1
00:00:00,000 --> 00:00:09,920
You've had a dynamic where money has become freer than free.

2
00:00:10,760 --> 00:00:15,680
If you talk about a Fed just gone nuts, all the central banks going nuts.

3
00:00:16,380 --> 00:00:17,860
So it's all acting like safe haven.

4
00:00:18,400 --> 00:00:23,500
I believe that in a world where central bankers are tripping over themselves to devalue their

5
00:00:23,500 --> 00:00:28,480
currency, Bitcoin wins. In the world of fiat currencies, Bitcoin is the victor.

6
00:00:28,480 --> 00:00:31,360
I mean, that's part of the bull case for Bitcoin.

7
00:00:31,800 --> 00:00:34,240
If you're not paying attention, you probably should be.

8
00:00:36,500 --> 00:00:40,760
Vinny, you're a very quick internet celebrity this week.

9
00:00:40,860 --> 00:00:41,540
Welcome to the show.

10
00:00:42,520 --> 00:00:43,540
Yeah, pretty crazy.

11
00:00:44,580 --> 00:00:45,220
I like Mayday.

12
00:00:46,080 --> 00:00:48,060
Thanks for having me, Marty.

13
00:00:48,200 --> 00:00:49,360
It's nice to finally meet you in person.

14
00:00:50,200 --> 00:00:54,980
I'm a subscriber to the TFTC, and I like what you guys do.

15
00:00:55,100 --> 00:00:56,480
So it's cool to be on the show.

16
00:00:56,480 --> 00:01:02,820
So I just like I made a goal to post videos and be more active on Twitter.

17
00:01:02,820 --> 00:01:07,420
And three videos later, I got Jack Dorsey retweeting me.

18
00:01:07,660 --> 00:01:10,380
So that worked out pretty well.

19
00:01:11,020 --> 00:01:12,420
It's pretty, pretty sweet.

20
00:01:12,680 --> 00:01:15,000
And it is a name of the game these days.

21
00:01:15,100 --> 00:01:15,800
Content marketing.

22
00:01:15,980 --> 00:01:17,600
You got to get in it, prove that you know something.

23
00:01:18,300 --> 00:01:19,300
It's tiring sometimes.

24
00:01:20,740 --> 00:01:21,300
Yeah, right.

25
00:01:21,300 --> 00:01:23,380
people beating you to the punch

26
00:01:23,380 --> 00:01:24,380
getting on

27
00:01:24,380 --> 00:01:27,600
getting the people they want on their podcast

28
00:01:27,600 --> 00:01:29,020
before you stuff like that

29
00:01:29,020 --> 00:01:31,740
Greg beat me to the punch this week

30
00:01:31,740 --> 00:01:33,220
but no we had that back and forth

31
00:01:33,220 --> 00:01:35,560
last week when I

32
00:01:35,560 --> 00:01:36,160
think we

33
00:01:36,160 --> 00:01:39,660
we reposted your original video

34
00:01:39,660 --> 00:01:41,320
on Buzz and I quote tweeted about

35
00:01:41,320 --> 00:01:43,460
sort of L402 agentic payments

36
00:01:43,460 --> 00:01:44,740
and imagining that and I think

37
00:01:44,740 --> 00:01:47,680
I think we definitely talk about Buzz

38
00:01:47,680 --> 00:01:49,780
we are going to talk about Buzz

39
00:01:49,780 --> 00:01:50,860
and how it works.

40
00:01:51,080 --> 00:01:52,620
But I think taking a step back

41
00:01:52,620 --> 00:01:56,240
and just thinking about using these agents in general

42
00:01:56,240 --> 00:01:58,400
or using agents, using AI models,

43
00:01:58,820 --> 00:02:02,740
thinking of harnesses, models, agents.

44
00:02:03,380 --> 00:02:05,840
That's where I feel like most people

45
00:02:05,840 --> 00:02:06,960
on the outside looking in,

46
00:02:07,000 --> 00:02:09,240
if you haven't been playing around

47
00:02:09,240 --> 00:02:10,320
with these tools for a lot,

48
00:02:10,380 --> 00:02:11,540
it's all so confusing.

49
00:02:13,340 --> 00:02:15,540
And most people don't know where to start.

50
00:02:15,680 --> 00:02:16,160
And we've started,

51
00:02:16,620 --> 00:02:18,660
we actually launched this TFTC roundtable

52
00:02:18,660 --> 00:02:21,220
where we just have a private group of people.

53
00:02:22,320 --> 00:02:26,380
And we've been playing with this stuff for two years now

54
00:02:26,380 --> 00:02:27,940
with the models at the very least,

55
00:02:28,040 --> 00:02:31,140
but with the harnesses and OpenClaw and Hermes

56
00:02:31,140 --> 00:02:32,180
for the last seven months.

57
00:02:32,480 --> 00:02:34,640
And we're like, okay, we sort of know our way around.

58
00:02:34,800 --> 00:02:36,020
And we're not technical at all.

59
00:02:36,440 --> 00:02:37,960
I know enough to be dangerous,

60
00:02:37,960 --> 00:02:43,100
but certainly wouldn't consider myself a software engineer.

61
00:02:43,460 --> 00:02:46,600
Set up my first VPS in January of this year.

62
00:02:46,600 --> 00:02:55,520
but um i set up my first vps um two weeks ago so and i am a software engineer yeah it's okay

63
00:02:55,520 --> 00:03:00,340
but i'm just usually mostly hosting on cloud providers and stuff like that so

64
00:03:00,340 --> 00:03:05,540
yeah but i mean based off of like our pre-recording like a little powwow there

65
00:03:05,540 --> 00:03:11,640
like how do you view the state of ai and these tools and how to use them and how how people

66
00:03:11,640 --> 00:03:18,240
should be? Well, I think you summed it up pretty well because it's really cool. It's very surprising

67
00:03:18,240 --> 00:03:27,220
to me to see how technical people like you can sound. You guys, you run your business,

68
00:03:27,740 --> 00:03:34,280
you know your workflows, you know how to describe what it is you need. And the agents are able to

69
00:03:34,280 --> 00:03:38,600
give you that stuff. And then you're able to learn very quickly. You don't know the code syntax,

70
00:03:38,600 --> 00:03:42,1000
but you're talking about hosting stuff on virtual private servers and things like that.

71
00:03:43,420 --> 00:03:49,660
It's pretty amazing the technical ability and the level of knowledge that you can attain just by using these tools.

72
00:03:50,080 --> 00:03:52,040
So I think that's where we're at.

73
00:03:52,100 --> 00:03:54,600
I think the playing field is being leveled.

74
00:03:55,160 --> 00:04:01,540
There are definitely the doers and the non-doers, but it's no longer limited by technical ability anymore.

75
00:04:02,840 --> 00:04:04,120
No, it's certainly not.

76
00:04:04,120 --> 00:04:05,160
You just talk to your computer.

77
00:04:05,160 --> 00:04:13,500
That's like another thing that fascinates me is it seems like the form factor or the medium through which we interact with computers is changing.

78
00:04:13,700 --> 00:04:15,800
I mean, that's what software development is, right?

79
00:04:15,840 --> 00:04:18,820
You were talking to your computer, but in a different kind of language, right?

80
00:04:18,900 --> 00:04:20,520
Now you're talking to your computer in English.

81
00:04:21,200 --> 00:04:22,000
So, yeah.

82
00:04:22,460 --> 00:04:22,860
Yeah.

83
00:04:23,380 --> 00:04:28,520
And it's like I'm a huge voice to text maximalist, just option spacebar.

84
00:04:28,720 --> 00:04:30,680
I saw you were demoing Handy.

85
00:04:30,780 --> 00:04:31,680
I use Super Whisper.

86
00:04:32,000 --> 00:04:33,020
I haven't tried Handy yet.

87
00:04:33,020 --> 00:04:40,060
but it looked very similar and what um what are the like how long you've been playing with these

88
00:04:40,060 --> 00:04:46,260
tools like obviously you've been demoing buzz but i imagine i mean you're building wasp um which is

89
00:04:46,260 --> 00:04:52,040
trying to solve one of the pain points of people interacting with these models and these agents

90
00:04:52,040 --> 00:04:59,460
so what's your journey been experimenting with this and yeah so like you said um i'm a founding

91
00:04:59,460 --> 00:05:02,300
developer relations engineer on Wasp.

92
00:05:02,300 --> 00:05:05,700
Wasp team, which is like a full stack framework

93
00:05:05,700 --> 00:05:07,300
that makes it very,

94
00:05:07,300 --> 00:05:21,023
and the easiest way to explain it in this context is that it makes it very easy for humans and agents to build web apps with it Because it just again like we talking about these things are like you know abstraction layers on top of another

95
00:05:21,303 --> 00:05:25,703
So like the way Buzz is an abstraction layer on top of the coding agents.

96
00:05:26,443 --> 00:05:32,823
Wasp is like an abstraction layer on top of the normal tech stack that you would use to build a web app.

97
00:05:32,823 --> 00:05:35,043
But like it's usually all these disjointed parts.

98
00:05:35,043 --> 00:05:39,083
You have to kind of glue them all together yourself or nowadays it's your agent doing it.

99
00:05:39,723 --> 00:05:44,303
But we have this like, you know, configuration file.

100
00:05:44,483 --> 00:05:47,703
It's like a central place where you can just write really simple config.

101
00:05:48,063 --> 00:05:52,903
And then the compiler like Wasp, the framework, puts it all, glues all the pieces together for you.

102
00:05:53,243 --> 00:05:58,443
So it's just like it makes, it does a lot of heavy lifting for you or your agent.

103
00:05:58,483 --> 00:06:03,143
And then makes reviewing and looking at the pieces that have been put together a lot easier

104
00:06:03,143 --> 00:06:06,983
because the code has been reduced to just a few lines of conflict.

105
00:06:06,983 --> 00:06:13,463
So in building WASP, obviously, once these tools start coming out,

106
00:06:13,463 --> 00:06:18,183
you're going to start using them. And when ChatGPT dropped, that was the first thing I did.

107
00:06:18,183 --> 00:06:27,463
I was like, how can I... I'm going to paste in an example of a WASP config file and see if ChatGPT

108
00:06:27,463 --> 00:06:32,183
can do it. And this was back when it was GPT-3. One of my first YouTube videos was

109
00:06:32,183 --> 00:06:38,483
build a full stack app in 10 minutes with ChatGPT and Wasp. And it was just like copying,

110
00:06:38,623 --> 00:06:42,923
pasting stuff back because we didn't have coding agents yet. So that already worked. And I was like,

111
00:06:43,023 --> 00:06:46,643
okay, cool. We're on to something here. This is nice. And then it's also like,

112
00:06:47,123 --> 00:06:53,243
right when the OpenAI API dropped, I was like, oh shit, how can I put this into an app? So

113
00:06:53,243 --> 00:07:00,383
it sounds silly now, but I built an app that was a cover letter generator. It was just a GPT wrapper.

114
00:07:00,383 --> 00:07:04,143
You'll hear people joke about these all the time. Oh, GPT wrappers, bro.

115
00:07:04,143 --> 00:07:11,023
But I made, I don't know, $10,000 off of a GPT wrapper just because I did it first.

116
00:07:11,343 --> 00:07:15,183
I put it on and put it behind Stripe Payments. It's a really shitty app

117
00:07:16,543 --> 00:07:21,263
right when the API dropped. So that's been my journey starting out. I see this stuff and I'm

118
00:07:21,263 --> 00:07:26,063
like, cool, what creative or what cool thing can I try with it? What cool thing can I do with it?

119
00:07:26,063 --> 00:07:32,943
And I take the other road. I'm not one of these workflow freaks where I think everything needs

120
00:07:32,943 --> 00:07:36,863
to be super detailed and stuff. But there's definitely potential in all this stuff. And I

121
00:07:36,863 --> 00:07:45,343
think just testing it out, finding the right way to use it just unlocks a lot of new possibilities

122
00:07:45,343 --> 00:07:55,183
for especially entrepreneurs, like young or people starting out that didn't have access to legal

123
00:07:55,183 --> 00:08:01,263
advice or I don't know, tax advice, you can get really far with that stuff, build a business,

124
00:08:01,723 --> 00:08:06,483
build a product. Or if you have a service business, you can build small software,

125
00:08:06,743 --> 00:08:12,463
personal tools. And it's just like, opens up new worlds and new economies. So I really like

126
00:08:12,463 --> 00:08:17,803
that part of it. I did too. And it's... I mean, if you've been a subscriber,

127
00:08:17,883 --> 00:08:20,883
you've probably heard us talk about it. I mean, we're a team of six here, five or six,

128
00:08:20,883 --> 00:08:26,163
depending on the contractor work that we need on any given month.

129
00:08:26,283 --> 00:08:29,523
But it's insane what we've been able to do.

130
00:08:29,743 --> 00:08:31,383
And I know there's some people listening to this like,

131
00:08:31,443 --> 00:08:32,443
oh, Marty, stop talking to us.

132
00:08:32,503 --> 00:08:34,963
It's like, I'm talking about this so much because I think

133
00:08:34,963 --> 00:08:36,783
if you haven't been playing around with this,

134
00:08:36,823 --> 00:08:40,403
you really need to start doing so.

135
00:08:40,503 --> 00:08:43,323
And I think there's some decision paralysis

136
00:08:43,323 --> 00:08:44,863
because people are like, where do I start?

137
00:08:46,963 --> 00:08:50,863
One of my personal preferences that I really have become

138
00:08:50,863 --> 00:08:57,983
convinced of over the last seven months and i think you sort of would think the same way as why

139
00:08:57,983 --> 00:09:02,583
like buzz is so appealing it's like don't lock yourself into one model provider like i like

140
00:09:02,583 --> 00:09:08,563
having a harness i've been using hermes for many months and before that open claw and i just like

141
00:09:08,563 --> 00:09:14,663
the ability to have the harness which is i view as like the nervous system uh you use the model as

142
00:09:14,663 --> 00:09:20,663
the as like the the agent brain but then like all this exists in the vps that i set up in january

143
00:09:20,663 --> 00:09:31,023
And then that has local file and folder systems that are our company brain that the model, the model can plug into and then send that to the nervous system to get stuff done.

144
00:09:33,163 --> 00:09:40,663
Yep, definitely. Yeah. And I saw that you were talking about how you have all this context built up and these, you know, in Hermes.

145
00:09:41,383 --> 00:09:46,723
And now that you can just plug that into Buzz and share it with other agents is like a huge unlock.

146
00:09:46,723 --> 00:10:00,083
So, I mean, that stuff's really cool. I think openness is... We're starting to see the openness factor of being able to have access to open source models and just choices in the AI ecosystem.

147
00:10:00,083 --> 00:10:07,723
That's becoming more and more important because of whatever top-down policies or government mandates or just...

148
00:10:07,723 --> 00:10:13,163
you know, that stuff might just be too expensive for some kid who wants to get his idea off the ground.

149
00:10:13,423 --> 00:10:18,643
And like, yeah, you got to have access to an open source model, switch it over or use shared compute,

150
00:10:18,883 --> 00:10:30,966
which Buzz has which is really cool feature Go for it Yeah How do you view this closed source frontier open AI Anthropic versus open weight Chinese model

151
00:10:31,946 --> 00:10:40,106
I mean, it's good competition. Let's see where it goes. Cloud code is definitely, I mean,

152
00:10:40,666 --> 00:10:48,066
we have to give a lot of credit to like Anthropic and OpenAI. They've paved the way for sure.

153
00:10:48,066 --> 00:10:55,926
but we see like their response to things is always kind of like take a step back like

154
00:10:55,926 --> 00:11:00,386
serious you guys sure about that like you sure you want to go with that marketing messaging

155
00:11:00,386 --> 00:11:06,506
like I don't know there's always things like that or I'm waiting for them to

156
00:11:06,506 --> 00:11:14,806
I assume that token subsidy is a real thing and that we won't get these prices forever but you

157
00:11:14,806 --> 00:11:19,326
never know because just stuff is progressing so fast so i think it's good it's healthy for the

158
00:11:19,326 --> 00:11:25,206
ecosystem and um i think the other players that are like kind of behind on anthropic they like it

159
00:11:25,206 --> 00:11:29,966
too because it allows them to catch up um so i think it's just interesting to watch i'm just kind

160
00:11:29,966 --> 00:11:37,886
of watching from from the outside using it and um uh yeah just having fun um to kind of like bring

161
00:11:37,886 --> 00:11:43,726
one of your points that you made earlier um about oh shit i lost my train of thought

162
00:11:43,726 --> 00:11:45,726
anyway

163
00:11:45,726 --> 00:11:48,146
I mean we continue

164
00:11:48,146 --> 00:11:50,806
was it like the model like the one thing I agree

165
00:11:50,806 --> 00:11:52,066
I think Anthropic and OpenAI

166
00:11:52,066 --> 00:11:54,006
despite the

167
00:11:54,006 --> 00:11:56,926
their flaws mainly that they're

168
00:11:56,926 --> 00:11:59,406
run by either sociopathic

169
00:11:59,406 --> 00:12:01,006
or effective altruist

170
00:12:01,006 --> 00:12:03,406
they have an effective

171
00:12:03,406 --> 00:12:05,546
altruist at the helm of one and a sociopath

172
00:12:05,546 --> 00:12:06,966
at the helm of the other

173
00:12:06,966 --> 00:12:08,926
it is undeniable that the

174
00:12:08,926 --> 00:12:11,446
models they produced are incredible

175
00:12:11,446 --> 00:12:13,686
and that's what I worry about here in the States

176
00:12:13,686 --> 00:12:19,906
is them really positioning to get a regulatory mode

177
00:12:19,906 --> 00:12:23,426
and getting their way and the government killing the open weight,

178
00:12:23,906 --> 00:12:26,226
the ability of the open weight models to progress.

179
00:12:26,406 --> 00:12:29,626
But cautiously optimistic that we'll avoid that.

180
00:12:29,626 --> 00:12:32,686
But bringing it back is like, again, the harnesses

181
00:12:32,686 --> 00:12:36,066
and the one piece of advice I give to people

182
00:12:36,066 --> 00:12:39,046
who are beginning to play around with this

183
00:12:39,046 --> 00:12:43,566
and set up agentic flows is like, don't get vendor lock in.

184
00:12:43,686 --> 00:12:49,846
Like I haven't opened Codex desktop or Claw desktop in six months.

185
00:12:49,846 --> 00:12:54,726
I've just been interacting predominantly through Telegram with my Hermes agent.

186
00:12:54,906 --> 00:13:00,386
I have a group chat with it with a bunch of different topics and it's represent parallel sessions.

187
00:13:00,706 --> 00:13:02,646
And so it's able to get work done.

188
00:13:02,926 --> 00:13:11,706
And the only time I'll open up Claw or Codex really is if I have to hop in the terminal and debug something, I'll open the CLI directly.

189
00:13:12,706 --> 00:13:12,846
Yep.

190
00:13:13,046 --> 00:13:13,246
Yep.

191
00:13:13,686 --> 00:13:35,046
That makes a lot of sense. And you remind me of what I wanted to say earlier, which was like you said, people have decision paralysis around the stuff. And I think really the important thing is just pick one, start using it. It doesn't really matter which. The same topics, the same things apply to all the others.

192
00:13:35,046 --> 00:13:36,726
So it doesn't really matter which one you start with.

193
00:13:36,846 --> 00:13:44,366
Get your hands on the one that looks good or affordable or fits your philosophy and then just start using it to do stuff.

194
00:13:45,126 --> 00:13:45,266
No.

195
00:13:46,706 --> 00:13:47,926
No, shifting to buzz.

196
00:13:48,066 --> 00:13:52,626
I mean, I think we've both played around with it for the last week.

197
00:13:52,786 --> 00:13:54,306
It's definitely rough around the edges.

198
00:13:54,506 --> 00:13:57,106
Definitely still a prototype, I think.

199
00:13:57,206 --> 00:13:58,926
But last night, it took me a while.

200
00:13:59,766 --> 00:14:01,526
Going back, it took me actually like two days.

201
00:14:01,526 --> 00:14:03,526
I spent like an hour trying to do it.

202
00:14:03,526 --> 00:14:09,386
on Monday and then last night I finally got around to finishing it but like connecting

203
00:14:09,386 --> 00:14:16,846
the Hermes agent to Buzz and getting it um interacting with Fizz uh Bumble and and Honey

204
00:14:16,846 --> 00:14:22,866
the three agents that that Buzz has out of the box and it was pretty crazy and uh for me

205
00:14:22,866 --> 00:14:28,806
it was uh it was a bit of a heavier lift because again I have I have my Hermes agent running in

206
00:14:28,806 --> 00:14:34,446
the VPS. So the way that buzz works, it's running locally on your machine. And so I have Hermes

207
00:14:34,446 --> 00:14:40,806
desktop running locally on the machine too, but I had to SSH into the VPS on Hermes desktop and then

208
00:14:40,806 --> 00:14:47,926
port the, uh, basically like tunneling from buzz on my computer to Hermes on my computer to Hermes

209
00:14:47,926 --> 00:14:52,826
in the cloud. Nobody would know that you're not a software developer talking like that.

210
00:14:52,826 --> 00:15:02,826
No, but somebody probably could have done it in five minutes, but it took me the better part of like three hours over two days to figure it out.

211
00:15:04,026 --> 00:15:04,646
But I did.

212
00:15:04,846 --> 00:15:06,086
Yeah, exactly.

213
00:15:06,086 --> 00:15:13,146
but i think i'd be interested to get your thoughts too i know you explained them on greg's podcast

214
00:15:13,146 --> 00:15:20,046
yesterday but just in your mind compared to just using codex or cloud code or

215
00:15:20,046 --> 00:15:24,686
an agent harness or wasp like how how's buzz different and what is it online

216
00:15:24,686 --> 00:15:31,626
um yeah i think like i said it a few times in like different tweets and stuff that

217
00:15:31,626 --> 00:15:44,309
But I think the Slack killer thing is a nice piece of marketing It a little bit superficial because I don really think that the only thing or even the main thing

218
00:15:44,428 --> 00:15:51,309
I think the main thing, the main drivers behind it is this ability to switch models and harnesses.

219
00:15:51,428 --> 00:15:58,149
And it's like a Trojan horse to get people to switch over to local open source models.

220
00:15:58,149 --> 00:16:03,309
give them the ability to use Claude and Codex, but also to switch to

221
00:16:03,309 --> 00:16:07,309
any other open source model or any other

222
00:16:07,309 --> 00:16:11,329
open source harness like OpenCode or Goose or one of those.

223
00:16:12,149 --> 00:16:15,409
And because if you can look a little bit

224
00:16:15,409 --> 00:16:19,029
around the corner, you can see, I mean, it's not even that hard. Timmy K3 is like

225
00:16:19,029 --> 00:16:23,149
bumping up next to the frontier models for a fraction of the cost.

226
00:16:23,149 --> 00:16:27,149
So it already gives you a perfect avenue to go

227
00:16:27,149 --> 00:16:32,449
that route. So they're kind of like... I see it kind of like a Trojan horse for open source models

228
00:16:32,449 --> 00:16:39,209
and for shared compute. And then further down the line, Bitcoin, Lightning payments,

229
00:16:39,209 --> 00:16:45,569
whether it's agent to agent, human to agent, human to human. My guess is they start small,

230
00:16:46,269 --> 00:16:52,689
early preview, buggy, but they work out the kinks with the users so they know which kinks to really

231
00:16:52,689 --> 00:16:58,029
focus on and then slowly release those underlying features.

232
00:16:58,829 --> 00:17:00,848
And another one of those is Git.

233
00:17:01,229 --> 00:17:04,169
I think they're looking to replace GitHub.

234
00:17:04,488 --> 00:17:07,289
So you've got all this code on GitHub, all your code.

235
00:17:07,289 --> 00:17:10,589
And if it's public, anybody can trade a model on that.

236
00:17:10,769 --> 00:17:16,069
The whole idea is Buzz works like this global context window for you and your community or

237
00:17:16,069 --> 00:17:17,129
your company or whatever.

238
00:17:17,129 --> 00:17:24,968
and then they have under the surface an ability to host your repositories remotely on your VPS or

239
00:17:24,968 --> 00:17:31,488
on your server whichever server that you run whenever your relay is hosted self-hosted so I

240
00:17:31,488 --> 00:17:36,769
see them I see it as being many things more than just a slack killer you know and those are the

241
00:17:36,769 --> 00:17:42,448
directions I can foresee it going in yeah well and I mean you're you seem to be very well versed on

242
00:17:42,448 --> 00:17:44,488
because you've done some videos on Nostra specifically,

243
00:17:44,609 --> 00:17:46,069
but I think Nostra...

244
00:17:46,069 --> 00:17:47,929
I know Nostra's at the core of this

245
00:17:47,929 --> 00:17:50,708
and is somebody who's been a long time Nostra bull.

246
00:17:50,809 --> 00:17:53,728
I think I was probably one of the first 100 people on Nostra.

247
00:17:54,448 --> 00:17:55,409
Maybe first 1,000.

248
00:17:55,609 --> 00:17:57,208
I'd be more confident saying the first 1,000.

249
00:17:57,369 --> 00:17:57,769
So I've been on Nostra since.

250
00:17:57,769 --> 00:17:59,869
When did it launch, actually? Do you remember?

251
00:18:00,869 --> 00:18:01,649
I think 2022.

252
00:18:03,508 --> 00:18:04,649
If I go...

253
00:18:05,389 --> 00:18:06,029
Let me see.

254
00:18:07,289 --> 00:18:09,329
I think I was on it like three months after it.

255
00:18:09,849 --> 00:18:11,689
Or a month after it launched.

256
00:18:11,689 --> 00:18:16,688
it was very it was like a very niche like big not even a bitcoin side project but it was like

257
00:18:16,688 --> 00:18:26,089
a side project a bunch of bitcoin developers worked on i've been on since yeah july wow

258
00:18:26,089 --> 00:18:34,169
it's three days past my fourth noster birthday july 26 2022 um nice nice yeah i got on in 2023

259
00:18:34,169 --> 00:18:39,928
I saw, but I'm not a huge like primal user or a Nostra user.

260
00:18:39,928 --> 00:18:46,228
But that app I was telling you about earlier, the GPT wrapper, I was like, okay, I want

261
00:18:46,228 --> 00:18:48,669
to learn how to use Lightning Payments.

262
00:18:48,669 --> 00:18:52,349
So I put Lightning Auth.

263
00:18:52,349 --> 00:18:54,208
I think it's LN URL Auth in there.

264
00:18:54,208 --> 00:18:55,889
It's been a while since I messed with it.

265
00:18:55,889 --> 00:19:00,609
And I actually got some Lightning Payments for people to generate cover letters.

266
00:19:00,609 --> 00:19:01,928
So that was cool.

267
00:19:01,929 --> 00:19:06,208
That was like, it seems ancient now in AI years.

268
00:19:06,349 --> 00:19:11,049
It was like 2023 or 2024 that I put it up there.

269
00:19:11,869 --> 00:19:12,829
Yeah, so it was pretty funny.

270
00:19:13,789 --> 00:19:17,488
Yeah, but I mean, to your point, like Primal, Domus,

271
00:19:18,968 --> 00:19:20,809
so everybody listening doesn't know what NOSTER is,

272
00:19:20,809 --> 00:19:23,728
notes and other stuff transmitted over relays.

273
00:19:23,849 --> 00:19:25,169
It's a communications protocol.

274
00:19:25,728 --> 00:19:27,688
Very simple in the first.

275
00:19:29,109 --> 00:19:31,708
Predominant use cases or applications built on it

276
00:19:31,708 --> 00:19:33,029
were social media based.

277
00:19:33,468 --> 00:19:34,529
And for the longest time,

278
00:19:35,329 --> 00:19:37,049
Nostra developers and anybody

279
00:19:37,049 --> 00:19:39,448
who's been paying close attention to development,

280
00:19:39,569 --> 00:19:40,988
I think Jack is one of those people.

281
00:19:41,188 --> 00:19:43,329
I've talked with him specifically about this.

282
00:19:44,429 --> 00:19:45,589
Over the years,

283
00:19:46,089 --> 00:19:48,508
social media is just like the tip of the iceberg.

284
00:19:48,748 --> 00:19:52,029
Just this ability to use private public key pairs

285
00:19:52,029 --> 00:19:54,008
to sign events and have cryptographic proof

286
00:19:54,008 --> 00:19:56,389
that something existed at some point in time

287
00:19:56,389 --> 00:19:58,849
in a certain state is very powerful.

288
00:19:59,309 --> 00:20:00,649
And the social media use case,

289
00:20:00,649 --> 00:20:06,129
you can prove that somebody who controlled a private key at this point in time wrote this message

290
00:20:06,129 --> 00:20:09,649
and relate it to the network.

291
00:20:09,769 --> 00:20:17,609
But now, like you're saying, I think one of the biggest problems that many have with these LLMs,

292
00:20:17,728 --> 00:20:21,508
particularly if you're using codecs or cloud code only,

293
00:20:21,748 --> 00:20:28,928
is the context windows are relatively short if you're pinging the models a lot.

294
00:20:28,928 --> 00:20:34,728
So you can jam the context window or compact it multiple times a day.

295
00:20:34,728 --> 00:20:39,609
And then your your AI system gets some form of amnesia

296
00:20:39,609 --> 00:20:43,609
if you don't have a second brain or something set up that it's plugged into.

297
00:20:43,609 --> 00:20:49,968
And that's where I think Buzz leveraging Nostr in this historical context.

298
00:20:50,011 --> 00:20:56,411
that you have over time with signed events is an unlock for creating like a corpus,

299
00:20:56,551 --> 00:21:00,251
a context that builds over time that the agents can just plug into.

300
00:21:00,871 --> 00:21:02,591
Yeah, that's a really good observation.

301
00:21:03,111 --> 00:21:06,991
I always looked at it more like the thing I thought was cool is that it's, you know,

302
00:21:07,051 --> 00:21:08,291
it's a permissionless protocol.

303
00:21:08,291 --> 00:21:11,031
So you can just kind of interact with anything on the protocol.

304
00:21:11,031 --> 00:21:15,591
So like you could, you can just create these Frankenstein apps, you know, you could connect,

305
00:21:16,031 --> 00:21:19,831
you know, imagine trying to connect Slack and Discord and GitHub together.

306
00:21:20,011 --> 00:21:20,951
and like put them together.

307
00:21:21,071 --> 00:21:21,791
Like you can't really do that.

308
00:21:21,851 --> 00:21:23,151
You could do that very easily with Buzz

309
00:21:23,151 --> 00:21:26,051
and some other apps or things running on the protocol.

310
00:21:26,291 --> 00:21:30,831
So seeing Buzz come out built on top of Nostre

311
00:21:30,831 --> 00:21:32,391
and being like, okay, cool.

312
00:21:32,531 --> 00:21:35,171
There is a really nice use case for Nostre

313
00:21:35,171 --> 00:21:36,271
outside of social media.

314
00:21:36,671 --> 00:21:37,391
This is exciting.

315
00:21:37,611 --> 00:21:39,051
Let's see what else we can do, you know?

316
00:21:39,471 --> 00:21:40,831
So Freaks, this episode was brought to you

317
00:21:40,831 --> 00:21:42,111
by our good friends at BitKey.

318
00:21:42,331 --> 00:21:44,111
Self-custody is one of the most important things

319
00:21:44,111 --> 00:21:45,071
we do as Bitcoiners.

320
00:21:45,071 --> 00:21:46,631
Not your keys, not your coins.

321
00:21:46,891 --> 00:21:48,731
A lot of people never make the jump

322
00:21:48,731 --> 00:21:50,171
because the process feels intimidating.

323
00:21:50,391 --> 00:21:52,231
BitKey is trying to make that jump easier.

324
00:21:52,731 --> 00:21:53,971
You guys know it pretty well here already.

325
00:21:54,111 --> 00:21:57,071
It's a Bitcoin wallet from Block built around a simple idea.

326
00:21:57,431 --> 00:21:59,751
Let's give people a better path to holding their own keys

327
00:21:59,751 --> 00:22:03,251
without making them feel like they need to become a security engineer overnight.

328
00:22:03,711 --> 00:22:05,631
If you have Bitcoin sitting in an exchange

329
00:22:05,631 --> 00:22:07,431
and you have been meaning to take custody,

330
00:22:07,851 --> 00:22:08,851
stop procrastinating.

331
00:22:09,151 --> 00:22:13,251
Use the code TFTC10 for 10% off the new BitKey

332
00:22:13,251 --> 00:22:16,331
at bitkey.world slash TFTC10.

333
00:22:16,831 --> 00:22:17,731
All right, freaks.

334
00:22:17,731 --> 00:22:19,531
You know, I don't take sponsor money from products.

335
00:22:19,571 --> 00:22:20,271
I wouldn't use myself.

336
00:22:20,351 --> 00:22:20,871
So listen up.

337
00:22:21,031 --> 00:22:24,191
The Avon Bitcoin Visa card is one of the most interesting things I've seen in the Bitcoin

338
00:22:24,191 --> 00:22:25,431
lending space in a long time.

339
00:22:25,691 --> 00:22:26,191
Here's the deal.

340
00:22:26,391 --> 00:22:30,291
You can get a line of credit up to a million dollars backed by your Bitcoin without selling

341
00:22:30,291 --> 00:22:31,451
a single SAT.

342
00:22:31,591 --> 00:22:33,991
No games, no annual fees, no minimum draws.

343
00:22:34,571 --> 00:22:38,051
And your Bitcoin is custodied by Bitco, one of the most trusted names in digital asset

344
00:22:38,051 --> 00:22:38,571
security.

345
00:22:38,911 --> 00:22:39,711
Avon never lends it out.

346
00:22:39,791 --> 00:22:40,831
There's no rehypothecation.

347
00:22:40,971 --> 00:22:41,771
You stay in control.

348
00:22:42,251 --> 00:22:45,431
You can lock in a fixed rate for up to 10 years.

349
00:22:45,711 --> 00:22:46,111
10 years.

350
00:22:46,111 --> 00:22:48,251
That's 10 times longer than most lenders out there.

351
00:22:48,671 --> 00:22:50,611
We'll go interest only for up to five years.

352
00:22:51,131 --> 00:22:53,691
Rates start at 8.99% APR.

353
00:22:54,031 --> 00:22:57,391
For a product that lets you keep your stack and still access liquidity, it's hard to beat.

354
00:22:57,611 --> 00:22:59,151
On top of this, that's what?

355
00:22:59,191 --> 00:23:02,131
You also get 2% unlimited cash back every time you use the card.

356
00:23:02,591 --> 00:23:04,011
Spend fiat, keep your Bitcoin.

357
00:23:04,551 --> 00:23:05,371
That's the whole game.

358
00:23:05,811 --> 00:23:09,171
If you've been stacking for years and you need liquidity without triggering a taxable event,

359
00:23:09,571 --> 00:23:11,191
this is worth a serious look.

360
00:23:11,191 --> 00:23:13,771
Go to aven.com slash bitcoin.

361
00:23:13,771 --> 00:23:20,351
that's a v e n dot com slash bitcoin check it out and then the agents get their own identity

362
00:23:20,351 --> 00:23:27,011
which i think is uh interesting i'm not i haven't explored the the full thought experiment about

363
00:23:27,011 --> 00:23:33,271
what that means but um just thinking about where this because like i have my hermes agent

364
00:23:33,271 --> 00:23:38,331
and everybody's like when are you going to let other people on buzz get access so i never because

365
00:23:38,331 --> 00:23:41,371
it's got access to a server with a bunch of proprietary information on it.

366
00:23:43,011 --> 00:23:45,971
But you can think of a scenario

367
00:23:45,971 --> 00:23:48,211
where people just build individual agents

368
00:23:48,891 --> 00:23:51,771
that don't have as much sensitive proprietary information,

369
00:23:51,771 --> 00:23:53,371
don't have access to that information.

370
00:23:53,371 --> 00:23:55,091
People can just begin sharing agents.

371
00:23:55,091 --> 00:23:57,771
They can have like Matrix Agent Smith like

372
00:23:59,251 --> 00:24:02,371
reproducibility

373
00:24:02,371 --> 00:24:06,451
that just basically emanate throughout buzz communities.

374
00:24:07,091 --> 00:24:07,691
Yeah.

375
00:24:07,691 --> 00:24:25,991
Yeah, exactly. Because, because they can move, you know, you can move with that when you go take your identity with you to a new community it comes with. But I also think that like, it's there and built on Noster so that it can enable sharing of resources of compute and paying for those, you know.

376
00:24:25,991 --> 00:24:31,271
so i think um i mean there's two there's more than one side right it's like all the benefits

377
00:24:31,271 --> 00:24:36,951
of nostr but i think that's a that's going to be something we'll see and i mean i wrote that

378
00:24:36,951 --> 00:24:42,711
in one of my first tweets and jack retweeted it so there's a good there's a good um uh

379
00:24:42,711 --> 00:24:48,951
good possibility that that is what they're planning yeah no and then like the fact that

380
00:24:48,951 --> 00:24:53,911
it's on nostr too it's open source protocol a lot of the applications but on top of it are open

381
00:24:53,911 --> 00:24:54,891
source as well.

382
00:24:56,471 --> 00:24:57,211
And so you can

383
00:24:57,211 --> 00:24:59,871
like the permissionless nature of it too.

384
00:24:59,991 --> 00:25:01,531
You can imagine just sending agents

385
00:25:01,531 --> 00:25:03,731
like, hey, somebody had to build something like this on Noster

386
00:25:03,731 --> 00:25:05,591
and go find it, incorporate it into our

387
00:25:05,591 --> 00:25:07,651
workspace. And the whole

388
00:25:07,651 --> 00:25:09,171
idea of shared compute, there's

389
00:25:09,171 --> 00:25:10,871
Routster,

390
00:25:11,551 --> 00:25:13,551
open agents, there are these compute

391
00:25:13,551 --> 00:25:15,611
markets that have already been built

392
00:25:15,611 --> 00:25:17,571
on top of Noster. So the ability

393
00:25:17,571 --> 00:25:19,411
to port in that code

394
00:25:19,411 --> 00:25:21,691
and just create an open marketplace

395
00:25:21,691 --> 00:25:23,511
like, hey, I have a

396
00:25:23,511 --> 00:25:25,331
GPU running in my house.

397
00:25:25,491 --> 00:25:27,311
I'm not using it. I'm going to put a

398
00:25:27,311 --> 00:25:28,651
L402 gateway

399
00:25:28,651 --> 00:25:31,131
on top of it, plug into

400
00:25:31,131 --> 00:25:33,271
Roustor or OpenAgence. I'm going to use

401
00:25:33,271 --> 00:25:35,391
their code to basically

402
00:25:35,391 --> 00:25:37,471
market that I have this compute available

403
00:25:37,471 --> 00:25:39,251
and anybody that

404
00:25:39,251 --> 00:25:41,371
is connected to me via Buzz

405
00:25:41,371 --> 00:25:43,251
if our mpubs are connected

406
00:25:43,251 --> 00:25:45,471
like you, you'll be able to access

407
00:25:45,471 --> 00:25:47,611
this compute as well if you pay for it.

408
00:25:48,311 --> 00:25:49,571
Yeah. I mean, it's pretty cool.

409
00:25:49,711 --> 00:25:51,331
We saw what happened. I'm sure

410
00:25:51,331 --> 00:25:53,211
people or you know about

411
00:25:53,211 --> 00:25:56,711
what was going on in India, where they're banning BitChat and stuff like that.

412
00:25:56,711 --> 00:26:08,088
And then it just like when you have these kinds of shared channels over open protocols it pretty hard to shut off access to a model if they being shared that way I would assume right

413
00:26:08,808 --> 00:26:12,128
So that's also a cool possibility.

414
00:26:13,408 --> 00:26:13,628
Yeah.

415
00:26:13,628 --> 00:26:17,748
I mean, I forget what the Noster GitHub replacement is called.

416
00:26:19,868 --> 00:26:22,348
But yeah, if you get that in there, it's open source,

417
00:26:22,348 --> 00:26:27,708
and the code is stored on relays that people are self-hosting,

418
00:26:27,808 --> 00:26:29,268
it's going to be very hard to shut that down.

419
00:26:31,228 --> 00:26:31,708
Definitely.

420
00:26:32,848 --> 00:26:33,328
Cool.

421
00:26:33,508 --> 00:26:35,208
So we've been pretty philosophical.

422
00:26:35,428 --> 00:26:39,248
Should we do any demos or what else?

423
00:26:39,308 --> 00:26:39,708
What are you thinking?

424
00:26:40,528 --> 00:26:41,868
I think let's do a demo.

425
00:26:41,868 --> 00:26:46,208
And maybe as you're doing a demo of how you're using this,

426
00:26:47,048 --> 00:26:49,808
explain what the unlock is.

427
00:26:49,808 --> 00:26:54,188
like for me, like again, the agents being able to coordinate like Martin,

428
00:26:55,008 --> 00:26:57,008
who is our Hermes agent.

429
00:26:57,008 --> 00:27:01,188
When I got him connected, I made him basically like the Sargent Arms lead connector.

430
00:27:01,388 --> 00:27:04,848
And then I rewrote the system prompts for Fizz, Bumble and Honey

431
00:27:05,548 --> 00:27:07,288
and created one other agent.

432
00:27:07,288 --> 00:27:11,468
Basically, Martin became our orchestrator and he's got access to

433
00:27:13,668 --> 00:27:16,268
basically like our we put all of our meeting,

434
00:27:16,268 --> 00:27:19,308
like our transcripts of our meetings, contracts,

435
00:27:19,808 --> 00:27:23,508
uh advertisement schedules that we have to get in so he's got access to all that company

436
00:27:23,508 --> 00:27:29,648
information so martin you know what we're trying to get done in the business uh you know so sort of

437
00:27:29,648 --> 00:27:35,688
some of the low-hanging fruit initiatives that we haven't begun working on like all right hop in here

438
00:27:35,688 --> 00:27:43,788
with fizz bumble uh and honey and delegate some of the tasks that we have not finished yet to them

439
00:27:43,788 --> 00:27:49,108
um and it was like i was watching last night there was like a probably like a 45 minute loop

440
00:27:49,108 --> 00:27:53,388
of them just going back and forth until they got to a point of actually completing a task.

441
00:27:53,488 --> 00:27:54,648
I was like, holy crap, this is crazy.

442
00:27:55,388 --> 00:28:01,028
Yeah. It's pretty good at that too. I'm surprised at the end-to-end workflows that it's able to

443
00:28:01,028 --> 00:28:05,168
complete, know when to keep going, when to delegate, when to stop and stuff like that.

444
00:28:05,208 --> 00:28:09,108
So that's pretty cool. Sounds like you might even be doing more

445
00:28:09,108 --> 00:28:12,348
practical stuff than I am because you're actually using it for

446
00:28:12,348 --> 00:28:16,328
your team. And meanwhile,

447
00:28:16,328 --> 00:28:21,788
I'm just kind of playing around doing like, you know, demo stuff.

448
00:28:21,788 --> 00:28:23,788
Can you see the screen here?

449
00:28:23,788 --> 00:28:24,788
Yep.

450
00:28:24,788 --> 00:28:25,788
Yeah.

451
00:28:25,788 --> 00:28:29,788
And let me just get this like kind of minimized here.

452
00:28:29,788 --> 00:28:33,788
So yeah, like you were saying, you know, what's a good one.

453
00:28:33,788 --> 00:28:38,328
You know, one thing I shared earlier today that a lot of people seem to like was this

454
00:28:38,328 --> 00:28:45,828
prompt where, you know, I'm pinning models to the agents.

455
00:28:45,828 --> 00:28:50,848
So I'll have one that is pinned to Sonnet, like a lower level model, and one that's pinned

456
00:28:50,848 --> 00:28:54,728
to Fable for more complex tasks.

457
00:28:54,848 --> 00:28:58,468
But I'll have them bounce stuff back and forth because I know the workflow.

458
00:28:58,468 --> 00:29:05,108
So I'll tell Shared Boy, you download a transcript from the video and this transcript, pass it

459
00:29:05,108 --> 00:29:11,428
to Fizz, and Fizz, which is Fable, find the 5 most surprising ideas from the transcript

460
00:29:11,428 --> 00:29:16,748
with timestamps and really get chunks where you're not cutting off a sentence or an idea

461
00:29:16,748 --> 00:29:24,648
and pass that new document of chunked transcript back to Shared Boy, who's Sonnet, use FFmpeg,

462
00:29:24,888 --> 00:29:27,428
cut out those sections to make short clips to post to social media.

463
00:29:27,688 --> 00:29:32,568
So I get them to make basically shorts for me for Twitter and stuff with that.

464
00:29:32,668 --> 00:29:34,888
And then like you said, they're bouncing stuff back and forth.

465
00:29:34,888 --> 00:29:42,008
And I find this kind of workflow way nicer than in Cloud Code where you have sub-agents.

466
00:29:42,208 --> 00:29:47,228
I don't know why, but I never caught on to using sub-agents.

467
00:29:47,828 --> 00:29:52,628
You have the same thing, basically, but just something about having them in a shared chat,

468
00:29:52,728 --> 00:29:53,048
which is like...

469
00:29:53,948 --> 00:29:59,848
People have been gravitating towards using mobile apps, mobile solutions, right?

470
00:30:00,808 --> 00:30:04,308
Because of something about that where you can just kind of have conversations with your

471
00:30:04,308 --> 00:30:09,248
teammates, with the agent. It just, I don't know, it feels nicer. And I really like that about Buzz.

472
00:30:09,528 --> 00:30:15,948
That's just like one example that I used it for for today, where I'd prefer to use it over

473
00:30:15,948 --> 00:30:21,168
something like Cloud Code. Yeah, well, in this exact example, so we have this exact workflow,

474
00:30:21,428 --> 00:30:28,088
we built this for the pot, like, we'll use this workflow for this podcast, like a very similar

475
00:30:28,088 --> 00:30:31,428
workflow. It's probably not the exact same, but we do the same thing where it's like, hey,

476
00:30:31,428 --> 00:30:35,028
take the transcript with the timestamps of this episode,

477
00:30:35,868 --> 00:30:40,128
find the most engaging parts.

478
00:30:40,568 --> 00:30:43,928
Actually, we have a Twitter API, a third-party Twitter API that we use.

479
00:30:44,988 --> 00:30:48,088
Scrape that, look at what's trending, and if anything

480
00:30:48,088 --> 00:30:52,388
that we talked about matches with something that's beginning to trend, maybe we should focus on that.

481
00:30:52,968 --> 00:30:56,948
And then find the timestamps of the clip and go clip it.

482
00:30:56,948 --> 00:31:06,788
But we have our social media manager who has access to Martin in a sort of private Discord channel doing that workflow in a silo.

483
00:31:07,028 --> 00:31:22,164
And so when I think about Buzz what this opens up is the ability to take our social media manager and martin the single agent out of that silo and like pull them yep into more collaborative space where yep not only

484
00:31:22,164 --> 00:31:27,604
could he ask martin to do this but like fit he could delegate specific tasks within this this

485
00:31:27,604 --> 00:31:32,564
particular workflow to to get better better results and then on top of that like you know

486
00:31:32,564 --> 00:31:38,564
have the human members of our team hop in and be like well actually yeah like you guys did like

487
00:31:38,564 --> 00:31:41,684
here's some input from me about another angle we could take on this.

488
00:31:41,684 --> 00:31:44,404
And yeah, it just really consolidates

489
00:31:46,124 --> 00:31:47,724
consolidates the

490
00:31:47,724 --> 00:31:49,444
the work and makes it more open.

491
00:31:49,444 --> 00:31:51,564
And that's actually

492
00:31:51,564 --> 00:31:54,164
one thing I've been thinking a lot about, and it's actually

493
00:31:54,604 --> 00:31:57,044
funny enough, influenced by Dorsey.

494
00:31:57,084 --> 00:32:01,164
And I think Dorsey is really emerging as somebody who's viewing

495
00:32:01,844 --> 00:32:04,804
this whole AI revolution with with a very clear mind

496
00:32:04,844 --> 00:32:08,084
and particularly his paper that he wrote with

497
00:32:08,564 --> 00:32:17,384
Olof from a roll off, excuse me, from Sequoia and then the podcast they did about the intelligence layer companies becoming intelligence layers.

498
00:32:17,384 --> 00:32:33,404
And like this whole concept of instead of individual employees or members of your team working in these silos, like, yes, they will have delegated tasks and they'll have goals and there will be a division of labor.

499
00:32:33,404 --> 00:32:44,504
But the ability of these agents to open up collaboration across the team and for the team to have access to all the information about what everybody else is doing is extremely powerful.

500
00:32:44,504 --> 00:32:48,064
And I think that's something that people really haven't caught on to yet either.

501
00:32:48,624 --> 00:32:55,624
Yeah. And that's why I like to kind of refer to it as it's the first step in the right direction to have a global context window.

502
00:32:55,624 --> 00:33:02,004
Right. Because it's like usually you have, like you were saying, things siloed are spread out between different apps and you're bouncing back between them.

503
00:33:02,004 --> 00:33:07,064
you lose context, you lose the ability to collaborate with other people, get input from

504
00:33:07,064 --> 00:33:11,244
other people where it's like, you know, you just talk about what you want to do, your ideas,

505
00:33:11,244 --> 00:33:15,304
and then you can have something implemented for you right there in that moment, right?

506
00:33:15,344 --> 00:33:21,104
So it just like speeds things up, gives you this global context window, so to speak.

507
00:33:21,404 --> 00:33:26,744
And I think that's like a really cool direction with this.

508
00:33:26,744 --> 00:33:42,704
And one other thing I want to point out was like, you know, I'm doing this as a one-off, like, it's kind of like a skill or whatever. It's a prompt, right? But like, with a lot of that stuff, I think personally, I'm trying to, I'm inspired by Buzz that it's built on Nostra.

509
00:33:42,704 --> 00:33:48,224
I'm trying to think of ways to incorporate Noster into apps that I build.

510
00:33:48,344 --> 00:33:52,504
Because I think it makes sense when it's a deterministic workflow, right?

511
00:33:52,544 --> 00:34:02,684
When it's like, you know, it's just a very strict process that's going to be repeated over and over to build some kind of like just niche, small app that you host that does that.

512
00:34:02,684 --> 00:34:11,844
So like you're talking about where it's like scraping the using X API, scraping X for certain trends, cross-referencing that.

513
00:34:11,844 --> 00:34:25,024
I build something similar. It's just like a little demo. You might have seen it in the video that I posted on Twitter. And I originally had an externally facing API. And I just thought it would be cool to learn a bit more about Noster.

514
00:34:25,024 --> 00:34:28,424
instead of my agent running a workflow

515
00:34:28,424 --> 00:34:30,244
or like a recurring daily task

516
00:34:30,244 --> 00:34:32,624
and doing that call and using tokens for that stuff,

517
00:34:33,024 --> 00:34:36,784
why don't I use a recurring job in my Wasp app?

518
00:34:36,844 --> 00:34:39,524
Because that's like also something really easy to do in Wasp

519
00:34:39,524 --> 00:34:45,404
is just recurring jobs are a primitive in Wasp.

520
00:34:45,404 --> 00:34:47,204
So you just like set up a recurring job,

521
00:34:47,284 --> 00:34:48,624
tell the agent, set up a recurring job

522
00:34:48,624 --> 00:34:51,704
that takes the same stats that you're pushing

523
00:34:51,704 --> 00:34:54,584
to the external API, but push them to Noster.

524
00:34:55,024 --> 00:35:00,304
Just make it a Noster event, sign it and push to the Noster on my relay.

525
00:35:00,304 --> 00:35:06,784
And so I just get now to tweet stats every day from my app pushing to Noster.

526
00:35:06,784 --> 00:35:10,624
So the agent isn't doing this, but it's going into the agent context.

527
00:35:10,624 --> 00:35:14,624
So I can just reply to this here and be like, cool.

528
00:35:18,624 --> 00:35:23,984
Tell me what's working and what's not based on the current trends like you're doing.

529
00:35:23,984 --> 00:35:25,564
Stuff like that, I think is really cool.

530
00:35:26,244 --> 00:35:31,904
I don't think it's like nailed the ability to use Nostr to its full potential.

531
00:35:32,424 --> 00:35:34,884
But I think just through trying out things like this,

532
00:35:34,884 --> 00:35:39,784
we might be able to find cool ways, creative ways to build apps on Nostr

533
00:35:39,784 --> 00:35:43,344
that are integrated into your relays and your buzz communities.

534
00:35:44,284 --> 00:35:44,764
What's up, Freaks?

535
00:35:44,824 --> 00:35:46,864
When you take Bitcoin seriously, you start with custody.

536
00:35:47,084 --> 00:35:49,304
You want to control your keys, avoid single points of failure,

537
00:35:49,504 --> 00:35:52,624
and make sure your savings cannot disappear because you or someone else screwed up.

538
00:35:52,624 --> 00:35:54,944
That is what Unchained has been focused on since 2016.

539
00:35:55,284 --> 00:35:59,984
Unchained is the leader in collaborative multi-sig custody and Bitcoin financial services that keep you in control.

540
00:36:00,184 --> 00:36:03,544
They secure over $12 billion in Bitcoin for more than 12,000 clients.

541
00:36:03,944 --> 00:36:07,464
That means about one out of every 200 Bitcoin sits inside an Unchained vault.

542
00:36:07,624 --> 00:36:08,324
Their model is simple.

543
00:36:08,424 --> 00:36:09,964
You hold two keys, they hold one key.

544
00:36:10,124 --> 00:36:14,484
And it always takes two keys to move Bitcoin, meaning their single key can't access your Bitcoin on its own.

545
00:36:14,584 --> 00:36:18,444
Just resilient, shared custody that gives you institutional-grade security while keeping you sovereign.

546
00:36:18,624 --> 00:36:20,484
Unchained also lets you trade straight from your vault.

547
00:36:20,484 --> 00:36:22,144
access Bitcoin backed commercial loans,

548
00:36:22,144 --> 00:36:35,800
open a Bitcoin IRA where you hold your own keys and set up personal business trust or retirement vaults They even offer inheritance solutions built for long hodlers Or opt for the highest level private client service with Unchained Signature and get a dedicated account manager discounted

549
00:36:35,800 --> 00:36:39,820
trading fees, exclusive access to events and features, and much, much more. If you want a

550
00:36:39,820 --> 00:36:44,060
partner that helps you secure and grow your Bitcoin without giving up control, go to unchained.com

551
00:36:44,060 --> 00:36:49,100
and use the code TFTC10 at checkout to get 10% off your new Bitcoin multisig vault. That's

552
00:36:49,100 --> 00:36:54,020
tftc10 at unchained.com. Freaks, look at me. I'm glowing. I've got like an angel's halo

553
00:36:54,020 --> 00:36:58,900
going around me. You know why that is? I feel good. I feel taken care of. I feel blessed,

554
00:36:59,040 --> 00:37:02,480
healthy, happy. And that is because I'm a CrowdHealth member. My family and I have been

555
00:37:02,480 --> 00:37:06,940
CrowdHealth members for five years now, literally this month, five years ago, we joined CrowdHealth.

556
00:37:06,940 --> 00:37:11,180
We've had two babies. We've had multiple health events and we're never going back to health

557
00:37:11,180 --> 00:37:16,280
insurance. CrowdHealth is crowdfunded healthcare. So you sign up for CrowdHealth, you pay a monthly

558
00:37:16,280 --> 00:37:22,380
fee. You help out with other people's bills. And it's significantly cheaper than health insurance.

559
00:37:22,520 --> 00:37:27,060
We were on COBRA. It's a family of three when I left my last job before I went full-time with

560
00:37:27,060 --> 00:37:34,560
CFTC. Went on the crowd health. Now as a family of five, we pay, I believe, $700 a month. It's

561
00:37:34,560 --> 00:37:38,520
significantly cheaper. They're going to negotiate prices lower for you. They've consistently

562
00:37:38,520 --> 00:37:44,960
negotiated healthcare prices as much as 50, 60, 80% in many cases. They help out with babies.

563
00:37:44,960 --> 00:37:48,620
If you have a pregnancy, you pay the first $3,000 and the crowd covers the rest.

564
00:37:49,240 --> 00:37:53,940
If you have a regular health event, you pay $500 and the crowd pays the rest.

565
00:37:54,060 --> 00:37:55,320
Go to joincrowdhealth.com.

566
00:37:55,600 --> 00:37:56,120
Sign up today.

567
00:37:56,340 --> 00:37:57,260
Use the code TFTC.

568
00:37:57,580 --> 00:37:58,980
Opt out of health insurance.

569
00:37:59,120 --> 00:38:00,600
I'm uninsured, baby, and I love it.

570
00:38:00,800 --> 00:38:02,940
Use the code TFTC at joincrowdhealth.com.

571
00:38:03,180 --> 00:38:07,860
You'll get $99 a month for the first three months that you're on the crowd health platform

572
00:38:07,860 --> 00:38:08,740
in the community.

573
00:38:09,000 --> 00:38:09,320
Big winners.

574
00:38:09,720 --> 00:38:10,540
You found sovereign money.

575
00:38:10,820 --> 00:38:13,500
Now find sovereign health and sovereign healthcare.

576
00:38:13,500 --> 00:38:20,620
I think one of the underappreciated aspects of that, building on Nostra too, is the network effect.

577
00:38:20,720 --> 00:38:22,900
Because what Buzz essentially is, is a Nostra client.

578
00:38:23,260 --> 00:38:29,560
It's just a client, it's a front end built on top of the protocol and the relays connected to that protocol.

579
00:38:30,300 --> 00:38:36,360
And what many people, particularly the Nostra haters over the years, have not realized is that all Nostra needs to do,

580
00:38:36,360 --> 00:38:43,660
similar to Bitcoin, is just survive long enough and maintain a critical massive network effect that

581
00:38:43,660 --> 00:38:49,240
if it continues to grow for entrepreneurs, specifically if you're building apps,

582
00:38:50,000 --> 00:38:56,060
the way that Nostra works with the public private key pairs and the way clients work is like,

583
00:38:56,580 --> 00:39:04,860
I have a primal, I created a new NSEC and public key for Buzz for my individual profile there,

584
00:39:04,860 --> 00:39:09,740
but I could easily import the NSEC that I've been using for four years.

585
00:39:10,220 --> 00:39:14,380
And so the same NSEC I use on Prime, I use on Domus, I use on Wisp,

586
00:39:14,500 --> 00:39:18,180
I use on Zap.Stream, I use on Rouser.

587
00:39:18,740 --> 00:39:26,060
I can just port that over to Buzz and have the full context of my Noster history brought to Buzz.

588
00:39:26,480 --> 00:39:32,280
And so instead of trying to, basically as an entrepreneur releasing an app,

589
00:39:32,280 --> 00:39:34,700
trying to bootstrap a network effect.

590
00:39:34,840 --> 00:39:36,240
Like if your app's good enough,

591
00:39:36,840 --> 00:39:39,640
anybody on Noster with a private public key pair

592
00:39:39,640 --> 00:39:41,780
can just easily sign into your app with that

593
00:39:41,780 --> 00:39:43,500
and bring full context with them,

594
00:39:43,560 --> 00:39:44,760
which is extremely powerful.

595
00:39:45,580 --> 00:39:45,680
Yeah.

596
00:39:45,820 --> 00:39:47,260
And it's kind of cool to see like,

597
00:39:47,580 --> 00:39:49,920
you know, sometimes we're like for people,

598
00:39:50,580 --> 00:39:52,060
but these forward thinking technologies,

599
00:39:52,240 --> 00:39:53,400
it takes a while.

600
00:39:53,400 --> 00:39:54,860
Like you said, it just has to not die,

601
00:39:55,180 --> 00:39:56,780
but it's like people build it.

602
00:39:56,780 --> 00:40:00,100
They don't even know that like AI and coding agents

603
00:40:00,100 --> 00:40:01,040
are coming around the corner,

604
00:40:01,040 --> 00:40:04,420
but it takes something, some other kind of progression,

605
00:40:04,700 --> 00:40:09,040
some other kind of step change to then like open up like the aha moment, right?

606
00:40:09,040 --> 00:40:10,860
Where it's like, oh shit, this is it.

607
00:40:10,960 --> 00:40:13,880
This is like, this is going to work now, you know, this might really work.

608
00:40:14,100 --> 00:40:15,660
And that's how I kind of feel like it's happening here.

609
00:40:15,720 --> 00:40:18,060
It's like the beginning of that aha moment where it's like,

610
00:40:18,120 --> 00:40:20,480
oh, Nasser can be, Nasser can be bigger

611
00:40:20,480 --> 00:40:24,500
and can really play that role that it was designed to play.

612
00:40:25,020 --> 00:40:26,120
So I'm excited about that.

613
00:40:26,720 --> 00:40:28,840
Yeah. And it's like a weird feedback loop too,

614
00:40:28,840 --> 00:40:32,200
where like the AI vibe coding is sort of enabling it in a way.

615
00:40:33,840 --> 00:40:38,720
Instead of having to read like the docs on how Nostra works,

616
00:40:38,780 --> 00:40:41,000
it's like you just tell your clanker, like figure out.

617
00:40:41,160 --> 00:40:41,780
Like I did it.

618
00:40:42,240 --> 00:40:47,020
When I spun out my OpenClaw agent, I was just messing around,

619
00:40:47,120 --> 00:40:47,880
like seeing what it could do.

620
00:40:47,960 --> 00:40:50,220
I was like, okay, like I want you to be able to spend Bitcoin,

621
00:40:50,220 --> 00:40:54,640
like go figure out what the best wallet is

622
00:40:54,640 --> 00:40:56,200
and the best way for me to get you Bitcoin.

623
00:40:56,320 --> 00:40:57,100
It did some research.

624
00:40:57,220 --> 00:40:58,400
It's like, hey, we have a server.

625
00:40:58,840 --> 00:41:02,520
There's this thing called Phoenix D where we can run a lightning server on.

626
00:41:03,080 --> 00:41:05,600
We can spin up a lightning server in our VPS.

627
00:41:06,200 --> 00:41:07,060
We should use that.

628
00:41:07,160 --> 00:41:12,680
I was like, OK, now I'll just send you like when you when you set it up, send me

629
00:41:12,680 --> 00:41:18,420
send me an invoice to to basically create a channel because the way Phoenix works, it's

630
00:41:18,420 --> 00:41:22,080
like, OK, when you set up the server, send me an on chain address.

631
00:41:22,180 --> 00:41:25,900
I'll send Bitcoin to that and then you'll submarine swap that into a lightning channel

632
00:41:25,900 --> 00:41:26,680
so that you can spend.

633
00:41:26,680 --> 00:41:29,800
And it did that.

634
00:41:29,800 --> 00:41:31,980
And I was like, OK, you have a server.

635
00:41:33,360 --> 00:41:36,980
You have Bitcoin like you have L and URL off.

636
00:41:36,980 --> 00:41:39,960
Like since you have your server, you can sign the private key and you can sign

637
00:41:39,997 --> 00:41:46,397
into websites that that are ellen url auth enabled i was like all right like go to ellen markets and

638
00:41:46,397 --> 00:41:50,797
i want to see you like put a trade get to go along bitcoin like sign in go long it did that

639
00:41:51,437 --> 00:41:56,077
then i was like okay i want like i want you to manage this like just create like a simple

640
00:41:56,077 --> 00:42:01,357
trend following um trading strategy i don't care if you lose money i just want to do this for uh

641
00:42:02,237 --> 00:42:07,437
experiment reasons like also create an osster account um and then post your trades on a daily

642
00:42:07,437 --> 00:42:13,797
basis and it did that like it created an nsec and an mpub and was posting the nostril autonomously

643
00:42:13,797 --> 00:42:17,197
for like a month before i was like all right this is this is cool but i don't feel like

644
00:42:17,197 --> 00:42:23,457
keeping up with uh with the trades um but like the going back to the feedback loop like

645
00:42:23,457 --> 00:42:28,457
to your point about like it just needs to survive and then something will happen where

646
00:42:28,457 --> 00:42:33,397
it really creates that aha moment and like it's a symbiosis where like vibe coding's enabling

647
00:42:33,397 --> 00:42:37,097
the accessibility to these protocols,

648
00:42:37,237 --> 00:42:39,597
which are a lot of times

649
00:42:39,597 --> 00:42:41,157
like techno babble to many people,

650
00:42:41,237 --> 00:42:42,317
but you don't have to understand

651
00:42:42,317 --> 00:42:43,337
the techno babble anymore.

652
00:42:43,457 --> 00:42:44,217
Just like tell your client.

653
00:42:45,717 --> 00:42:46,897
Yeah, yeah, that's crazy.

654
00:42:47,157 --> 00:42:47,997
It's really fun

655
00:42:47,997 --> 00:42:49,937
because you just have the idea

656
00:42:49,937 --> 00:42:50,977
and then you just go for it.

657
00:42:51,037 --> 00:42:51,517
I love that.

658
00:42:52,257 --> 00:42:52,437
Yeah.

659
00:42:52,897 --> 00:42:54,437
Something else I do a lot,

660
00:42:54,537 --> 00:42:56,217
like I just get,

661
00:42:56,457 --> 00:42:58,717
I get it to create HTML presentations for me

662
00:42:58,717 --> 00:42:59,657
so that I can learn stuff

663
00:42:59,657 --> 00:43:00,337
because you were talking about like,

664
00:43:00,397 --> 00:43:01,797
I don't know how to use

665
00:43:01,797 --> 00:43:02,737
or build on Noster,

666
00:43:02,737 --> 00:43:08,057
but I just tell my client here to do it. Or if I want to learn basically a high level thing,

667
00:43:08,117 --> 00:43:14,377
I'll just be like, create an HTML presentation. And I actually did that for Noster. So I was like,

668
00:43:14,397 --> 00:43:19,977
I'm a full stack developer. Make sure I really know what I'm talking about. Create that presentation

669
00:43:19,977 --> 00:43:24,317
for me. Just like an HTML file. I love doing that to learn about stuff so that I get a deeper

670
00:43:24,317 --> 00:43:28,497
knowledge. And then I did this before I started building that app that was sending Noster events.

671
00:43:28,497 --> 00:43:33,137
So when it does stuff, I still have a clue what it's doing. And if I run into problems,

672
00:43:33,137 --> 00:43:40,417
I can maybe point them in the right direction. So that's cool. That was fun while building

673
00:43:41,537 --> 00:43:48,337
this app here that I can just click sync. And then I get that event, that Noster event in Buzz.

674
00:43:49,217 --> 00:43:54,097
And then when it comes in there, some of the workflows right there, boom, came in, tells me,

675
00:43:54,097 --> 00:43:57,937
hey, you got new tweet stats. And then I can just start chatting with him.

676
00:43:57,937 --> 00:44:03,297
So some of the workflows in Buzz are still a little bit iffy. I don't know.

677
00:44:04,417 --> 00:44:09,857
It's an experimental feature. So in their defense, they've got it in settings under experiments.

678
00:44:09,857 --> 00:44:16,897
You can click on workflows or projects. And I had some work, some don't. Some are a little iffy.

679
00:44:16,897 --> 00:44:21,297
So I think they'll get it worked out though. Yeah, I think that's cool.

680
00:44:21,297 --> 00:44:23,297
I do as well

681
00:44:23,297 --> 00:44:24,777
the

682
00:44:24,777 --> 00:44:27,617
I'm sorry I got my kids yelling

683
00:44:27,617 --> 00:44:28,497
in the background right here

684
00:44:28,497 --> 00:44:29,757
the

685
00:44:29,757 --> 00:44:33,777
do you think this is making people

686
00:44:33,777 --> 00:44:35,697
more productive like I think that's one of the

687
00:44:35,697 --> 00:44:37,237
big questions particularly for the

688
00:44:37,237 --> 00:44:39,437
bears and the doomers out there like

689
00:44:39,437 --> 00:44:40,617
oh it's great like usage

690
00:44:40,617 --> 00:44:43,617
is there actually more productivity in the

691
00:44:43,617 --> 00:44:44,017
economy

692
00:44:44,017 --> 00:44:49,737
can't just ask a question like that

693
00:44:49,737 --> 00:44:50,497
and then leave Marty

694
00:44:50,497 --> 00:44:53,357
I just shut the door.

695
00:44:53,357 --> 00:44:54,677
I just smell something.

696
00:44:56,737 --> 00:45:00,637
Like, that's a good question because yes, it can.

697
00:45:00,997 --> 00:45:04,597
Is it, I think we got to wait a little while to see the effects, of course.

698
00:45:04,597 --> 00:45:07,717
Like, it's going to take a while to trickle through, but like,

699
00:45:09,637 --> 00:45:23,374
on a general like on a broader basis But I think if you know what you want and if you know what you doing you know what you want and you know when Even if you asking these things for

700
00:45:23,374 --> 00:45:28,814
advice, if you know when it's giving bad advice, or you have a good sense of what's the better

701
00:45:28,814 --> 00:45:36,014
advice, which advice to take, then yeah, you're... I started that app in a company.

702
00:45:36,014 --> 00:45:43,934
I wouldn't have been able to do that. I would probably would not have done it pre 2023,

703
00:45:45,074 --> 00:45:52,814
pre AI, because I'm not the kind of person that's going to go out on a limb and hire a tax advisor

704
00:45:52,814 --> 00:45:58,654
and all these people. I literally did the majority of the work first off with just agents,

705
00:45:58,854 --> 00:46:03,334
copy and pasting websites, screenshots, like, what's this mean? What do I got to do here?

706
00:46:03,334 --> 00:46:05,734
What do I got to do? And just like slogging through it.

707
00:46:05,814 --> 00:46:08,754
And before we really had like good agents like this, but like, yeah,

708
00:46:08,774 --> 00:46:12,794
if you're driven to do that kind of stuff you have, you have,

709
00:46:12,894 --> 00:46:16,514
so you just have an idea and a will to do it, you can do it. So, yeah,

710
00:46:16,694 --> 00:46:21,154
I think for the right people, it's a multiplier for sure.

711
00:46:21,494 --> 00:46:26,534
It's a great lever. It's a huge lever. And in the wrong hands,

712
00:46:26,774 --> 00:46:31,034
you know, it's just going to be a, it's going to lead to nothing as well.

713
00:46:31,034 --> 00:46:32,834
You know, that's the way it goes.

714
00:46:33,334 --> 00:46:35,694
Yeah, I mean, you used the word earlier, but I think

715
00:46:36,934 --> 00:46:40,494
in terms of like deterministic workflows and sharing them.

716
00:46:41,874 --> 00:46:43,894
But I agree to like that's the way I view it.

717
00:46:43,894 --> 00:46:47,294
That's what I tell people is like the way I use these tools

718
00:46:47,294 --> 00:46:51,094
is I know what the output should be, particularly for our workflows at TFTC.

719
00:46:51,094 --> 00:46:52,894
And so like I know when it's wrong, it's like.

720
00:46:54,374 --> 00:47:00,294
I don't expect the models to go out and like create something new for us,

721
00:47:00,294 --> 00:47:01,174
if that makes sense.

722
00:47:01,174 --> 00:47:07,094
It's like, I know we have this task that we need done and we typically don't get it done because we don't have enough bandwidth.

723
00:47:07,434 --> 00:47:09,194
Like, I know what the end result should be.

724
00:47:09,274 --> 00:47:12,554
Like, please go do that and get the output.

725
00:47:12,814 --> 00:47:13,214
Right.

726
00:47:13,294 --> 00:47:13,774
Is it wrong?

727
00:47:14,194 --> 00:47:15,274
If it's right, thank you.

728
00:47:15,354 --> 00:47:15,734
Good job.

729
00:47:15,794 --> 00:47:17,234
If it's wrong, you messed up here.

730
00:47:17,434 --> 00:47:17,854
Do that.

731
00:47:17,854 --> 00:47:24,494
I think people falter is thinking that it's going to just do something magical for them.

732
00:47:24,494 --> 00:47:27,894
And like, these are essentially, they're large language models.

733
00:47:27,894 --> 00:47:31,254
They're just doing a probabilistic analysis of what the best,

734
00:47:31,434 --> 00:47:36,374
what the best next word is and the output.

735
00:47:36,374 --> 00:47:40,494
And like, you just need to know what the output should be and apply that lens to it.

736
00:47:40,494 --> 00:47:43,534
Like, don't say, build me a business that makes a billion dollars a year.

737
00:47:43,614 --> 00:47:44,234
Make no mistakes.

738
00:47:44,234 --> 00:47:45,394
Right, right.

739
00:47:45,794 --> 00:47:46,154
Yeah.

740
00:47:46,154 --> 00:47:47,034
You still got to do the work.

741
00:47:47,174 --> 00:47:48,494
It's just easier to do the work.

742
00:47:48,794 --> 00:47:49,434
That's about it.

743
00:47:49,494 --> 00:47:52,094
You know, so it's easier to get to,

744
00:47:52,094 --> 00:47:56,294
it's easier to get something done that you might have basically no knowledge on previously.

745
00:47:56,614 --> 00:48:01,014
You're a great example. Being able to self-host these things, these tools to

746
00:48:01,014 --> 00:48:05,134
virtual private servers and connect to the SSH into them and all this stuff.

747
00:48:05,134 --> 00:48:10,054
That stuff was very hard just four years ago.

748
00:48:12,274 --> 00:48:19,614
To me, it's not really a debate. But when I see companies that have token mandates,

749
00:48:19,614 --> 00:48:22,114
It's like, you have to use so many tokens.

750
00:48:22,274 --> 00:48:28,214
You have to use AI to this, you know, hit these benchmark, hit these targets.

751
00:48:28,894 --> 00:48:32,574
And, you know, the people who don't, the people who sat around and did nothing before

752
00:48:32,574 --> 00:48:35,254
are just going to waste those tokens, you know?

753
00:48:35,294 --> 00:48:38,294
So it's like, it all depends on how you approach it.

754
00:48:38,974 --> 00:48:39,094
Yeah.

755
00:48:40,114 --> 00:48:40,354
Great.

756
00:48:40,434 --> 00:48:41,214
Bring this back to Buzz.

757
00:48:41,214 --> 00:48:56,751
What would be your top request for a feature Top request for a feature I think they doing it right I willing to These are experimental features This is early preview stuff

758
00:48:58,891 --> 00:49:00,811
I think what I would like to see

759
00:49:00,811 --> 00:49:02,751
is if you're used to...

760
00:49:02,751 --> 00:49:05,071
If you're used to working in a terminal

761
00:49:05,071 --> 00:49:07,571
and just these views,

762
00:49:07,671 --> 00:49:09,871
and then if you're a software developer,

763
00:49:10,031 --> 00:49:11,651
you might want to jump back

764
00:49:11,651 --> 00:49:12,831
and run your own commands

765
00:49:12,831 --> 00:49:13,871
like you're used to that stuff.

766
00:49:14,071 --> 00:49:17,751
It could be cool if they had something embedded in here like that for the more technical people.

767
00:49:19,511 --> 00:49:20,791
But it's not like...

768
00:49:20,791 --> 00:49:22,151
It's not...

769
00:49:22,151 --> 00:49:23,431
Yeah, the cool thing is it's open source.

770
00:49:24,431 --> 00:49:30,071
Someone like me or someone could put that in as a feature and submit a PR to block.

771
00:49:30,631 --> 00:49:31,611
So maybe we'll see that.

772
00:49:31,751 --> 00:49:34,171
But I think I like the approach.

773
00:49:34,171 --> 00:49:38,471
I'm willing to deal with some kind of the rough edges at the moment while it's really early preview.

774
00:49:38,931 --> 00:49:41,611
Because I think it's going in a very cool direction.

775
00:49:41,611 --> 00:49:49,011
And I didn't, you know, I'm like, I'm not one to jump on bandwagons just because they're trendy.

776
00:49:49,191 --> 00:49:51,951
Like if I see something that interests me, then I'll try it out.

777
00:49:53,331 --> 00:49:56,711
So yeah, this seems like a pretty cool approach.

778
00:49:57,131 --> 00:50:02,911
And I want to see more integration with, I want to see what I would like to actually see

779
00:50:02,911 --> 00:50:06,871
is other cool stuff happening on Nostra that gets integrated here in a creative way

780
00:50:06,871 --> 00:50:10,251
so that we can use these tools together in creative ways.

781
00:50:10,251 --> 00:50:12,331
but I think we're still kind of figuring it out.

782
00:50:12,411 --> 00:50:12,991
At least I am.

783
00:50:14,471 --> 00:50:14,911
Yeah.

784
00:50:15,271 --> 00:50:17,491
And like the tweet that you responded to,

785
00:50:17,551 --> 00:50:20,811
I think the first big unlock could be

786
00:50:21,631 --> 00:50:24,931
basically forking or implementing

787
00:50:24,931 --> 00:50:28,091
Rouser open agents for a market to compute,

788
00:50:28,211 --> 00:50:29,691
particularly for open source models,

789
00:50:29,991 --> 00:50:33,211
and then equipping the agents with Bitcoin wallets

790
00:50:33,211 --> 00:50:34,691
that they can load up.

791
00:50:34,771 --> 00:50:36,991
Or to your point, like I think you said on Greg,

792
00:50:37,071 --> 00:50:40,011
it's like being able to tip other humans or agents

793
00:50:40,011 --> 00:50:45,211
to go do work for you. Very trivially. Yeah. I mean, look at primals, or I'm sorry,

794
00:50:45,211 --> 00:50:51,851
like Noster. I use Primal mainly, but Noster is such a good example. And I mean, Lynn Alden has

795
00:50:51,851 --> 00:50:56,731
pointed this out before that the incentive structure is so different than Twitter. When

796
00:50:56,731 --> 00:51:03,371
you make something useful on Noster, people literally tip you, send you money. And now imagine

797
00:51:03,371 --> 00:51:10,991
that same. So we know it works. We know people are willing to tip for valuable information,

798
00:51:11,171 --> 00:51:16,051
insights, work, things like that. Now imagine you have that here in Buzz where it's like

799
00:51:16,051 --> 00:51:21,031
an open community. So it's not just your company, right? You're doing something private, but let's

800
00:51:21,031 --> 00:51:25,471
say we all join together and we start like some open community that's working on an open source

801
00:51:25,471 --> 00:51:29,671
project. And someone just comes up with a really cool idea and mentions it in the community. You

802
00:51:29,671 --> 00:51:34,291
could pay them for good ideas because then you get the agents to implement them.

803
00:51:34,291 --> 00:51:45,131
Or then you pay whoever's running the really cool high-performance open source model, you

804
00:51:45,131 --> 00:51:52,631
send them a zap to implement that task on their shared compute or on their agent.

805
00:51:52,631 --> 00:51:54,091
So that's really cool.

806
00:51:54,091 --> 00:51:56,351
I think that's what I want to see basically.

807
00:51:56,351 --> 00:52:00,891
I think we will see that if, um, it's like you said, if it just stays around long enough,

808
00:52:00,891 --> 00:52:07,471
it doesn't die. Like a bounty board too. Um, yep. Yep. It's create bounties for particular,

809
00:52:07,631 --> 00:52:13,291
particular workflows or tasks to be done. And it's like the perfect example, like this podcast

810
00:52:13,291 --> 00:52:17,771
is hosted on Noster. We use fountain, their podcast host. It's a, it's a Noster client.

811
00:52:17,891 --> 00:52:32,048
And so like there going to be people who listen to this podcast and stream us Bitcoin over over the network um and like if you were like i could if you like i could literally put your end pub in this episode i think we can

812
00:52:32,048 --> 00:52:37,688
do it individual episodes and like you could share in the stream of bitcoin that's coming our way as

813
00:52:37,688 --> 00:52:44,988
people are are boosting and streaming sats to to this episode cool i'll spend it on some sweet

814
00:52:44,988 --> 00:52:45,828
powerful agents

815
00:52:45,828 --> 00:52:47,628
in the future

816
00:52:47,628 --> 00:52:48,268
in the future

817
00:52:48,268 --> 00:52:49,048
when it gets

818
00:52:49,048 --> 00:52:50,148
implemented

819
00:52:50,148 --> 00:52:51,168
but yeah

820
00:52:51,168 --> 00:52:51,728
that's what I would

821
00:52:51,728 --> 00:52:52,148
like to see

822
00:52:52,148 --> 00:52:53,308
yeah

823
00:52:53,308 --> 00:52:54,088
I know it's getting

824
00:52:54,088 --> 00:52:54,888
late where you are

825
00:52:54,888 --> 00:52:56,888
how

826
00:52:56,888 --> 00:52:58,548
how should we

827
00:52:58,548 --> 00:52:59,008
end this

828
00:52:59,008 --> 00:53:00,408
any final thoughts

829
00:53:00,408 --> 00:53:00,828
any

830
00:53:00,828 --> 00:53:02,528
calls to action

831
00:53:02,528 --> 00:53:03,108
any

832
00:53:03,108 --> 00:53:04,588
philosophical

833
00:53:04,588 --> 00:53:05,568
musings about

834
00:53:05,568 --> 00:53:06,428
the state of AI

835
00:53:06,428 --> 00:53:07,168
where we're going

836
00:53:07,168 --> 00:53:07,908
are we getting

837
00:53:07,908 --> 00:53:09,408
job destruction

838
00:53:09,408 --> 00:53:11,008
nah yeah

839
00:53:11,008 --> 00:53:11,748
no I think we did

840
00:53:11,748 --> 00:53:12,588
a pretty good job

841
00:53:12,588 --> 00:53:13,568
of doing

842
00:53:13,568 --> 00:53:14,208
of

843
00:53:14,208 --> 00:53:14,628
of

844
00:53:14,988 --> 00:53:18,668
of covering that stuff. I like the angle we took here. It was cool, different than the other

845
00:53:18,668 --> 00:53:27,368
podcasts. So that's nice. No, I think this is pretty good. Maybe if people want to know more

846
00:53:27,368 --> 00:53:33,848
or hear more, they should let us know. And then that'd be cool to... There might be some things

847
00:53:33,848 --> 00:53:39,548
out there that people are interested in that we haven't really hit on. And then we can explore

848
00:53:39,548 --> 00:53:45,528
further talk about it um on on the social media platforms or do another one of these that would

849
00:53:45,528 --> 00:53:53,488
be cool that'd be awesome well uh appreciate you coming on thanks for having me sure it's been a

850
00:53:53,488 --> 00:53:58,288
hectic week for you you're just out there talking about the tools that you're using and become a

851
00:53:58,288 --> 00:54:04,248
become a little internet celebrity this week so i appreciate you coming on this show and uh

852
00:54:04,248 --> 00:54:04,648
You're welcome.

853
00:54:05,988 --> 00:54:07,428
It seems like you're a Bitcoiner.

854
00:54:08,928 --> 00:54:10,448
At least you're playing around with it,

855
00:54:10,548 --> 00:54:12,468
which is cool to see.

856
00:54:12,468 --> 00:54:15,288
And Nostra, you're becoming well-versed on it.

857
00:54:15,828 --> 00:54:17,628
These are two projects that obviously

858
00:54:17,628 --> 00:54:19,748
I've been very passionate about for many years.

859
00:54:19,948 --> 00:54:22,888
And it feels like this agentic economy

860
00:54:22,888 --> 00:54:27,608
is the moment for Nostra and Bitcoin to shine.

861
00:54:27,788 --> 00:54:29,888
And it seems like we're getting to the point

862
00:54:29,888 --> 00:54:32,328
where people are beginning to recognize that.

863
00:54:32,328 --> 00:54:35,148
it was just cool to see you talk

864
00:54:35,148 --> 00:54:37,448
about these

865
00:54:37,448 --> 00:54:39,428
technologies and the potential for them on a show

866
00:54:39,428 --> 00:54:41,348
like Greg Eisenberg who really doesn't cover this

867
00:54:41,348 --> 00:54:42,488
stuff much so

868
00:54:42,488 --> 00:54:45,448
yeah yeah totally

869
00:54:45,448 --> 00:54:45,788
agree

870
00:54:45,788 --> 00:54:49,428
alright well hopefully we'll do this

871
00:54:49,428 --> 00:54:51,348
again at some point in the future and until

872
00:54:51,348 --> 00:54:53,348
then enjoy it brother

873
00:54:53,348 --> 00:54:54,508
you too

874
00:54:54,508 --> 00:54:55,888
peace and love freaks

875
00:54:55,888 --> 00:54:59,028
thank you for listening to this episode of TFTC

876
00:54:59,028 --> 00:55:01,388
if you've made it this far I imagine

877
00:55:01,388 --> 00:55:06,788
you got some value out of the episode. If so, please share it far and wide with your friends

878
00:55:06,788 --> 00:55:11,648
and family. We're looking to get the word out there. Also, wherever you're listening, whether

879
00:55:11,648 --> 00:55:18,428
that's YouTube, Apple, Spotify, make sure you like and subscribe to the show. And if you can leave a

880
00:55:18,428 --> 00:55:23,548
rating on the podcasting platforms, that goes a long way. Last but not least, if you want to get

881
00:55:23,548 --> 00:55:29,808
these episodes a day early and ad free, make sure you download the Fountain podcasting app

882
00:55:29,808 --> 00:55:32,588
You can go to fountain.fm to find that.

883
00:55:33,328 --> 00:55:37,068
$5 a month gets you every episode a day early, ad-free.

884
00:55:37,868 --> 00:55:38,628
Helps the show.

885
00:55:39,048 --> 00:55:40,168
Gives you incredible value.

886
00:55:41,188 --> 00:55:44,388
So please consider subscribing via Fountain as well.

887
00:55:44,948 --> 00:55:45,848
Thank you for your time.

888
00:55:46,428 --> 00:55:47,248
And until next time.

889
00:55:47,888 --> 00:55:48,088
Okay.