WEBVTT

1
00:00:16.559 --> 00:00:20.960
<v Speaker 1>All right, Hi, welcome everyone, this is another episode. Let's started,

2
00:00:21.000 --> 00:00:25.679
<v Speaker 1>they'll say, and we're talking today with Madnus Mueller from Greenway.

3
00:00:26.160 --> 00:00:27.640
<v Speaker 2>All right, Mad is welcome.

4
00:00:28.440 --> 00:00:29.600
<v Speaker 1>Why don't we kick it off?

5
00:00:29.800 --> 00:00:31.719
<v Speaker 2>Tell us a little bit about yourself.

6
00:00:35.240 --> 00:00:39.399
<v Speaker 3>I thank you for having me here. Yeah, so two

7
00:00:39.439 --> 00:00:42.159
<v Speaker 3>years ago I was I was hitchhiking around the world

8
00:00:42.840 --> 00:00:47.399
<v Speaker 3>through Central America, through Middle East from Germany, tom lest

9
00:00:47.679 --> 00:00:51.799
<v Speaker 3>through India, Southeast Asia, and half of my time was

10
00:00:51.799 --> 00:00:55.880
<v Speaker 3>wasted at stupid traffic lights. So I thought back then,

11
00:00:56.039 --> 00:00:59.679
<v Speaker 3>like which century we're living in, Like this cannot be true.

12
00:01:01.200 --> 00:01:04.959
<v Speaker 3>So doing a hacker Ton in Germany with some colleagues

13
00:01:04.959 --> 00:01:10.400
<v Speaker 3>from my undergrad and cognitive science so neuroscientists, we tackled

14
00:01:10.400 --> 00:01:14.560
<v Speaker 3>this problem and we built the first PROTECT pilot project

15
00:01:14.599 --> 00:01:17.560
<v Speaker 3>for that we could actually manage in a simulation to

16
00:01:17.799 --> 00:01:22.239
<v Speaker 3>like release skyrocket, like all the metrics like Seal two emissions,

17
00:01:22.239 --> 00:01:25.840
<v Speaker 3>lowered downfield usage, waiting times, and we thought, wow, this

18
00:01:25.840 --> 00:01:29.760
<v Speaker 3>this is incredible. And yeah, since then we are on

19
00:01:29.799 --> 00:01:34.359
<v Speaker 3>this journey for almost two years now to tackle this

20
00:01:34.439 --> 00:01:38.599
<v Speaker 3>problem with a vision to both every single traffic light

21
00:01:38.760 --> 00:01:45.000
<v Speaker 3>on this planet. And while doing this, I moved from

22
00:01:45.000 --> 00:01:48.640
<v Speaker 3>my undergrad to my to my master program in cyric

23
00:01:48.840 --> 00:01:53.920
<v Speaker 3>at Etah, where I'm surrounded with many motivated people, especially

24
00:01:54.040 --> 00:01:57.000
<v Speaker 3>around the student project house. It's like an accelerator where

25
00:01:57.200 --> 00:02:01.719
<v Speaker 3>you're forbidden to study on your project on your university courses,

26
00:02:01.760 --> 00:02:03.799
<v Speaker 3>so you have to work on your court, on your project,

27
00:02:04.319 --> 00:02:09.560
<v Speaker 3>and I just love to be surrounded by people push.

28
00:02:09.960 --> 00:02:13.639
<v Speaker 3>That's that's how I came here today.

29
00:02:14.840 --> 00:02:17.080
<v Speaker 4>So, Magnus, I mean, why did we double click on

30
00:02:17.120 --> 00:02:19.719
<v Speaker 4>the problem itself for a little bit, right, for people

31
00:02:20.240 --> 00:02:25.319
<v Speaker 4>to understand better? So you said you were hitchhiking. Obviously

32
00:02:26.080 --> 00:02:28.919
<v Speaker 4>that is a challenge by itself, right In addition to that,

33
00:02:29.919 --> 00:02:32.599
<v Speaker 4>you are stopping at two way too many traffic lights

34
00:02:32.599 --> 00:02:36.319
<v Speaker 4>and spending a lot of time. So uh, for people

35
00:02:36.400 --> 00:02:40.080
<v Speaker 4>who probably don't know too much about traffic lights and

36
00:02:40.120 --> 00:02:44.560
<v Speaker 4>how it works today, right, I mean, is what goes

37
00:02:44.599 --> 00:02:47.319
<v Speaker 4>on today in most of the world. You think, right,

38
00:02:47.479 --> 00:02:51.159
<v Speaker 4>why why people stop at these lights? And maybe it's

39
00:02:51.159 --> 00:02:54.800
<v Speaker 4>a primitive way of doing it, maybe it's not the

40
00:02:54.840 --> 00:02:57.639
<v Speaker 4>best optimized way to do it, But I mean, what

41
00:02:57.759 --> 00:03:00.719
<v Speaker 4>is the real problem itself? Can you maybe two minutes

42
00:03:00.759 --> 00:03:01.000
<v Speaker 4>on that?

43
00:03:01.120 --> 00:03:04.639
<v Speaker 3>Yes? So I guess everyone who lives in a city

44
00:03:04.639 --> 00:03:07.479
<v Speaker 3>with traffic lights knows the situation, like fix them in

45
00:03:07.520 --> 00:03:09.800
<v Speaker 3>the middle of the night where you drive and you

46
00:03:09.879 --> 00:03:12.479
<v Speaker 3>face a red traffic light and they think, okay, house

47
00:03:12.439 --> 00:03:15.000
<v Speaker 3>is possible, like there's no car intersection? Why do I

48
00:03:15.039 --> 00:03:18.520
<v Speaker 3>have read? And of course different cultures deal different with

49
00:03:18.560 --> 00:03:23.400
<v Speaker 3>that situation. Some just go over some way. But if

50
00:03:23.439 --> 00:03:26.199
<v Speaker 3>you think that problem, which is now really clear to everyone,

51
00:03:26.360 --> 00:03:28.879
<v Speaker 3>fix some to the rush hour okay, where you have

52
00:03:29.000 --> 00:03:32.719
<v Speaker 3>thousand cars from every side and you have there a

53
00:03:32.879 --> 00:03:36.080
<v Speaker 3>stupid traffic lights which in many cities just run on

54
00:03:36.360 --> 00:03:40.199
<v Speaker 3>static cycles, so every side just gets the same amount

55
00:03:40.199 --> 00:03:43.680
<v Speaker 3>of brief time, no matter what's the current traffic, what's

56
00:03:43.680 --> 00:03:45.960
<v Speaker 3>the weather, if there was a big football game and

57
00:03:46.000 --> 00:03:49.080
<v Speaker 3>there are now thousand people coming from one side. So

58
00:03:49.919 --> 00:03:53.400
<v Speaker 3>in many cities they have like just still stupid traffic

59
00:03:53.439 --> 00:03:56.120
<v Speaker 3>lights and some for someone in Germany they now started

60
00:03:56.159 --> 00:04:00.960
<v Speaker 3>to tackle this problem by investing like millions of euros

61
00:04:01.479 --> 00:04:04.520
<v Speaker 3>and too expensive sensors, so they open the street, play

62
00:04:04.520 --> 00:04:09.360
<v Speaker 3>some pressure sensors or install cameras to then optimize single intersections.

63
00:04:09.919 --> 00:04:13.639
<v Speaker 3>But if you think about that like nowadays, especially why hitchhicking,

64
00:04:13.719 --> 00:04:16.560
<v Speaker 3>I realized every day around the world uses mobile phones

65
00:04:16.600 --> 00:04:20.279
<v Speaker 3>in their car and with that with Google Maps, tom

66
00:04:20.360 --> 00:04:24.800
<v Speaker 3>Tom Rixia many providers, you have globally available real time

67
00:04:24.920 --> 00:04:28.839
<v Speaker 3>data for the whole planet, and based on that data,

68
00:04:28.959 --> 00:04:32.279
<v Speaker 3>we build models to optimize those traffic lights, not just

69
00:04:32.319 --> 00:04:36.439
<v Speaker 3>for one intersections, but for whole cities. So those interactions,

70
00:04:36.439 --> 00:04:38.480
<v Speaker 3>they can talk to each other. You can say, hey,

71
00:04:38.800 --> 00:04:41.720
<v Speaker 3>I send to you now ten cars coming this way.

72
00:04:42.720 --> 00:04:45.519
<v Speaker 3>With this communication, they can have a much more efficient

73
00:04:45.879 --> 00:04:47.360
<v Speaker 3>optimization for the whole city.

74
00:04:48.319 --> 00:04:50.519
<v Speaker 4>Got it? So any have you done any sort of

75
00:04:50.560 --> 00:04:54.639
<v Speaker 4>research magnets to see how big this market is? You know,

76
00:04:54.720 --> 00:04:58.519
<v Speaker 4>obviously you obviously seem passionate about the problem itself, right,

77
00:04:58.560 --> 00:05:01.199
<v Speaker 4>But I mean for you to spend time and say, oh,

78
00:05:01.360 --> 00:05:03.680
<v Speaker 4>I want to solve this. I want to solve this

79
00:05:03.720 --> 00:05:07.680
<v Speaker 4>by starting a company. I mean, what sort of numbers

80
00:05:09.120 --> 00:05:14.639
<v Speaker 4>market cab or market size rather any research numbers you have, yes.

81
00:05:15.000 --> 00:05:17.360
<v Speaker 3>Yes, of course, so right now we'll do a lot

82
00:05:17.399 --> 00:05:20.120
<v Speaker 3>of fund raising. So I'm familiar with all this numbers,

83
00:05:20.519 --> 00:05:24.199
<v Speaker 3>Like the total available market is around ten billion dollars

84
00:05:24.279 --> 00:05:27.879
<v Speaker 3>in that space with a forty percent growth rate. Because

85
00:05:27.959 --> 00:05:30.439
<v Speaker 3>for example, in Germany there are now many smart city

86
00:05:30.560 --> 00:05:32.800
<v Speaker 3>Also in India, I saw there like one hundred new

87
00:05:32.800 --> 00:05:37.240
<v Speaker 3>smart cities so the government like really pushes those initiatives

88
00:05:38.600 --> 00:05:42.439
<v Speaker 3>as different reason has stealed two and sustainability issues, but

89
00:05:42.519 --> 00:05:46.120
<v Speaker 3>also air pollution. Also in Germany, Many, many cities are

90
00:05:46.480 --> 00:05:49.600
<v Speaker 3>just don't have enough people to manage their traffic lights

91
00:05:49.639 --> 00:05:52.920
<v Speaker 3>like manually, so they invest more and more in those

92
00:05:52.959 --> 00:05:54.720
<v Speaker 3>automated solutions.

93
00:05:55.279 --> 00:05:59.759
<v Speaker 4>Got it. So it obviously affects us, say every day everyone,

94
00:06:00.040 --> 00:06:01.720
<v Speaker 4>I mean anyone who's on the road, I mean whether

95
00:06:01.759 --> 00:06:05.000
<v Speaker 4>you're a pedestrian or whether you're driving a car or

96
00:06:05.240 --> 00:06:10.759
<v Speaker 4>you're driving a commercial truck. So that's a very unique

97
00:06:10.759 --> 00:06:16.720
<v Speaker 4>problem that you're trying to solve. So obviously sorry, good.

98
00:06:16.399 --> 00:06:19.480
<v Speaker 3>Yeah, yeah, you're completely right, Like it impacts all of us.

99
00:06:19.519 --> 00:06:22.480
<v Speaker 3>And if you think it impacts in so many different industries.

100
00:06:22.519 --> 00:06:25.120
<v Speaker 3>If you, for example, think okay, you're sitting banganor and

101
00:06:25.160 --> 00:06:30.040
<v Speaker 3>you're now ordering your food and your food delivery, it's

102
00:06:30.079 --> 00:06:33.079
<v Speaker 3>like maybe for you those couple of seconds which is late,

103
00:06:33.519 --> 00:06:36.079
<v Speaker 3>isn't a big difference because of stupid traffic lights. But

104
00:06:36.120 --> 00:06:38.360
<v Speaker 3>if you think, like for such a global business there's

105
00:06:38.439 --> 00:06:42.199
<v Speaker 3>like millions of trips every day, a couple of seconds

106
00:06:42.240 --> 00:06:44.480
<v Speaker 3>per trip is like immense and you can think that

107
00:06:44.560 --> 00:06:48.680
<v Speaker 3>from the logistic the truck through the bicycle industry like

108
00:06:49.360 --> 00:06:53.199
<v Speaker 3>it just impacts basically everything understood.

109
00:06:53.439 --> 00:06:55.879
<v Speaker 4>So we've spoken about the problem. I think we have

110
00:06:55.879 --> 00:06:59.160
<v Speaker 4>a fair idea of what the problem is. So I

111
00:06:59.560 --> 00:07:03.480
<v Speaker 4>see greenway has an AI in it. So what is

112
00:07:03.519 --> 00:07:07.160
<v Speaker 4>your approach to solving this problem with greenway?

113
00:07:09.120 --> 00:07:14.199
<v Speaker 3>Okay, so what was done until now was you look

114
00:07:14.240 --> 00:07:18.439
<v Speaker 3>at the city and you calculate, Okay, this traffic light

115
00:07:18.519 --> 00:07:21.279
<v Speaker 3>is five hundred meters away from this traffic light, so

116
00:07:21.600 --> 00:07:24.800
<v Speaker 3>we need to switch this traffic lightlight thirty seconds later green,

117
00:07:24.879 --> 00:07:28.120
<v Speaker 3>so that cars or bicycles, whatever you want to optimize,

118
00:07:28.160 --> 00:07:31.639
<v Speaker 3>have kind of a seamless flat green greenway, steamless flow.

119
00:07:32.519 --> 00:07:34.879
<v Speaker 3>But of course for us humans, that's hard to do

120
00:07:34.920 --> 00:07:39.079
<v Speaker 3>that with twenty different lodes, twenty different intersections and their

121
00:07:39.240 --> 00:07:43.040
<v Speaker 3>their complexity, the interactions between them, and that's where our

122
00:07:43.399 --> 00:07:46.240
<v Speaker 3>OAI comes into. Plank we have. We can create a

123
00:07:46.279 --> 00:07:51.399
<v Speaker 3>simulation of a city stack bangal or here, San Francisco, Berlin.

124
00:07:52.240 --> 00:07:55.600
<v Speaker 3>Create a simulation and then in a simulation we can

125
00:07:55.639 --> 00:08:00.920
<v Speaker 3>simulate everything. We can simulate cars, bicycle, trucks, buses, drives

126
00:08:00.920 --> 00:08:04.199
<v Speaker 3>around like in a real world. Now we can train

127
00:08:04.279 --> 00:08:11.000
<v Speaker 3>in AI, which in the beginning just completely stupid control

128
00:08:11.079 --> 00:08:13.600
<v Speaker 3>the traffic light. You can imagine it's like a baby

129
00:08:13.639 --> 00:08:17.319
<v Speaker 3>which comes to the world and there's just stupid actions

130
00:08:17.360 --> 00:08:20.079
<v Speaker 3>like putting the hand into the fire and gets feedback

131
00:08:20.199 --> 00:08:22.839
<v Speaker 3>and gets better and better and hair and like this.

132
00:08:22.920 --> 00:08:26.720
<v Speaker 3>You can also imagine our AI. We can throw thousands

133
00:08:26.720 --> 00:08:31.639
<v Speaker 3>of different like traffic situations on it. We can rush

134
00:08:31.720 --> 00:08:35.000
<v Speaker 3>our middle of the night, big football game, and all

135
00:08:35.000 --> 00:08:39.480
<v Speaker 3>those different data distributions can then get learned from our

136
00:08:39.559 --> 00:08:43.480
<v Speaker 3>system to get better and better. You can just choose

137
00:08:43.600 --> 00:08:46.440
<v Speaker 3>what it should optimize. Some cities they want to optimize

138
00:08:46.440 --> 00:08:49.200
<v Speaker 3>for speed, some for seal tool emissions, some they want

139
00:08:49.240 --> 00:08:54.759
<v Speaker 3>to improve buses or want to prioritize bicycles, and based

140
00:08:54.799 --> 00:08:57.639
<v Speaker 3>on what the city wants, you can then design your

141
00:08:57.639 --> 00:09:01.919
<v Speaker 3>optimization function to optimize statinism. Then, in the second step

142
00:09:02.080 --> 00:09:04.720
<v Speaker 3>in the real world, you don't take the data from

143
00:09:05.000 --> 00:09:09.919
<v Speaker 3>some Google maps or from sometimes feed it into your system,

144
00:09:10.080 --> 00:09:15.080
<v Speaker 3>which is learned in assimilation and then outputs the best

145
00:09:15.080 --> 00:09:17.960
<v Speaker 3>option to now in real time based on this data.

146
00:09:18.320 --> 00:09:19.720
<v Speaker 3>Control the traffic.

147
00:09:19.919 --> 00:09:23.639
<v Speaker 4>Got it, So I think I get it, But at

148
00:09:23.639 --> 00:09:26.480
<v Speaker 4>the same time, I mean I'm a little I'm trying

149
00:09:26.480 --> 00:09:29.519
<v Speaker 4>to understand a little better on the real time data

150
00:09:29.919 --> 00:09:30.200
<v Speaker 4>of it.

151
00:09:30.279 --> 00:09:30.440
<v Speaker 3>Right.

152
00:09:30.480 --> 00:09:34.879
<v Speaker 4>Obviously with AI, you're training it with data that you

153
00:09:35.039 --> 00:09:39.360
<v Speaker 4>already have based on different permutations and combinations, like you said.

154
00:09:40.039 --> 00:09:42.799
<v Speaker 4>But at the same time, I mean, you know, traffic

155
00:09:42.879 --> 00:09:46.159
<v Speaker 4>is always unpredictable, right, I mean, you know, a group

156
00:09:46.159 --> 00:09:49.600
<v Speaker 4>of hundred might choose to have a party and they

157
00:09:49.759 --> 00:09:52.559
<v Speaker 4>might be going in you know, fifty different cars, which

158
00:09:52.639 --> 00:09:55.360
<v Speaker 4>is kind of an outlier, right, But I mean, how

159
00:09:55.399 --> 00:09:58.840
<v Speaker 4>do you so you have a combination of historical plus

160
00:09:58.879 --> 00:10:03.480
<v Speaker 4>real time data being fed and constantly kind of training

161
00:10:03.519 --> 00:10:06.320
<v Speaker 4>your model or updating area. Is that the right way

162
00:10:06.360 --> 00:10:07.000
<v Speaker 4>to think about it?

163
00:10:08.960 --> 00:10:12.320
<v Speaker 3>Exactly? Yeah? So of course, like it's about making your

164
00:10:12.320 --> 00:10:15.120
<v Speaker 3>models better and better and better and fitting more and

165
00:10:15.159 --> 00:10:19.240
<v Speaker 3>more outlier cases into your model. And for example, if

166
00:10:19.240 --> 00:10:23.240
<v Speaker 3>you take like, yeah, traffic, like you say, is such

167
00:10:23.279 --> 00:10:26.399
<v Speaker 3>a huge diversity, Like you can just imagine, okay, here outside,

168
00:10:26.480 --> 00:10:29.840
<v Speaker 3>is now a car from Amazon Prime? Then then maybe

169
00:10:29.840 --> 00:10:32.759
<v Speaker 3>blocking the traffic light. Right, There's so many different cases.

170
00:10:33.240 --> 00:10:36.480
<v Speaker 3>But by creating a model which is trained on millions

171
00:10:36.559 --> 00:10:37.440
<v Speaker 3>of different.

172
00:10:37.200 --> 00:10:40.600
<v Speaker 5>Data distributions and then you deploy them practice, and of

173
00:10:40.639 --> 00:10:44.000
<v Speaker 5>course you will figure out in the beginning cases which

174
00:10:44.000 --> 00:10:47.840
<v Speaker 5>are unexpected where which you need to handle for but

175
00:10:47.960 --> 00:10:51.759
<v Speaker 5>over time, like self driving cars to get better and

176
00:10:51.799 --> 00:10:53.080
<v Speaker 5>better and better from.

177
00:10:53.000 --> 00:10:59.720
<v Speaker 3>Learning more and more and more regarded data distributions. Understand, yes,

178
00:11:00.159 --> 00:11:02.720
<v Speaker 3>this is interesting, the cool thing here?

179
00:11:05.000 --> 00:11:06.399
<v Speaker 2>Make you have messed this up?

180
00:11:06.480 --> 00:11:06.879
<v Speaker 3>I think?

181
00:11:11.039 --> 00:11:11.720
<v Speaker 4>Then I'll go ahead.

182
00:11:13.759 --> 00:11:16.480
<v Speaker 1>Yeah, I was gonna ask, at least the solution is

183
00:11:16.519 --> 00:11:20.320
<v Speaker 1>going to sit through with the state level agencies or

184
00:11:20.840 --> 00:11:25.519
<v Speaker 1>the traffic agencies. How has that interaction been, right? I

185
00:11:25.559 --> 00:11:28.519
<v Speaker 1>get like I would be curious to hear your reactions

186
00:11:28.519 --> 00:11:33.480
<v Speaker 1>with them.

187
00:11:34.320 --> 00:11:36.240
<v Speaker 3>You mean to go to market, so how we sell

188
00:11:36.279 --> 00:11:36.639
<v Speaker 3>to the city.

189
00:11:36.840 --> 00:11:39.399
<v Speaker 1>Yeah, like, because once you would have exposed the solution,

190
00:11:39.600 --> 00:11:42.000
<v Speaker 1>I'm sure they're like, oh, why our system is not

191
00:11:42.080 --> 00:11:44.519
<v Speaker 1>good enough? Like was that the reaction of people who

192
00:11:44.519 --> 00:11:47.440
<v Speaker 1>were very open to oh, look that there is a

193
00:11:47.440 --> 00:11:48.440
<v Speaker 1>better way of doing it.

194
00:11:52.480 --> 00:11:55.039
<v Speaker 3>So for sure there are some like like you have

195
00:11:55.080 --> 00:11:58.759
<v Speaker 3>to understand and all our customer interviews, we realize those

196
00:11:58.799 --> 00:12:04.320
<v Speaker 3>cities especially they have nowadays a huge problem with skill shortage,

197
00:12:04.879 --> 00:12:07.440
<v Speaker 3>so they don't have enough people to handle those problems.

198
00:12:08.159 --> 00:12:13.159
<v Speaker 3>And for example, in normal small, medium sized cities, there

199
00:12:13.159 --> 00:12:16.919
<v Speaker 3>are hundreds of construction sites every year which changed the

200
00:12:17.000 --> 00:12:23.759
<v Speaker 3>road network and to handle those road blockages, those cities

201
00:12:23.799 --> 00:12:29.000
<v Speaker 3>they pay expensive factional engineering offices who then create new

202
00:12:29.039 --> 00:12:34.840
<v Speaker 3>traffic signals schedules by hand for those intersections. So by

203
00:12:34.879 --> 00:12:39.240
<v Speaker 3>doing those customer interviews, we realized, okay, with those skill

204
00:12:39.320 --> 00:12:42.120
<v Speaker 3>shortage where they really don't have enough people to look

205
00:12:42.120 --> 00:12:45.320
<v Speaker 3>for anything, we can have one of the biggest value

206
00:12:45.440 --> 00:12:48.240
<v Speaker 3>proposition to them. And so you really need to figure

207
00:12:48.240 --> 00:12:50.639
<v Speaker 3>out I mean, in the end of course you benefit

208
00:12:50.679 --> 00:12:53.919
<v Speaker 3>the whole society, but in a first step, like you say,

209
00:12:54.039 --> 00:12:56.399
<v Speaker 3>you sell the cities. So first you need to figure

210
00:12:56.399 --> 00:12:59.279
<v Speaker 3>out why would the city buy the solution, why would

211
00:12:59.279 --> 00:13:03.679
<v Speaker 3>they waste time on you? And one is skill shortage,

212
00:13:03.840 --> 00:13:08.080
<v Speaker 3>another one is still to a must reduction, and third

213
00:13:08.120 --> 00:13:12.799
<v Speaker 3>one is for example, direct cost savings in the the

214
00:13:12.840 --> 00:13:16.639
<v Speaker 3>public transport sector when they need less buses to keep

215
00:13:16.720 --> 00:13:19.879
<v Speaker 3>up the bus frequency. Imagine the bus in the city

216
00:13:19.919 --> 00:13:22.240
<v Speaker 3>wants that every thirty minutes is a bus in front

217
00:13:22.240 --> 00:13:25.320
<v Speaker 3>of your house which can pick you up. And if

218
00:13:25.320 --> 00:13:29.240
<v Speaker 3>now traffic is poor, they need more buses. But if

219
00:13:29.279 --> 00:13:32.960
<v Speaker 3>you improve your the system, then they need less buses.

220
00:13:33.159 --> 00:13:37.080
<v Speaker 3>And such a bus is super super expensive, like normally

221
00:13:37.080 --> 00:13:41.039
<v Speaker 3>they keep one for like ten years, costs around one million,

222
00:13:41.320 --> 00:13:45.440
<v Speaker 3>so to handle them for one year costs around one

223
00:13:45.559 --> 00:13:49.200
<v Speaker 3>hundred to more than two hundred thousand euros per year,

224
00:13:49.519 --> 00:13:52.639
<v Speaker 3>and that's where you can provide them like a value proposition.

225
00:13:53.759 --> 00:13:57.879
<v Speaker 3>And if you have like those three arguments, then you

226
00:13:57.879 --> 00:14:00.399
<v Speaker 3>can go to cities and of course, like we have

227
00:14:00.519 --> 00:14:03.879
<v Speaker 3>heart problems as a young startups that they to get

228
00:14:03.919 --> 00:14:05.720
<v Speaker 3>trust off those cities, and our.

229
00:14:05.879 --> 00:14:10.200
<v Speaker 6>Strategy is to go with with pilot projects, which we

230
00:14:10.279 --> 00:14:13.440
<v Speaker 6>offer them almost for free to say, okay, let us

231
00:14:13.519 --> 00:14:16.679
<v Speaker 6>try this out so you can discover how much you

232
00:14:16.759 --> 00:14:20.639
<v Speaker 6>benefit from that and.

233
00:14:19.720 --> 00:14:23.000
<v Speaker 3>Over time win more and more trust off those cities.

234
00:14:24.399 --> 00:14:27.919
<v Speaker 4>Got it, Thanks, thanks my migness. So one of the

235
00:14:30.200 --> 00:14:31.639
<v Speaker 4>I don't know if it is you call it a

236
00:14:31.679 --> 00:14:33.919
<v Speaker 4>residual effect or a side effect. This actually can be

237
00:14:34.000 --> 00:14:39.039
<v Speaker 4>a big selling point I'm assuming is what goes hand

238
00:14:39.080 --> 00:14:43.639
<v Speaker 4>in hand is if you regulate traffic efficiently and you

239
00:14:44.039 --> 00:14:48.120
<v Speaker 4>regulate traffic safely, you can avoid a lot of accidents

240
00:14:48.120 --> 00:14:51.120
<v Speaker 4>as well. Right, I mean, you know why do most

241
00:14:51.120 --> 00:14:53.559
<v Speaker 4>of the accidents happen because you know, people are in

242
00:14:53.559 --> 00:14:56.879
<v Speaker 4>a rushia. People are frustrated because you know, the traffic

243
00:14:56.960 --> 00:15:00.159
<v Speaker 4>light is in red for so long and they take

244
00:15:00.200 --> 00:15:03.039
<v Speaker 4>a you know, a risk to just cut across the

245
00:15:03.080 --> 00:15:06.080
<v Speaker 4>street and go or you know speed or whatnot. So

246
00:15:06.759 --> 00:15:11.240
<v Speaker 4>I mean, is your solution with Green Bay trying to

247
00:15:11.279 --> 00:15:15.519
<v Speaker 4>pitch you know, public safety on the roads as also

248
00:15:15.639 --> 00:15:18.000
<v Speaker 4>one of these effects. I mean, is that something you've

249
00:15:18.000 --> 00:15:18.879
<v Speaker 4>thought about as well.

250
00:15:21.519 --> 00:15:25.200
<v Speaker 3>So we are aware of studies which show that if

251
00:15:25.200 --> 00:15:29.720
<v Speaker 3>you improve traffic flow so less stopping code traffic, then

252
00:15:30.120 --> 00:15:35.440
<v Speaker 3>this increases road safety. And we can clearly improve traffic

253
00:15:35.480 --> 00:15:38.960
<v Speaker 3>flow somewhere in simulation in rush hour we can sometimes

254
00:15:39.000 --> 00:15:41.679
<v Speaker 3>reduce a number of waiting vehicles, but up to ninety percent.

255
00:15:43.000 --> 00:15:46.159
<v Speaker 3>And but asn't now we have never used that fact.

256
00:15:46.679 --> 00:15:50.519
<v Speaker 3>I think that's something which especially needs to figure it out,

257
00:15:50.559 --> 00:15:53.919
<v Speaker 3>like what clear percentage we can say, or like how

258
00:15:53.919 --> 00:15:57.000
<v Speaker 3>many accidents less are there. It's a thing which is

259
00:15:57.039 --> 00:16:00.840
<v Speaker 3>really hard to measure for us right now. But long term,

260
00:16:01.039 --> 00:16:05.519
<v Speaker 3>like this just goes hand in hand and with my vision.

261
00:16:05.559 --> 00:16:09.600
<v Speaker 3>And the cool thing here is that if you improve

262
00:16:09.720 --> 00:16:12.720
<v Speaker 3>one factor, then you improve so many other factors. You

263
00:16:12.799 --> 00:16:18.759
<v Speaker 3>improves your two waiting time, fuel usage, road safety, stability.

264
00:16:19.559 --> 00:16:22.879
<v Speaker 3>That's one thing which really amazed me about this problem.

265
00:16:23.559 --> 00:16:25.639
<v Speaker 4>Awesome magnets. I mean, it's a it's a great idea.

266
00:16:26.559 --> 00:16:31.679
<v Speaker 4>Obviously you started this based off your experience traveling the world,

267
00:16:32.120 --> 00:16:34.639
<v Speaker 4>so you didn't see it in just one place. I

268
00:16:34.639 --> 00:16:38.039
<v Speaker 4>mean this is applicable kind of in every city around

269
00:16:38.080 --> 00:16:41.919
<v Speaker 4>the world. I mean, you know, you've you're obviously from Germany,

270
00:16:42.679 --> 00:16:46.399
<v Speaker 4>You've seen the traffic in in Bangalore. So do you

271
00:16:46.440 --> 00:16:50.559
<v Speaker 4>do you think, I mean greenway will work for any

272
00:16:50.799 --> 00:16:55.200
<v Speaker 4>permutation and combination sort of thing, or in other words,

273
00:16:55.360 --> 00:16:57.720
<v Speaker 4>it will it work for any any city you think,

274
00:16:57.799 --> 00:17:01.759
<v Speaker 4>any modern city so to speak, or you think you

275
00:17:01.879 --> 00:17:05.799
<v Speaker 4>have a sort of a template for an ideal city

276
00:17:05.880 --> 00:17:09.720
<v Speaker 4>where greenway will work now and maybe work elsewhere later.

277
00:17:10.240 --> 00:17:11.200
<v Speaker 4>What is your thought on that?

278
00:17:14.559 --> 00:17:17.680
<v Speaker 3>So, of course we have our initial target customer group

279
00:17:17.799 --> 00:17:20.200
<v Speaker 3>where we start with this, but our plan is to

280
00:17:20.279 --> 00:17:23.039
<v Speaker 3>make this work everywhere, to solve of every single traffic

281
00:17:23.119 --> 00:17:26.240
<v Speaker 3>light on this on this planet. And of course some

282
00:17:26.400 --> 00:17:29.880
<v Speaker 3>cities are faster, somewhat slower, So we focus, especially in

283
00:17:29.880 --> 00:17:32.319
<v Speaker 3>the beginning, just on those who love us and really

284
00:17:32.319 --> 00:17:36.400
<v Speaker 3>want to develop it just together with us. And our

285
00:17:36.519 --> 00:17:39.960
<v Speaker 3>vision is like long term to make the whole process

286
00:17:40.240 --> 00:17:44.680
<v Speaker 3>around smart cities really easier for cities. Right now, imagine

287
00:17:44.680 --> 00:17:48.920
<v Speaker 3>you're a developer and you want to develop your app

288
00:17:49.119 --> 00:17:52.200
<v Speaker 3>for the App Store, so that everyone can benefit from it, right,

289
00:17:52.319 --> 00:17:54.440
<v Speaker 3>so you just go to Google play Store or App

290
00:17:54.440 --> 00:17:58.400
<v Speaker 3>Store and to upload your app. But in cities this

291
00:17:58.480 --> 00:18:02.039
<v Speaker 3>is right now, super super hard because every city uses

292
00:18:02.039 --> 00:18:05.400
<v Speaker 3>a different system and you have to do tenders. But

293
00:18:06.119 --> 00:18:11.079
<v Speaker 3>like my long term vision is that long young developers

294
00:18:11.319 --> 00:18:13.559
<v Speaker 3>and there'll be in India and Germany or in the

295
00:18:13.680 --> 00:18:17.119
<v Speaker 3>US if the ideas can come to a city and

296
00:18:17.200 --> 00:18:21.640
<v Speaker 3>an easy framework can bring in their ideas and easy

297
00:18:21.720 --> 00:18:27.480
<v Speaker 3>sandbox like format to run experiments on some infrastructure from

298
00:18:27.519 --> 00:18:31.240
<v Speaker 3>small they save parts of the city to test out

299
00:18:31.279 --> 00:18:32.960
<v Speaker 3>new stuff. And I think with that we can have

300
00:18:33.359 --> 00:18:36.359
<v Speaker 3>in so many different ways new innovation which benefits in

301
00:18:36.400 --> 00:18:40.759
<v Speaker 3>the end all of us will live in those cities. Great.

302
00:18:43.599 --> 00:18:46.079
<v Speaker 1>I'm still really more of the fact that it's hitchhiking

303
00:18:46.119 --> 00:18:46.680
<v Speaker 1>that got.

304
00:18:46.519 --> 00:18:47.319
<v Speaker 4>You to the solution.

305
00:18:47.720 --> 00:18:51.640
<v Speaker 1>To be honest, I would be like, you weren't even

306
00:18:51.720 --> 00:18:53.759
<v Speaker 1>driving at that point, you still got bothered with the

307
00:18:53.799 --> 00:18:59.839
<v Speaker 1>traffic lights. That's just seriously amazing. But it's also it's

308
00:18:59.880 --> 00:19:03.480
<v Speaker 1>the scale of the problem too, right, This is you

309
00:19:03.519 --> 00:19:06.200
<v Speaker 1>said it yourself, right, You're starting with a small setups

310
00:19:06.319 --> 00:19:08.519
<v Speaker 1>that's the one city in then expand globally.

311
00:19:09.039 --> 00:19:12.440
<v Speaker 2>That's a massive vision, right, how is it and how

312
00:19:12.519 --> 00:19:14.839
<v Speaker 2>is your day to day right when you go out

313
00:19:14.880 --> 00:19:17.000
<v Speaker 2>and like, Okay, I'm gonna achieve this one at a time,

314
00:19:17.440 --> 00:19:18.640
<v Speaker 2>how does that day look like.

315
00:19:22.440 --> 00:19:27.000
<v Speaker 3>My day to day life. So it really depends on

316
00:19:27.039 --> 00:19:30.960
<v Speaker 3>the face of the business. Like sometimes I remember two

317
00:19:30.960 --> 00:19:34.279
<v Speaker 3>months ago, I was coding day and night, just thinking,

318
00:19:34.799 --> 00:19:39.559
<v Speaker 3>brainstorming on like a flip shot, you know, and drawing

319
00:19:39.880 --> 00:19:44.160
<v Speaker 3>architectures of our AI model. How's the whole pipeline going

320
00:19:44.759 --> 00:19:48.279
<v Speaker 3>right now? It's a whole day like fund raising. Right

321
00:19:48.319 --> 00:19:53.319
<v Speaker 3>now we have fund raising half a million euros and

322
00:19:53.359 --> 00:19:56.240
<v Speaker 3>so I reach out to many investors right now, I'm

323
00:19:56.240 --> 00:20:01.119
<v Speaker 3>here in Silicon Valley and just pitch I worked a

324
00:20:01.119 --> 00:20:04.119
<v Speaker 3>lot along pitch Deck, learned a lot to improve there.

325
00:20:04.480 --> 00:20:06.920
<v Speaker 3>About legal stuff, I learned a lot. So I think

326
00:20:06.920 --> 00:20:09.599
<v Speaker 3>that's it's one of the most amazing things to be

327
00:20:09.839 --> 00:20:12.920
<v Speaker 3>a founder, to just get insights into so many different domains,

328
00:20:13.000 --> 00:20:16.680
<v Speaker 3>learn about legal, learn about hiring, learn about tech, to

329
00:20:16.680 --> 00:20:19.920
<v Speaker 3>be a generalist. And I think especially for crewious people

330
00:20:20.200 --> 00:20:23.240
<v Speaker 3>like us, they're one of the most amazing things to do.

331
00:20:24.480 --> 00:20:30.839
<v Speaker 4>So for anyone listening Magnus, you are fundraising and you

332
00:20:30.839 --> 00:20:34.720
<v Speaker 4>you're maybe again based on what I know I will

333
00:20:34.759 --> 00:20:36.759
<v Speaker 4>say it and you can correct it. You're looking for

334
00:20:36.839 --> 00:20:39.440
<v Speaker 4>angels for a start, right I mean you're in an

335
00:20:39.440 --> 00:20:42.599
<v Speaker 4>initial seed face or you can probably talk about what

336
00:20:42.759 --> 00:20:46.119
<v Speaker 4>sort of funding you would rather take in right now.

337
00:20:49.079 --> 00:20:52.400
<v Speaker 3>Yes, So we got nominated for like a three million

338
00:20:52.759 --> 00:20:55.400
<v Speaker 3>grant in Germany where we want to hack at them

339
00:20:55.440 --> 00:20:58.960
<v Speaker 3>at the federal Ministry. And to secure this grant, we

340
00:20:59.480 --> 00:21:03.839
<v Speaker 3>are our saying five hundred k and we have already

341
00:21:03.960 --> 00:21:08.000
<v Speaker 3>the first angels committed. It's all around pre seed, like

342
00:21:08.200 --> 00:21:12.279
<v Speaker 3>we're especially looking for people who bring smart money on

343
00:21:12.319 --> 00:21:14.200
<v Speaker 3>the table, who wants to bring a network on a

344
00:21:14.279 --> 00:21:17.880
<v Speaker 3>table in the mobility space. Can be a tech space

345
00:21:18.799 --> 00:21:23.240
<v Speaker 3>advisor from from Google, can be also in the government

346
00:21:23.400 --> 00:21:27.119
<v Speaker 3>sector like everything. Just someone who is also frustrated about

347
00:21:27.119 --> 00:21:30.400
<v Speaker 3>this problem and wants to solve it. I'm happy to

348
00:21:30.440 --> 00:21:33.519
<v Speaker 3>talk with. Can be pre seed be cs or or

349
00:21:33.599 --> 00:21:36.119
<v Speaker 3>angels who really believe in that mission to solve that

350
00:21:36.200 --> 00:21:39.640
<v Speaker 3>problem globally. And it's crazy if you do the calculation,

351
00:21:39.759 --> 00:21:42.599
<v Speaker 3>like how many million tons of seal two we can

352
00:21:42.720 --> 00:21:48.200
<v Speaker 3>save with that solution, Like it's insane and that's really

353
00:21:48.240 --> 00:21:49.880
<v Speaker 3>what what motivates me.

354
00:21:49.880 --> 00:21:53.920
<v Speaker 4>To somebody anyone with money in the bank and a checkbook. Right,

355
00:21:54.079 --> 00:21:56.240
<v Speaker 4>that's that's that's that's what you're looking for.

356
00:21:57.839 --> 00:22:02.359
<v Speaker 3>Yeah, basically someone who brings a new new ideas.

357
00:22:02.559 --> 00:22:06.759
<v Speaker 4>I'm always so I want to do a little bit

358
00:22:06.799 --> 00:22:10.359
<v Speaker 4>of a flashback maybe, right Obviously we've talked in about

359
00:22:10.559 --> 00:22:15.279
<v Speaker 4>enough about your hitchhiking, so to speak. But I mean,

360
00:22:15.319 --> 00:22:17.599
<v Speaker 4>did you always want to be an entrepreneur or it

361
00:22:17.720 --> 00:22:18.799
<v Speaker 4>just happened by chance?

362
00:22:24.839 --> 00:22:27.359
<v Speaker 7>I think in the world where I grew up right now,

363
00:22:27.920 --> 00:22:31.359
<v Speaker 7>it's like a really hype it's all around ath Agent's

364
00:22:31.480 --> 00:22:35.039
<v Speaker 7>Rakes project house that was an esoprick.

365
00:22:35.400 --> 00:22:39.079
<v Speaker 3>Like, Okay, maybe maybe I say this also because I'm

366
00:22:39.079 --> 00:22:42.519
<v Speaker 3>in this, baba, it could be also true because everyone

367
00:22:42.640 --> 00:22:46.880
<v Speaker 3>around me is like an entrepreneur. But yeah, I think

368
00:22:47.440 --> 00:22:50.920
<v Speaker 3>like also, when I was younger growing up and I

369
00:22:50.960 --> 00:22:54.200
<v Speaker 3>had problems, I always thought, okay, like what's the chance here,

370
00:22:54.599 --> 00:22:59.160
<v Speaker 3>Like I I remember I was sixteen, I'm selling like

371
00:22:59.599 --> 00:23:03.039
<v Speaker 3>Tisha designs online and I need to upload those designs

372
00:23:03.240 --> 00:23:07.079
<v Speaker 3>to like Ama Zone, and I just wasted my time

373
00:23:07.119 --> 00:23:09.480
<v Speaker 3>with uploading. So I just started, okay, writing my own

374
00:23:09.519 --> 00:23:15.200
<v Speaker 3>boughts to to upload that stuff. Just whenever if you

375
00:23:15.279 --> 00:23:18.759
<v Speaker 3>face a problem, I thought, okay, okay, what chance is here,

376
00:23:18.880 --> 00:23:22.519
<v Speaker 3>what solution could be here? Which also I don't better

377
00:23:22.839 --> 00:23:25.319
<v Speaker 3>fits from it, and I think this is what an

378
00:23:25.440 --> 00:23:27.400
<v Speaker 3>entrepreneur does in the beginning.

379
00:23:28.119 --> 00:23:32.079
<v Speaker 1>Yeah, do you still think it's all hyped up being

380
00:23:32.079 --> 00:23:32.839
<v Speaker 1>an entrepreneur?

381
00:23:39.000 --> 00:23:42.160
<v Speaker 3>I think right now a lot here in my age,

382
00:23:42.279 --> 00:23:46.319
<v Speaker 3>like many young people want to be really independent and

383
00:23:46.640 --> 00:23:50.279
<v Speaker 3>want to create their own company. And I think like

384
00:23:51.079 --> 00:23:53.799
<v Speaker 3>right now, especially online, like we have so many tools

385
00:23:53.799 --> 00:23:57.279
<v Speaker 3>which support us with that makes it easier and easier

386
00:23:57.920 --> 00:24:01.880
<v Speaker 3>to just go out and co found is went investors

387
00:24:02.759 --> 00:24:06.680
<v Speaker 3>great first MVPs, like the structure to do that is

388
00:24:07.480 --> 00:24:08.160
<v Speaker 3>become much.

389
00:24:08.039 --> 00:24:11.119
<v Speaker 1>More Would you recommend caution or would you be more

390
00:24:11.160 --> 00:24:13.599
<v Speaker 1>like you know, hey, more power at this point, like

391
00:24:13.720 --> 00:24:14.799
<v Speaker 1>knowing what you know now?

392
00:24:18.640 --> 00:24:21.799
<v Speaker 3>Yeah, if I would recommend to be an entrepreneur, yeah,

393
00:24:22.480 --> 00:24:25.960
<v Speaker 3>so I think, yeah, of course I wouldn't. I would

394
00:24:26.000 --> 00:24:29.400
<v Speaker 3>recommend it. Yeah, especially if you're like curious, like if

395
00:24:29.400 --> 00:24:31.319
<v Speaker 3>you feel inside of you that you want to be

396
00:24:31.400 --> 00:24:33.680
<v Speaker 3>it and there's just a little bit, you know, maybe

397
00:24:33.680 --> 00:24:35.799
<v Speaker 3>a little bit of fear or just can't be anything

398
00:24:35.799 --> 00:24:38.160
<v Speaker 3>which holds you back, then I would definitely recommend it

399
00:24:38.200 --> 00:24:41.599
<v Speaker 3>to you. But I think we often forget also in

400
00:24:41.759 --> 00:24:46.799
<v Speaker 3>big companies they are often like really entrepreneurs, you know,

401
00:24:47.000 --> 00:24:49.799
<v Speaker 3>like even if you're working in a big tech or

402
00:24:50.079 --> 00:24:52.519
<v Speaker 3>medium sized company, you can be an entrepreneur and really

403
00:24:53.000 --> 00:24:57.240
<v Speaker 3>innovate that company and run experiments and many examples where

404
00:24:57.279 --> 00:25:02.079
<v Speaker 3>they do everything with an entrepren basically does I think

405
00:25:02.200 --> 00:25:05.440
<v Speaker 3>the advantage of just being like in my situation is

406
00:25:05.519 --> 00:25:09.200
<v Speaker 3>just that you're kind of start from scratching. Really you

407
00:25:09.279 --> 00:25:11.359
<v Speaker 3>learn like everything from legal stuff.

408
00:25:11.039 --> 00:25:16.319
<v Speaker 8>To product to investors through hiring, and that's just really

409
00:25:16.400 --> 00:25:20.640
<v Speaker 8>an amazing experiment experience which you don't get and working

410
00:25:20.680 --> 00:25:21.440
<v Speaker 8>in big type.

411
00:25:23.440 --> 00:25:25.920
<v Speaker 3>But the mindset itself, you cannot everywhere.

412
00:25:28.839 --> 00:25:31.799
<v Speaker 4>Anything you would have done differently in your journey. Magnets

413
00:25:31.799 --> 00:25:32.640
<v Speaker 4>looking back.

414
00:25:36.119 --> 00:25:39.640
<v Speaker 3>A hundred things, one hundred things, like I think I

415
00:25:39.640 --> 00:25:43.240
<v Speaker 3>have every day. I have like a list with things

416
00:25:43.240 --> 00:25:48.119
<v Speaker 3>which I would do differently, little beaches, personal habits or

417
00:25:48.400 --> 00:25:50.720
<v Speaker 3>especially in the in the startup, like with some of

418
00:25:50.880 --> 00:25:54.400
<v Speaker 3>how we set up the legal stuff during the beginning,

419
00:25:54.440 --> 00:25:59.079
<v Speaker 3>we didn't have the best thing and then like no

420
00:25:59.200 --> 00:26:02.960
<v Speaker 3>way are really looking okay with what people you start

421
00:26:03.000 --> 00:26:07.640
<v Speaker 3>the company so you fully fully trust them, and thats

422
00:26:07.720 --> 00:26:11.319
<v Speaker 3>a I think a long long list with things that

423
00:26:11.359 --> 00:26:14.720
<v Speaker 3>would I've just learned on the on the goal. And

424
00:26:14.799 --> 00:26:18.440
<v Speaker 3>I think that's also completely fine because now I've learned

425
00:26:18.440 --> 00:26:18.920
<v Speaker 3>that stuff.

426
00:26:19.759 --> 00:26:20.319
<v Speaker 4>Who were the.

427
00:26:22.279 --> 00:26:23.880
<v Speaker 2>Yeah, I was gonna say, who are some of the

428
00:26:23.920 --> 00:26:26.000
<v Speaker 2>first people you told about, like, Hey, I'm going to

429
00:26:26.079 --> 00:26:28.160
<v Speaker 2>start this up, this is an idea I'm going to

430
00:26:28.200 --> 00:26:34.480
<v Speaker 2>take forward.

431
00:26:33.000 --> 00:26:36.000
<v Speaker 3>The first people which I told this to. That's a

432
00:26:36.000 --> 00:26:41.880
<v Speaker 3>good question. I don't remember who was like their first one.

433
00:26:43.119 --> 00:26:46.319
<v Speaker 3>I think there's problem. This is in my brain alia

434
00:26:46.480 --> 00:26:49.599
<v Speaker 3>for such a long time, and I thought about, okay,

435
00:26:49.599 --> 00:26:54.039
<v Speaker 3>how to solve this, and then it just happened somehow,

436
00:26:54.119 --> 00:26:58.519
<v Speaker 3>and then I was just on it, just I guess

437
00:26:58.519 --> 00:27:01.119
<v Speaker 3>friends around me. But it wasn't like hey, I'm now

438
00:27:01.160 --> 00:27:04.480
<v Speaker 3>an entrepreneur or how I have now a startup. It

439
00:27:04.519 --> 00:27:07.119
<v Speaker 3>was never like this. It was more like, in the beginning,

440
00:27:07.200 --> 00:27:10.880
<v Speaker 3>like a side project which we started, and then I

441
00:27:10.960 --> 00:27:15.400
<v Speaker 3>got more and more and more. That's a good question.

442
00:27:17.640 --> 00:27:21.279
<v Speaker 4>It's a given way. You are magnus with green Way.

443
00:27:22.200 --> 00:27:27.599
<v Speaker 4>What are some of your current challenges? What what can

444
00:27:27.720 --> 00:27:31.400
<v Speaker 4>people in the community who are listening to this approach

445
00:27:31.480 --> 00:27:35.200
<v Speaker 4>you with for help and growth and whatnot? So any

446
00:27:35.240 --> 00:27:38.079
<v Speaker 4>anything you want to ask from the community listening.

447
00:27:41.519 --> 00:27:45.559
<v Speaker 3>Yeah, so, as a young startup, you what I think

448
00:27:45.599 --> 00:27:49.839
<v Speaker 3>someone also learned this. Every startup has assumptions which it

449
00:27:49.920 --> 00:27:54.559
<v Speaker 3>needs to valudate before it finds product market fit. And

450
00:27:54.799 --> 00:27:58.279
<v Speaker 3>for someone in our case, the assumptions, Okay, our city

451
00:27:58.319 --> 00:28:01.559
<v Speaker 3>is really willing to pay x amount of money for

452
00:28:01.880 --> 00:28:07.599
<v Speaker 3>our solution. Is our solution really gonna work scalable in cities?

453
00:28:08.279 --> 00:28:11.519
<v Speaker 3>And so we have a couple of assumptions, like seven

454
00:28:11.519 --> 00:28:15.920
<v Speaker 3>assumptions which we need to validate. And I would say

455
00:28:15.920 --> 00:28:18.440
<v Speaker 3>one of the biggest hurdles now Bottle makes, which we

456
00:28:18.519 --> 00:28:21.200
<v Speaker 3>need to overcome as fast as possible, is just to

457
00:28:21.240 --> 00:28:26.079
<v Speaker 3>demonstrate our solution and as many cities as possible. And

458
00:28:26.079 --> 00:28:29.240
<v Speaker 3>we are right now starting in Ostabrook, the first Chiland

459
00:28:29.519 --> 00:28:33.400
<v Speaker 3>in Germany. But if anywhere around the world, you know,

460
00:28:34.480 --> 00:28:38.079
<v Speaker 3>like cities which are innovative for me, even have contacts

461
00:28:38.720 --> 00:28:41.759
<v Speaker 3>which could be interested, or you just want our solution

462
00:28:41.839 --> 00:28:44.559
<v Speaker 3>in your city because you're frustrated about the traffic lights,

463
00:28:45.039 --> 00:28:49.599
<v Speaker 3>then I'm super happy to connect to and yeah, solve

464
00:28:49.680 --> 00:28:50.160
<v Speaker 3>this problem.

465
00:28:50.359 --> 00:28:53.480
<v Speaker 4>And in terms of where you are with the solution itself,

466
00:28:53.519 --> 00:28:56.400
<v Speaker 4>I mean the solution is ready to go. You've written

467
00:28:56.440 --> 00:29:00.079
<v Speaker 4>the code, it's been tested and good to go to

468
00:29:00.119 --> 00:29:03.599
<v Speaker 4>we say uh, do a pilot in a city, Is

469
00:29:04.200 --> 00:29:07.200
<v Speaker 4>that what you'd say? I guess.

470
00:29:08.880 --> 00:29:13.440
<v Speaker 3>So ouri model definitely works to optimize traffic lights in

471
00:29:13.480 --> 00:29:19.240
<v Speaker 3>the simulation, so broot type is demonstrated. But of course

472
00:29:19.319 --> 00:29:21.640
<v Speaker 3>the integration through the real world, that's what we are

473
00:29:21.720 --> 00:29:24.720
<v Speaker 3>right now doing in the in the first city in Ostabrook.

474
00:29:25.279 --> 00:29:28.720
<v Speaker 3>That's a challenge where we will definitely change and a

475
00:29:28.759 --> 00:29:34.920
<v Speaker 3>lot in the and our pipeline, our network. But yeah,

476
00:29:35.319 --> 00:29:38.759
<v Speaker 3>especially doing the next three months, we will be robuster

477
00:29:38.880 --> 00:29:42.759
<v Speaker 3>and robuster and you know, as a startup beginning to

478
00:29:42.799 --> 00:29:45.799
<v Speaker 3>start to hack something together. But as soon as you're done,

479
00:29:46.039 --> 00:29:49.000
<v Speaker 3>more growing business hundred percent sure in two years we

480
00:29:49.039 --> 00:29:52.640
<v Speaker 3>will need to rewrite our whole code and our whole

481
00:29:52.759 --> 00:29:57.079
<v Speaker 3>pipeline to make it more more robust and more scalable.

482
00:29:57.160 --> 00:29:59.480
<v Speaker 3>But that's that's right now, not the not the goal.

483
00:29:59.759 --> 00:30:01.799
<v Speaker 4>How big is a team right now? Are you a

484
00:30:01.839 --> 00:30:06.519
<v Speaker 4>one man army Magnus or who else is helping you

485
00:30:06.599 --> 00:30:07.279
<v Speaker 4>with this right now?

486
00:30:10.200 --> 00:30:17.920
<v Speaker 3>Yes? So to other co founders who work on this.

487
00:30:18.480 --> 00:30:22.039
<v Speaker 3>We have an advisor from really clever guy from from

488
00:30:22.079 --> 00:30:25.000
<v Speaker 3>Google who gives us much advice on how to set

489
00:30:25.039 --> 00:30:29.559
<v Speaker 3>up our pipeline, how to build like really good models

490
00:30:29.559 --> 00:30:33.680
<v Speaker 3>which can process in the right direction. And if you

491
00:30:33.759 --> 00:30:35.839
<v Speaker 3>get this grand it's right now. I'm supposed to start

492
00:30:35.880 --> 00:30:39.680
<v Speaker 3>in October. Then we have like a plan with to

493
00:30:39.799 --> 00:30:42.799
<v Speaker 3>eight other people which we will hire to tackle this problem.

494
00:30:42.880 --> 00:30:45.640
<v Speaker 4>Awesome. So you once you get the funding in, I mean,

495
00:30:46.359 --> 00:30:48.960
<v Speaker 4>you are going to bring in some more smart, smart

496
00:30:49.000 --> 00:30:52.880
<v Speaker 4>people with that funding to make this better. So hiring

497
00:30:52.960 --> 00:30:55.839
<v Speaker 4>is on the horizon. That's that's cool. And I forgot

498
00:30:55.839 --> 00:30:58.640
<v Speaker 4>to ask, I mean, since you mentioned model intermined me.

499
00:30:58.759 --> 00:31:01.960
<v Speaker 4>So are these more is your own custom models magnets?

500
00:31:01.960 --> 00:31:05.000
<v Speaker 4>Are you using any of your any of the open

501
00:31:05.000 --> 00:31:09.160
<v Speaker 4>source models out there for to run your data and

502
00:31:09.240 --> 00:31:09.759
<v Speaker 4>all of that?

503
00:31:12.839 --> 00:31:17.920
<v Speaker 3>Okay, this is all custom models. We tried many different

504
00:31:18.000 --> 00:31:22.960
<v Speaker 3>architectures from graphel networks to transformers, but yeah, the whole

505
00:31:22.960 --> 00:31:27.759
<v Speaker 3>pipeline is all custom a custom made for this problem.

506
00:31:28.279 --> 00:31:30.839
<v Speaker 3>Is also not that they are like some some large

507
00:31:30.920 --> 00:31:34.759
<v Speaker 3>language models which you know, we know from GVTS or

508
00:31:35.160 --> 00:31:37.359
<v Speaker 3>Lama model which you can just throw at that problem.

509
00:31:37.440 --> 00:31:40.240
<v Speaker 3>It's like more problem where you have to get to

510
00:31:40.279 --> 00:31:41.119
<v Speaker 3>custom development.

511
00:31:42.920 --> 00:31:45.079
<v Speaker 4>Do you want to wrap it up? Sorry, if you

512
00:31:45.119 --> 00:31:46.440
<v Speaker 4>have any other questions to go for it.

513
00:31:46.920 --> 00:31:49.440
<v Speaker 2>You can wrap it up with no, I think I

514
00:31:49.480 --> 00:31:50.960
<v Speaker 2>think this is good Nanos.

515
00:31:51.319 --> 00:31:52.680
<v Speaker 1>Thank you so much for taking the time.

516
00:31:52.799 --> 00:31:56.799
<v Speaker 2>I like you're really humble, and your like ingenuity here

517
00:31:57.039 --> 00:31:59.440
<v Speaker 2>is at display. So we wish you good luck with

518
00:31:59.839 --> 00:32:02.079
<v Speaker 2>all this. It looks like plan.

519
00:32:02.839 --> 00:32:04.880
<v Speaker 1>And then again, thank you for taking the time.

520
00:32:09.039 --> 00:32:12.480
<v Speaker 3>Thank you very much for all your questions and also

521
00:32:12.519 --> 00:32:15.319
<v Speaker 3>your interesting parts on on the safety aspect of it.

522
00:32:15.960 --> 00:32:19.960
<v Speaker 3>Really really looking forward to solving this problem together.

523
00:32:20.759 --> 00:32:22.960
<v Speaker 4>All the best Magnets. We'll stay in touch and then

524
00:32:23.000 --> 00:32:25.559
<v Speaker 4>what we'll do is we'll publish all the details of

525
00:32:25.559 --> 00:32:29.839
<v Speaker 4>your website and your email and everything when the episode

526
00:32:29.960 --> 00:32:32.559
<v Speaker 4>goes out so people can reach out to you directly.

527
00:32:32.599 --> 00:32:33.680
<v Speaker 4>Thanks so much, Magnus.

528
00:32:35.000 --> 00:32:53.559
<v Speaker 3>Thank you, Bye Mae.
