النص 🔗
WEBVTT
1
00:00:05.200 --> 00:00:08.119
Hey, folks, welcome back to another episode of the Ruby
2
00:00:08.199 --> 00:00:12.919
Rogues podcast. This week, on our panel we have Valentino Stole. Hey, now,
3
00:00:13.039 --> 00:00:15.839
I'm Charles Maxwoot from Top End Devs And yeah, it's
4
00:00:15.880 --> 00:00:18.879
been a while Valentino, we've kind of had a lot
5
00:00:18.920 --> 00:00:21.879
going on, just picking things back up. Do you want
6
00:00:21.920 --> 00:00:23.800
to give people a quick update as to where you're
7
00:00:23.839 --> 00:00:25.320
at and then I'll do the same thing and then
8
00:00:25.320 --> 00:00:27.960
we can dive into the rest of this topic for today.
9
00:00:28.640 --> 00:00:28.960
Yeah.
10
00:00:29.039 --> 00:00:31.399
Yeah, you know, earlier in the year I moved gigs,
11
00:00:31.760 --> 00:00:34.119
I was at doc Semity and I switched over to
12
00:00:34.759 --> 00:00:38.159
the Lovely team Agusta working on AI related stuff.
13
00:00:38.240 --> 00:00:40.200
Pretty wild thing's happening.
14
00:00:40.399 --> 00:00:43.600
Yeah, you know, lots of So when you say you're
15
00:00:43.600 --> 00:00:47.520
working on AI stuff for Gusto, are you integrating AI
16
00:00:48.079 --> 00:00:52.079
based features into what Gusto does or you know, well,
17
00:00:52.119 --> 00:00:53.960
what does that look like? I guess it seems like
18
00:00:54.039 --> 00:00:55.840
there's a wide world of things that people are doing
19
00:00:55.840 --> 00:00:56.240
with AI.
20
00:00:57.320 --> 00:00:59.560
There is a wide world of things. So they have
21
00:00:59.679 --> 00:01:04.079
a you know, Chapot Gus who's like the assistant for
22
00:01:04.159 --> 00:01:08.280
your business, your small business, and uh, you know, they're
23
00:01:08.319 --> 00:01:12.239
basically just integrating their entire ecosystem into the chato okay,
24
00:01:13.159 --> 00:01:14.040
amongst other things.
25
00:01:14.359 --> 00:01:16.359
There's a lot of other initiatives. That's that's the one
26
00:01:16.400 --> 00:01:18.319
I've been focused on in my op okay.
27
00:01:18.359 --> 00:01:20.319
So yeah, pretty much, anything that you would want to
28
00:01:20.359 --> 00:01:23.239
do as a small business, think about what an AI
29
00:01:23.319 --> 00:01:26.359
assistant might help out with that, especially when you have
30
00:01:26.400 --> 00:01:28.959
a small business platform you can plug into.
31
00:01:30.239 --> 00:01:34.040
It's it's kind of exciting, very very cool. I'd love
32
00:01:34.079 --> 00:01:36.680
to dig into that. It looks like a lot of fun.
33
00:01:36.799 --> 00:01:39.239
So yeah, So for me, about the same time you
34
00:01:39.400 --> 00:01:43.319
transition over to Gusto, I dropped my contract and went
35
00:01:43.359 --> 00:01:45.159
and worked for price Picks and so I've been at
36
00:01:45.200 --> 00:01:49.280
price Picks since March and I've spent quite a bit
37
00:01:49.319 --> 00:01:51.359
of time working on a lot of the social features.
38
00:01:51.400 --> 00:01:53.159
So if you're if you get into the app and
39
00:01:53.200 --> 00:01:57.040
you're you want to follow another member's profile or you
40
00:01:57.079 --> 00:01:59.439
want to they have the feeds where you can see
41
00:01:59.439 --> 00:02:02.239
what other people or wagering or stuff like that. You know,
42
00:02:02.319 --> 00:02:04.760
it kind of makes it fun and you know you're
43
00:02:04.799 --> 00:02:06.480
able to kind of see more of the things that
44
00:02:06.519 --> 00:02:08.719
other people are doing and you know kind of build
45
00:02:08.759 --> 00:02:11.039
stuff off of that. And anyway, I've I've been spending
46
00:02:11.039 --> 00:02:13.039
a lot of time on that and on the profile stuff.
47
00:02:13.080 --> 00:02:16.159
So that's where a lot of my work has come.
48
00:02:16.199 --> 00:02:18.879
It's actually kind of funny because my wife and I'll
49
00:02:18.879 --> 00:02:21.319
be sitting watching TV and a price picks that will
50
00:02:21.360 --> 00:02:23.280
come up, and it's, you know, it's like, hey, did
51
00:02:23.280 --> 00:02:26.039
you know that you could you know whatever, and I
52
00:02:26.080 --> 00:02:27.560
and I look at her and I go, yeah, I
53
00:02:27.599 --> 00:02:30.080
built that, right, at least I built them back end of.
54
00:02:30.080 --> 00:02:32.719
It, right, are you on there? You know, pick making
55
00:02:32.759 --> 00:02:33.280
your picks?
56
00:02:33.360 --> 00:02:33.560
You know?
57
00:02:35.000 --> 00:02:35.080
No.
58
00:02:35.439 --> 00:02:39.960
In fact, my track record on picking the right stuff
59
00:02:40.039 --> 00:02:44.080
to win is abysmal. I mean, you know, obviously as
60
00:02:44.080 --> 00:02:46.759
an employee, I can't actually play for real money, but
61
00:02:47.039 --> 00:02:49.000
you know, if I want to play, I can play,
62
00:02:49.039 --> 00:02:51.319
you know, and it's kind of fun. I just you know,
63
00:02:51.400 --> 00:02:57.280
I can't. I can't depositor withdraw money and so anyway,
64
00:02:57.319 --> 00:03:00.639
it's just it's just yeah, it's so so it's all
65
00:03:00.639 --> 00:03:03.639
in fun. But yeah, I almost never win.
66
00:03:03.800 --> 00:03:07.120
So it is funny to see, like, you know, ads
67
00:03:07.159 --> 00:03:09.439
pop up and you're like, hey, yeah, I know that.
68
00:03:10.280 --> 00:03:13.360
Yeah, yeah. But my deal is is I don't really
69
00:03:13.360 --> 00:03:16.599
follow NFL or NBA or you know, any of the
70
00:03:17.080 --> 00:03:21.080
big sports that people are are in there playing on
71
00:03:21.360 --> 00:03:25.080
So I think I think I'd have a better shot
72
00:03:25.159 --> 00:03:28.120
if I was like a die hard Eagles fan or something,
73
00:03:28.240 --> 00:03:30.719
you know. And so it's like, I'm going to put
74
00:03:30.759 --> 00:03:33.800
something in on every Eagles game, but I don't because
75
00:03:33.800 --> 00:03:36.599
I just don't care. Yeah, but yeah, So we were
76
00:03:36.639 --> 00:03:40.520
Load full transcript
talking before the we got recording, and you said that
77
00:03:40.560 --> 00:03:45.120
you've been working on this autogenesis stuff and Gym.
78
00:03:45.400 --> 00:03:48.599
It's a term I came across called autogenetic, which basically
79
00:03:48.639 --> 00:03:54.599
just means self generating, and Okay, I've started to explore
80
00:03:54.680 --> 00:03:58.039
like what it might look like for these AI things
81
00:03:58.080 --> 00:04:02.159
to just like assemble the themselves things that let them
82
00:04:02.199 --> 00:04:04.879
do more rather than having me decide.
83
00:04:04.599 --> 00:04:05.520
What it should do more.
84
00:04:06.080 --> 00:04:06.400
Mhm.
85
00:04:07.360 --> 00:04:10.080
And that part of my exploration is this gem called
86
00:04:10.199 --> 00:04:12.800
it's a Ruby gem called Agentic. I started as just
87
00:04:12.879 --> 00:04:16.360
like I wanted a way to do plan and execution
88
00:04:16.519 --> 00:04:20.319
the workflows. So if you're not familiar with those, it's
89
00:04:20.360 --> 00:04:24.360
a way for you to have an AI thing an LLM,
90
00:04:24.439 --> 00:04:27.480
create a plan and then execute that plan. And so
91
00:04:27.959 --> 00:04:31.480
you can think cloud code right, is a perfect example
92
00:04:31.519 --> 00:04:36.560
of how this kind of started in a more practical way.
93
00:04:36.800 --> 00:04:40.240
There there were others before them, but you know, a
94
00:04:40.279 --> 00:04:43.600
plan execute is very like common pattern for AI stuff.
95
00:04:43.800 --> 00:04:45.279
And as I was.
96
00:04:45.199 --> 00:04:50.720
Building it, I had these like, you know, agents that
97
00:04:51.519 --> 00:04:58.040
I was like manually creating, and I thought, why am
98
00:04:58.079 --> 00:05:01.000
I creating these things? There has to be a that
99
00:05:01.079 --> 00:05:03.800
the plan could just be like, okay, what kinds of
100
00:05:03.920 --> 00:05:06.480
you know, what do I need in order to accomplish
101
00:05:06.720 --> 00:05:07.240
this goal?
102
00:05:08.000 --> 00:05:08.279
Right?
103
00:05:08.839 --> 00:05:14.560
And then I have you know, if I introduced concepts
104
00:05:14.839 --> 00:05:19.279
to the LLM that it knew how it could use
105
00:05:19.319 --> 00:05:22.439
them and how it could build them, could it do
106
00:05:22.480 --> 00:05:25.120
it effectively? And so the obvious one is agent, right,
107
00:05:25.240 --> 00:05:29.120
Like you have instructions and it can do things, it
108
00:05:29.120 --> 00:05:32.199
has tools available to it, and so can an LLM
109
00:05:32.839 --> 00:05:37.480
with just knowledge about like that construct build its own
110
00:05:37.879 --> 00:05:42.319
and assemble its own agents to accomplished tasks that it
111
00:05:42.360 --> 00:05:43.160
has to do.
112
00:05:43.279 --> 00:05:44.759
And so that's where I kind of like really.
113
00:05:44.680 --> 00:05:49.040
Dug into this agentic gem and started I created this
114
00:05:49.199 --> 00:05:53.199
like way to assemble agents based on just like instructions
115
00:05:53.199 --> 00:05:56.360
and giving it a role, and with that like primitive
116
00:05:56.519 --> 00:05:59.519
giving it a name, a role and instructions, throwing a
117
00:05:59.560 --> 00:06:02.639
task it and be like, hey, like assemble whatever agents
118
00:06:02.680 --> 00:06:05.480
you need to accomplish this task and give me the
119
00:06:05.480 --> 00:06:06.160
result of that.
120
00:06:06.399 --> 00:06:08.879
Right, So it reminds me a little bit of some
121
00:06:08.920 --> 00:06:12.480
of the conversations we've had with other people about AI
122
00:06:12.600 --> 00:06:17.319
agents and lms, where effectively, I think kind of the
123
00:06:17.360 --> 00:06:21.199
basic version is you have one agent or one program
124
00:06:21.279 --> 00:06:22.920
and you give it a task and it just kind
125
00:06:22.959 --> 00:06:25.920
of runs until it gets the stuff done right. And
126
00:06:25.959 --> 00:06:29.240
so then we've talked specifically, I'm thinking of when we
127
00:06:29.319 --> 00:06:32.519
talked to Obi about Ray where he said, you know,
128
00:06:32.639 --> 00:06:35.439
I've got multiple agents, right, So I've got like a
129
00:06:35.480 --> 00:06:38.959
calendar scheduler agent, I've got this agent, I've got that agent,
130
00:06:39.000 --> 00:06:40.639
I've got another agent, right, and so they all kind
131
00:06:40.639 --> 00:06:43.600
of specialize, and then he's got one or two that
132
00:06:43.800 --> 00:06:46.920
kind of orchestrate things at different levels and so and
133
00:06:46.959 --> 00:06:48.879
a lot of that was done deliberately, right. It's like,
134
00:06:48.959 --> 00:06:51.120
I'm going to have a calendar agent, I'm going to
135
00:06:51.160 --> 00:06:54.519
have a chat agent, I'm going to have a whatever
136
00:06:54.560 --> 00:06:57.720
else agent. And what you're saying is is in your case,
137
00:06:57.839 --> 00:07:01.839
you're saying, Okay, I just need this task done right,
138
00:07:01.920 --> 00:07:04.800
and so you make up what the agents are, right,
139
00:07:04.839 --> 00:07:08.560
and so you're giving that or that level of design
140
00:07:08.600 --> 00:07:10.519
and orchestration to the LLM as well.
141
00:07:11.199 --> 00:07:13.040
Exactly because.
142
00:07:14.240 --> 00:07:18.240
Because this object oriented, right, and all these types constructs
143
00:07:18.279 --> 00:07:22.279
are defined in code, I could save the artifacts of those, right.
144
00:07:22.360 --> 00:07:26.759
So like, as it's building out these agents to accomplish tasks,
145
00:07:27.120 --> 00:07:29.079
it's saving them off for use later.
146
00:07:29.920 --> 00:07:30.079
Right.
147
00:07:30.160 --> 00:07:31.839
So like if it goes.
148
00:07:31.600 --> 00:07:34.720
And if it has like a bigger plan that it's
149
00:07:34.759 --> 00:07:37.040
trying to get through and a goal is trying to accomplish,
150
00:07:37.160 --> 00:07:40.040
and it's creating all these subtasks and
making agents and
151
00:07:40.120 --> 00:07:43.199
then reuse those agents as it goes through the plan,
152
00:07:43.639 --> 00:07:46.519
and so like let's say it's like just like a
153
00:07:46.560 --> 00:07:49.759
research agent that it decides to make, and it goes
154
00:07:50.040 --> 00:07:54.160
and it researches some content and then pulls back information
155
00:07:54.240 --> 00:07:56.360
and saves it in a file, and that's like what
156
00:07:56.399 --> 00:07:58.759
it was built to do. And then it comes across
157
00:07:58.800 --> 00:08:00.959
another task it is like I need to research about
158
00:08:00.959 --> 00:08:03.879
this new thing. You can just reuse that agent and
159
00:08:04.480 --> 00:08:09.399
because like it then becomes available to the system as like, hey,
160
00:08:09.439 --> 00:08:12.839
this is these are agents that are available right at
161
00:08:12.879 --> 00:08:15.759
every given turn in the task, you can choose to
162
00:08:15.959 --> 00:08:18.399
pick one of those existing ones or build a new one.
163
00:08:18.439 --> 00:08:21.839
And sometimes you know, if the research is if the
164
00:08:22.439 --> 00:08:25.199
task is not related enough to what is trying to
165
00:08:25.240 --> 00:08:27.839
do like let's say it was like just generic research
166
00:08:27.879 --> 00:08:29.920
on the web, but it needed to research in a
167
00:08:29.959 --> 00:08:32.759
specific file that it would create a new agent for
168
00:08:32.960 --> 00:08:36.639
file research. All right, So it's it's kind of interesting
169
00:08:36.679 --> 00:08:42.200
to watch this thing kind of bloom, right, uh huh
170
00:08:42.240 --> 00:08:43.840
as you give it different things to do.
171
00:08:44.440 --> 00:08:47.480
So one thing that I'm wondering about is it seemed
172
00:08:47.519 --> 00:08:51.679
like some of the sub jobs or subclasses of agent
173
00:08:51.799 --> 00:08:54.039
or however you want to look at, that they had
174
00:08:54.120 --> 00:08:57.519
pretty specific functions that they needed, right, So for example,
175
00:08:57.559 --> 00:09:01.279
talking to a calendar or you know, connecting to a
176
00:09:01.320 --> 00:09:05.120
particular service or things like that. Does it create those
177
00:09:05.159 --> 00:09:08.759
two and actually write the function code for those sometimes?
178
00:09:11.799 --> 00:09:13.639
Right? So that's the beauty of this is like it's
179
00:09:13.679 --> 00:09:15.480
an experiment and things that all.
180
00:09:15.559 --> 00:09:17.200
It really is coming from my job.
181
00:09:17.360 --> 00:09:20.720
Like, yeah, sometimes it does effectively do that, you know.
182
00:09:20.919 --> 00:09:24.799
Huh when it gets runs there are cases where it
183
00:09:25.080 --> 00:09:27.159
like you know, because I do have limitters on it
184
00:09:27.200 --> 00:09:32.600
that like don't let it like recursively you know, get
185
00:09:32.600 --> 00:09:33.120
to itself.
186
00:09:33.120 --> 00:09:34.080
So if it fails to.
187
00:09:34.039 --> 00:09:36.039
Do something, it doesn't get stuck and it could just
188
00:09:36.120 --> 00:09:38.399
move on and say I wasn't able to do that,
189
00:09:38.519 --> 00:09:40.360
And so it does do that, but yeah, I would
190
00:09:40.360 --> 00:09:43.000
say the more complicated things, it tries to just break
191
00:09:43.039 --> 00:09:46.360
it apart into smaller things and try and accomplish those.
192
00:09:46.480 --> 00:09:48.639
And so I haven't really pushed the limits.
193
00:09:48.279 --> 00:09:51.399
Of it yet, right, So, I guess one thing that
194
00:09:51.440 --> 00:09:53.759
I'm curious about with some of this, because I guess
195
00:09:53.759 --> 00:09:55.960
you could also just say, you know, here are some
196
00:09:56.039 --> 00:09:59.360
functions that I just have available, right, and then it
197
00:09:59.399 --> 00:10:03.600
could build the agents around those however it wants. But
198
00:10:03.679 --> 00:10:06.120
I guess I'm wondering, you know, how granular does it get?
199
00:10:06.720 --> 00:10:09.879
And I'm also curious what the implications are for Let's
200
00:10:09.919 --> 00:10:12.679
say I want to actually build and design something like
201
00:10:12.720 --> 00:10:14.600
this on my own. I don't want to do the
202
00:10:14.639 --> 00:10:18.360
auto genetic stuff. I just want to, you know, I
203
00:10:18.720 --> 00:10:22.960
want to decide where the boundaries are for for my agents.
204
00:10:23.000 --> 00:10:25.720
You know, does this inform those decisions for you? But
205
00:10:26.480 --> 00:10:30.039
let's let's back up real quick, like how how granular
206
00:10:30.080 --> 00:10:32.320
does it get? And how you know, how does it
207
00:10:32.360 --> 00:10:35.240
handle some of that stuff? Because I'm imagining, for example,
208
00:10:35.480 --> 00:10:38.320
let's say it did need to do some scheduling or
209
00:10:38.799 --> 00:10:42.720
you know, calendar management, right, it could have a connect
210
00:10:42.759 --> 00:10:45.120
to Google Calendar, and I have these six functions that
211
00:10:45.159 --> 00:10:48.120
it can do, or it could say, you know, I'm
212
00:10:48.240 --> 00:10:52.919
just a busy checker and I'm an appointment updater and
213
00:10:52.960 --> 00:10:55.480
I'm right, And so you could end up with agents
214
00:10:55.480 --> 00:10:57.919
that do a bunch of different things as opposed to
215
00:10:57.919 --> 00:11:01.200
one that just kind of generically and it is Google Calendar.
216
00:11:02.080 --> 00:11:02.679
Yeah, I get that.
217
00:11:02.759 --> 00:11:05.480
I mean I built this in a very modular way
218
00:11:05.480 --> 00:11:08.639
because I wanted the ability to have like agents that
219
00:11:08.679 --> 00:11:11.759
I specifically made with certain things. And so you can
220
00:11:12.080 --> 00:11:16.399
build your own agent, and there's even like you can
221
00:11:16.440 --> 00:11:19.120
give it like specifications if you don't want to fill
222
00:11:19.159 -->
00:11:21.559
in all the details, so you can create like kind
223
00:11:21.600 --> 00:11:22.960
of a spec for how the.
224
00:11:22.960 --> 00:11:24.759
Agent should be built.
225
00:11:25.039 --> 00:11:28.320
Okay, but yeah, there's like a register, so you could
226
00:11:28.360 --> 00:11:30.639
like register your agents and then it would make use
227
00:11:30.679 --> 00:11:33.320
of those like in the normal process as it's looking
228
00:11:33.360 --> 00:11:36.879
to accomplish tasks, and you can bypass all have to
229
00:11:36.960 --> 00:11:40.159
use Yeah you don't have to use self assembly.
230
00:11:40.440 --> 00:11:44.039
Yeah right, but but what how how far does the
231
00:11:44.080 --> 00:11:44.840
self assembly go?
232
00:11:45.039 --> 00:11:46.759
It goes pretty deep? Yeah, I mean it.
233
00:11:47.399 --> 00:11:51.360
So I built like a capability system I call it,
234
00:11:51.919 --> 00:11:55.440
where like let's say, you know, a capability could be
235
00:11:55.559 --> 00:12:00.080
most similar to like tools, I guess in the modern realm,
236
00:12:00.120 --> 00:12:01.919
but like I think we'd more of like okay, be
237
00:12:01.960 --> 00:12:05.840
able to search the web, like read a file, generate
238
00:12:05.879 --> 00:12:10.120
a pdf. Like these are all capabilities, right, And so
239
00:12:10.159 --> 00:12:12.919
I made like kind of an agent capability system that
240
00:12:13.000 --> 00:12:16.399
you can register with the agentic system and just say
241
00:12:16.440 --> 00:12:21.480
okay you have and it's like all defined abstractly with okay,
242
00:12:21.559 --> 00:12:25.879
you have this capability, and here's the implementation function and
243
00:12:25.919 --> 00:12:29.519
it takes inputs and it generates a normalized response.
244
00:12:29.639 --> 00:12:32.000
And these like.
245
00:12:32.039 --> 00:12:35.919
Specifications that you're generating for the capability help inform the
246
00:12:36.480 --> 00:12:40.200
agentic system as well what it can do, right as
247
00:12:40.240 --> 00:12:44.919
it's building agents too, So like you can basically define
248
00:12:45.000 --> 00:12:49.039
kind of like what what is capable for agents to
249
00:12:49.120 --> 00:12:51.879
be built with, right, And so it's not just gonna
250
00:12:52.320 --> 00:12:54.559
go in like say oh I can go and like
251
00:12:54.720 --> 00:12:58.919
connect Google Calendar and like automate a huge pipeline. There's
252
00:12:58.960 --> 00:13:01.240
only so many capability is that you can register at
253
00:13:01.279 --> 00:13:03.879
a time. And so like I made it kind of
254
00:13:04.039 --> 00:13:06.799
with that informed decision of like I don't want to
255
00:13:07.399 --> 00:13:08.399
just make stuff up.
256
00:13:08.360 --> 00:13:10.919
Because it was at first.
257
00:13:10.799 --> 00:13:13.000
Not really doing too great, but as soon as you
258
00:13:13.080 --> 00:13:15.440
put some like kind of guardrails around it and give
259
00:13:15.480 --> 00:13:17.120
it like, oh, you can only.
260
00:13:17.000 --> 00:13:19.840
Kind of do these things. It performs really well.
261
00:13:20.080 --> 00:13:23.039
And so like when you especially for you know, it's
262
00:13:23.080 --> 00:13:26.840
funny now that like research a deep research is a thing, right,
263
00:13:27.039 --> 00:13:29.279
Like that's like the easiest thing to do with all
264
00:13:29.320 --> 00:13:32.519
of these agents. It's just like right, the other report
265
00:13:32.720 --> 00:13:37.799
and like search the web, right, like so easy to do, right, yeah,
266
00:13:37.799 --> 00:13:39.440
And so like what happens when you want to do
267
00:13:39.559 --> 00:13:42.679
like next things and have it like yeah, like you said,
268
00:13:42.759 --> 00:13:44.919
talk to APIs or things like that.
269
00:13:45.879 --> 00:13:48.799
It's yeah, it's interesting to see how it evolves.
270
00:13:49.600 --> 00:13:53.799
Yeah, it does? Does it ever evolve? I'm gonna I,
271
00:13:53.879 --> 00:13:55.559
you know, I'm going to kind of build my own
272
00:13:55.840 --> 00:13:58.519
tools or my own capabilities or do you just lock
273
00:13:58.600 --> 00:14:00.919
that down? So it's like you have to ask.
274
00:14:00.799 --> 00:14:05.840
So I've tried, uh my, my preliminited. My initial goal
275
00:14:06.039 --> 00:14:07.919
was could I get it to build itself?
276
00:14:08.120 --> 00:14:11.840
Right? So, like if I I through just like a
277
00:14:12.159 --> 00:14:14.399
plan a goal at it, like hey, I want.
278
00:14:14.240 --> 00:14:18.320
To create like a self assembling agent system in Ruby, right,
279
00:14:18.399 --> 00:14:19.200
and could I.
280
00:14:19.159 --> 00:14:21.440
Get that to actually happen?
281
00:14:22.440 --> 00:14:22.559
Right?
282
00:14:22.639 --> 00:14:25.799
And what right? Like what agents would it built?
283
00:14:26.000 --> 00:14:26.200
You know?
284
00:14:26.200 --> 00:14:30.720
I created a coding agent for Ruby. Right, it created
285
00:14:30.879 --> 00:14:37.039
like uh, you know a I don't know, PM like agents,
286
00:14:37.240 --> 00:14:40.480
like managed a project. Right, It did all these things,
287
00:14:40.799 --> 00:14:41.639
and it got like.
288
00:14:43.240 --> 00:14:43.840
It got to a.
289
00:14:43.799 --> 00:14:46.159
Certain point where it was just like, all right, it
290
00:14:46.200 --> 00:14:49.559
just spent way too long, and it like it said, oh,
291
00:14:49.759 --> 00:14:52.000
I've gone through too many turns, and now I can't
292
00:14:52.440 --> 00:14:55.720
like I say it was decent. You know, it wasn't
293
00:14:55.720 --> 00:14:56.080
what I.
294
00:14:56.039 --> 00:15:01.360
Would code, right, but it's a little rising how far
295
00:15:01.440 --> 00:15:03.279
it did get and the agents that it built, and
296
00:15:03.360 --> 00:15:06.320
so I've actually reused and repurposed some of the agents
297
00:15:06.360 --> 00:15:09.399
that it made in my own interesting, which is kind
298
00:15:09.440 -->
00:15:12.159
of fun. And you know, the probably the biggest benefit
299
00:15:12.200 --> 00:15:15.360
to me personally is I got it to use Olama locally,
300
00:15:17.279 --> 00:15:19.960
so I could just use starcoder or something like that
301
00:15:20.279 --> 00:15:22.480
to run on my own machines and not have to
302
00:15:22.559 --> 00:15:25.279
spend any more. Yeah, but I'm trying to evolve it.
303
00:15:25.279 --> 00:15:29.799
It has this like extension system that I'm trying to
304
00:15:30.240 --> 00:15:33.639
like adapt where you can give it a domain, so
305
00:15:33.720 --> 00:15:35.679
like if you want it to be scoped on healthcare,
306
00:15:35.919 --> 00:15:39.639
then you can add like specific knowledge to that domain
307
00:15:39.879 --> 00:15:43.240
and have it use it in its assembly and execution.
308
00:15:43.519 --> 00:15:48.440
And I have like this initial like self learning system
309
00:15:48.480 --> 00:15:51.519
that I've started to to explore, where it keeps track
310
00:15:51.559 --> 00:15:55.960
of records of itself and tries to create patterns and
311
00:15:56.039 --> 00:16:00.559
like strategies based on how you use it, so it'll
312
00:16:00.600 --> 00:16:05.639
like slowly evolve in different ways based on how you
313
00:16:05.879 --> 00:16:09.399
like train it ultimately or tell it how to learn.
314
00:16:11.679 --> 00:16:13.799
And so I've been exploring That's probably where I want
315
00:16:13.799 --> 00:16:16.600
to spend more of my time. Next is kind of
316
00:16:16.600 --> 00:16:20.080
getting it to recognize things that it does well and
317
00:16:20.200 --> 00:16:24.120
doesn't and how do I tell it and inform it
318
00:16:24.200 --> 00:16:28.000
when it's doing something that it shouldn't be doing or not.
319
00:16:28.519 --> 00:16:32.240
I haven't really figured out that like human intervention aspect
320
00:16:32.919 --> 00:16:34.919
right at the moment. It's kind of just like making
321
00:16:34.919 --> 00:16:35.759
that up on its own.
322
00:16:35.960 --> 00:16:37.919
So it's kind of interesting.
323
00:16:37.480 --> 00:16:40.720
To explore what models do and what they learn on
324
00:16:40.759 --> 00:16:43.679
their own because they are all different. It's kind of
325
00:16:43.679 --> 00:16:46.879
fun to rerun the same experiments with different models and
326
00:16:47.000 --> 00:16:49.120
see how it evolves differently.
327
00:16:49.440 --> 00:16:54.720
Yeah, I bet so. I'm a little curious, you know,
328
00:16:54.759 --> 00:16:57.600
as you get into this, like what is it showing
329
00:16:57.639 --> 00:17:00.720
you or telling you about using agents or building agents?
330
00:17:00.759 --> 00:17:03.159
Like what has it taught you any lessons that it's
331
00:17:03.240 --> 00:17:05.880
like when I do this on this other project, I
332
00:17:05.880 --> 00:17:08.480
ought to build my agents more this way or that way.
333
00:17:08.839 --> 00:17:11.319
It's yeah, I would say the biggest thing I've kind
334
00:17:11.319 --> 00:17:14.240
of taken away is that lms are not good at
335
00:17:14.279 --> 00:17:20.039
like managing their own artifacts, right, Like if you tell
336
00:17:20.079 --> 00:17:23.559
it to like do something and like keep track of something,
337
00:17:24.160 --> 00:17:27.559
it's going to do it differently almost every time, and
338
00:17:27.720 --> 00:17:30.599
like you might see some normalization, but like it's going
339
00:17:30.680 --> 00:17:32.400
to take a lot of prompting to get it to
340
00:17:32.559 --> 00:17:36.000
like be any like deterministic at all.
341
00:17:36.200 --> 00:17:39.880
And so I've I've found that like trying to trying to.
342
00:17:39.839 --> 00:17:44.680
Help it avoid maybe some of those pathways to generate
343
00:17:44.720 --> 00:17:48.119
specific things in certain formats to just avoid those. Getting
344
00:17:48.119 --> 00:17:50.119
back to the lessons, it's hard to tell what is
345
00:17:50.160 --> 00:17:53.480
a good lesson or not right because so much of
346
00:17:53.519 --> 00:17:56.319
it is like the LM's deciding what to do. And
347
00:17:56.359 --> 00:18:00.279
I guess what I found is the more struck sure
348
00:18:00.680 --> 00:18:04.720
and reils that you give to llms, the more deterministic
349
00:18:05.359 --> 00:18:10.880
you can make what it does. And so it doesn't
350
00:18:10.960 --> 00:18:17.279
know anything, but if you if you can help kind
351
00:18:17.279 --> 00:18:20.519
of visualize things for it, it seems.
352
00:18:20.240 --> 00:18:22.240
To produce much better results.
353
00:18:23.200 --> 00:18:26.400
What I mean by that is like you know it
354
00:18:26.640 --> 00:18:29.400
has a ton of training data, so you know you
355
00:18:29.519 --> 00:18:31.400
kind of know, like you have a good idea and
356
00:18:31.559 --> 00:18:33.799
understanding of what training data has just by asking you
357
00:18:33.880 --> 00:18:37.759
a bunch of questions, right, and but you can get
358
00:18:37.799 --> 00:18:42.279
an idea for like what concepts it has too, right,
359
00:18:42.480 --> 00:18:45.720
And so I like to like poke the models all
360
00:18:45.759 --> 00:18:49.559
the time on what concepts it can recognize, right, And
361
00:18:49.599 --> 00:18:51.759
if you give it a new concept, can it like
362
00:18:52.759 --> 00:18:58.480
continue to like reading about that concept and like you know,
363
00:18:58.599 --> 00:19:01.960
mutate it at as like you would right, Like if
364
00:19:02.000 --> 00:19:05.119
you're going to create like a user object in rails, right,
365
00:19:05.279 --> 00:19:07.960
like and you wanted to add a new attribute to it?
366
00:19:08.039 --> 00:19:09.599
Is like that straightforward?
367
00:19:09.680 --> 00:19:12.240
Like would you be like, well, why would I add, right,
368
00:19:12.359 --> 00:19:15.680
like a shopping cart to a user? Maybe you would, right,
369
00:19:15.799 --> 00:19:18.440
But like would you would you add like a I
370
00:19:18.440 -->
00:19:21.319
don't know something super unrelated like a I don't know
371
00:19:21.359 --> 00:19:23.839
what Maybe that's a bad example. Let's say you had
372
00:19:23.839 --> 00:19:26.920
a school, would you add like a grocery store to it?
373
00:19:27.079 --> 00:19:28.240
Right? Right? Uh?
374
00:19:28.440 --> 00:19:31.279
Can the LLM like know that kind of thing?
375
00:19:31.759 --> 00:19:35.000
The answer is yes, the lms are very good at
376
00:19:35.000 --> 00:19:38.200
those connections of things, right, And so like, uh, the
377
00:19:38.240 --> 00:19:42.079
further away that the concepts are actually better to the genet,
378
00:19:42.839 --> 00:19:46.359
like the generations will get right, because that's what it's doing.
379
00:19:46.400 --> 00:19:49.839
It's like trying to hone in on very like similar things,
380
00:19:49.960 --> 00:19:52.119
right and like what the next things are. And so
381
00:19:52.160 --> 00:19:56.079
if you can give it more like funneling going back
382
00:19:56.359 --> 00:20:00.039
to Obi's like you know, narrowing the path, right, the
383
00:20:00.079 --> 00:20:02.440
more you can do that, even on a conceptual level,
384
00:20:02.759 --> 00:20:06.480
the better, right. And so that's where I've kind of
385
00:20:06.519 --> 00:20:09.839
like taken, like been blown away by how well this works.
386
00:20:10.160 --> 00:20:12.480
Is like I can just give it more and more.
387
00:20:12.759 --> 00:20:17.119
Concrete concepts for it to reason about, and it can
388
00:20:17.160 --> 00:20:20.359
figure out how they work together, right, And then okay, well,
389
00:20:20.400 --> 00:20:23.480
if you then help it, like tell it how those
390
00:20:23.480 --> 00:20:26.559
things connect and work together, it doesn't even better. And
391
00:20:26.599 --> 00:20:29.000
so like and the more things that you can like
392
00:20:29.440 --> 00:20:33.000
you know, glue together and firm up, like, the better
393
00:20:33.079 --> 00:20:35.440
that it performs, and the more determinists.
394
00:20:34.839 --> 00:20:36.519
That you can get it. And so I guess that's
395
00:20:36.640 --> 00:20:37.279
kind of what I've.
396
00:20:37.200 --> 00:20:41.279
Taken, is like if you can decouple that idea and
397
00:20:41.400 --> 00:20:44.240
like make a bunch of things so that you can
398
00:20:44.279 --> 00:20:48.119
define those like concepts and how they work together, then
399
00:20:48.160 --> 00:20:49.759
you'll get the best result.
400
00:20:49.480 --> 00:20:55.160
From all of this, gotcha, So which is the most
401
00:20:55.160 --> 00:20:58.039
important to master? Then? Is is it the prompt? Is
402
00:20:58.079 --> 00:21:03.160
it the definition of the problem? Is it more affinement
403
00:21:03.279 --> 00:21:03.839
on the tool?
404
00:21:04.920 --> 00:21:06.400
It's always the definition of the realm.
405
00:21:06.519 --> 00:21:09.599
I mean helm's are dumb, right, Like they can't come
406
00:21:09.680 --> 00:21:11.880
up with their own stuff, right, Like you could try
407
00:21:11.920 --> 00:21:14.680
your best and like tell it to create the best
408
00:21:14.680 --> 00:21:18.279
company in the world. It's not gonna make any money, right,
409
00:21:18.319 --> 00:21:21.720
Like it has no desires, you know, like it's missing
410
00:21:21.759 --> 00:21:23.799
a lot of the things that it takes to like
411
00:21:24.519 --> 00:21:29.359
create something substantial, like to create something that's meaningful to you,
412
00:21:29.480 --> 00:21:31.599
because it doesn't really care about you.
413
00:21:32.480 --> 00:21:33.920
It doesn't care about anyway.
414
00:21:34.359 --> 00:21:37.079
So you know, it's always you know, that's why you
415
00:21:37.079 --> 00:21:40.039
know spectrum in development if you've heard that, Like that's
416
00:21:40.079 --> 00:21:44.640
become so popular because like really this how what you're
417
00:21:44.640 --> 00:21:47.680
telling it to make and do is like the most
418
00:21:47.680 --> 00:21:48.759
important part.
419
00:21:50.920 --> 00:21:53.079
Yeah, and so the more Yeah.
420
00:21:53.200 --> 00:21:55.720
It sounds a little bit like So we had a
421
00:21:55.759 --> 00:22:01.759
conversation on JavaScript Jabber with Eric Kens anyway, he works
422
00:22:01.240 --> 00:22:06.039
for Amazon, and he was on talking about their Kiro editor.
423
00:22:06.319 --> 00:22:08.680
That that was kind of we talked about it literally
424
00:22:08.680 --> 00:22:11.559
like two weeks later. Curser added, their killer feature, which
425
00:22:11.680 --> 00:22:14.480
was the plan. Right, So you had agent, you had
426
00:22:14.599 --> 00:22:17.519
asking you. Now you have a plan and so it'll
427
00:22:17.519 --> 00:22:19.920
actually pull together the entire plan and things like that.
428
00:22:20.000 --> 00:22:21.920
And so it sounds like what you're talking about is
429
00:22:21.960 --> 00:22:23.720
the better your plan is and the better you can
430
00:22:23.759 --> 00:22:27.000
specify what you want, the better the tool works.
431
00:22:27.160 --> 00:22:29.880
Yeah, totally, and the better the plan works.
432
00:22:30.160 --> 00:22:35.960
Yeah, you know, forget the tools on their own, Like
433
00:22:36.079 --> 00:22:39.920
the tools are just actions that can be taken, right,
434
00:22:40.000 --> 00:22:43.319
and so it's it's all about the plan. It's all
435
00:22:43.319 --> 00:22:48.279
about what you really want to do, right, Like if
436
00:22:48.319 --> 00:22:52.759
I tell my son to go outside and like clean up,
437
00:22:52.839 --> 00:22:56.960
I wouldn't expect anything to happen, you know, Like what
438
00:22:57.000 --> 00:22:57.640
does that mean?
439
00:22:57.880 --> 00:23:00.319
You know, it wouldn't mean anything for me if I
440
00:23:00.440 --> 00:23:02.000
was asked to go outside and clean up, I guess
441
00:23:02.039 --> 00:23:04.480
like rape, Like I don't.
442
00:23:04.400 --> 00:23:08.839
Yeah, so I guess. Part of my question then is,
443
00:23:09.160 -->
00:23:12.680
you know, it seems like AI is evolving so fast, right,
444
00:23:12.759 --> 00:23:15.599
and so, like you were talking about this autogenetic AI
445
00:23:15.799 --> 00:23:20.160
agent stuff and I was like, I mean, you explained
446
00:23:20.160 --> 00:23:22.359
it to me in like two sentences and I understood
447
00:23:22.400 --> 00:23:24.480
what it was, but I don't know if it's something
448
00:23:24.480 --> 00:23:27.920
that I would have dreamed up on my own. And
449
00:23:28.000 --> 00:23:30.400
it seems like, you know that this is just another
450
00:23:30.640 --> 00:23:35.839
step along the way toward wherever we wind up with AI.
451
00:23:36.160 --> 00:23:39.680
And so part of me is wondering, is this is
452
00:23:39.720 --> 00:23:42.039
this a tool or a technique that people are going
453
00:23:42.079 --> 00:23:45.599
to start adopting now, and where where does it lead
454
00:23:45.680 --> 00:23:48.279
us to over the next six months to a year.
455
00:23:48.359 --> 00:23:50.559
I think we're already starting to see that where like
456
00:23:51.160 --> 00:23:54.480
the where you know, where I first saw the style
457
00:23:54.680 --> 00:23:58.839
of AI use was like air handling. Some air happens
458
00:23:58.960 --> 00:24:02.799
while you're developing and you ask an LM, can you
459
00:24:02.839 --> 00:24:03.160
fix this?
460
00:24:03.400 --> 00:24:04.839
Can you handle this case?
461
00:24:05.839 --> 00:24:06.079
You know?
462
00:24:06.319 --> 00:24:11.799
And a lot of times, especially for JavaScript errors, right,
463
00:24:12.480 --> 00:24:15.400
that was like the classic example back in the day
464
00:24:15.799 --> 00:24:18.079
when you're using an LM and you want you know,
465
00:24:18.240 --> 00:24:22.319
JSON back and it gave you improperly format a JSON
466
00:24:22.680 --> 00:24:25.359
and you ask the LM again, hey fix this JSON,
467
00:24:25.839 --> 00:24:28.559
and ninety nine percent of the time it'll fix that, Jason,
468
00:24:28.680 --> 00:24:30.759
so you don't have an issue, and this goes and stuff.
469
00:24:30.759 --> 00:24:32.720
I feel lazy when I do that, but I do it.
470
00:24:32.640 --> 00:24:35.119
All the time, all the time, right, And so like
471
00:24:35.720 --> 00:24:37.720
this makes a lot of sense, and this is a
472
00:24:37.720 --> 00:24:41.519
little bit like autogenetic, right, Like you're getting the system
473
00:24:42.039 --> 00:24:46.240
like the self healing aspects is like autogenetic, like you're
474
00:24:46.279 --> 00:24:51.559
getting the system itself to generate, you know, Like and
475
00:24:51.799 --> 00:24:54.039
I think it's going like we're starting to see you know,
476
00:24:54.079 --> 00:24:58.319
products crop up around this kind of thing like security analysis,
477
00:24:59.119 --> 00:25:02.160
security prevention and right, like being able to get ahead
478
00:25:02.559 --> 00:25:06.599
of like these issues ahead of time, having something like
479
00:25:07.000 --> 00:25:10.480
we're we're kind of seeing the ambient response so far
480
00:25:10.759 --> 00:25:13.920
of things that are just latent sitting in your system
481
00:25:14.279 --> 00:25:18.160
that are then analyzing and then getting actions to set
482
00:25:18.240 --> 00:25:20.680
up to do later, which is less like of this
483
00:25:21.599 --> 00:25:26.440
you know maybe generative aspect of itself, but it is
484
00:25:26.480 --> 00:25:29.039
a little bit like you know, still that self feeling
485
00:25:29.200 --> 00:25:33.720
self like you know, improving nature, which are along the
486
00:25:33.759 --> 00:25:38.079
same lines in my mind. And so I'm wondering if
487
00:25:38.079 --> 00:25:41.160
we're more like getting to that, like you know, Nvidia
488
00:25:41.279 --> 00:25:44.319
is trying to make their own like kernel right where
489
00:25:44.359 --> 00:25:47.039
an LM sits on the kernel, which is really interesting
490
00:25:47.440 --> 00:25:51.240
And what what does it look like when the system
491
00:25:51.279 --> 00:25:57.279
that you're using in general, right is like an agent, right,
492
00:25:57.359 --> 00:26:01.160
and it's it's a little that's like kind of the
493
00:26:01.200 --> 00:26:04.160
mind bend the right, Like yeah, okay, Like if you
494
00:26:04.240 --> 00:26:06.400
just log on a computer, you start talking to it
495
00:26:06.480 --> 00:26:10.200
and it can do stuff for you, like kind of wild, right,
496
00:26:10.319 --> 00:26:11.960
Like what does that do to apps?
497
00:26:12.039 --> 00:26:12.319
Right when?
498
00:26:12.359 --> 00:26:14.720
And you can be like, all right, well create slack.
499
00:26:14.759 --> 00:26:16.960
I want to communicate with my friends, right, and like,
500
00:26:17.079 --> 00:26:18.240
right it goes I was.
501
00:26:18.279 --> 00:26:21.000
Going to ask how far down the rabbit hole does
502
00:26:21.039 --> 00:26:24.079
it go? Right where it's it's okay, Well, I'm going
503
00:26:24.119 --> 00:26:26.839
to generate myself because you know, initially I could see
504
00:26:26.880 --> 00:26:29.279
it where it's okay, I've got a browser, I've gotta this,
505
00:26:29.400 --> 00:26:32.119
I've got that. But yeah, eventually it just gets to
506
00:26:32.160 --> 00:26:34.000
the point where it's like I'm going to generate a
507
00:26:34.039 --> 00:26:37.960
windowing system, right, I'm going to generate a something I
508
00:26:37.960 --> 00:26:41.759
can make API calls with. And so you know, my
509
00:26:42.000 --> 00:26:46.440
interface to the world through my operating system is completely
510
00:26:46.480 --> 00:26:50.880
different from yours because it built something around how I
511
00:26:51.039 --> 00:26:54.279
think about how I communicate with the world and how
512
00:26:54.359 --> 00:26:58.160
I research things and how I approach different things as
513
00:26:58.160 --> 00:27:02.160
opposed to you. And yeah, and so I don't use
514
00:27:02.240 --> 00:27:06.839
the standard app. I use the
custom whatever that it knows.
515
00:27:06.880 --> 00:27:08.920
I like, I mean, I think Google is onto the
516
00:27:09.000 --> 00:27:12.079
right thing with their agent agent protocols. But I think
517
00:27:12.200 --> 00:27:14.440
I think they were just too early, right, Like we
518
00:27:14.519 --> 00:27:18.599
need we need more protocols, like everybody like trashes MCP
519
00:27:18.960 --> 00:27:21.000
for being like, oh, it's just like a wrap around
520
00:27:21.119 --> 00:27:25.079
open API, which maybe it is, but like I think
521
00:27:25.279 --> 00:27:30.279
the definitions of the specifications are the value, right, like
522
00:27:31.119 --> 00:27:34.319
defining what it means to be a tool, how how
523
00:27:34.359 --> 00:27:39.279
that tool interacts, how it can like respond, how it's defined,
524
00:27:39.759 --> 00:27:44.720
and then you know, going further, what are the protocols
525
00:27:44.799 --> 00:27:46.759
that can communicate with it?
526
00:27:47.599 --> 00:27:49.519
And so like all of that stuff is very important,
527
00:27:49.519 --> 00:27:49.880
and like.
528
00:27:50.400 --> 00:27:53.559
That is kind of like what is missing and what
529
00:27:53.640 --> 00:27:56.240
will be most important if we move to this world
530
00:27:56.279 --> 00:27:59.720
of like an operating system level, right, is like it'll
531
00:27:59.759 --> 00:28:04.000
just be a you know, huge like pool of protocols
532
00:28:04.599 --> 00:28:07.759
that like, okay, if you're creating an app like on
533
00:28:07.839 --> 00:28:10.839
this new system, it the artifact of that is the
534
00:28:10.839 --> 00:28:14.319
protocol of how to use that that then other things
535
00:28:14.640 --> 00:28:19.160
can inspect and then build for right, And so I
536
00:28:19.200 --> 00:28:21.759
see this kind of like and it's a little funny
537
00:28:21.759 --> 00:28:24.240
because like the path to get there is like a
538
00:28:24.240 --> 00:28:27.720
bunch of trash, right, Like the paths again, where we
539
00:28:27.759 --> 00:28:30.799
are today is like currently trash. You know, so like
540
00:28:31.519 --> 00:28:33.440
we had to get through all of this like bad
541
00:28:33.559 --> 00:28:37.359
generation before to be like confident enough now where it's
542
00:28:37.359 --> 00:28:41.519
like we're really good and you're kind of like impressed
543
00:28:41.519 --> 00:28:44.319
by it, but like to get to that next level again,
544
00:28:44.559 --> 00:28:46.839
you have to get through all of the trash work.
545
00:28:47.279 --> 00:28:49.400
And we're like we're already seeing that with like AI
546
00:28:49.480 --> 00:28:51.319
slop right, like that's the new thing.
547
00:28:52.440 --> 00:28:56.079
We We've always done this, right, It's just it feels
548
00:28:56.160 --> 00:28:59.039
like the pace of iteration is so much faster, right,
549
00:28:59.240 --> 00:29:01.920
I mean, you know, go back through rails right, you know,
550
00:29:02.119 --> 00:29:04.680
we we had some people had some other great ideas.
551
00:29:04.680 --> 00:29:07.720
They put them into MERB. We went through that heinous
552
00:29:07.920 --> 00:29:12.000
upgrade you know, to Rails three, which was super painful,
553
00:29:12.319 --> 00:29:16.240
the asset pipeline situation right where we went from sprockets
554
00:29:16.319 --> 00:29:20.640
to webpacker out to currently prop shaft, which is better,
555
00:29:20.680 --> 00:29:24.920
but it's still not like super intuitive friendly whatever you
556
00:29:24.960 --> 00:29:28.079
know fixes all my issues, right, it's just way more
557
00:29:28.119 --> 00:29:32.480
approachable than webpacker, right, And so we're going through the
558
00:29:32.519 --> 00:29:35.359
same thing here where I mean I remember having conversations
559
00:29:35.400 --> 00:29:38.559
with just regular people like my father in law where
560
00:29:38.599 --> 00:29:42.279
he's like, well, never trust AI because it hallucinates all
561
00:29:42.279 --> 00:29:44.880
the time. And I said, well, give it a couple
562
00:29:44.960 --> 00:29:47.920
of years because they're going to keep improving it, right,
563
00:29:48.039 --> 00:29:51.880
And so does it still hallucinate? Yeah, but does it
564
00:29:51.920 --> 00:29:53.519
do it a lot less and does it have a
565
00:29:53.559 --> 00:29:58.519
lot more tools at disposal? Absolutely? And so again, like
566
00:29:58.559 --> 00:30:00.440
you're saying, I mean, we're just going to kind of
567
00:30:00.519 --> 00:30:03.640
have to see how this evolves. It'll be really interesting
568
00:30:03.680 --> 00:30:06.160
to see what gets picked up and what gets dropped
569
00:30:06.160 --> 00:30:08.400
and if we find a better way. I mean, one
570
00:30:08.440 --> 00:30:10.720
of the issues I have with things like MCP is
571
00:30:10.720 --> 00:30:12.480
that it takes up a whole ton of my context
572
00:30:12.559 --> 00:30:14.839
to tell it all the things it can do, and
573
00:30:15.960 --> 00:30:18.319
you know, and it's like, no, I want the context
574
00:30:18.319 --> 00:30:21.759
to be here's all the stuff that Chuck cares about, right,
575
00:30:22.039 --> 00:30:24.519
figure the f out right? And so.
576
00:30:26.000 --> 00:30:29.319
Yeah, it's interesting. A concept was brought up at.
577
00:30:29.160 --> 00:30:34.119
The AI Engineering Code Conference our Code Summit recently in
578
00:30:34.200 --> 00:30:34.519
New York.
579
00:30:34.839 --> 00:30:36.640
Concept called progressive disclosure.
580
00:30:36.960 --> 00:30:41.079
And it's an interaction design like principle of just like
581
00:30:41.240 --> 00:30:47.240
incrementally like disclosing new like information to a user right
582
00:30:47.400 --> 00:30:50.880
or to an interface. And this is now being applied
583
00:30:50.920 --> 00:30:53.960
a lot to like coding agents because of this exact
584
00:30:54.000 --> 00:30:56.599
problem you're saying, where all right, you have like I
585
00:30:56.640 --> 00:31:01.000
don't know,
thousands of MCP servers and tools and documents,
586
00:31:01.079 --> 00:31:03.319
and you know, like there's no way it can keep
587
00:31:03.359 --> 00:31:05.920
all that in its context. How do you like surface
588
00:31:05.960 --> 00:31:08.079
the right things at the right time? Like it's a
589
00:31:08.160 --> 00:31:11.160
common like current problem, and this seems to be like
590
00:31:11.200 --> 00:31:13.799
the best solution that I've seen so far of like
591
00:31:14.480 --> 00:31:20.240
basically creating like smaller chunked like summarizations of what the
592
00:31:20.400 --> 00:31:24.480
different things are that can be surfaced, and then providing
593
00:31:24.519 --> 00:31:28.039
it a you know, a link ultimately to find out
594
00:31:28.039 --> 00:31:32.440
more right, right, like demand pages right, Like man, you
595
00:31:32.519 --> 00:31:36.400
know that's why like CLI tools will always work better
596
00:31:36.759 --> 00:31:40.319
than any MCP server you set up, because like the
597
00:31:40.480 --> 00:31:46.880
help mechanisms are so like token conscious yep, and also
598
00:31:47.039 --> 00:31:51.519
like available and straightforward, like it's all normalized, right, Like
599
00:31:51.519 --> 00:31:55.720
there's a protocol that like it follows right and gives
600
00:31:55.759 --> 00:31:58.359
you the information that is needed in order to learn
601
00:31:58.359 --> 00:32:00.640
how to use it. But also you just be like,
602
00:32:01.119 --> 00:32:03.119
you know, show me all the commands I have, right,
603
00:32:03.200 --> 00:32:06.200
and it doesn't give you like pages of text. It
604
00:32:06.200 --> 00:32:10.079
gives you like a one liner of like all the commands, right, yeah,
605
00:32:10.079 --> 00:32:13.799
And like that's that is very valuable to like nlll
606
00:32:14.000 --> 00:32:14.400
F right.
607
00:32:15.079 --> 00:32:17.039
Yeah, it's like this kind of concept.
608
00:32:17.480 --> 00:32:19.759
I think it's being more and more just like bod
609
00:32:19.799 --> 00:32:23.480
skills are a perfect example of this progressive disclosure where
610
00:32:23.559 --> 00:32:25.799
you have like this made a data the front matter
611
00:32:25.839 --> 00:32:28.720
they call it, where you could say, hey, this is
612
00:32:28.799 --> 00:32:31.319
like information about what the skill does and is and
613
00:32:31.720 --> 00:32:33.640
the things that can be used with it and the
614
00:32:33.680 --> 00:32:36.880
tools that it uses, and like just surface this right
615
00:32:37.119 --> 00:32:39.559
to all the other ones and it does like an
616
00:32:39.559 --> 00:32:40.400
incredible job.
617
00:32:41.599 --> 00:32:44.319
Yeah, way better, yeah, way better than the tools.
618
00:32:45.039 --> 00:32:45.279
Yeah.
619
00:32:45.599 --> 00:32:48.079
Not that not that tools aren't valuable, but I think
620
00:32:48.119 --> 00:32:51.480
we're like kind of moving away from the idea of
621
00:32:51.559 --> 00:32:55.000
these like actionable things needing to be dumped at the
622
00:32:55.480 --> 00:32:56.200
m all the time.
623
00:32:57.000 --> 00:33:00.960
Right, So I kind of want to spin a little
624
00:33:01.000 --> 00:33:04.680
bit back toward the autogenetic AI team. You know that
625
00:33:04.720 --> 00:33:07.240
you you it kind of spins up its own set
626
00:33:07.279 --> 00:33:09.839
of agents to do the work. Are you using this
627
00:33:09.960 --> 00:33:14.720
anywhere in production or experimenting with this anywhere where it's
628
00:33:14.839 --> 00:33:16.000
likely to go into production?
629
00:33:16.279 --> 00:33:18.880
No? No yet, I do have.
630
00:33:19.440 --> 00:33:23.440
I do have some experiments in the works of using
631
00:33:23.519 --> 00:33:26.960
it within a rails app uh that I that I
632
00:33:27.000 --> 00:33:29.920
hope to get to production. It's it's hard because it's
633
00:33:29.960 --> 00:33:34.039
like the models still aren't quite there. Right, they're better, right,
634
00:33:36.200 --> 00:33:38.359
you know, the best performance I've seen is from Opus
635
00:33:38.400 --> 00:33:38.960
four five.
636
00:33:39.079 --> 00:33:40.319
But it's just like so it's a.
637
00:33:40.319 --> 00:33:44.119
Little less extensive now, but like right, yeah, not not
638
00:33:44.279 --> 00:33:48.960
worthwhile to like introduce in a you know, in any
639
00:33:48.960 --> 00:33:53.599
official capacity on my own, so to be cost effective.
640
00:33:54.319 --> 00:33:57.200
Yeah, So I guess the other question related to that
641
00:33:57.279 --> 00:33:59.759
then is and it sounds like the answer to this
642
00:33:59.839 --> 00:34:02.319
qu question is going to be yeah, that's correct. But
643
00:34:03.039 --> 00:34:06.200
so the main limitation to this is the limitations on
644
00:34:06.240 --> 00:34:09.719
the capabilities of the models. And so if we had
645
00:34:09.800 --> 00:34:13.119
stronger models that were able to write better code or
646
00:34:13.360 --> 00:34:16.679
make better decisions, or maybe had a larger context window
647
00:34:16.719 --> 00:34:19.519
so you could it could figure out more stuff and
648
00:34:19.559 --> 00:34:22.679
remember more stuff. Those those kinds of things would make
649
00:34:22.760 --> 00:34:25.840
this a much more effective approach. Yeah.
650
00:34:25.880 --> 00:34:31.119
I mean it's interesting because I see production changing, right,
651
00:34:31.199 --> 00:34:34.239
Like when people say, well is this in production? You
652
00:34:34.280 --> 00:34:38.880
know your local system is ultimately becoming production now, right
653
00:34:38.920 --> 00:34:42.960
with all of these coding agents. Like if I wanted
654
00:34:42.960 --> 00:34:45.679
to like for my job personally, you know, maybe I'm
655
00:34:45.679 --> 00:34:49.039
biased because like I'm a programmer, right, but like if
656
00:34:49.400 --> 00:34:51.840
part of my job is to like review code, right,
657
00:34:52.320 --> 00:34:54.920
And so I'm a coding agent
looks up to the
658
00:34:54.920 --> 00:34:59.079
getthub cli and can review the prs that are open
659
00:34:59.159 --> 00:35:02.239
that I'm assigned to and give me a breakdown and
660
00:35:02.880 --> 00:35:10.920
have some actionable comments like right, and so like all
661
00:35:11.000 --> 00:35:13.960
that stuff is kind of like your local machine is
662
00:35:13.960 --> 00:35:17.039
becoming more and more of a production system that you
663
00:35:17.039 --> 00:35:19.599
can run more and more things on, right, and especially
664
00:35:19.639 --> 00:35:21.960
as we start, like as I start to see this
665
00:35:22.000 --> 00:35:24.880
stuff coming, like I feel like the production line is
666
00:35:24.920 --> 00:35:28.119
going to blend with local so much because of what
667
00:35:28.199 --> 00:35:30.719
you can produce on your local machine now where you
668
00:35:30.760 --> 00:35:33.920
don't need to offload that work in the cloud anymore
669
00:35:34.119 --> 00:35:36.719
because you can just generate a quick ashumel page and
670
00:35:36.719 --> 00:35:39.639
whether or not it like persists or not, like that's fine,
671
00:35:39.920 --> 00:35:42.719
because it was just to show you something, right, or
672
00:35:42.719 --> 00:35:46.079
to do something and like create that interface, and that
673
00:35:46.119 --> 00:35:50.519
those like the interfaces are becoming temporary, right, like and
674
00:35:50.760 --> 00:35:54.360
at least for our work, right, but I can see
675
00:35:54.400 --> 00:35:56.480
I see it more and more, right, and so like
676
00:35:56.960 --> 00:35:59.960
you could do like a big question is always like, well,
677
00:36:00.000 --> 00:36:01.719
well what can't.
678
00:36:01.440 --> 00:36:03.159
You do with cloud code? Right?
679
00:36:03.320 --> 00:36:06.320
What can't you do with chat GPT? Right, what can't
680
00:36:06.320 --> 00:36:08.639
you do with these things on their own? And there's
681
00:36:08.840 --> 00:36:12.280
the answer to that becomes less and less things.
682
00:36:12.440 --> 00:36:12.639
Right.
683
00:36:13.440 --> 00:36:15.199
And so if you're running all of this on your
684
00:36:15.239 --> 00:36:19.719
machine anyway, like where is production right if you're doing
685
00:36:19.760 --> 00:36:22.920
more and more work on these things. And so I
686
00:36:22.960 --> 00:36:25.000
see it as like your local environment kind of like
687
00:36:25.280 --> 00:36:27.519
taking on more of the chunk out of that production.
688
00:36:28.119 --> 00:36:31.480
And I use this library a lot on my local
689
00:36:31.559 --> 00:36:34.559
machine to do different tasks that I know it does well, right,
690
00:36:35.000 --> 00:36:38.519
And so like, really most of the exploration that we're
691
00:36:38.519 --> 00:36:41.400
seeing is well, what does it work well doing?
692
00:36:42.000 --> 00:36:44.159
And the answer to that is like more things.
693
00:36:43.840 --> 00:36:46.440
Because the models are getting better, right, But it's also
694
00:36:46.960 --> 00:36:49.639
like go use it, try it out, and if it
695
00:36:49.679 --> 00:36:52.039
works for you, like just keep using it.
696
00:36:53.159 --> 00:36:56.760
Yeah, Like I think if I can restate what you're saying,
697
00:36:57.039 --> 00:36:59.639
because whenever we think of production, like you know, if
698
00:36:59.639 --> 00:37:01.599
you work a company that you know has like this
699
00:37:01.679 --> 00:37:05.159
giant rails app or you know, micro services or what however,
700
00:37:05.199 --> 00:37:09.559
however your architected, however, your architecture, production is is that
701
00:37:09.679 --> 00:37:12.280
set of code that you deploy out to the web
702
00:37:12.320 --> 00:37:15.519
servers so that people can interact. But what you're saying
703
00:37:15.639 --> 00:37:19.400
is is production anymore is wherever the work's getting done.
704
00:37:19.599 --> 00:37:24.679
And so if you know, in that case, then you're using,
705
00:37:25.079 --> 00:37:31.719
for example, the auto autogenetic tool to get work done
706
00:37:32.199 --> 00:37:35.679
locally because that's where the work is done, you know.
707
00:37:35.760 --> 00:37:39.320
And similarly, in a lot of these other cases, the
708
00:37:39.639 --> 00:37:41.760
line's going to get blurred from is it on the
709
00:37:41.800 --> 00:37:46.400
production to server to you know, where am I getting
710
00:37:46.400 --> 00:37:48.559
the work done? Right? So is it going to work
711
00:37:48.599 --> 00:37:52.280
on my machine and then connect to some quote unquote
712
00:37:52.320 --> 00:37:55.119
production system out there in the cloud or you know,
713
00:37:55.159 --> 00:37:57.119
and how much of this is going to live back
714
00:37:57.159 --> 00:38:00.639
here with wherever I'm at and wherever I'm doing the
715
00:38:00.679 --> 00:38:02.480
work and wherever I'm interacting with it?
716
00:38:02.840 --> 00:38:04.800
Yeah, you know, we had we had Dave kamer on
717
00:38:05.800 --> 00:38:08.679
at one point where he was talking about his local
718
00:38:08.719 --> 00:38:11.119
server setup, which is just mind bogging if you if
719
00:38:11.119 --> 00:38:13.199
you ever get to talk to Dave, ask him, ask
720
00:38:13.320 --> 00:38:19.440
him about his local service setup. But I guess right,
721
00:38:19.920 --> 00:38:23.519
but it this was years ago to now, right, But
722
00:38:23.599 --> 00:38:26.400
he had to a point where you know, he could
723
00:38:26.440 --> 00:38:32.079
basically send a a web request to this server with
724
00:38:32.159 --> 00:38:34.840
a job to do, right, like almost like a job
725
00:38:34.880 --> 00:38:38.000
in Q but to his local machine right right, And
726
00:38:38.039 --> 00:38:40.400
I see, like more like from a system that like
727
00:38:40.559 --> 00:38:42.440
you know, was had an app and everything.
728
00:38:42.840 --> 00:38:43.400
I think it was.
729
00:38:43.559 --> 00:38:48.480
This was for transcribing the videos on
Drifting Drifting Ruby, right,
730
00:38:48.639 --> 00:38:50.599
And he had this job that was like okay, like
731
00:38:50.639 --> 00:38:53.719
in queue the transcription process and it would like basically
732
00:38:53.719 --> 00:38:56.320
trigger back home at his computer and run it through
733
00:38:56.320 --> 00:38:58.159
some local models so we wouldn't have to pay for
734
00:38:58.199 --> 00:39:01.000
any of it, and then transrib it right, and then
735
00:39:01.079 --> 00:39:05.119
send the request back up. So again like perfect example
736
00:39:05.199 --> 00:39:10.920
of like where is production? Right? Like right, Granted he
737
00:39:10.920 --> 00:39:14.280
he has his own like legit production set up at home.
738
00:39:15.480 --> 00:39:18.360
Yeah, he has a server rack and all kinds of
739
00:39:18.360 --> 00:39:19.039
stuff at home.
740
00:39:19.159 --> 00:39:22.760
But you know, like it's still the same. You know,
741
00:39:22.800 --> 00:39:25.000
it's still the same, like where's the work getting done?
742
00:39:25.079 --> 00:39:27.400
I feel like more people don't want it to get
743
00:39:27.400 --> 00:39:30.159
done in the cloud, you know, like all of the
744
00:39:30.320 --> 00:39:33.360
DH stuff you know has been pushing back against the
745
00:39:33.400 --> 00:39:37.039
cloud and having you know, machines running in your closet.
746
00:39:37.199 --> 00:39:37.400
Right.
747
00:39:37.519 --> 00:39:39.480
I feel like that's going to become more and more popular.
748
00:39:39.880 --> 00:39:43.280
And like what does that mean then for production if
749
00:39:43.320 --> 00:39:44.719
you're distributing it like that?
750
00:39:45.039 --> 00:39:48.719
Yeah, And that's really interesting too write because yeah, it
751
00:39:48.760 --> 00:39:50.840
seems like the way you're talking about this, Yeah, a
752
00:39:50.880 --> 00:39:53.320
lot of that becomes a lot more not only possible,
753
00:39:53.360 --> 00:39:57.840
but convenient. Right where I have more control, I have
754
00:39:57.920 --> 00:40:02.719
more capabilities, it's more personalized, and it's all because it's
755
00:40:02.840 --> 00:40:05.719
right here in front of me. And so then the
756
00:40:05.880 --> 00:40:09.559
services in the cloud become less about oh what can
757
00:40:09.559 --> 00:40:11.599
I do with the user interface and a lot more
758
00:40:11.599 --> 00:40:15.039
about hey, what can you do for me in whatever
759
00:40:15.159 --> 00:40:16.519
thing I'm trying to accomplish?
760
00:40:16.639 --> 00:40:17.320
Yeah, exactly.
761
00:40:17.760 --> 00:40:20.920
I mean imagine the day where you can run like
762
00:40:20.960 --> 00:40:25.280
a GPT five level model, like just on a computer
763
00:40:25.360 --> 00:40:28.960
in the background, right, Like eventually it'll get there. So like,
764
00:40:29.000 --> 00:40:33.840
what does what does that mean if you're like no
765
00:40:33.880 --> 00:40:37.639
longer need like the internet to do that kind of
766
00:40:37.719
--> 00:40:43.400
computation right right, And like there was slowly the internets.
767
00:40:43.440 --> 00:40:46.000
We like that's how we communicate. We still have to
768
00:40:46.039 --> 00:40:52.480
like communicate to like solve any real problem. Right, But yeah, again,
769
00:40:52.559 --> 00:40:55.199
it like turns more into like the protocol and communication
770
00:40:55.400 --> 00:40:59.119
layers more than anything. I just see that aspect of
771
00:40:59.159 --> 00:41:01.280
things eating more of this than anything.
772
00:41:01.480 --> 00:41:04.079
So one last question I guess I have on this,
773
00:41:04.320 --> 00:41:06.840
and it's it's somewhat related to something you said before,
774
00:41:06.920 --> 00:41:09.719
but also related to this approach that you've got here
775
00:41:09.840 --> 00:41:14.400
where you've got it kind of autogenerating agents. And before
776
00:41:14.440 --> 00:41:16.599
what you said was and I don't remember if it
777
00:41:16.679 --> 00:41:18.519
was before the call or not, but you mentioned that
778
00:41:19.079 --> 00:41:23.039
you're not writing as much code, right, And so my
779
00:41:23.239 --> 00:41:26.639
question is is I guess there are two parts of this,
780
00:41:26.679 --> 00:41:29.159
So I ask the first one is this has changed
781
00:41:29.159 --> 00:41:30.880
the way that you do your job? Right?
782
00:41:31.000 --> 00:41:31.199
Yes?
783
00:41:31.239 --> 00:41:34.199
And no, I mean this particular project. I have another
784
00:41:34.400 --> 00:41:37.599
project called the AI Software Architect that is like literally
785
00:41:37.639 --> 00:41:40.000
just markdown files and that does most of my job
786
00:41:40.079 --> 00:41:41.320
for me, and it's great.
787
00:41:41.400 --> 00:41:43.719
And I would say yes, like a you.
788
00:41:43.679 --> 00:41:47.960
Know, it's hard because like coming if you're new, right
789
00:41:48.079 --> 00:41:51.559
coming into the industry, like you still need to have
790
00:41:52.119 --> 00:41:55.679
like the knowledge and experience of like how to develop
791
00:41:55.719 --> 00:41:58.639
and practice software and systems, how systems work.
792
00:41:58.840 --> 00:42:01.360
Maybe the you don't have to know.
793
00:42:01.480 --> 00:42:06.039
About like semicolon's and where to put like syntax stuff more,
794
00:42:06.159 --> 00:42:08.280
but you still need to know how to build systems
795
00:42:08.519 --> 00:42:11.000
and how how to integrate and the concept building.
796
00:42:11.159 --> 00:42:13.880
I see that becoming more prevalent and more.
797
00:42:14.039 --> 00:42:17.320
Maybe something that people should focus on is that conceptual
798
00:42:17.719 --> 00:42:21.400
like conceptualization and compression, and like you know, managing and
799
00:42:21.440 --> 00:42:24.960
thinking through those concepts, because that is ultimately what what
800
00:42:25.039 --> 00:42:27.599
your job becomes when you just lean heavy into all
801
00:42:27.599 --> 00:42:30.840
these agents. Is like you're just conveying concepts that you
802
00:42:30.880 --> 00:42:34.000
want to create that don't exist, right, and like it
803
00:42:34.239 --> 00:42:37.599
can't do that because it's not trained on those concepts, right,
804
00:42:37.679 --> 00:42:40.119
And so it's like really just comes down to like
805
00:42:41.039 --> 00:42:44.079
and again I hate to keep like mentioning DHH, but
806
00:42:44.199 --> 00:42:47.079
like you know, all of his old stuff coming up
807
00:42:47.280 --> 00:42:49.639
is coming up again, where it's like, you know, software
808
00:42:49.679 --> 00:42:53.519
is writing, right, Like when you're writing software, you're really authored,
809
00:42:53.719 --> 00:42:58.400
like you're you know, it's a communication like thing. So
810
00:42:59.000 --> 00:43:02.199
like my job is still the same, and I still
811
00:43:02.239 --> 00:43:06.079
need to like communicate in very specific ways to get
812
00:43:06.079 --> 00:43:08.800
what I want out of it. And the better I communicate,
813
00:43:09.000 --> 00:43:12.000
the better the things work right in the long run
814
00:43:12.519 --> 00:43:16.159
and maintain better, right, and people can like work with
815
00:43:16.239 --> 00:43:19.440
it too, right, And so nothing has really changed, I guess,
816
00:43:19.480 --> 00:43:20.159
is what I'm saying.
817
00:43:20.920 --> 00:43:23.719
Yeah, except it seems like you're operating at a different
818
00:43:23.760 --> 00:43:26.920
level where you're actually now telling systems what you want
819
00:43:27.079 --> 00:43:30.480
instead of getting in and telling the system what to do.
820
00:43:30.519 --> 00:43:34.119
If that makes sense, right, Where you're writing more prompts
821
00:43:34.159 --> 00:43:34.840
and less code.
822
00:43:34.960 --> 00:43:37.480
Yeah, that's true. Yeah, I feel like that's true of
823
00:43:37.519 --> 00:43:38.559
most people at this point.
824
00:43:38.719 --> 00:43:39.039
Yeah.
825
00:43:39.679 --> 00:43:42.440
Yeah, Well if not, I would like to hear from you, you.
826
00:43:42.400 --> 00:43:47.480
Know, right, well yeah, and I yeah, I'm just thinking
827
00:43:47.480 --> 00:43:49.440
of all the reasons why you may end up in
828
00:43:49.840 --> 00:43:54.960
a slightly different situation. But I would be speculating, and
829
00:43:55.000 --> 00:43:57.519
I don't know how useful that is. I guess that.
830
00:43:57.599 --> 00:44:00.840
The second part of this question, then, is is, so
831
00:44:01.039 --> 00:44:04.800
let's imagine that I'm I've been doing this for a while, right,
832
00:44:04.840 --> 00:44:07.280
you know, I've been writing rails for twenty years now,
833
00:44:08.000 --> 00:44:09.559
you know, but I talk to other people, you know,
834
00:44:09.599 --> 00:44:12.639
it's ten years or fifteen years or five years or whatever,
835
00:44:13.119 --> 00:44:14.880
you know. So I'm out there, you know, I'm building
836
00:44:14.920 --> 00:44:17.760
apps in Ruby, and
I'm looking at things like this
837
00:44:17.920 --> 00:44:20.440
and saying, okay, well, now you have code writing code,
838
00:44:20.679 --> 00:44:23.000
you have models writing code. A lot of this is
839
00:44:23.039 --> 00:44:25.639
more prompt engineering than software engineering, but you have to
840
00:44:25.719 --> 00:44:29.360
understand the software engineering. So what does my job look like,
841
00:44:29.920 --> 00:44:32.199
you know, within the next year, two years, three years,
842
00:44:32.199 --> 00:44:35.280
four years, And what do I need to be paying
843
00:44:35.320 --> 00:44:40.199
attention to and learning so that I'm not just a
844
00:44:40.239 --> 00:44:44.159
repository for I can generate code because it looks like
845
00:44:44.199 --> 00:44:45.960
a machine's going to be able to do that soon.
846
00:44:46.079 --> 00:44:50.840
Yeah, I mean the thing is like the machines still
847
00:44:50.920 --> 00:44:55.079
generate things that people need to know about, right, Like
848
00:44:56.119 --> 00:45:00.320
it's not like it's creating novel things. It's not creating HTTP, right,
849
00:45:00.519 --> 00:45:03.519
Like it's not creating its own protocols, which maybe will
850
00:45:03.519 --> 00:45:07.719
be the another future, right maybe, but so like people
851
00:45:07.760 --> 00:45:12.000
still need to understand those concepts, right, how does HTTP work?
852
00:45:12.159 --> 00:45:13.880
Like if you're making something that you want to put
853
00:45:13.920 --> 00:45:16.280
on the Internet, Like the Internet isn't going.
854
00:45:16.159 --> 00:45:18.440
To change in the next ten years.
855
00:45:19.239 --> 00:45:22.280
Maybe it will, but like unlikely, right, And so like
856
00:45:22.320 --> 00:45:25.440
you still have these protocols that are used that you
857
00:45:25.519 --> 00:45:30.119
need to understand. You know, you need to understand you
858
00:45:30.159 --> 00:45:33.480
know HDML, you know maybe maybe not so much that
859
00:45:33.679 --> 00:45:37.920
HTML like aspects of things, but like how it's communicated and.
860
00:45:37.800 --> 00:45:39.599
Served, right and how users see it.
861
00:45:39.920 --> 00:45:44.239
If you're like doing dynamic content and programmatic like flows,
862
00:45:44.280 --> 00:45:49.119
like you need to understand like system processing and architecture
863
00:45:49.239 --> 00:45:55.239
and you know, best practices for like how services.
864
00:45:54.760 --> 00:45:55.840
Communicate to each other.
865
00:45:56.119 --> 00:45:58.760
Right, Like there's a bunch of bunch of fundamentals that
866
00:45:58.800 --> 00:46:04.440
are still applicable, Like in traditional computer science, and maybe
867
00:46:04.480 --> 00:46:08.039
like the whole testing aspect of things is changing, like
868
00:46:08.559 --> 00:46:11.119
how you test and what you test. Like, I feel
869
00:46:11.159 --> 00:46:13.519
like we're still not, you know, all in agreement on
870
00:46:14.039 --> 00:46:17.280
that those aspects of things anyway, right, but it's still there.
871
00:46:17.360 --> 00:46:21.599
People still like I wouldn't trust delivering anything to people
872
00:46:21.639 --> 00:46:24.599
that pay me money, right if I didn't test it,
873
00:46:24.880 --> 00:46:26.960
because I don't want to have to like be a
874
00:46:27.000 --> 00:46:31.800
customer support person, right right, and like also like a
875
00:46:31.800 --> 00:46:36.599
little bit shame on you, right like right.
876
00:46:36.840 --> 00:46:42.000
So, so it seems like though that the skill set
877
00:46:42.159 --> 00:46:45.920
has shifted from being able to sit down and actually
878
00:46:45.960 --> 00:46:48.760
like crank the code out to being able to ask
879
00:46:48.800 --> 00:46:51.199
for what you want. But it also seems like what
880
00:46:51.239 --> 00:46:54.000
you're saying is is you still have to conceptually understand
881
00:46:54.079 --> 00:46:57.360
how software goes together and how the systems work so
882
00:46:57.400 --> 00:47:00.119
that you can intelligently ask for what you want and
883
00:47:00.199 --> 00:47:02.480
you can also intelligently validate what you get.
884
00:47:02.719 --> 00:47:04.719
Right, Yeah, you have to know the concepts, I mean
885
00:47:04.760 --> 00:47:09.360
circling back to that, right, like, yeah, you may not
886
00:47:09.440 --> 00:47:12.000
need to know get, but you have to know how
887
00:47:12.360 --> 00:47:16.800
code changes flow works, right, yeah, like even if it
888
00:47:16.920 --> 00:47:20.440
uses SVN or you know, God forbid us SVN, but like,
889
00:47:20.559 --> 00:47:22.760
you know, can you use some other like you know,
890
00:47:22.920 --> 00:47:28.159
code management tool? Right, Like you need to know how
891
00:47:28.199 --> 00:47:30.840
those things work just fundamentally so that you could be
892
00:47:30.920 --> 00:47:34.719
like what change right, Like so you know how to
893
00:47:34.880 --> 00:47:37.559
ask the thing for the very specific things. You know,
894
00:47:37.599 --> 00:47:40.599
maybe it can like make to add the changes that
895
00:47:40.639 --> 00:47:43.679
you need and like you know, revert things when they
896
00:47:43.679 --> 00:47:46.400
go wrong. Right, But you need to know those keywords, right,
897
00:47:46.440 --> 00:47:48.480
You need to know that those are possible, and you
898
00:47:48.480 --> 00:47:51.159
need to know the concept So again back to the concepts.
899
00:47:51.320 --> 00:47:53.119
They're just like a bunch of concepts you need to
900
00:47:53.320 --> 00:47:57.360
like know right, so that you can like really max
901
00:47:57.440 --> 00:47:59.360
out with these coding agents.
902
00:47:59.800 --> 00:48:03.760
Right. So I guess the final question I'll ask, because
903
00:48:03.800 --> 00:48:06.960
I think this is just getting us to an interesting place.
904
00:48:07.039 --> 00:48:08.599
Is the way I learned a lot of the stuff
905
00:48:08.599 --> 00:48:11.280
that you're talking about
having to know is that I
906
00:48:11.400 --> 00:48:13.719
had to do it on my own for a long time.
907
00:48:14.719 --> 00:48:17.440
And then you've got some of these newer folks that
908
00:48:17.519 --> 00:48:20.880
are you know, graduating from college or coming up through
909
00:48:21.199 --> 00:48:25.599
the boot camps or self teaching that haven't done it
910
00:48:25.679 --> 00:48:29.360
as zillion times like I have. So how do they
911
00:48:29.440 --> 00:48:32.960
learn this stuff? Like is it a different avenue do
912
00:48:33.119 --> 00:48:37.880
the AI systems llms actually help them learn how to
913
00:48:37.960 --> 00:48:41.199
do this? I mean, what do you do for people
914
00:48:41.199 --> 00:48:44.000
who are new that haven't built, you know, twenty years
915
00:48:44.000 --> 00:48:47.360
of muscle memory on on how to build web apps
916
00:48:47.440 --> 00:48:49.559
or how to use command line or things like that.
917
00:48:49.480 --> 00:48:52.599
Process is still the same, Like you know, go learn
918
00:48:52.599 --> 00:48:55.400
to yourself and use these tools to your advantage. Right,
919
00:48:55.559 --> 00:48:58.000
when something doesn't go as you expect or you don't
920
00:48:58.039 --> 00:49:03.159
know something, ask right, I guess that makes sense. Yeah,
921
00:49:03.440 --> 00:49:06.400
it's the harder part is like you know, okay, knowing
922
00:49:06.480 --> 00:49:10.760
what to ask right, and that I feel like there's
923
00:49:10.800 --> 00:49:13.679
still a lot of room for traditional like courses, right,
924
00:49:13.960 --> 00:49:16.320
is like there's going to be a lot of times
925
00:49:16.320 --> 00:49:18.159
where you're just not going to know what to ask
926
00:49:18.320 --> 00:49:23.239
and you'll never get there. And traditional like coursewear and
927
00:49:23.559 --> 00:49:27.639
workloads like that teach very specific things. Will it help
928
00:49:27.679 --> 00:49:30.280
you introduce that? Introduce that to you, right? And like
929
00:49:30.559 --> 00:49:35.039
maybe once you've visualized like what all the like the
930
00:49:35.079 --> 00:49:37.400
course material are, then maybe you could dig in like
931
00:49:37.960 --> 00:49:41.199
maybe this whole like mi T open course where like
932
00:49:41.719 --> 00:49:45.880
you know, Stanford ree learning stuff. You know, that could
933
00:49:45.920 --> 00:49:48.280
be the future because it just provides all of the
934
00:49:48.320 --> 00:49:50.960
concepts and material that you would need to know for
935
00:49:51.079 --> 00:49:55.679
very specific things, and then the agents can help you,
936
00:49:56.559 --> 00:49:59.320
like because you could create plans, right, a learning plan,
937
00:49:59.800 --> 00:50:01.960
like help me learn how to do this thing. Here's
938
00:50:02.000 --> 00:50:05.480
the course material, right, and like why do you need
939
00:50:05.519 --> 00:50:08.000
the course? But at the same time, you know, like
940
00:50:08.079 --> 00:50:10.800
it's the concepts and the material and like all these
941
00:50:10.840 --> 00:50:11.760
things that.
942
00:50:11.719 --> 00:50:14.599
Are going to be like kind of the value.
943
00:50:15.519 --> 00:50:20.199
And so don't go out there exploiting uh, you know,
944
00:50:20.280 --> 00:50:22.039
open courses course please.
945
00:50:22.440 --> 00:50:22.960
You know, it's a.
946
00:50:22.880 --> 00:50:26.800
Great platform, lots of great learning out there, and if
947
00:50:26.840 --> 00:50:28.559
you want, you can earn your own.
948
00:50:28.639 --> 00:50:30.719
Degrees out of it. From what I've seen.
949
00:50:31.480 --> 00:50:34.559
Kind of yep, makes sense, all right, Well, is there
950
00:50:34.599 --> 00:50:36.719
anything else that people ought to know about any of
951
00:50:36.719 --> 00:50:39.000
this stuff? Kind of meander through a bunch of stuff
952
00:50:39.039 --> 00:50:42.760
beyond autogenetic stuff, but I think it's helpful for people
953
00:50:42.760 --> 00:50:43.840
to understand what it's doing.
954
00:50:43.960 --> 00:50:46.159
Yeah, I mean, if you're working on something, let me know.
955
00:50:46.519 --> 00:50:50.440
I'm the code name v on on Twitter. This stuff
956
00:50:50.480 --> 00:50:53.559
is just really I'm working on another project now on
957
00:50:54.559 --> 00:51:02.039
exploring the idea of letting letting lllms pave their own
958
00:51:02.119 --> 00:51:07.599
path with their own memories. Actually, one of my Uh.
959
00:51:08.039 --> 00:51:11.480
One of my coworkers, Martin, he like made this prompt
960
00:51:11.599 --> 00:51:14.679
where you basically just like ask an LLM to like
961
00:51:14.840 --> 00:51:19.840
generate a profile about itself, right, and like what is
962
00:51:19.880 --> 00:51:22.000
it like almost like to try and get its like
963
00:51:22.079 --> 00:51:24.440
soul out of itself. And it's really interesting, Like yes,
964
00:51:24.599 --> 00:51:27.159
the models all different, you know, all the different models
965
00:51:27.199 --> 00:51:30.239
the same thing, and like the results are wildly different.
966
00:51:30.519 --> 00:51:32.800
It kind of gives you some like insight into like
967
00:51:32.880 --> 00:51:38.039
how the models operate just like holistically I think. But yeah,
968
00:51:38.039 --> 00:51:40.960
I have another project. I'm calling it seed box, but
969
00:51:41.159 --> 00:51:44.360
like just asking an LM. All right, here's what you
970
00:51:44.360 --> 00:51:46.440
did last time. What do you want to do next?
971
00:51:46.800 --> 00:51:49.199
You know, more experimentation like this, We need more like
972
00:51:49.920 --> 00:51:54.079
you know, stuff out there to experiment with and just
973
00:51:54.119 --> 00:51:56.920
like see what these things are capable of, because we're
974
00:51:56.960 --> 00:51:59.440
trying to come up with ideas for what they're good at,
975
00:51:59.559 --> 00:52:02.199
and like is that like the best?
976
00:52:02.480 --> 00:52:02.639
Right?
977
00:52:02.719 --> 00:52:05.320
Like shouldn't they also be coming up with ideas so
978
00:52:05.599 --> 00:52:06.400
what they're good at?
979
00:52:06.519 --> 00:52:07.719
Right? What does that mean?
980
00:52:07.920 --> 00:52:10.119
You know, there's a lot, there's so much exploration I'm
981
00:52:10.119 --> 00:52:10.880
excited to see.
982
00:52:11.719 --> 00:52:11.920
Yeah.
983
00:52:12.039 --> 00:52:13.039
Funny now very cool?
984
00:52:13.559 --> 00:52:17.400
All right, Well let's go and do some picks. You
985
00:52:17.440 --> 00:52:18.000
have some picks.
986
00:52:18.239 --> 00:52:20.519
Yeah, we were talking before the show. There's a project
987
00:52:20.519 --> 00:52:21.400
called open code.
988
00:52:21.639 --> 00:52:26.320
It's like a cloud code alternative, fully open source works
989
00:52:26.360 --> 00:52:29.599
on your act Windows, Linux. It's really impressive. I've been
990
00:52:29.679 --> 00:52:33.599
using it lately and yeah, it's fantastic.
991
00:52:33.760 --> 00:52:34.280
Check it out.
992
00:52:34.519 --> 00:52:37.679
Nice. I'm gonna throw out a board game pick, as
993
00:52:37.719 --> 00:52:40.239
I am wont to do, and then I will man
994
00:52:40.280 --> 00:52:42.519
I sound sold fashion when I say it that way anyway,
995
00:52:42.719 --> 00:52:46.800
and then and then I'll probably throw out something else. So, yeah,
996
00:52:46.639 --> 00:52:48.840
the game that we've been playing lately is that we
997
00:52:48.920 --> 00:52:51.760
played last time I got together with my friends was Infiltrators.
998
00:52:51.800 --> 00:52:56.280
And so Infiltrators is you have a bunch of suspects
999
00:52:56.960 --> 00:52:59.079
and you're trying to figure out who they are, and
1000
00:52:59.119 --> 00:53:02.639
it's just a color, a number, and so usually on
1001
00:53:02.679 --> 00:53:05.519
your first turn, everybody nabs a suspect, and so you
1002
00:53:05.599 --> 00:53:08.360
know you have information that nobody else has because you
1003
00:53:08.360 --> 00:53:10.840
can't tell people who your suspect is, but you know
1004
00:53:10.880 --> 00:53:13.880
who your suspect is. And so then you play cards
1005
00:53:13.920 --> 00:53:17.079
on other people or on yourself in order to figure
1006
00:53:17.079 --> 00:53:19.599
out who the suspects are. And so it's a process
1007
00:53:19.639 --> 00:53:23.360
of elimination, right because you when you play a card
1008
00:53:23.519 --> 00:53:26.599
on a suspect, it either has something in common with
1009
00:53:26.639 --> 00:53:29.480
it or nothing in common with it, and so it's
1010
00:53:29.519 --> 00:53:31.639
just a process of elimination to figure out what it is.
1011
00:53:31.880 --> 00:53:35.119
And then it has kind of the concept that you
1012
00:53:35.159 --> 00:53:38.320
get out of the Crew where it has multiple missions,
1013
00:53:39.079 --> 00:53:41.960
and so it'll say, use these colors, use these numbers.
1014
00:53:42.360 --> 00:53:45.480
You have so many bullets, right because you're executing your
1015
00:53:45.519 --> 00:53:48.400
suspects when you know who they are. And so anyway,
1016
00:53:48.440 --> 00:53:51.199
it's it's pretty fun place, pretty fast. You play up
1017
00:53:51.239 --> 00:53:56.119
to five people, I think, and anyway, really really enjoyed it.
1018
00:53:56.199 --> 00:53:58.639
If you don't want the gun and bullet aspect, you
1019
00:53:58.679 --> 00:54:00.880
can track that. However, you're going to track that. You know,
1020
00:54:00.920 --> 00:54:03.840
it's basically you have so many tries and then you know,
1021
00:54:04.000 --> 00:54:05.719
you try not to run out of cards and things
1022
00:54:05.719 --> 00:54:09.920
like that. So anyway, super duper fun. So I'm gonna
1023
00:54:09.920 --> 00:54:12.639
pick that, and then I'm trying to think what else
1024
00:54:12.679 --> 00:54:15.400
to pick. I mean, lately, I've just been using the
1025
00:54:15.719 --> 00:54:19.719
plan feature on Cursor and then right I go look
1026
00:54:19.719 --> 00:54:21.639
at what it did and tell it what it did wrong,
1027
00:54:21.719 --> 00:54:25.639
and it cleans it up and it's pretty nice, you know,
1028
00:54:25.679 --> 00:54:28.320
And like I said, for my full time job, I'm
1029
00:54:28.519 --> 00:54:32.440
copilot and you know, works more or less the same
1030
00:54:32.480 --> 00:54:35.559
way and does a great job, and so liking those,
1031
00:54:35.760 --> 00:54:38.440
so I guess I'll all shout those out just kind
1032
00:54:38.480 --> 00:54:41.760
of as where I'm sitting now. And then one last
1033
00:54:41.800 --> 00:54:45.559
thing I'm going to mention is so I've been putting
1034
00:54:45.559 --> 00:54:48.280
together two things and one of them is and I'm
1035
00:54:48.280 --> 00:54:50.559
going to do an episode on it. I'm not sure
1036
00:54:50.599 --> 00:54:53.000
if I'm going to release this episode first for that one,
1037
00:54:53.159 --> 00:54:57.360
So if you've already heard the whole episode on it, great,
1038
00:54:57.400 --> 00:55:00.440
But I'm a big fan of the seventy five Hard
1039
00:55:00.519 --> 00:55:04.280
Challenge by Andy Frazella. You know, I've lost a bunch
1040
00:55:04.280 --> 00:55:07.360
of weight doing seventy five Hard. I feel like I've
1041
00:55:07.440 --> 00:55:10.960
leveled up as a person doing seventy five Hard, and
1042
00:55:11.000 --> 00:55:12.480
so I thought, well, what if there was something like
1043
00:55:12.480 --> 00:55:16.199
this for code right, And so I'm putting together a
1044
00:55:16.280 --> 00:55:20.960
code Forge seventy five Challenge. It's based very heavily on
1045
00:55:21.039 --> 00:55:24.880
seventy five Hard, except instead of workouts, you're you know
1046
00:55:24.920 --> 00:55:27.360
you're writing software. He has you read a book for
1047
00:55:27.440 --> 00:55:30.400
ten minutes a day. I adopted the same thing. Right,
1048
00:55:30.440 --> 00:55:32.280
go find a tech book on something you want to learn,
1049
00:55:33.519 --> 00:55:35.519
you know. So it's that kind of thing. So I'll
1050
00:55:35.519 --> 00:55:38.039
walk through all the different pieces on the other on
1051
00:55:38.400 --> 00:55:41.199
the other episode, I'm looking to expand it to be
1052
00:55:41.639 --> 00:55:45.239
a so he expanded it out to be a year
1053
00:55:45.280 --> 00:55:49.039
long challenge. So you know, seventy five Hards the first
1054
00:55:49.079 --> 00:55:51.800
phase of the challenge, and so I'm looking to do
1055
00:55:51.840 --> 00:55:55.000
that too, because I want to encourage people to speak
1056
00:55:55.119 --> 00:55:57.880
at an event, whether it's a meetup or a conference.
1057
00:55:57.960 --> 00:56:01.079
I want to encourage people to you know, generate content
1058
00:56:01.119 --> 00:56:02.760
and things like that because I think it helps your career.
1059
00:56:03.320 --> 00:56:06.079
And so there will be other phases to the program
1060
00:56:06.159 --> 00:56:09.639
similar to what seventy five Hard does, and I'm gonna
1061
00:56:10.400 --> 00:56:13.280
I'm planning on putting together a little tracking app with
1062
00:56:13.400 --> 00:56:16.519
rails and hot wire Native so that you can track
1063
00:56:16.599 --> 00:56:19.920
your progress right and then if you miss one of
1064
00:56:19.960 --> 00:56:23.800
the items, then you have to start over anyway. So
1065
00:56:23.840 --> 00:56:25.280
I'm putting that together and then the other thing I'm
1066
00:56:25.320 --> 00:56:27.360
putting together. Both of them are relevant to what we've
1067
00:56:27.360 --> 00:56:30.039
been talking about today. I've been finding as I talk
1068
00:56:30.119 --> 00:56:35.119
to people, and Valentino I think made the case for this, honestly, Yeah,
1069
00:56:35.360 --> 00:56:37.360
because I work with people and talk to people, there
1070
00:56:37.360 --> 00:56:41.440
are folks that have major gaps in their knowledge in
1071
00:56:41.480 --> 00:56:44.039
some areas, and I do too, honestly with regards to
1072
00:56:44.119 --> 00:56:47.360
Ruby or Rails. Right, there are things that it's like, oh,
1073
00:56:47.400 --> 00:56:49.360
I didn't know it did that, or oh I didn't
1074
00:56:49.400 --> 00:56:51.480
know that. You know. The way that we do things
1075
00:56:51.480 --> 00:56:53.519
now is we architect it this way so that way, right,
1076
00:56:53.519 --> 00:56:56.800
because I have a life and so I don't, you know,
1077
00:56:56.800 --> 00:56:58.840
I don't get into all the nitty gritty of what
1078
00:56:59.000 --> 00:57:01.320
came out in some point too, and how do I
1079
00:57:01.440 --> 00:57:04.360
use it and what's the best way around that? And
1080
00:57:04.440 --> 00:57:07.559
so if you want to do the Code for seventy
1081
00:57:07.599 --> 00:57:09.760
five challenge and you want to level up on Rails,
1082
00:57:10.679 --> 00:57:13.639
then I'm putting together what I'm calling Ruby Geniuses, and
1083
00:57:14.280 --> 00:57:17.480
it'll have stuff or actually it's Rails Geniuses, but it'll
1084
00:57:17.480 --> 00:57:20.320
have Ruby and Rails content and there will be that
1085
00:57:20.440 --> 00:57:22.679
daily level up kind of thing, and then we're going
1086
00:57:22.760 --> 00:57:25.360
to have there'll be different membership levels. So if you
1087
00:57:25.440 --> 00:57:28.440
just want the tutorials and stuff, great, and then if
1088
00:57:28.440 --> 00:57:30.400
you want to be part of the training and things
1089
00:57:30.400 --> 00:57:32.239
like that that we're doing every week in the book club,
1090
00:57:32.440 --> 00:57:35.159
then you can get a higher level. And then I'm
1091
00:57:35.159 --> 00:57:37.800
doing the same thing for AI, and that's also going
1092
00:57:37.840 --> 00:57:40.880
to be focused in the tools, which is part of
1093
00:57:40.920 --> 00:57:44.679
what we talk today, and then also building AI agents
1094
00:57:44.719 --> 00:57:49.039
and AI enabled features, free applications. That stuff's just moving
1095
00:57:49.079 --> 00:57:51.800
so fast. I feel like, you know, having a group
1096
00:57:51.800 --> 00:57:53.800
that gets together on a regular basis and looks at
1097
00:57:53.800 --> 00:57:55.199
it and talks about it and says, hey, have you
1098
00:57:55.239 --> 00:57:58.199
seen this is very very helpful and handy, And so
1099
00:57:58.679 --> 00:58:00.440
you can sign up for one or the other or both.
1100
00:58:00.639 --> 00:58:02.639
There will be a discount if you sign up for both.
1101
00:58:02.800 --> 00:58:06.440
But I plan to address this, you know, we'll we'll
1102
00:58:06.440 --> 00:58:09.320
have weekly meetups and book clubs and things like that.
1103
00:58:09.519 --> 00:58:11.840
I'm trying to figure out exactly how to do the
1104
00:58:11.840 --> 00:58:14.599
book clubs so that you're kind of getting more of
1105
00:58:14.639 --> 00:58:16.920
the evergreen stuff that's not changing as fast with the
1106
00:58:17.000 --> 00:58:20.679
AI approach and tools and things like that. But we'll
1107
00:58:20.679 --> 00:58:23.679
figure that out and we'll go along as we go.
1108
00:58:23.800 --> 00:58:27.239
But I feel like if you're leveling up in these areas,
1109
00:58:27.400 --> 00:58:29.760
then you're going to put yourself in a position where,
1110
00:58:30.320 --> 00:58:34.519
no matter how much the models do for you, or
1111
00:58:34.760 --> 00:58:38.360
how different companies approach their workforce or things like that,
1112
00:58:38.440 --> 00:58:42.679
you'll always have a competitive edge because you know you
1113
00:58:42.800 --> 00:58:46.119
understand the architecture of what you're building or what you're
1114
00:58:46.119 --> 00:58:48.440
getting help building, and then you're also going to understand
1115
00:58:48.880 --> 00:58:52.920
the tools and the architecture of what the capabilities are
1116
00:58:53.320 --> 00:58:57.159
when you need to build something with AI. Anyway, you
1117
00:58:57.199 --> 00:59:01.920
can go check those out. It's going to be Railsgeniuses
1118
00:59:01.920 --> 00:59:06.079
dot com and Aidevgeniuses dot com. So I'm just gonna
1119
00:59:06.119 --> 00:59:08.599
put those out there. You'll get a whole lot more
1120
00:59:08.679 --> 00:59:11.760
explanation on the code for seventy five episode if you
1121
00:59:11.960 --> 00:59:14.400
get a chance to listen to that. And then I
1122
00:59:14.440 --> 00:59:19.320
am going to be offering a launch discount through the
1123
00:59:19.400 --> 00:59:21.679
fifth of January. And the reason I'm going through the
1124
00:59:21.679 --> 00:59:24.599
fifth of January is that as I've talked to people,
1125
00:59:24.719 --> 00:59:27.800
some people want to expense this to work, and some
1126
00:59:27.840 --> 00:59:30.199
people have used all their budget for twenty twenty five
1127
00:59:31.440 --> 00:59:34.360
and want to expense it in twenty twenty six. Oh,
1128
00:59:35.039 --> 00:59:37.039
I will give you the opportunity to do so with
1129
00:59:37.119 --> 00:59:39.599
the discount, And if you want to use up the
1130
00:59:39.679 --> 00:59:43.039
rest of your twenty twenty five budget and things like that,
1131
00:59:43.199 --> 00:59:45.599
then you can do that too. And if you need
1132
00:59:45.639 --> 00:59:47.880
some kind of arrangement where it's like, well, I only
1133
00:59:47.880 --> 00:59:49.599
have so much twenty twenty five budget, and I want
1134
00:59:49.599 --> 00:59:53.280
to use some my twenty twenty six budget and reach
1135
00:59:53.320 --> 00:59:54.559
out to me and we'll figure it out. But I'm
1136
00:59:54.599 --> 00:59:56.239
not going to hard pitch it. If it sounds like
1137
00:59:56.280 --> 00:59:58.800
something you want, I'm putting it together because it's something
1138
00:59:58.840 --> 01:00:01.960
that I wanted. I was like, I am missing stuff,
1139
01:00:02.039 --> 01:00:04.880
and I feel like if I get people together in
1140
01:00:04.920 --> 01:00:07.960
a group, then I will miss less stuff. And then
1141
01:00:08.000 --> 01:00:10.280
it also gives me an excuse to go and learn
1142
01:00:10.760 --> 01:00:13.840
things that, you know, maybe apply beyond what I get
1143
01:00:13.840 --> 01:00:17.719
in my full time job. So anyway, that's what we're doing.
1144
01:00:18.320 --> 01:00:19.960
And yeah, I just I want to give you the
1145
01:00:20.000 --> 01:00:22.280
tools so that no matter where any of this goes,
1146
01:00:22.480 --> 01:00:24.639
you know, you have the skills, you have the knowledge,
1147
01:00:24.639 --> 01:00:26.159
and you can you can go and kind of build
1148
01:00:26.199 --> 01:00:28.119
whatever kind of life and career you want. And I
1149
01:00:28.199 --> 01:00:30.039
guess we'll wrap it up here until next time.
1150
01:00:30.280 --> 01:00:30.719
Next out