743
00:44:16.960 --> 00:44:22.519
<v Speaker 3>an echo, or they would buy a Google Home device.

744
00:44:24.440 --> 00:44:28.679
<v Speaker 3>And you could sell, like I mean right now, a

745
00:44:28.800 --> 00:44:32.760
<v Speaker 3>DGX Spark clone, the thing with one hundred and twenty

746
00:44:32.800 --> 00:44:37.960
<v Speaker 3>eight gigs of unified memory and a petaflop of COUDA

747
00:44:38.039 --> 00:44:40.960
<v Speaker 3>and tensor cause and you can pick one of those

748
00:44:41.039 --> 00:44:44.960
<v Speaker 3>up for three thousand, three and a half thousand of

749
00:44:45.000 --> 00:44:53.119
<v Speaker 3>your local dollarish currencies. And that's the first generation of

750
00:44:53.159 --> 00:44:59.920
<v Speaker 3>that thing. And so in five years time, that spec

751
00:45:00.320 --> 00:45:02.760
<v Speaker 3>is going to be available. As you know, it's not

752
00:45:02.800 --> 00:45:04.800
<v Speaker 3>going to be quite Raspberry Pie, but it'll it'll have

753
00:45:04.880 --> 00:45:10.119
<v Speaker 3>come down under sort of close to the Mac Mini

754
00:45:11.480 --> 00:45:14.960
<v Speaker 3>level of pricing. Mac minnis, you know, with sixty four

755
00:45:14.960 --> 00:45:16.920
<v Speaker 3>gigs or one hundred and twenty eight gigs would be

756
00:45:17.360 --> 00:45:18.360
<v Speaker 3>plenty big enough.

757
00:45:20.079 --> 00:45:25.800
<v Speaker 1>My machine is a MD Rising nine nine ninety x

758
00:45:25.840 --> 00:45:30.559
<v Speaker 1>twelve core ninety six gigs RAM, the Nvidia g tour

759
00:45:30.760 --> 00:45:33.880
<v Speaker 1>g fors rtx fifty ninety with thirty two gigs of

760
00:45:33.960 --> 00:45:39.079
<v Speaker 1>v RAM. And yeah, like I said, quenn three six

761
00:45:39.440 --> 00:45:41.159
<v Speaker 1>runs in there just fine.

762
00:45:41.320 --> 00:45:46.840
<v Speaker 3>Yep, And yeah, I do. I think that's that's where

763
00:45:46.840 --> 00:45:50.639
<v Speaker 3>we're going to end up. One of the things, particularly

764
00:45:50.719 --> 00:45:56.320
<v Speaker 3>with with Demon, one of the sort of features that

765
00:45:56.400 --> 00:45:58.239
<v Speaker 3>it has because I couldn't figure out how to get

766
00:45:58.239 --> 00:46:02.239
<v Speaker 3>other things to do this is every extension can specify

767
00:46:02.280 --> 00:46:07.960
<v Speaker 3>a different model, and so it's like you could have read, write,

768
00:46:08.320 --> 00:46:13.639
<v Speaker 3>Bash edit all these different things. The extension that talks

769
00:46:13.639 --> 00:46:16.480
<v Speaker 3>to your Gmail account and those run on your locally

770
00:46:16.519 --> 00:46:21.760
<v Speaker 3>hosted model. But web search, which is a pain to

771
00:46:21.840 --> 00:46:26.920
<v Speaker 3>do locally because you need an API endpoint that you

772
00:46:26.920 --> 00:46:29.440
<v Speaker 3>can hit and you have to pay for all of those.

773
00:46:29.599 --> 00:46:32.920
<v Speaker 1>There are MCP servers for that. Yeah, so you could

774
00:46:32.920 --> 00:46:35.000
<v Speaker 1>just plug those in as you want to do.

775
00:46:35.159 --> 00:46:38.280
<v Speaker 3>But or you could, you know, just say, use the

776
00:46:38.320 --> 00:46:40.400
<v Speaker 3>Gemini model whenever you want to do a web search

777
00:46:40.679 --> 00:46:44.679
<v Speaker 3>and you can just drop out quickly go to Gemini,

778
00:46:45.039 --> 00:46:48.800
<v Speaker 3>or maybe use sort of a slightly bigger, more complicated

779
00:46:48.840 --> 00:46:53.920
<v Speaker 3>model on Olarma cloud because you're doing a web search, so.

780
00:46:54.320 --> 00:46:56.559
<v Speaker 2>It's a different process. You can use it different mechanism.

781
00:46:56.840 --> 00:47:00.400
<v Speaker 3>Yes, I suppose technically what you searched for or is

782
00:47:00.519 --> 00:47:04.119
<v Speaker 3>useful information, but somebody's recording that anyway. If you search

783
00:47:04.159 --> 00:47:07.039
<v Speaker 3>at Google, it's not like they're not keeping track of

784
00:47:07.039 --> 00:47:10.440
<v Speaker 3>that sure, and so you know, so it's like, yeah,

785
00:47:10.480 --> 00:47:14.440
<v Speaker 3>the ability to be pragmatic about privacy and security and

786
00:47:14.519 --> 00:47:16.440
<v Speaker 3>where things are hosted and all this sort of stuff

787
00:47:16.480 --> 00:47:18.079
<v Speaker 3>and to be able yeah, like I say, to use

788
00:47:18.079 --> 00:47:22.320
<v Speaker 3>a completely different model for certain extension types and be

789
00:47:22.360 --> 00:47:26.400
<v Speaker 3>able to configure that is a useful thing.

790
00:47:26.800 --> 00:47:29.960
<v Speaker 1>We have a new customer at appinax. In reading the contract,

791
00:47:30.519 --> 00:47:33.880
<v Speaker 1>there's a clause in there that no date, none of

792
00:47:33.920 --> 00:47:38.519
<v Speaker 1>their data will ever be entered into an AI large

793
00:47:38.559 --> 00:47:44.199
<v Speaker 1>language model for privacy reasons and you know, none of

794
00:47:44.239 --> 00:47:47.239
<v Speaker 1>their code and all that stuff. So then we get

795
00:47:47.280 --> 00:47:51.000
<v Speaker 1>working and we've got to get up repo with all

796
00:47:51.039 --> 00:47:55.960
<v Speaker 1>the code that has access to other data, and you know,

797
00:47:56.480 --> 00:47:59.480
<v Speaker 1>kind of had to clarify with the customer. You know,

798
00:47:59.519 --> 00:48:02.159
<v Speaker 1>what is the reason, what is the thing that you're

799
00:48:02.360 --> 00:48:04.800
<v Speaker 1>most concerned about that you have this clause in here,

800
00:48:05.639 --> 00:48:09.119
<v Speaker 1>and it was privacy. You know, it's basically they've heard

801
00:48:09.159 --> 00:48:14.000
<v Speaker 1>the stories of people just taking requirements dumping them into

802
00:48:14.079 --> 00:48:19.000
<v Speaker 1>chat GPT. Chat GPT now knows all about them, and

803
00:48:19.239 --> 00:48:22.000
<v Speaker 1>you know, they lose control of their intellectual property and

804
00:48:22.039 --> 00:48:27.639
<v Speaker 1>all this stuff. So it's taking some convincing, but we're

805
00:48:27.679 --> 00:48:32.039
<v Speaker 1>convincing them that with getthub copilot, there's a way to

806
00:48:32.079 --> 00:48:36.239
<v Speaker 1>opt out of them using your data to train their models.

807
00:48:36.760 --> 00:48:41.079
<v Speaker 1>And they have your data anyway in GitHub, so it's

808
00:48:41.119 --> 00:48:44.119
<v Speaker 1>not like it's going outside of that. The only thing

809
00:48:44.159 --> 00:48:46.480
<v Speaker 1>that I need to be sure of is that if

810
00:48:46.480 --> 00:48:51.159
<v Speaker 1>we're using Claude sonnet for example, does Claude know does

811
00:48:51.239 --> 00:48:54.480
<v Speaker 1>Anthropic now know about your data?

812
00:48:54.639 --> 00:48:57.440
<v Speaker 2>I mean, this is what happens when you mix a match,

813
00:48:57.519 --> 00:48:59.039
<v Speaker 2>right is now you have to think of each of

814
00:48:59.079 --> 00:48:59.880
<v Speaker 2>the layers.

815
00:49:00.440 --> 00:49:02.760
<v Speaker 1>Yeah, so that's the stuff we're working through right now.

816
00:49:04.119 --> 00:49:08.320
<v Speaker 3>So yeah, it's it's the thing I'd love about all

817
00:49:08.320 --> 00:49:10.599
<v Speaker 3>of this stuff. And you know, the work I've been

818
00:49:10.639 --> 00:49:14.239
<v Speaker 3>doing with various kinds of AI and everything over the

819
00:49:14.320 --> 00:49:16.960
<v Speaker 3>last two years, it hasn't settled yet.

820
00:49:17.840 --> 00:49:21.360
<v Speaker 2>It's like we're far from it. We're nowhere, But I say,

821
00:49:21.519 --> 00:49:22.119
<v Speaker 2>what do we know?

822
00:49:22.360 --> 00:49:23.400
<v Speaker 1>Here comes the rug.

823
00:49:25.440 --> 00:49:27.960
<v Speaker 3>I've done a lot of kind of historical talk looking

824
00:49:28.000 --> 00:49:31.239
<v Speaker 3>at the history of programming languages and that sort of thing,

825
00:49:31.280 --> 00:49:36.840
<v Speaker 3>and Fort Tram and Cobold and Algol and whatever, and yeah,

826
00:49:36.880 --> 00:49:40.239
<v Speaker 3>there was a time when people were inventing the paradigms

827
00:49:40.639 --> 00:49:44.679
<v Speaker 3>and that sort of thing. But then at some point

828
00:49:44.679 --> 00:49:48.400
<v Speaker 3>we had C and then we had C plus plus

829
00:49:48.679 --> 00:49:52.280
<v Speaker 3>and it's kind of like everything since then has just

830
00:49:52.400 --> 00:49:56.360
<v Speaker 3>been variations on a theme to one extent or another.

831
00:49:56.400 --> 00:49:58.800
<v Speaker 3>There was the dot com thing and the internet thing,

832
00:49:58.800 --> 00:50:03.920
<v Speaker 3>and that was it was cool. But yeah, this is

833
00:50:04.119 --> 00:50:08.679
<v Speaker 3>still at that kind of pioneering gold rush stage where

834
00:50:09.239 --> 00:50:11.480
<v Speaker 3>there's a lot of stupidity going on, but there's also

835
00:50:11.519 --> 00:50:15.760
<v Speaker 3>a lot of like really creative work still to be done,

836
00:50:16.280 --> 00:50:17.599
<v Speaker 3>and it's fun to be a part of that.

837
00:50:17.719 --> 00:50:20.280
<v Speaker 2>Well. Part of this is while there's too much money around,

838
00:50:20.679 --> 00:50:22.800
<v Speaker 2>you don't make good choices, like we do need to

839
00:50:22.800 --> 00:50:25.719
<v Speaker 2>be more efficient and more disapinted. And so as you

840
00:50:25.760 --> 00:50:27.840
<v Speaker 2>see the money starting to come out of the system

841
00:50:27.960 --> 00:50:30.360
<v Speaker 2>and they you know, your chances are becoming a billionaire

842
00:50:30.440 --> 00:50:33.880
<v Speaker 2>now and are disappearing. So those folks leave and good

843
00:50:33.920 --> 00:50:37.360
<v Speaker 2>riddance to them. Yes, we get to the engineering side

844
00:50:37.360 --> 00:50:40.000
<v Speaker 2>of can we make this actually practical and useful? You know?

845
00:50:40.159 --> 00:50:42.199
<v Speaker 2>Comparing this to the dark com boom, it's like it's

846
00:50:42.239 --> 00:50:46.360
<v Speaker 2>two thousands, the end is coming, but the heck's not

847
00:50:46.440 --> 00:50:49.039
<v Speaker 2>going to go away, just the dumb. The Dumb's going

848
00:50:49.119 --> 00:50:49.360
<v Speaker 2>to go.

849
00:50:50.599 --> 00:50:54.760
<v Speaker 3>Yes, Yeah, And one thing I'm hoping with this is

850
00:50:54.800 --> 00:50:59.360
<v Speaker 3>that you know, back in the day with not a

851
00:50:59.400 --> 00:51:03.559
<v Speaker 3>mollusk I did. I got a lot of engagement with

852
00:51:03.599 --> 00:51:06.599
<v Speaker 3>that project. People wrote kind of a Mongo dB adapter,

853
00:51:06.840 --> 00:51:10.199
<v Speaker 3>and I think there was actually simple data for Twitter.

854
00:51:10.639 --> 00:51:12.559
<v Speaker 3>Somebody wrote a thing where you could write simple data

855
00:51:12.599 --> 00:51:16.840
<v Speaker 3>queries against the Twitter fire and I think, you know,

856
00:51:16.880 --> 00:51:20.440
<v Speaker 3>I know there was still a ton of net shark

857
00:51:20.519 --> 00:51:25.599
<v Speaker 3>programmers out there, and I know they're using sort of

858
00:51:25.920 --> 00:51:32.360
<v Speaker 3>generative AI, but this is something where I'm kind of

859
00:51:32.400 --> 00:51:35.360
<v Speaker 3>like going, hey, look, here's the actual harness is written

860
00:51:35.960 --> 00:51:38.920
<v Speaker 3>in dot net, and it's kind of moved it a

861
00:51:39.000 --> 00:51:42.519
<v Speaker 3>little bit further along from just the Microsoft extensions, which

862
00:51:42.559 --> 00:51:46.079
<v Speaker 3>give you fine grained building blocks, and it's kind of

863
00:51:46.119 --> 00:51:48.519
<v Speaker 3>here's an actual agent and you can hack on it,

864
00:51:48.679 --> 00:51:51.320
<v Speaker 3>and you can share your hacks and you can contribute

865
00:51:51.360 --> 00:51:53.800
<v Speaker 3>back and so forth. And I'm hoping it's going to

866
00:51:54.280 --> 00:51:58.480
<v Speaker 3>open up this kind of the joy of experimentation to

867
00:51:59.000 --> 00:52:02.559
<v Speaker 3>a bunch more people who, for whatever reason, you know.

868
00:52:02.440 --> 00:52:04.760
<v Speaker 2>I'm talking to teams now who are no longer arguing

869
00:52:04.760 --> 00:52:06.920
<v Speaker 2>over futures, are just building all the versions they can

870
00:52:06.920 --> 00:52:08.320
<v Speaker 2>think of and then comparing them.

871
00:52:08.519 --> 00:52:08.800
<v Speaker 1>Ah.

872
00:52:08.880 --> 00:52:11.159
<v Speaker 2>Yes, as the code generation goes so quickly, Yeah, I

873
00:52:11.199 --> 00:52:13.079
<v Speaker 2>could just think about code differently now.

874
00:52:13.920 --> 00:52:21.960
<v Speaker 3>Yeah, and yeah, it's like which of these is I've

875
00:52:22.079 --> 00:52:26.079
<v Speaker 3>actually so I had Demon dot Console, which was just

876
00:52:26.280 --> 00:52:30.440
<v Speaker 3>a standard console application, and then briefly there was Demon

877
00:52:30.679 --> 00:52:35.000
<v Speaker 3>dot TUI, which was using the terminal dot guy newgat package,

878
00:52:35.679 --> 00:52:38.920
<v Speaker 3>but that was very broken for a variety of reasons,

879
00:52:39.920 --> 00:52:42.440
<v Speaker 3>and so then it reverted back, and now it's Demon

880
00:52:42.519 --> 00:52:49.400
<v Speaker 3>dot terminal, which is using Spector Console. But yeah, and

881
00:52:49.440 --> 00:52:54.960
<v Speaker 3>it's like going down the TWI dead end would have

882
00:52:55.000 --> 00:52:58.320
<v Speaker 3>wasted a week of development time a couple of years ago,

883
00:52:58.719 --> 00:53:01.199
<v Speaker 3>whereas this time it was just one evening. We got

884
00:53:01.199 --> 00:53:03.639
<v Speaker 3>halfway through the evening and I was kind of like,

885
00:53:03.760 --> 00:53:07.239
<v Speaker 3>this isn't working, and we're going to revert back the

886
00:53:07.280 --> 00:53:11.199
<v Speaker 3>last few changes and pick up from the console application again.

887
00:53:11.679 --> 00:53:17.280
<v Speaker 3>And yeah, it's it doesn't cost anywhere near the same,

888
00:53:17.400 --> 00:53:20.639
<v Speaker 3>so you can actually spike you can. Actually I've always

889
00:53:20.639 --> 00:53:25.239
<v Speaker 3>had this thing about you should build it once and

890
00:53:25.280 --> 00:53:27.920
<v Speaker 3>then throw that away and then build it again properly

891
00:53:28.679 --> 00:53:31.599
<v Speaker 3>with all the lessons you learned from that first build.

892
00:53:32.079 --> 00:53:34.880
<v Speaker 3>And that's actually a reasonable proposition. Now it's kind of

893
00:53:34.920 --> 00:53:40.679
<v Speaker 3>do a really dirty, exploratory vibe coded build, but get

894
00:53:40.679 --> 00:53:44.559
<v Speaker 3>the agent to keep a record of all the things

895
00:53:44.599 --> 00:53:49.800
<v Speaker 3>and the decision record architecture decisions and so forth, and

896
00:53:49.800 --> 00:53:52.599
<v Speaker 3>then you can literally use that to generate an insanely

897
00:53:52.760 --> 00:53:57.400
<v Speaker 3>detailed spec and effectively do a clean room implementation of

898
00:53:57.400 --> 00:54:00.840
<v Speaker 3>your prototype. The prototype is.

899
00:54:00.840 --> 00:54:02.760
<v Speaker 2>A sort of off the back of the experiment.

900
00:54:03.000 --> 00:54:06.599
<v Speaker 3>Yeah, and then you know, you get people going all

901
00:54:06.679 --> 00:54:09.599
<v Speaker 3>vibe coded stuff. The code's an absolute mess. But this

902
00:54:09.760 --> 00:54:12.719
<v Speaker 3>is a solution to that. Use the vibe coding to

903
00:54:13.159 --> 00:54:18.079
<v Speaker 3>prototype and then with all the constraints and clean code

904
00:54:18.079 --> 00:54:22.280
<v Speaker 3>and don't repeat yourself and yagny and kiss and whatever

905
00:54:22.360 --> 00:54:25.320
<v Speaker 3>else to a ground up reimplementation.

906
00:54:26.440 --> 00:54:29.039
<v Speaker 1>I find myself doing a lot of reading when I'm

907
00:54:29.039 --> 00:54:33.679
<v Speaker 1>working with an AI agent. In other words, I sort

908
00:54:33.719 --> 00:54:37.079
<v Speaker 1>of give it an overview. Is if it's a greenfield project,

909
00:54:37.079 --> 00:54:39.280
<v Speaker 1>I'll give it an overview, and then I'll ask it

910
00:54:39.320 --> 00:54:43.360
<v Speaker 1>to come up with a plan, you know, in multiple steps,

911
00:54:43.440 --> 00:54:46.440
<v Speaker 1>and then write a customer facing document that even I

912
00:54:46.440 --> 00:54:49.960
<v Speaker 1>can understand, well that even my customer can understand and

913
00:54:50.000 --> 00:54:52.800
<v Speaker 1>I can understand. And then I go through the plan

914
00:54:53.199 --> 00:54:58.000
<v Speaker 1>and figure out is this step necessary, why you know?

915
00:54:58.119 --> 00:55:00.960
<v Speaker 1>And what about this step? And it'll come up with

916
00:55:01.000 --> 00:55:05.320
<v Speaker 1>things that I hadn't thought of. But you know, sometimes

917
00:55:05.360 --> 00:55:09.159
<v Speaker 1>it might be a little over ambitious and but but

918
00:55:09.280 --> 00:55:12.159
<v Speaker 1>I like to work that way first on the architecture,

919
00:55:12.159 --> 00:55:16.559
<v Speaker 1>on the plan, before I even do anything coding wise,

920
00:55:17.079 --> 00:55:20.400
<v Speaker 1>and that is the most important part of the project,

921
00:55:20.519 --> 00:55:23.119
<v Speaker 1>if you ask me. But it's a lot of you know,

922
00:55:23.480 --> 00:55:25.719
<v Speaker 1>talking and a lot of reading.

923
00:55:26.280 --> 00:55:27.639
<v Speaker 3>Absolutely. Yeah.

924
00:55:28.039 --> 00:55:34.039
<v Speaker 1>Yeah, So we have the link to it on GitHub.

925
00:55:34.079 --> 00:55:37.079
<v Speaker 1>I think you already provided that the show notes.

926
00:55:37.639 --> 00:55:42.519
<v Speaker 3>Yeah, so yeah, and yeah, by the time it's this

927
00:55:43.280 --> 00:55:46.800
<v Speaker 3>episode goes out, I will have been making noise about

928
00:55:46.840 --> 00:55:48.199
<v Speaker 3>it and hopefully that'll be.

929
00:55:48.239 --> 00:55:50.480
<v Speaker 2>The force goes out during the conference.

930
00:55:50.719 --> 00:55:53.719
<v Speaker 3>Nice, Oh that'll look brilliantly then, yeah, almost like we

931
00:55:53.800 --> 00:55:57.599
<v Speaker 3>had a plan. So yeah, I've actually I've turned up

932
00:55:57.639 --> 00:56:01.519
<v Speaker 3>with my list of things to cover and so forth.

933
00:56:01.559 --> 00:56:08.880
<v Speaker 3>So yes, but I think anything covered, No, it's I

934
00:56:08.880 --> 00:56:14.239
<v Speaker 3>think we've covered everything. It does local models, it's the

935
00:56:14.239 --> 00:56:17.079
<v Speaker 3>permission models and all this sort of stuff. It is.

936
00:56:17.320 --> 00:56:21.480
<v Speaker 3>It is properly open source. It's Mozilla Public License two

937
00:56:21.480 --> 00:56:26.960
<v Speaker 3>point zero. And yeah, I hope people will at least

938
00:56:27.000 --> 00:56:29.639
<v Speaker 3>take a look at it. If nobody, I'm definitely going

939
00:56:29.639 --> 00:56:32.519
<v Speaker 3>to tell if nobody engages, I do actually need it

940
00:56:32.559 --> 00:56:37.880
<v Speaker 3>for my bigger more elaborate plans, but it would be

941
00:56:37.960 --> 00:56:40.480
<v Speaker 3>nice if people did like it and use it and

942
00:56:40.519 --> 00:56:41.440
<v Speaker 3>play with it and stuff.

943
00:56:41.440 --> 00:56:43.679
<v Speaker 2>So, because the way all good things start, you build

944
00:56:43.679 --> 00:56:45.199
<v Speaker 2>a thing you need and you wonder if other people

945
00:56:45.280 --> 00:56:45.559
<v Speaker 2>need it.

946
00:56:45.639 --> 00:56:47.360
<v Speaker 1>Yeah, Frankly, well, I'm going to check it out, and

947
00:56:47.400 --> 00:56:50.559
<v Speaker 1>I'm really looking forward to your more adorable project that

948
00:56:50.599 --> 00:56:52.719
<v Speaker 1>we will learn more about sometime in the future, and

949
00:56:52.760 --> 00:56:54.280
<v Speaker 1>you will come back and tell us about that.

950
00:56:54.320 --> 00:56:57.760
<v Speaker 3>Right, you will be the first people I tell fantastic.

951
00:56:58.519 --> 00:57:02.159
<v Speaker 1>Yeah, Endell, thank you very much. It's always a pleasure

952
00:57:02.199 --> 00:57:05.000
<v Speaker 1>to talk to you, and h this was no different,

953
00:57:05.440 --> 00:57:07.280
<v Speaker 1>mind blowing as always doing the awesome.

954
00:57:07.480 --> 00:57:07.760
<v Speaker 3>Thank you.

955
00:57:08.519 --> 00:57:29.199
<v Speaker 4>I will We'll talk to you next time on dot rocks.

956
00:57:24.639 --> 00:57:36.079
<v Speaker 5>Dot net Rocks is brought to you by Franklin's Net

957
00:57:36.239 --> 00:57:40.199
<v Speaker 5>and produced by Pop Studios, a full service audio, video

958
00:57:40.239 --> 00:57:44.400
<v Speaker 5>and post production facility located physically in New London, Connecticut,

959
00:57:44.599 --> 00:57:49.360
<v Speaker 5>and of course in the cloud online at pwop dot com.

960
00:57:49.599 --> 00:57:51.719
<v Speaker 5>Visit our website at d O T N E, t

961
00:57:51.960 --> 00:57:55.960
<v Speaker 5>R O c k S dot com for RSS feeds, downloads,

962
00:57:56.119 --> 00:57:59.760
<v Speaker 5>mobile apps, comments, and access to the full archives going

963
00:57:59.800 --> 00:58:03.239
<v Speaker 5>back the show number one, recorded in September two thousand

964
00:58:03.239 --> 00:58:05.920
<v Speaker 5>and two, and make sure you check out our sponsors.

965
00:58:06.039 --> 00:58:08.880
<v Speaker 5>They keep us in business. Now go write some code,

966
00:58:09.440 --> 00:58:13.320
<v Speaker 5>see you next time you got JAD middle vans by

967
00:58:13.440 --> 00:58:13.480
<v Speaker 5>the

968
00:58:18.880 --> 00:58:20.679
<v Speaker 1>Home the Texas
