1
00:00:01,920 --> 00:00:05,320
Hey everybody, welcome back to 
the Elon Musk Podcast. 

2
00:00:05,400 --> 00:00:08,720
This is a show where we discuss 
the critical crossroads that 

3
00:00:08,720 --> 00:00:13,560
shape SpaceX, Tesla X, The 
Boring Company, and Neurolink. 

4
00:00:13,880 --> 00:00:21,320
I'm your host, Will Walden. 
What if ChatGPT could become 

5
00:00:21,320 --> 00:00:25,080
your personal agent and 
independently complete your 

6
00:00:25,080 --> 00:00:28,400
daily tasks without your direct 
guidance? 

7
00:00:29,360 --> 00:00:34,080
So on Wednesday, Open AI 
unveiled a new ChatGPT feature 

8
00:00:34,080 --> 00:00:37,400
called Agent, designed 
specifically to autonomously 

9
00:00:37,400 --> 00:00:41,400
carry out tasks on behalf of 
you, its user. 

10
00:00:41,800 --> 00:00:44,160
Moving beyond simple chat bot 
conversations. 

11
00:00:44,440 --> 00:00:47,560
And Open AI released the Agent 
function officially after months

12
00:00:47,560 --> 00:00:51,840
of internal testing and testing 
with users on a very short list.

13
00:00:52,480 --> 00:00:56,320
And now they aim to push AI 
capabilities towards performing 

14
00:00:56,320 --> 00:01:00,160
real world actions without 
continuous human oversight. 

15
00:01:01,160 --> 00:01:06,440
Now this agent is really cool it
it lets users delegate complex 

16
00:01:06,440 --> 00:01:11,680
multi step tasks directly to 
ChatGPT, such as booking travel 

17
00:01:11,680 --> 00:01:15,680
reservations, conducting 
detailed research, or managing 

18
00:01:15,720 --> 00:01:19,640
personal scheduling. 
Now once given a task, the agent

19
00:01:19,640 --> 00:01:23,000
navigates multiple websites, 
gathers relevant information, 

20
00:01:23,360 --> 00:01:26,680
makes decisions and completes 
actions online independently. 

21
00:01:27,120 --> 00:01:31,640
For example, a user might 
instruct the agent to plan a 

22
00:01:31,640 --> 00:01:35,520
weekend trip to San Francisco 
and it would book the best rated

23
00:01:35,520 --> 00:01:39,680
flights, hotels, and activities 
entirely without user 

24
00:01:39,680 --> 00:01:42,400
intervention beyond the initial 
request. 

25
00:01:43,040 --> 00:01:46,040
Now what you could do is you 
could tell it what airline you 

26
00:01:46,040 --> 00:01:50,520
would like to use, what your 
price race, what your price 

27
00:01:50,520 --> 00:01:54,640
range is for your flight in your
hotel and how much money you can

28
00:01:54,640 --> 00:01:57,000
spend on your activities and 
what kind of activities you 

29
00:01:57,000 --> 00:02:00,560
like. 
And it will search for all of 

30
00:02:00,560 --> 00:02:06,040
that for you without any 
intervention beyond the initial 

31
00:02:06,040 --> 00:02:08,720
prompt. 
Now, Open AI designed the agent 

32
00:02:08,919 --> 00:02:11,440
to understand the user's 
preferences and to act 

33
00:02:11,440 --> 00:02:14,800
accordingly, refining its 
actions over time by analyzing 

34
00:02:14,800 --> 00:02:18,000
past interactions with you. 
Now, this personalization allows

35
00:02:18,000 --> 00:02:20,960
it to better anticipate 
individual users needs, 

36
00:02:21,000 --> 00:02:24,200
selecting choices closely 
aligned with specific habits 

37
00:02:24,200 --> 00:02:26,920
that you have, and also your 
tastes. 

38
00:02:27,320 --> 00:02:30,480
How the agent's effectiveness 
depends on its ability to 

39
00:02:30,480 --> 00:02:33,800
continuously learn from each 
action, gradually reducing the 

40
00:02:33,800 --> 00:02:41,120
need for explicit instructions. 
So if ChatGPT sends you an 

41
00:02:41,120 --> 00:02:43,720
airline that's a little bit out 
of your price range for the 

42
00:02:43,720 --> 00:02:47,680
flight, then you can go back and
you can prompt it again and say 

43
00:02:47,840 --> 00:02:50,400
that flight was a little bit too
expensive. 

44
00:02:50,440 --> 00:02:52,960
Please find me one that's less 
expensive. 

45
00:02:52,960 --> 00:02:58,760
Here's my price range now. 
Also, if they book you on trips 

46
00:02:59,480 --> 00:03:02,600
and you don't like the 
activities that they assigned 

47
00:03:02,600 --> 00:03:05,960
for you or they want you to do, 
then of course you can tell them

48
00:03:06,000 --> 00:03:09,320
you don't like it. 
It's like having literally a 

49
00:03:09,320 --> 00:03:12,800
personal assistant right in the 
palm of your hand, right in your

50
00:03:12,800 --> 00:03:16,600
phone, which is incredible. 
I remember, OK, so this is kind 

51
00:03:16,600 --> 00:03:20,520
of dating me, but my mom and I 
used to go to the travel agent 

52
00:03:20,520 --> 00:03:23,480
in town. 
This is before the Internet was 

53
00:03:23,480 --> 00:03:25,720
even a thing. 
There were things called travel 

54
00:03:25,720 --> 00:03:28,000
agents. 
There was no Google Flights. 

55
00:03:28,000 --> 00:03:30,800
There was no like just Google a 
trip that you want to do. 

56
00:03:32,080 --> 00:03:36,080
You'd have to go into an office.
And these services are still 

57
00:03:36,080 --> 00:03:39,280
available, but it's, you know, 
it's like you pay extra for it 

58
00:03:39,800 --> 00:03:42,960
and it's not democratized like 
flights are now. 

59
00:03:43,360 --> 00:03:46,840
But you'd go into an office and 
you'd talk to somebody and you 

60
00:03:46,840 --> 00:03:49,080
tell them where you want to go 
one time. 

61
00:03:49,080 --> 00:03:52,440
You want to go to Niagara Falls?
This is a real world example. 

62
00:03:52,440 --> 00:03:54,280
We had to go to. 
We want to go to Niagara Falls. 

63
00:03:54,280 --> 00:03:56,720
My mom and dad hadn't been there
in 10 years. 

64
00:03:56,720 --> 00:03:58,200
They didn't really know what to 
do. 

65
00:03:58,440 --> 00:04:01,160
There's no Internet, so you 
don't know what's there right 

66
00:04:01,160 --> 00:04:03,920
now. 
And we lived 3 or 4 hours away 

67
00:04:03,920 --> 00:04:07,680
from Niagara Falls, so we didn't
really know what to do. 

68
00:04:07,680 --> 00:04:11,080
We didn't know where to look. 
So we went to a travel agent and

69
00:04:11,080 --> 00:04:13,240
we told the travel agent what 
our budget was. 

70
00:04:13,680 --> 00:04:15,240
I remember the lady was very 
nice. 

71
00:04:16,519 --> 00:04:19,920
She complimented me on my 
Montego Bay T-shirt that I had 

72
00:04:19,920 --> 00:04:24,120
when I was a kid, which I bought
not in Montego Bay, but at a 

73
00:04:24,120 --> 00:04:27,800
department store in town. 
And she was very courteous. 

74
00:04:27,800 --> 00:04:31,880
She gave us maps. 
She, which is incredible as 

75
00:04:31,880 --> 00:04:34,080
well, like a paper map. 
And you have to, you know, you 

76
00:04:34,080 --> 00:04:36,920
unfolded it. 
And she told us, you know, you 

77
00:04:36,920 --> 00:04:38,600
shouldn't fly. 
You should probably drive there 

78
00:04:38,600 --> 00:04:41,240
because it's cheaper to drive. 
And here's a map. 

79
00:04:41,240 --> 00:04:45,720
Can your car make it there? 
And my mom said, yeah, of course

80
00:04:45,720 --> 00:04:48,600
I can. 
So she gave us a map, told us 

81
00:04:48,600 --> 00:04:52,120
along the way, she circled 
things along the way, like, you 

82
00:04:52,120 --> 00:04:53,880
want to stop here? 
You want to stop, you know, 

83
00:04:53,880 --> 00:04:57,080
these 5 or 6 different places, 
Here's a great place to eat. 

84
00:04:57,080 --> 00:04:59,080
You know, you're going to have 
three kids in the car. 

85
00:04:59,080 --> 00:05:00,400
They're going to be bathroom 
breaks. 

86
00:05:00,400 --> 00:05:04,840
So within the first two hours, 
like, pull over here, go, you 

87
00:05:04,840 --> 00:05:06,680
know, go get McDonald's or 
whatever it was. 

88
00:05:07,600 --> 00:05:11,920
But sure enough, after that 
interaction was done, my mom had

89
00:05:11,920 --> 00:05:17,840
a whole plan for the trip to 
Niagara Falls. 4 hours there, 4 

90
00:05:17,840 --> 00:05:20,280
hours home, things to do In 
between. 

91
00:05:20,280 --> 00:05:23,680
We went to the Ripley's Believe 
It or Not museum, which had a 

92
00:05:24,040 --> 00:05:26,760
bunch of like really interesting
crazy stuff. 

93
00:05:27,160 --> 00:05:29,200
I remember that and I was a 
little kid, so I can still 

94
00:05:29,200 --> 00:05:32,360
remember this vividly. 
There's a wax museum we went to 

95
00:05:32,360 --> 00:05:37,640
and there's like a like a, a 
restaurant that was, I think it 

96
00:05:37,640 --> 00:05:39,920
was sort of like a Space Needle 
kind of thing, like a Seattle 

97
00:05:39,920 --> 00:05:41,520
Space Needle. 
I can't really remember exactly 

98
00:05:41,520 --> 00:05:46,800
what it was, but I remember we 
did that cool trip and when my 

99
00:05:46,800 --> 00:05:51,240
mom got back, she was very 
excited that everything was 

100
00:05:51,240 --> 00:05:53,600
taken care of. 
The travel agent had booked a 

101
00:05:53,600 --> 00:05:55,960
hotel for us. 
The travel agent had booked a 

102
00:05:55,960 --> 00:05:58,880
restaurant for us that night 
when we got into town. 

103
00:05:58,880 --> 00:06:04,280
When we got in Niagara Falls, 
they also booked us reservations

104
00:06:04,280 --> 00:06:06,920
for some of the attractions, 
which is really cool. 

105
00:06:07,160 --> 00:06:12,200
And this is what Open AI does 
with the, with this new agent 

106
00:06:12,200 --> 00:06:14,320
thing. 
It's not just for trips, though.

107
00:06:14,320 --> 00:06:16,400
You can have it do whatever you 
want it to do. 

108
00:06:16,920 --> 00:06:19,200
You know, trips are just one of 
the things that it can do. 

109
00:06:20,040 --> 00:06:24,880
You can, you can instruct it to 
do anything for you, anything 

110
00:06:24,880 --> 00:06:26,600
like a personal assistant would 
do for you. 

111
00:06:27,520 --> 00:06:30,360
So if you need to make 
appointments, you know, I have 

112
00:06:30,440 --> 00:06:34,720
a, here's my, here's my doctor's
appointment coming up. 

113
00:06:35,720 --> 00:06:38,000
You know, I need to get, I need 
to book a doctor's appointment. 

114
00:06:38,480 --> 00:06:40,880
Can you see if it's available or
something like that? 

115
00:06:40,960 --> 00:06:45,120
And they would contact the 
doctor's office for you through 

116
00:06:45,120 --> 00:06:47,880
the contact form or maybe even 
do a call eventually. 

117
00:06:47,880 --> 00:06:50,800
I'm not sure if they could do 
phone calls yet, but possibly. 

118
00:06:52,040 --> 00:06:53,920
But those things are in the 
future. 

119
00:06:54,040 --> 00:06:58,680
I'm sure this is going to be a 
breakthrough product for Open 

120
00:06:58,680 --> 00:07:02,400
AI. 
Now, this functionality requires

121
00:07:02,400 --> 00:07:05,200
integrating ChatGPT with 
external services. 

122
00:07:05,400 --> 00:07:08,400
Services though, leverages 
application programming 

123
00:07:08,400 --> 00:07:12,560
interfaces, which are APIs to 
interact directly with other 

124
00:07:12,560 --> 00:07:16,840
apps and platforms. 
Now Open AI had to establish 

125
00:07:16,840 --> 00:07:20,480
partnerships with major travel 
sites, booking services, 

126
00:07:20,480 --> 00:07:23,680
productivity platforms, and also
financial tools. 

127
00:07:24,120 --> 00:07:27,520
And these integrations enable 
the agent to execute tests 

128
00:07:27,520 --> 00:07:32,120
seamlessly, automating processes
that previously required manual 

129
00:07:32,120 --> 00:07:35,160
operations by users. 
So in the morning, if you wake 

130
00:07:35,160 --> 00:07:37,920
up, you can just give it a 
prompt like, hey, I'm I need to 

131
00:07:37,920 --> 00:07:48,040
rent a house in Atlanta, GA 
September 15th through the 30th 

132
00:07:48,040 --> 00:07:51,040
because I'm just going to stay 
there for a couple weeks and I 

133
00:07:51,040 --> 00:07:54,920
just want a house to stay at. 
Go find me a house to rent and 

134
00:07:54,920 --> 00:07:59,760
ChatGPT can find you that house 
and also give you the 

135
00:07:59,760 --> 00:08:02,160
information about which house 
you know. 

136
00:08:02,160 --> 00:08:04,720
Send you back some links and let
you know which one is the best 

137
00:08:04,720 --> 00:08:06,480
option for you and for your 
taste. 

138
00:08:07,080 --> 00:08:11,360
Pretty impressive so far. 
So they have to have security 

139
00:08:11,360 --> 00:08:14,240
and privacy. 
It's a major focus right now 

140
00:08:14,240 --> 00:08:15,960
during the agents development 
phase. 

141
00:08:16,480 --> 00:08:20,720
And this is all sensitive 
automated actions with personal 

142
00:08:20,720 --> 00:08:23,680
data. 
Opening Eye implemented strict 

143
00:08:23,680 --> 00:08:26,280
guidelines for this though, and 
there's technical safeguards to 

144
00:08:26,280 --> 00:08:30,000
protect user information, 
employing encryption and 

145
00:08:30,000 --> 00:08:33,120
rigorous data protection 
standards to achieve this. 

146
00:08:33,400 --> 00:08:36,960
The company is transparent about
this. 

147
00:08:37,840 --> 00:08:40,400
They tell you all the 
information that's collected and

148
00:08:40,400 --> 00:08:44,480
they clearly explain how and why
user data is stored, accessed, 

149
00:08:44,600 --> 00:08:47,600
and utilized during these 
automated tasks. 

150
00:08:48,640 --> 00:08:51,200
Now to facilitate the 
responsible use, Open AI 

151
00:08:51,200 --> 00:08:54,680
designed built in boundaries, 
restricting agent functionality 

152
00:08:54,680 --> 00:08:56,720
and sensitive or high risk 
scenarios. 

153
00:08:57,240 --> 00:09:00,640
These built in constraints 
prevent unauthorized purchases 

154
00:09:00,640 --> 00:09:05,080
of transactions above predefined
limits without additional user 

155
00:09:05,080 --> 00:09:07,800
verification. 
The users retained full 

156
00:09:07,800 --> 00:09:11,240
visibility over the agent's 
activity while it's happening, 

157
00:09:11,760 --> 00:09:15,040
and they received regular 
summaries detailing actions 

158
00:09:15,040 --> 00:09:18,000
completed and decisions that 
were made by the agent. 

159
00:09:18,800 --> 00:09:23,000
So unlike a person, that's your 
agent who probably doesn't check

160
00:09:23,000 --> 00:09:26,800
in all the time, open AI, 
enchant GPT, check in with you 

161
00:09:27,160 --> 00:09:29,640
after every part of the task, 
which is really great. 

162
00:09:29,640 --> 00:09:34,280
And you can tell them along the 
way, you know, if if you don't 

163
00:09:34,280 --> 00:09:36,480
like a part of what they're 
doing, and then you can tell 

164
00:09:36,480 --> 00:09:38,920
them to stop. 
Now there's challenges though, 

165
00:09:38,920 --> 00:09:42,840
on potential criticisms 
concerning automated decision 

166
00:09:42,840 --> 00:09:47,960
making. 
So the accuracy of some of the 

167
00:09:47,960 --> 00:09:51,040
things that they're going to 
come up with right off the bat, 

168
00:09:51,040 --> 00:09:53,720
probably not going to be great, 
probably going to be pretty good

169
00:09:54,080 --> 00:09:55,880
and probably going to point you 
in the right direction. 

170
00:09:56,520 --> 00:10:00,160
And then you can tweak it in the
appropriateness of the agents 

171
00:10:00,160 --> 00:10:03,200
independent actions as well. 
So you have to be careful about 

172
00:10:03,960 --> 00:10:06,680
how you prompt this thing 
because if you say, I just want 

173
00:10:06,680 --> 00:10:10,360
to stay in a place that's under 
$300, it's going to send you 

174
00:10:10,360 --> 00:10:15,720
every motel, then hotel under 
$300.00 for per night. 

175
00:10:17,280 --> 00:10:20,600
So, you know, that's then you're
gonna have a huge list of like 

176
00:10:21,160 --> 00:10:25,080
roadside motels that are, you 
know, paid by the hour, which 

177
00:10:25,080 --> 00:10:26,880
wink, wink, you know what those 
kind are. 

178
00:10:27,240 --> 00:10:30,160
And also, you know, paid by the 
night and they're $70.00. 

179
00:10:30,160 --> 00:10:33,440
But like, they might not be the 
best place for you and your kids

180
00:10:33,440 --> 00:10:37,720
to be. 
So ChatGPT, like you got to be 

181
00:10:37,720 --> 00:10:41,680
accurate and appropriate with 
your prompting as you tell 

182
00:10:41,680 --> 00:10:45,520
ChatGPT and the agent what to 
search for. 

183
00:10:45,840 --> 00:10:48,880
That's what we have to be really
careful about, South. 

184
00:10:49,040 --> 00:10:50,440
Don't be broad with your 
statements. 

185
00:10:50,960 --> 00:10:55,400
Be very analytical with them and
give them absolutely everything 

186
00:10:55,400 --> 00:10:59,000
that you can think of, and then 
they'll do the actual work for 

187
00:10:59,000 --> 00:11:00,680
you. 
I'm going to test it out and 

188
00:11:00,680 --> 00:11:04,200
I'll come back with some more 
information for you on the next 

189
00:11:04,200 --> 00:11:06,400
episode, which will be dropping 
later today. 

190
00:11:06,880 --> 00:11:09,280
So please stay tuned for that. 
I'm going to go over the whole 

191
00:11:09,280 --> 00:11:14,280
thing and I'm going to work out 
the agent workflow as much as 

192
00:11:14,280 --> 00:11:16,560
possible and I'll let you know 
how that all works out. 

193
00:11:17,280 --> 00:11:18,720
So thank you so much for 
listening. 

194
00:11:18,760 --> 00:11:23,120
I have one ask of you, actually,
I asked this yesterday, but I 

195
00:11:23,120 --> 00:11:24,880
never really ask for these kind 
of things. 

196
00:11:24,880 --> 00:11:27,440
I usually do it like once a week
just because I don't want to 

197
00:11:27,440 --> 00:11:28,920
really. 
I don't really want to get into 

198
00:11:28,920 --> 00:11:33,760
it too much, but I've been doing
this show, I think we're at 900 

199
00:11:33,760 --> 00:11:36,160
episodes, something like that. 
Some ridiculous amount of 

200
00:11:36,160 --> 00:11:37,640
episodes. 
I've been doing it for like 4 

201
00:11:37,640 --> 00:11:40,720
years and in those four years I 
haven't really asked for 

202
00:11:40,720 --> 00:11:43,040
anything. 
I've never, you know, maybe 

203
00:11:43,040 --> 00:11:46,600
Patreon here and there or you 
know, follow the channel, 

204
00:11:47,400 --> 00:11:50,120
something like that. 
But I continue to do it every 

205
00:11:50,120 --> 00:11:55,240
morning, drop episodes every 
morning at 4:30 AM EST. 

206
00:11:56,000 --> 00:11:59,040
And I just need a favor from 
you. 

207
00:11:59,520 --> 00:12:01,680
If you could hit the follow or 
the subscribe button, that would

208
00:12:01,680 --> 00:12:04,000
be great. 
That's one favor I need to ask. 

209
00:12:04,000 --> 00:12:07,840
2 favors actually, and that'll 
only take you a second, but the 

210
00:12:07,840 --> 00:12:12,200
channel is in this. 
This show is in dire need of 

211
00:12:12,200 --> 00:12:16,880
some financial backing and I'm 
going to ask this one more time 

212
00:12:16,880 --> 00:12:18,960
this week and this is the final 
time I'm going to ask this week.

213
00:12:20,480 --> 00:12:27,480
If you have Venmo and you can 
send anything at all to Will Wil

214
00:12:27,560 --> 00:12:32,320
Dash WALDON help support the 
show. 

215
00:12:32,320 --> 00:12:37,600
It goes directly into all of my 
costs for the show and it's been

216
00:12:37,600 --> 00:12:41,200
really helpful. 
A few people have done it and I 

217
00:12:41,200 --> 00:12:45,400
want to give them shout outs 
because I told them I would last

218
00:12:45,400 --> 00:12:48,800
time I did this and I didn't do 
it yesterday. 

219
00:12:48,800 --> 00:12:50,160
So I feel kind of bad about 
that. 

220
00:12:51,440 --> 00:13:01,160
But you know, I had JW again 
with another $5 donation, have 

221
00:13:01,160 --> 00:13:12,040
JS with A10, we have MH with 50,
BSI can't say the full names, 

222
00:13:12,040 --> 00:13:15,960
but BS with $75. 
Thank you so much for all of 

223
00:13:15,960 --> 00:13:19,240
your donations and all of this 
helps me continue doing the 

224
00:13:19,240 --> 00:13:20,720
show. 
That's all I'm saying. 

225
00:13:20,720 --> 00:13:24,560
I put all my time and effort 
into this and I spend a lot of a

226
00:13:25,360 --> 00:13:29,880
lot of time that I could be 
spending with my family I spent 

227
00:13:29,880 --> 00:13:32,160
doing the show and like getting 
ready for the show. 

228
00:13:32,520 --> 00:13:34,840
So I do sacrifice a lot for the 
show, even though it's only 

229
00:13:34,880 --> 00:13:39,400
around 10 minutes every day. 
So if you're new here, thank you

230
00:13:39,400 --> 00:13:41,600
for listening. 
If you've been here for a while 

231
00:13:41,600 --> 00:13:44,440
and you've heard so many 
episodes, thank you for 

232
00:13:44,440 --> 00:13:46,560
listening as well. 
Thank you for being part of this

233
00:13:46,560 --> 00:13:49,400
great community and thank you to
everybody who's supporting me 

234
00:13:49,800 --> 00:13:51,080
and supporting the show on 
Venmo. 

235
00:13:51,080 --> 00:13:53,160
I really do appreciate you and 
I'm going to find some people 

236
00:13:53,160 --> 00:13:56,640
have been D Ming me and asking 
me to find other ways for them 

237
00:13:56,640 --> 00:13:59,600
to help out, but they because 
they don't have Venmo. 

238
00:13:59,600 --> 00:14:05,280
So I'm going to get I'm going to
get some other apps, cash app, 

239
00:14:05,280 --> 00:14:08,000
etcetera. 
So it can be very helpful that 

240
00:14:08,000 --> 00:14:11,480
way and I'll get it. 
I'll make a website for you so 

241
00:14:11,480 --> 00:14:13,480
you can go visit it and donate 
or whatever. 

242
00:14:14,040 --> 00:14:17,320
So that's it for now, everybody,
thank you so much. 

243
00:14:18,560 --> 00:14:20,280
Hey, thank you so much for 
listening today. 

244
00:14:20,280 --> 00:14:22,320
I really do appreciate your 
support. 

245
00:14:22,320 --> 00:14:25,120
If you could take a second and 
hit the subscribe or the follow 

246
00:14:25,120 --> 00:14:27,320
button on whatever podcast 
platform that you're listening 

247
00:14:27,320 --> 00:14:30,000
on right now, I greatly 
appreciate it. 

248
00:14:30,000 --> 00:14:32,680
It helps out the show 
tremendously and you'll never 

249
00:14:32,680 --> 00:14:35,640
miss an episode. 
And each episode is about 10 

250
00:14:35,640 --> 00:14:38,240
minutes or less to get you 
caught up quickly. 

251
00:14:38,640 --> 00:14:41,400
And please, if you want to 
support the show even more, go 

252
00:14:41,400 --> 00:14:46,680
to patreon.com/stage Zero. 
And please take care of 

253
00:14:46,680 --> 00:14:49,000
yourselves and each other. 
And I'll see you tomorrow.