전사 🔗
WEBVTT
00:00:00.640 --> 00:00:04.719
Hello everyone and welcome to another episode of Code and the Coding Coders to Coded.
00:00:04.799 --> 00:00:08.000
I'm your host, Drew Bragg, and I'm joined today by Scott Werner.
00:00:08.240 --> 00:00:12.320
Scott, for anyone who's unfamiliar with you, would you please do a quick introduction?
00:00:12.880 --> 00:00:13.199
Sure.
00:00:13.439 --> 00:00:14.320
Thanks, Drew.
00:00:14.640 --> 00:00:16.719
So yeah, my name's Scott Werner.
00:00:16.960 --> 00:00:21.920
I've been a Rubyist for since around 2008.
00:00:22.559 --> 00:00:32.640
Worked in a bunch of different places from small startups to Groupon to Adobe, starting my own startup called Sayspring.
00:00:33.359 --> 00:00:43.759
But now I'm at a new startup called Sublayer, and we're kind of doing all different kinds of stuff around AI and Ruby, which is kind of how we got connected, right?
00:00:44.079 --> 00:00:45.200
You're working with AI.
00:00:45.359 --> 00:00:45.920
What a shock.
00:00:46.159 --> 00:00:53.759
I feel like everyone is in some capacity, whether they're working with it as their job or they're working with it to help them with productivity.
00:00:53.920 --> 00:00:55.840
It is everywhere.
00:00:56.079 --> 00:00:57.119
It's unavoidable.
00:00:57.200 --> 00:01:06.640
So I'm glad we're going to talk about it because it is something that I've been shying away from talking about on the show, just because there are times where it feels a little bit like JavaScript frameworks.
00:01:06.719 --> 00:01:10.560
There's just something new with them like every other day.
00:01:10.879 --> 00:01:15.439
But before we get into the episode, let me do the rest of my normal spiel.
00:01:15.599 --> 00:01:19.120
For anyone new to the show, I'm going to be asking Scott three questions.
00:01:19.200 --> 00:01:22.480
I'm going to ask him what he's working on, what kind of blockers does he have?
00:01:22.640 --> 00:01:27.359
And the last question is what's something cool, new, or interesting that he's recently learned, discovered, built?
00:01:27.439 --> 00:01:28.159
It doesn't matter.
00:01:28.239 --> 00:01:29.760
It's whatever he wants to share.
00:01:29.920 --> 00:01:31.840
It's always my favorite question.
00:01:32.079 --> 00:01:33.680
So let's just dive right in.
00:01:33.840 --> 00:01:36.879
Scott, what are you working on specifically?
00:01:38.640 --> 00:01:43.200
That's a tough question, as for anybody that comes to subleyer.com might see.
00:01:43.359 --> 00:01:46.400
We're doing kind of a big mix of a bunch of different things.
00:01:46.719 --> 00:01:50.000
You know, most of my day right now is spent.
00:01:50.159 --> 00:01:51.760
So rewind a little bit.
00:01:51.920 --> 00:01:57.280
So I started Sublayer back about three, three and a half years ago.
00:01:57.840 --> 00:02:10.800
And the thing that kind of kicked off what we're doing is seeing GPT-4, like the demos that they were putting out for before GPT-4 came out, where like somebody would draw a UI and it would write the code to actually like make it display.
00:02:11.039 --> 00:02:16.400
And that point, seeing that, would made something click and that like these things are just going to keep getting better.
00:02:16.479 --> 00:02:19.759
These are like the worst these models are ever going to be.
00:02:19.919 --> 00:02:23.439
And it's going to fundamentally change software engineering.
00:02:23.759 --> 00:02:37.520
And I kind of brushed over it earlier, but I have been in extreme programming, a practitioner of extreme programming for almost over 10 years now of pair programming, test-driven development, agile.
00:02:38.000 --> 00:02:41.599
And seeing that, it was like a spark went off in my head.
00:02:41.759 --> 00:02:46.479
Everything that I knew or I thought I knew is going to change, and I want to be involved in that.
00:02:46.879 --> 00:02:53.599
And winding road, probably three episodes worth of podcasts to kind of talk about all the different experiments we've done.
00:02:53.680 --> 00:02:59.599
But where I found myself now doing a mix of training for agentic coding.
00:02:59.680 --> 00:03:07.840
So using Claude Code, those kind of things, doing one-on-one and small group training to kind of teach different techniques and get people up to speed.
00:03:29.520 --> 00:03:39.919
Writing a newsletter works on my machine, which kind of doing a lot of the experiments in public, learning in public, sharing a lot of open source, building products.
00:03:40.400 --> 00:03:53.439
And then getting close to launching a video series kind of very inspired by like Railscast, where it's like five to 15-minute really targeted techniques for agentic coding or using these tools.
00:03:53.759 --> 00:03:58.080
On top of artificial Ruby and all these other things that we're doing.
00:03:58.479 --> 00:04:05.599
Yeah, talk a little bit about Artificial Ruby for anyone who's not familiar with the meetup, because I think it is pretty cool.
00:04:05.919 --> 00:04:17.759
So Artificial Ruby, it actually kind of came out because as I was building out Sublayer, a lot of the stuff we were doing was in Ruby, and everybody I talked to asked me why Ruby.
00:04:18.319 --> 00:04:22.079
Investors are like, why are you doing like what's the distinction here in Ruby?
00:04:22.480 --> 00:04:28.399
Everybody, engineers, I would talk to is like, isn't AI like a Python and TypeScript kind of thing?
00:04:28.720 --> 00:04:34.480
And so I kind of got fed up as a little bit of tough word, is like a stronger word, but I it was just like, you know what?
00:04:34.560 --> 00:04:37.680
I'm sure there are more people out here doing this.
00:04:38.160 --> 00:04:48.160
And so we actually put together a happy hour where we're like, I bet we can get like 20 of our friends to come out and we'll buy them drinks and talk about Ruby and AI.
00:04:48.399 --> 00:04:58.879
So we did it and just shared a you know, a Luma invite out and got something like 50 people, and it was just like completely
Load full transcript
like beyond our expectations.
00:04:59.040 --> 00:05:01.360
And we were like, okay, there's like something here.
00:05:01.680 --> 00:05:04.079
In the middle of it, people were asking us when the next one was.
00:05:04.160 --> 00:05:04.879
And we were like, I don't know.
00:05:04.959 --> 00:05:09.839
We just kind of thought it was gonna be people we all knew, and it's just like it expanded to so many new people.
00:05:10.079 --> 00:05:13.600
So we did another one, and now we're about a year and a half in.
00:05:13.680 --> 00:05:23.519
It actually has a name because I spoke at RubyConf last year, and somebody came up to me and they were like, Yeah, I heard there's like this Ruby and AI event in New York, but I can't find it.
00:05:23.680 --> 00:05:28.160
And so we're like, oh, we need to actually like brand this and not the Ruby and AI happy hour and demo night.
00:05:28.240 --> 00:05:30.000
It's actually a name, all this stuff.
00:05:30.240 --> 00:05:33.519
It has a name, it's just kind of a hard, it's sort of like my podcast name.
00:05:33.600 --> 00:05:35.040
It's sort of hard to remember.
00:05:35.360 --> 00:05:38.399
But you actually rank really high, so that's the difference.
00:05:38.720 --> 00:05:46.480
Now we're artificial Ruby, we have a site, we have a venue that's great with beta works, a video crew, we record talks.
00:05:46.639 --> 00:05:59.439
It's actually kind of like become this thing where some people have said it's almost like a monthly mini conference, and so it's kind of taken on a life of its own and just kind of like guiding it as it drives itself.
00:05:59.759 --> 00:06:00.800
Yeah, that's super cool.
00:06:00.879 --> 00:06:12.399
I've been trying to carve out time that I can come up because it's not that far away from me, but it's just far enough away that I can't just be like, today I'm gonna go, why not?
00:06:12.639 --> 00:06:14.399
It requires a little bit of planning.
00:06:14.720 --> 00:06:14.959
Yeah.
00:06:15.199 --> 00:06:17.040
Ernesto has actually come up a whole bunch.
00:06:17.120 --> 00:06:17.920
I got to know him.
00:06:18.000 --> 00:06:20.480
Him and Ambu Labs are sponsors, actually.
00:06:20.560 --> 00:06:28.240
So it's been cool to get to know him and then some of his team and a couple people from his team have given talks and everything.
00:06:28.639 --> 00:06:32.959
If nothing else, I'll have you at Philly RB in January, right?
00:06:33.120 --> 00:06:33.759
We're still doing that.
00:06:34.000 --> 00:06:34.959
Yes, yeah, definitely.
00:06:35.360 --> 00:06:36.319
Yeah, that'll be cool.
00:06:36.480 --> 00:06:39.279
We're getting that back going in person, and it's been cool.
00:06:39.360 --> 00:06:44.160
We've it's smaller for now, but everyone we've done has had a handful more people.
00:06:44.399 --> 00:06:48.160
So it's nice to do the in-person meetups monthly again.
00:06:48.399 --> 00:06:55.439
Virtual is fun because you can talk to anybody anywhere, but there's definitely something to in-person that is a little more special.
00:06:55.759 --> 00:06:56.639
Yeah, I agree.
00:06:56.720 --> 00:07:03.759
I mean, it's one of the things too that we've heard from people, especially you know, from New York and meeting people with artificial Ruby.
00:07:04.240 --> 00:07:13.600
There are a bunch of people that have started their career during the pandemic and actually never gone to an in-person professional meetup at all, let alone a Ruby meetup.
00:07:13.839 --> 00:07:18.480
And so, yeah, getting a chance to like see people face to face.
00:07:18.959 --> 00:07:28.319
Another tangent we can go on is go imagine starting your professional software developer, software engineering career fully remote in the pandemic.
00:07:28.399 --> 00:07:34.000
You've never seen any of your coworkers in person, and you put your first PR up and it gets torn apart.
00:07:34.240 --> 00:07:34.560
Right?
00:07:34.800 --> 00:07:49.279
How hard it must be to be somebody like entering the industry in like a remote or hybrid first place where you kind of don't really get a chance to make relationships with people beyond like a name or an avatar and Slack or Discord.
00:07:49.920 --> 00:07:55.040
I was already in the industry, but I changed jobs during the pandemic.
00:07:55.279 --> 00:08:04.560
Went from one job to another, mostly because the job that I went to was now remote and we're like, oh, we're gonna stay remote.
00:08:04.720 --> 00:08:06.240
So now we can open up hiring.
00:08:06.319 --> 00:08:07.759
So I was able to get a job there.
00:08:07.920 --> 00:08:17.439
But it definitely was weird to go from I know what it's like to work at a place, but like in an office, hybrid style, right?
00:08:17.920 --> 00:08:20.399
Going to, I've never seen these people.
00:08:20.560 --> 00:08:26.720
And you know what the thing that screwed me up the most when I finally did meet them, I had no one's height correct.
00:08:26.959 --> 00:08:31.600
Everyone's height was way, I'm like, you're shorter than I thought, you're taller than I thought.
00:08:31.759 --> 00:08:33.120
Everyone's height was wrong.
00:08:33.200 --> 00:08:36.720
That's what screwed me up the most, which is funny to think about.
00:08:36.879 --> 00:08:38.879
But yeah, I think the meetups are great.
00:08:39.039 --> 00:08:41.600
It's sort of like having the conferences back, right?
00:08:41.679 --> 00:08:52.639
I've been saying, like, it's great to have the conferences back, it's great to have the conferences back, but it's also great to have meetups, especially when you've got cities like New York, Philly, SF Ruby took off like crazy.
00:08:52.799 --> 00:08:58.720
Just getting those people together too helps because sometimes those people don't travel to conferences.
00:08:58.799 --> 00:09:00.000
So you wouldn't see them otherwise.
00:09:00.159 --> 00:09:08.240
Sometimes those people are like new to the industry or they've been in it for a while and haven't interacted with the community.
00:09:08.480 --> 00:09:19.679
Now there's a place to interact with the community, and some ideas that would never have seen the light of day end up coming out just because you're standing there talking with the drink in your hand and oh, tell me more about that.
00:09:19.759 --> 00:09:24.720
And suddenly you're on this, it's 45 minutes to an hour later, and you're like, this is awesome.
00:09:25.279 --> 00:09:27.679
That doesn't happen over the internet as easily.
00:09:27.759 --> 00:09:28.960
It's more forced.
00:09:29.279 --> 00:09:31.039
We tried, we tried for a little while, right?
00:09:31.120 --> 00:09:33.120
Do you remember the Zoop happy hours?
00:09:33.440 --> 00:09:43.919
It was better than nothing, but given going to a meetup and interacting with people in person, and this is coming from someone who has a limited social battery.
00:09:44.000 --> 00:09:49.840
Like I get back from every conference, like, I'm good, I don't need to see any human beings for a few weeks now.
00:09:50.240 --> 00:09:52.639
When it's once a month, it's awesome.
00:09:52.960 --> 00:09:56.559
Not looking to go back to an office, but I do like my meetups.
00:09:56.720 --> 00:09:57.600
Yeah, yeah.
00:09:58.320 --> 00:10:05.600
So you've got your work, which is AI focused, and you've got your meetup, which is AI focused.
00:10:05.679 --> 00:10:11.600
So you are kind of one of the AI guys in Ruby.
00:10:11.759 --> 00:10:27.039
What do you think is missing from the Ruby ecosystem to make it where someone who's maybe doing AI work goes, well, I gotta use Python because Python's what you use for AI work.
00:10:27.200 --> 00:10:32.080
Someone who's doing AI work can legitimately see Ruby as an option to do AI work.
00:10:34.320 --> 00:10:38.639
That's something that I think about a lot and we talk about a lot of the meetups.
00:10:39.039 --> 00:10:50.639
But I think the time period, like the point in time that we're in right now with AI, it's so early, and nobody really knows what we're actually going to do with this.
00:10:50.879 --> 00:10:57.120
If it stops at just like chatbots, just like an AI, basically, it stops it at ChatGPT.
00:10:57.200 --> 00:10:58.480
I think it'll be a failure.
00:10:58.720 --> 00:11:03.200
I think there's so many more incredible things that we can do with this technology.
00:11:03.519 --> 00:11:10.720
What I think is missing, what we're trying to promote a lot with artificial Ruby, is kind of the experimentation.
00:11:10.960 --> 00:11:20.159
And so I think you look at what drove kind of the adoption of Ruby in the early 2000s was people could make websites.
00:11:20.240 --> 00:11:26.799
People were making web 2.0 apps with Java or PHP and stuff like that before.
00:11:27.120 --> 00:11:36.320
But it was Rails and somebody with DHH, with the Ruby mindset of like, I'm gonna approach this, I'm gonna make this a joy to work with.
00:11:36.480 --> 00:11:40.799
That we saw the doors open and like the flood of flood of people come in.
00:11:41.120 --> 00:11:47.039
I think where
we're at right now is like nobody really knows what exactly we're gonna do with this thing.
00:11:47.279 --> 00:11:52.960
And so we don't have that light bulb framework that's going to be the thing, right?
00:11:53.600 --> 00:11:59.200
I look back at that time period, and it looked like the Rubyists were the ones having fun.
00:11:59.360 --> 00:12:12.480
You know, I was listening to your episode with Aji talking about like the keynotes, and I wasn't just like blowing smoke, I've actually been doing a lot of trying to research like what made it work in those early days and why isn't it working now?
00:12:12.799 --> 00:12:17.360
And you know, one of the things that came up was one of DHH's keynotes.
00:12:17.759 --> 00:12:22.879
I think it was the keynote where he announced Rails, RubyConf.
00:12:23.039 --> 00:12:27.200
And he was like, you need to pick a fight, you need to create this enemy.
00:12:27.360 --> 00:12:30.080
And so it became enterprise developers.
00:12:30.159 --> 00:12:44.480
And like, oh, you're an enterprise developer, and like the Rubyists were the ones with like tattoos and different colored hair and t-shirts and shorts, and they were the ones that were like enjoying the work, and everybody else was enterprise developers filling out TPS reports.
00:12:44.799 --> 00:12:47.759
And I've kind of gone way off track here.
00:12:48.399 --> 00:12:49.360
There is no track.
00:12:49.600 --> 00:12:50.960
There's no track, okay.
00:12:51.279 --> 00:13:13.840
But so to bring it back, I think we were in this kind of weird period of probably something of what it looked like before Rails came out, where a lot of people just found Ruby or been using Ruby for a little while, were like completely unlocked from the things that they were doing before in their other languages, in their other back then it was there weren't even like open source IDEs really.
00:13:13.919 --> 00:13:16.799
It was like the languages being open source was uncommon.
00:13:16.879 --> 00:13:20.240
Now it's like everything's everybody expects everything to be open source.
00:13:20.559 --> 00:13:26.480
So I think my personal answer for this, I don't think it's a library, I don't think it's a tool.
00:13:26.720 --> 00:13:29.279
I think it's that feeling of having fun.
00:13:29.440 --> 00:13:35.679
And oh, that group of people, that group of programmers is doing really cool stuff and they look like they're having fun with this.
00:13:35.840 --> 00:13:37.120
I want to do that.
00:13:37.279 --> 00:13:48.080
Because like Claude Code or whatever your agent of choice is can just spin up a copy of a library, you point it to Langchain RB, and like do this in Langchain.py.
00:13:48.720 --> 00:13:50.559
And that might be a bad example.
00:13:50.799 --> 00:14:00.240
But some library in Python, some library in JavaScript, put it in Claude or Gemini or whatever and be like, make a copy of this in Ruby, like it mostly will get you there.
00:14:00.480 --> 00:14:06.399
But I think it's getting back to that culture of experimentation and fun and just doing cool shit because you can.
00:14:06.879 --> 00:14:10.000
Yeah, I think that's a good way of looking at it.
00:14:10.240 --> 00:14:34.320
Because we recently did a or are doing, I guess, at the time of this recording, a little bit of like an AI challenge at work, not hey, write all of your code or vibe code anything, but more of like go out of your way to use AI in your daily job as a way of seeing like how are we going to use this here?
00:14:34.639 --> 00:14:37.440
What is our AI usage look like?
00:14:37.600 --> 00:14:46.159
Because almost across the board, with very few exceptions, like none of us want AI doing our jobs for us or writing our code for us either.
00:14:46.240 --> 00:14:50.399
Like, we enjoy our jobs, we don't want AI to take it from us.
00:14:50.799 --> 00:14:58.639
But like to ignore that AI exists and just never use it just seems like we're putting ourselves at a disadvantage to other developers.
00:14:58.960 --> 00:15:05.840
So the challenge is just to like use it a little bit more and then submit the ways that you've used it.
00:15:06.000 --> 00:15:17.120
And I think it was such a good way to unblock, at least especially me, from AI, because it was such a well, if AI is going to take my job, I don't want to use it because fuck it.
00:15:17.279 --> 00:15:17.600
Right?
00:15:17.679 --> 00:15:18.879
Like, I don't like you.
00:15:18.960 --> 00:15:21.440
You're taking this thing that I legitimately enjoy doing.
00:15:21.600 --> 00:15:24.320
I like writing code, I like programming, I like solving problems.
00:15:24.480 --> 00:15:31.120
Why would I want to just dump it into this AI chatbot and let it do all the stuff that I enjoy?
00:15:32.000 --> 00:15:40.399
But because it was like a requirement to play with AI and figure out ways to use it, I've tried all different kinds of things now and I haven't even scratched the surface.
00:15:40.480 --> 00:15:42.320
And I'm actually kind of having fun with it.
00:15:42.480 --> 00:15:44.000
I'm not using it to write code.
00:15:44.159 --> 00:15:46.960
I'm using it to like explore things or come up with plans.
00:15:47.039 --> 00:15:52.639
I'm using it as like a rubber duck that talks back to me instead of just sitting there on my desk.
00:15:53.200 --> 00:16:06.240
It's not writing any code, and I'm having so much more fun with it than before when it was like, I guess I'll put it into GPT and see what it comes up with, or I'll tap into Claude and be like, I have this weird bug.
00:16:06.559 --> 00:16:12.639
Those ways didn't seem fun, but just playing with it seems like so much fun.
00:16:13.039 --> 00:16:20.480
Do you have any like on top of mind, any kind of like the biggest light bulb went off aha moment as you've been working with it through that project?
00:16:21.200 --> 00:16:23.120
I don't think there's any one thing.
00:16:23.279 --> 00:16:33.600
I've definitely learned a lot more of like clawed code was kind of cool
when I first installed it and like attached my first MCP server to it.
00:16:33.679 --> 00:16:43.360
We used linear to track bugs, and like the first time I was able to like go back and forth with it about a linear ticket without like copying and pasting everything in, that's kind of cool.
00:16:43.519 --> 00:16:47.759
I think there's something to this connecting MCPs together.
00:16:48.080 --> 00:16:52.960
The coolest thing that really was like an LLM on its own isn't awesome.
00:16:53.120 --> 00:16:55.440
It's a collection of things that's pretty awesome.
00:16:55.600 --> 00:17:02.240
Was I tried Tidewave by Jose Valim, got that installed, and started tinkering with it.
00:17:02.399 --> 00:17:12.799
And just having it run in the browser and be able to like click on something or talk about the page as a whole, it was leaps and bounds better than Claude on its own.
00:17:13.039 --> 00:17:17.440
I tried an experiment where I was like, hey, we have this slow-loading page, Claude.
00:17:18.000 --> 00:17:22.079
What do you think might be some low-hanging fruits or areas to explore?
00:17:22.400 --> 00:17:24.319
Kept it pretty broad.
00:17:24.720 --> 00:17:29.359
It came back with like a plan-ish places to look, whatever.
00:17:29.519 --> 00:17:39.359
I asked Tidewave, but because Tidewave was in the browser, it was reloading the page, it was looking at my logs, it was tapping into the database, it came, it had all of these contexts put together.
00:17:39.519 --> 00:17:44.000
The plan it came up with, first shot, was actually decent.
00:17:44.160 --> 00:17:53.119
It would require some iteration to get it to be a really viable plan, but it was just so much better because it had so much more context.
00:17:53.359 --> 00:17:59.119
So, for at least for me, the aha moment is like an LLM on its own can only do so much.
00:17:59.200 --> 00:18:04.240
But when you start giving it all of this context, it reduces my cognitive load.
00:18:04.400 --> 00:18:06.559
I don't need to keep all of the context in my head.
00:18:06.720 --> 00:18:12.079
I can focus on solving problems because the AI can keep all of the context in its memory.
00:18:12.400 --> 00:18:13.359
Yeah, that's super cool.
00:18:13.440 --> 00:18:18.720
I have TideWave downloaded it, but I haven't had a project to really dig into it with, but have to give that a shot.
00:18:18.960 --> 00:18:20.160
Yeah, it was cool.
00:18:20.400 --> 00:18:25.839
Another one of the devs used it to fix like a CSS bug and had decent success.
00:18:26.000 --> 00:18:29.039
I've had mixed results with CSS bugs.
00:18:29.359 --> 00:18:37.680
It's got like a selector tool, so you can select like a single element and talk about this element isn't positioned correctly or isn't the right whatever.
00:18:37.839 --> 00:18:40.240
And it can do some pretty cool things.
00:18:40.319 --> 00:18:46.559
But I feel like every time AI just is like, here's the 20 lines of CSS that'll fix it.
00:18:46.720 --> 00:18:51.920
It gives me the light bulb to go, oh, and then like one or two lines of CSS actually fixed it.
00:18:52.160 --> 00:18:54.640
My God, this thing is a slop generator.
00:18:54.960 --> 00:18:56.720
It fixed the bug.
00:18:56.960 --> 00:19:05.119
It technically did what I asked it to do, but it did it in such an overcomplicated like, I would never want to be the one to maintain this code way.
00:19:05.519 --> 00:19:11.759
That's what I need to figure out is how to get it to stop going way over what it needs to do.
00:19:11.839 --> 00:19:13.599
Like, keep it simple.
00:19:13.839 --> 00:19:17.519
I don't know how to convince the AI that like simple wins.
00:19:17.920 --> 00:19:21.279
It just wants to write a shit ton of code.
00:20:42.910 --> 00:20:43.550
Yeah.
00:20:44.269 --> 00:20:45.950
I kind of have two answers to that.
00:20:46.110 --> 00:20:48.830
One is depends on which model you're working with.
00:20:49.070 --> 00:21:07.870
Sonnet, for example, is one of the things that personality is the wrong word, but like you kind of get a sense of like, I imagine you've had that experience with Sonnet or Claude Sonnet, because it's known to kind of like you give it a vague instruction, it's gonna do five other things that seem reasonable and just kind of like make those up.
00:21:08.110 --> 00:21:14.670
Codex, for example, from OpenAI will be a lot more focused on like just doing the thing that you're asking for.
00:21:14.830 --> 00:21:21.310
And so you kind of start to get an intuition or start to like kind of drive different problems to different things.
00:21:21.630 --> 00:21:32.430
So the library that I used for the presentation at Rocky Mountain Ruby, Monkey's Paw, it actually does amazing with Sonnet because like I can just write a few lines.
00:21:32.509 --> 00:21:36.190
So Monkey's Paw is this prompt-based web framework.
00:21:36.509 --> 00:21:49.630
And you kind of write your slides, your pages in markdown files in your wishes folder, and then you load the page, it sends that prompt to an LLM and loads whatever it thinks should be on that slide or page.
00:21:49.950 --> 00:22:00.590
And it works way better with Sonnet because I can just write a couple lines and get this like wild the line with something the style of something like a mid-90s GeoCities site.
00:22:00.670 --> 00:22:11.230
And I've got like animated gradient backgrounds, I've got these SVG diagrams, just like from two lines of like, I just need a triangle or something.
00:22:11.470 --> 00:22:12.350
That's very cool.
00:22:12.590 --> 00:22:18.269
Yeah, if anybody hasn't seen Scott's talk from Rocky Mountain, I will link the video in the show notes.
00:22:18.350 --> 00:22:19.150
You need to watch it.
00:22:19.310 --> 00:22:21.950
It was great, and it is cool.
00:22:23.150 --> 00:22:32.670
That talk was such a good example of like playing with AIs, which was something that I wasn't doing.
00:22:32.990 --> 00:22:35.150
ChatGPT is just an LLM.
00:22:35.230 --> 00:22:40.509
Like you ask it for stuff and
it spits back out whatever information it has.
00:22:41.070 --> 00:23:04.350
But like seeing you do stuff with Monkey Paul is like it felt a little bit like some of Y's work, which I'm not trying to like shirk your ego here, but like just the playing, the doing something, not for oh, hey, I'm gonna make a new startup, or I'm gonna make a real monetizable application, or I'm gonna make something that like is in high demand.
00:23:04.509 --> 00:23:07.950
I'm not even gonna solve necessarily a problem I have.
00:23:08.110 --> 00:23:10.430
I'm just gonna build for the sake of building.
00:23:10.509 --> 00:23:12.269
I'm gonna be creative, I'm gonna be artsy.
00:23:12.350 --> 00:23:13.710
And like, like that was wise work.
00:23:13.790 --> 00:23:17.150
He was very creative, very artsy with Ruby.
00:23:17.390 --> 00:23:20.910
And sometimes he created something really cool that a lot of people wanted to use.
00:23:20.990 --> 00:23:26.350
And I'm sure a lot of stuff was just like this one-off, like, I just want to see if I can do it.
00:23:26.990 --> 00:23:35.230
And maybe that's not what you wanted to do with Monkey's Paw, but either way, like that's kind of what I was like, this is so cool.
00:23:35.390 --> 00:23:37.870
Like, you just built this framework because why not?
00:23:38.029 --> 00:23:46.350
Because I wanted to see, I wanted to iterate on something for fun, wanted to do something cool with this tool and see what I could do with it.
00:23:46.990 --> 00:23:48.750
Which actually brings up another point.
00:23:48.910 --> 00:23:53.470
If you the book I had it up and I forgot its name.
00:23:54.430 --> 00:24:02.029
The latent library, oh, right, which is another one of those, like, this is kind of interesting.
00:24:02.590 --> 00:24:06.590
I'll let you do the talking about it, but I have so many questions.
00:24:06.910 --> 00:24:07.550
Sure.
00:24:08.350 --> 00:24:20.190
Completely embarrassed about the why comparison, but why was one of the biggest personalities when I was talking about like, oh, the Ruby community was they're the ones having fun.
00:24:20.269 --> 00:24:21.710
I want to go be around them.
00:24:21.950 --> 00:24:25.070
Why was kind of the ringleader for that for me?
00:24:25.390 --> 00:24:31.870
And he had a very big impact on my entry into Ruby and into the industry.
00:24:32.350 --> 00:24:36.509
So definitely influenced the way that I think about software.
00:24:37.070 --> 00:24:37.470
Yeah.
00:24:37.630 --> 00:24:41.630
And so a lot of these ideas are coming out of just like, what can I do now?
00:24:41.790 --> 00:24:42.990
Not like, should I do it?
00:24:43.150 --> 00:24:44.830
It's just like, what can I do?
00:24:45.230 --> 00:24:55.870
And the other piece, and I kind of offhanded or kind of brushed over this earlier, that like I think there's so much more than just the chat interface and exploring that.
00:24:55.950 --> 00:25:05.230
And so that's where library came from, which is a book social network that none of the books or
categories actually exist.
00:25:05.790 --> 00:25:11.550
They only exist by you browsing, and the LLM hallucinates the categories and books for you.
00:25:11.710 --> 00:25:22.750
And then once you check out the book from the library, it generates a cover, it becomes real, and we're working toward alternative interfaces for actually generating the content of those books.
00:25:22.910 --> 00:25:27.710
So you can have this kind of collaborative hallucination authorship.
00:25:28.029 --> 00:25:42.350
Almost like what does this medium of an LLM or what does this medium afford us that we have this infinite creativity or infinite any permutation of characters up to the output limit of an LLM is possible.
00:25:42.830 --> 00:25:54.670
And so part of what Latent Library is trying to do is to give you an interface for kind of navigating that infinity and scoped toward books.
00:25:54.910 --> 00:26:03.070
But the idea is like there are all these other interfaces that we can do to find different permutations of these characters that mean different things.
00:26:03.550 --> 00:26:10.830
It's like, what's that old give enough monkeys typewriters, and eventually someone one of them will write Hamlet?
00:26:11.070 --> 00:26:22.350
It's interesting to see like you're kind of like drilling down this type of book, that type of book, drill it down until finally the AI hallucinates what you're looking for.
00:26:22.590 --> 00:26:24.910
I would have never thought to do that.
00:26:25.710 --> 00:26:32.590
And that's the cool, like interesting part for me when you like shared it with me.
00:26:32.750 --> 00:26:35.870
I was like, where does this idea come from?
00:26:36.269 --> 00:26:41.550
The creativity to me is not the oh, have AI generate a book, right?
00:26:41.710 --> 00:26:44.350
That's like that's actually not what I want AI to do.
00:26:44.430 --> 00:26:47.550
I want AI to do my damn laundry so that I can go write the book.
00:26:47.710 --> 00:26:48.990
That's where my headset's at.
00:26:49.070 --> 00:26:50.670
But like you've kind of flipped it on the head.
00:26:50.750 --> 00:26:55.710
It's like, yeah, I don't want AI to do this for me, but I have this idea and I just want to see what happens.
00:26:55.790 --> 00:26:58.509
Like, where in your brain does that come from?
00:26:58.830 --> 00:26:59.870
I don't know exactly.
00:27:00.029 --> 00:27:15.230
I'm kind of just pulling inspiration from everywhere that I think we're in this period of time where so many new things are possible that it's almost like the internet came out, and we're like, what can we do now that our machines are networked?
00:27:15.470 --> 00:27:23.710
And so part of the inspiration for even just starting the newsletter was like, I kept having these ideas, but I'm also working on a startup.
00:27:23.790 --> 00:27:28.430
And so, like, I'm just like, you know, just piling up these ideas that I'm not able to work on.
00:27:28.590 --> 00:27:40.990
And now through having this outlet, any random idea that I have, I can just like throw it a claw, clawed code, and just like, yeah, build me out a prototype, build me out an example, and let me see how that is.
00:27:41.230 --> 00:27:45.950
And actually, Monkey's Paw kind of I backed into it.
00:27:46.029 --> 00:27:48.190
So my talked at RubyConf last year.
00:27:48.350 --> 00:27:52.910
I had PowerPoint Copilot live generate my slides during my talk.
00:27:53.150 --> 00:27:58.509
And I kind of was thinking, I'm gonna take this further, and then thought through all the problems.
00:27:58.590 --> 00:28:03.950
Like I was sitting there typing in prompts or copy and pasting prompts while I'm up on behind the podium.
00:28:04.190 --> 00:28:05.630
And it was like, this sucks.
00:28:05.790 --> 00:28:09.470
And so a lot of it was just like, okay, like how do I package that into a product?
00:28:09.790 --> 00:28:15.310
I think it's just letting your mind wander of just like, huh, that thing's possible now.
00:28:15.550 --> 00:28:17.550
What's something fun I can do about this?
00:28:17.630 --> 00:28:21.790
Or like, or this sucks, but how can I make this not suck?
00:28:22.110 --> 00:28:40.750
Latent library, it's I don't remember what the spark was, but it is really just one of the things that I've found, especially with Claude Code and you know these other agenc builders, is in the past, when you had an idea for something, it was like, do I spend want to spend my weekends on this?
00:28:40.910 --> 00:28:45.310
Do I want to spend the next couple weeks to like get this to a state where I can share it with some friends?
00:28:45.550 --> 00:28:52.190
And now it's like I can send a prompt or send a couple prompts to this agent and like do other things.
00:28:52.350 --> 00:29:04.990
I can give Claude a prompt and go do my laundry and come back and check out what it looks like, which is a big unlock that it took a while of what you were talking about that you guys were doing at work of oh, I can do this now.
00:29:05.150 --> 00:29:09.950
What's something that I can have AI do for me that I couldn't before?
00:29:10.110 --> 00:29:13.150
And just like pulling on that thread and pulling on that thread.
00:29:13.470 --> 00:29:16.750
Yeah, it's a little bit like the rails scaffolds, right?
00:29:17.230 --> 00:29:33.150
I wouldn't use what the scaffolds generate for me as the final product, but it does make getting like the boilerplate crap out of the way really fast and like getting to the actual fun, hard-to-solve problem sooner.
00:29:33.390 --> 00:29:35.790
And that's where I actually want to be.
00:29:35.950 --> 00:29:44.990
I don't want to sit here and write the same boilerplate or this is a controller, it these are the actions it has, this is a model, this it needs a schema migration and all this.
00:29:45.150 --> 00:29:46.269
Yeah, yeah, yeah, yeah, yeah.
00:29:46.350 --> 00:29:47.070
I know how to do that.
00:29:47.150 --> 00:29:51.470
I want to do the hard problem business y stuff, business solution
stuff.
00:29:51.630 --> 00:29:53.070
That's where I want to be.
00:29:53.310 --> 00:30:01.390
So AI sort of feels like that's kind of maybe where it fits in, where it's like, these are the things that we know how to do.
00:30:01.550 --> 00:30:02.990
They don't take brain power.
00:30:03.150 --> 00:30:04.830
Let the LLM do it.
00:30:05.150 --> 00:30:07.310
Now let's go work on the real problems.
00:30:07.470 --> 00:30:10.430
Or at least I hope, because again, I don't want AI to take my job.
00:30:10.509 --> 00:30:11.390
I like my job.
00:30:11.470 --> 00:30:13.070
I enjoy what I do.
00:30:13.390 --> 00:30:20.509
Yeah, and I think Rails actually is a great example of what becomes possible when you take a lot of that boilerplate stuff away.
00:30:20.670 --> 00:30:29.710
Like, wouldn't have had Groupon or Twitter or Airbnb or Uber if people weren't able to like quickly experiment with things.
00:30:30.029 --> 00:30:30.990
For sure.
00:30:31.550 --> 00:30:36.990
I guess an interesting question now will be what do your blockers look like?
00:30:37.150 --> 00:30:45.870
Since you have this, like I hesitate to call it a magic tool to unblock you, but like it definitely is very good at unblocking you.
00:30:46.029 --> 00:30:54.590
If you have any kind of problem, like you can just dump it into various LLMs chatbots, and it will give you all kinds of ideas on how to unblock you and stuff.
00:30:54.670 --> 00:31:01.870
So, like, what does a blocker look like now for you in your startup or for artificial Ruby, whatever you want to talk about?
00:31:02.110 --> 00:31:09.070
Do you think AI has made an impact in your blockers, or has it just changed the type of blockers you have?
00:31:09.470 --> 00:31:11.230
I think it's both.
00:31:11.790 --> 00:31:22.670
I got to a point and got comfortable enough with something like Cloud Code, where I at one point had like four running and Four different projects at the same time.
00:31:22.910 --> 00:31:29.390
And so my blocker became just like, I can't even listen to music because I'm context switching so much that the music is distracting.
00:31:30.910 --> 00:31:36.029
It's definitely there are points where, like, okay, it's not good enough.
00:31:36.269 --> 00:31:37.070
It's not good enough.
00:31:37.150 --> 00:31:38.190
Our techniques aren't good enough.
00:31:38.350 --> 00:31:42.670
Our scaffolding isn't good enough to do the thing I'm trying to get it to do.
00:31:43.470 --> 00:31:50.430
And so part of it's mental and like personal of like, there's a tendency, like, oh, I know how to do it.
00:31:50.509 --> 00:31:53.630
I'm gonna put my time into coding and doing that.
00:31:53.870 --> 00:31:57.150
When in reality, like three months from now, an AI is gonna be able to do it in a prompt.
00:31:57.230 --> 00:32:00.910
So, like spending time doing that is not really worthwhile.
00:32:01.150 --> 00:32:11.070
And I think to I do an exercise very similar to like what you were talking about at work, where try to like get AI
to do the things for you.
00:32:11.150 --> 00:32:13.790
And when you're going to do something, can AI do this?
00:32:13.870 --> 00:32:17.310
And so I was procrastinating on something for a while.
00:32:17.470 --> 00:32:24.590
Of I had Claude on Rails, which is Obi Fernandez's, or I think Obi Fernandez is involved in this.
00:32:24.830 --> 00:32:29.310
It's kind of like a multi-agent system for Claude to build Rails apps.
00:32:29.470 --> 00:32:34.830
And it got the thing working, but it was kind of convoluted user flows.
00:32:34.910 --> 00:32:40.190
And I was like, I don't want to like dig through the routes and like look through all these things and like clean this up.
00:32:40.350 --> 00:32:42.029
And so it was just like putting it off.
00:32:42.190 --> 00:32:44.430
And a friend was like, why don't you just get Claude to do that?
00:32:44.509 --> 00:32:46.110
I was like, oh my God, you're right.
00:32:46.269 --> 00:32:54.430
That morning, I was just like, hey, Claude, can you map out all the routes and the primary user flows, the primary like paths that users would do to accomplish what they're trying to do?
00:32:54.750 --> 00:33:00.190
A couple minutes later, I had this whole like thing mapped out, and it was like, okay, these look kind of convoluted.
00:33:00.269 --> 00:33:01.870
Do you have any recommendations for simplifying it?
00:33:02.029 --> 00:33:04.509
Okay, got a whole bunch of recommendations for simplifying it.
00:33:04.670 --> 00:33:05.390
Okay, do that.
00:33:05.550 --> 00:33:09.630
And that was the thing that I'd been putting off for weeks, actually sitting down and doing it.
00:33:09.950 --> 00:33:15.390
A lot of the blockers are just retraining myself to be like, oh, I should just take five minutes.
00:33:15.470 --> 00:33:20.590
What's a new technique that I could try to get AI to do this rather than spending half a day on something?
00:33:21.550 --> 00:33:31.230
And then the other thing that's I can get up to four clouds running at the same time, but I kind of run out of, I have the ideas, but then you run out of ideas.
00:33:31.390 --> 00:33:46.110
And so part of the motivation for artificial Ruby, coming on podcasts and the newsletter and speaking conferences is really to try to build a community of people that we can toss ideas around back and forth about.
00:33:46.350 --> 00:33:57.710
I think that's the other blocker of just let's get together in a chat room or a meetup and just like riff on ideas because I feel like we haven't even scratched the surface of what these things can do.
00:33:58.110 --> 00:34:02.110
And really just trying to put stuff out there that people are like, that's interesting.
00:34:02.190 --> 00:34:05.390
I want to talk about this or I want to build stuff like this.
00:34:05.550 --> 00:34:09.230
I want to take these ideas and take them in a different direction.
00:34:09.469 --> 00:34:12.110
More people to chat with and just play with ideas.
00:34:12.590 --> 00:34:13.949
Can always use more.
00:34:14.670 --> 00:34:21.630
It's interesting too, because like that's I guess the one thing that AI really can't do is it can't have an idea.
00:34:22.110 --> 00:34:23.309
It needs a prompt.
00:34:23.389 --> 00:34:26.269
It needs to be responding to something nonstop.
00:34:26.590 --> 00:34:33.230
When we as humans like get bored or we don't have anything to do, like our brains just make up stuff.
00:34:33.389 --> 00:34:37.309
You start humming a song that doesn't exist, or like whatever.
00:34:37.869 --> 00:34:42.509
Maybe there is a future where AI gets to that point, but it's kind of not there, right?
00:34:42.829 --> 00:34:48.670
It needs human interaction in order to do any kind of generation.
00:34:49.150 --> 00:34:53.869
ChatGPT just sits there and does nothing until you ask it for something.
00:34:54.190 --> 00:34:57.389
I've been thinking about like how weird it is.
00:34:57.710 --> 00:35:05.710
You ask an LLM something, it just puts a bunch of stuff together and then spits it back at you in like this cohesive summary.
00:35:06.110 --> 00:35:08.269
It doesn't know anything.
00:35:08.349 --> 00:35:11.309
It's connecting dots and summarizing for you.
00:35:11.869 --> 00:35:17.230
I guess the other thing is like, what's my role in AI code generation or whatever?
00:35:17.309 --> 00:35:23.789
It's like, is it just sitting there making sure that the slop generator doesn't generate too much slop?
00:35:23.869 --> 00:35:26.429
Like, just enough slop to solve the problem.
00:35:26.590 --> 00:35:30.829
Like, don't create technical debt while you're solving the problem.
00:35:30.989 --> 00:35:34.829
Or is there something else that I need to learn?
00:35:35.149 --> 00:35:37.230
Like you keep on talking about like retraining yourself.
00:35:37.309 --> 00:35:56.269
Like, I'm trying to relearn how to do my job with AI involved in a way that still brings me the joy that I found programming and writing code and solving problems, but like gives me the productivity boost of I can ask it to write a method for me, and it can do that.
00:35:56.509 --> 00:36:01.869
I don't really want it to, but how can I get the productivity boost of AI while still loving my job?
00:36:02.269 --> 00:36:10.109
It kind of looks like very similar to what we were talking about before around Rails with scaffolding and everything kind of reduced a lot of the boilerplate.
00:36:10.349 --> 00:36:22.989
I don't know, I don't think a lot of people's arguments around what they were doing in Java before Rails for web apps, that they were like, the thing I love about building web apps in Java is all the boilerplate.
00:36:23.149 --> 00:36:27.309
It came out as the type system, how can you do anything without types?
00:36:27.389 --> 00:36:43.069
And like, almost like at that point in time, it was like, oh, the static types were solved and Java's solved programming, and Rails and the Ruby world came out and were like, yeah, but what if we do the opposite of all that and like don't even
have the code, you know, you can't even look at the code because it's all meta programmed.
00:36:43.230 --> 00:36:46.349
And a lot of people had a backlash against that.
00:36:46.670 --> 00:37:08.349
When what you got was fewer people were able to do so much more, and the industry actually expanded, like you ended up not needing 100 person plus teams and a bunch of stuff to build something like Twitter, Groupon, or Airbnb, which in '98 you probably did need hundreds of people.
00:37:08.909 --> 00:37:11.549
And I think we're seeing that again.
00:37:11.629 --> 00:37:23.629
And so I think a lot of the crud app stuff that we're moving beyond just like the scaffold, we're moving to a lot of the commodity work that we kind of do.
00:37:23.869 --> 00:37:29.309
Then we've got the focus on craft, and that is still going to stay.
00:37:29.549 --> 00:37:38.670
It's just like a lot of the stuff that we didn't really categorize as boilerplate before is becoming boilerplate, and we're just moving to another layer.
00:37:38.989 --> 00:38:48.789
I heard an analogy, I'm probably going to butcher this, but it's almost like as photography came out, and a lot of the people that were focused on painting, painting portraits and realistic, I don't know what the right term is, but realist painting, that by photography coming in and like taking the economic, the commodity piece of that away, photography became this whole other artistic medium.
00:38:49.029 --> 00:38:58.789
But it also kind of made it possible for the people that were focused on the craft of painting to like move into other avenues and find other interesting things to do.
00:38:58.949 --> 00:39:13.029
I don't know if we're actually going to get there, but I think the story is something like Picasso was an amazing painter, like painting reality, but also took it in another direction and was able to kind of learn all the rules to break all the rules.
00:39:13.349 --> 00:39:30.309
My guess and the way I'm kind of approaching it is like we're gonna see that same thing of like a lot of the commodity stuff that we spend our time doing is gonna get taken away, but like the craft of the building, basically like the creating software piece is still going to exist.
00:39:31.029 --> 00:39:37.190
The thing is, like, you know, I really like typing boilerplate or typing curly brackets and parentheses.
00:39:37.429 --> 00:39:38.630
That's probably going away.
00:39:38.710 --> 00:39:39.829
I'm sorry about that.
00:39:40.230 --> 00:39:44.150
But the creative problem solving, I don't think is going away.
00:39:44.469 --> 00:39:46.150
Yeah, good way to look at it.
00:39:46.789 --> 00:39:54.389
So the last question, which I feel like is a bit of a loaded one given some of the ideas that you've had, monkeys paws late in library, things like that.
00:39:54.469 --> 00:39:58.469
But like, what is something cool, new, or interesting?
00:39:58.789 --> 00:40:03.269
Doesn't have to be AR-related, doesn't have to be coding related,
but it absolutely can be.
00:40:03.349 --> 00:40:08.230
Like, what's something cool, new, or interesting you want to share that we haven't already talked about?
00:40:09.029 --> 00:40:17.670
Well, I guess another new thing that I put out that we haven't touched on, it's also been bouncing around in my head is Google recently put out this model.
00:40:17.829 --> 00:40:33.269
I think Anthropic has a computer use model as well, but Google put out a new computer use model where you give it a screenshot of a UI, it gives you back tool calls of what to do, like click at this X, Y coordinate or fill in this text field, whatever.
00:40:33.750 --> 00:40:47.750
Another thing that I've recently released is called it Touring Test, but it's a Cucumber extension that basically can turn your cucumber steps into computer use steps.
00:40:47.909 --> 00:40:53.190
So you describe what you want the agent to do, it'll do it, and then you write your assertions.
00:40:53.349 --> 00:41:03.750
So if given I'm a logged in user, your instruction is like when the agent logs out, then they should be on the homepage or whatever.
00:41:04.230 --> 00:41:07.269
The agent logs out is the only thing that's there.
00:41:07.429 --> 00:41:15.909
And so the agent sees your UI, it kind of determines where to go and how to log out, and it either does it or it doesn't.
00:41:16.230 --> 00:41:28.150
And the thing I'm trying to get at there is like it almost enables a new type of testing where your users are trying to accomplish certain things in your app.
00:41:28.469 --> 00:41:41.909
And an LLM is a reasonable, it's not gonna have all of the infer, you know, all of the intelligence or all of the abilities that your users might, but it's gonna take a, you know, have a reasonable attempt at these things.
00:41:42.070 --> 00:41:52.150
And if it can't do it, it's probably a good sign that there's some kind of usability issues on your site, which I think is actually kind of what we're trying to get at with testing in general, right?
00:41:52.230 --> 00:41:58.710
We don't really care that Capybara or or Selenium can select this element with this CSS class.
00:41:58.869 --> 00:42:05.909
We're trying to test that the users can add one of our products to their cart and they can check out and they can sign up.
00:42:06.469 --> 00:42:09.750
And there's the actual piece of it.
00:42:09.909 --> 00:42:17.190
There's the mechanical piece of it, but then there's also the can they actually figure out how to do it piece that wasn't really there before.
00:42:17.750 --> 00:42:18.710
Interesting.
00:42:19.029 --> 00:42:21.029
See, that's another use of AI.
00:42:21.110 --> 00:42:38.469
I don't think I would have thought like I've thought of obviously using AI to write my R spec tests or to generate tests for something it wrote or I wrote or add tests so I could do some TDD or what have you, but like using it in a completely different way.
00:42:39.269 --> 00:42:41.829
It is such a weird, interesting.
00:42:41.909 --> 00:42:44.070
Like, what are we gonna do with this thing?
00:42:44.230 --> 00:42:49.509
There's so many things it can do, but what the hell are we gonna do with it?
00:42:49.750 --> 00:42:50.550
I don't know.
00:42:50.869 --> 00:42:53.750
You're definitely a lot further down that path than I am.
00:42:53.829 --> 00:42:57.989
I'm trying to catch up, I think, a little bit on the what are we gonna do with this thing.
00:42:58.230 --> 00:43:14.070
I'm happy that work did this AI challenge because I do think it took me from like AI to like, all right, I'm slower this month because I'm playing with so much stuff, but like it is definitely going to improve my productivity in the long run.
00:43:14.230 --> 00:43:20.630
It's going to stop me from having to do some of the boilerplatey stuff that was just a time suck.
00:43:20.710 --> 00:43:21.429
Like, I could do it.
00:43:21.509 --> 00:43:22.230
It wasn't hard.
00:43:22.389 --> 00:43:31.670
I got knocked it out pretty quickly, but like definitely faster with AI and will unlock me to solve bigger and better problems.
00:43:32.230 --> 00:43:43.590
Yeah, I think that's that's a good point, too, is I've had a lot of conversations, especially with like old coworkers, of how to actually do these things or any any tips for this thing that I'm trying to do.
00:43:43.829 --> 00:43:46.630
And a lot of people are like, you have deadlines, right?
00:43:46.789 --> 00:43:48.150
I have to deliver this by Friday.
00:43:48.230 --> 00:43:53.829
I'm not gonna noodle around with AI until Wednesday on the off chance I'm late for this deliverable.
00:43:54.309 --> 00:44:00.630
And I think that's another really good thing that you have there with that space to experiment.
00:44:00.789 --> 00:44:14.309
And I wonder if a lot more people than realize it have that every company, every like engineering manager, engineering leader that I talk to is like, I want my team to be using AI more, but I don't know how to do it.
00:44:14.550 --> 00:44:24.230
And I wonder if it's just like letting them know that if you try to use AI to solve this problem and it takes a little bit longer, that's okay.
00:44:24.630 --> 00:44:28.869
In a way, we're all kind of back to being juniors in that space, right?
00:44:28.949 --> 00:44:34.789
Like when we were junior engineers, we couldn't produce X, Y, or Z as fast, but we eventually became seniors.
00:44:34.869 --> 00:44:39.750
And now we can do X, Y, and Z stupid fast, and we can work on bigger, better problems.
00:44:40.070 --> 00:44:47.269
But we need the time and space to like learn how to use the AI and use the AI right for us.
00:44:47.509 --> 00:44:52.230
There's 10 developers at Podia, and I think we all use AI differently.
00:44:52.469 --> 00:44:57.110
We all pretty much agree we don't want to just vibe code our PRs.
00:44:57.269 --> 00:44:58.469
No one's doing that.
00:44:58.710 --> 00:45:05.829
But we are all using AI in a way that helps us, and we know that in the long term
we're going to be more productive for it.
00:45:06.070 --> 00:45:10.389
Having that space to explore is, yeah, you're right, is super good.
00:45:10.550 --> 00:45:26.550
And I think that might be if there's more holdouts, maybe giving yourself the space or talking to your manager about getting the space to like my deadline is pushed back, not so I can slack off, but because I can explore doing things differently.
00:45:26.789 --> 00:45:29.829
Because keep up or you're gonna be left behind.
00:45:30.630 --> 00:45:31.190
Cool.
00:45:31.429 --> 00:45:32.550
That was a good one.
00:45:32.869 --> 00:45:42.710
When is the next artificial Ruby for anyone listening that's like, hey, I'm in the NYC area, Philly area, anywhere that's close enough to NYC to make that track.
00:45:43.029 --> 00:45:44.550
When is the next one?
00:45:44.710 --> 00:45:49.989
And do you have a schedule of events or is it kind of free form?
00:45:50.070 --> 00:45:51.029
How do they work?
00:45:51.429 --> 00:45:55.670
So the next one's December 3rd, and it's gonna be the last one for the year.
00:45:55.989 --> 00:46:00.630
Also, I've never really been involved in any kind of event planning whatsoever.
00:46:00.789 --> 00:46:04.070
And so, like, I'm kind of iterating and learning this as I go.
00:46:04.230 --> 00:46:06.309
We don't have a schedule of events yet.
00:46:06.469 --> 00:46:15.509
I think we'll probably try to announce the next one the night of the event, but we're also kind of like iterating.
00:46:15.590 --> 00:46:19.110
So the best would be to go to the site and sign up for the mailing list.
00:46:19.349 --> 00:46:26.389
We put out the information, and if you're not in the New York area, we'll also send out emails afterwards when the talks are up on YouTube.
00:46:26.710 --> 00:46:27.590
So nice.
00:46:27.670 --> 00:46:29.590
And that's artificialruby.com?
00:46:29.989 --> 00:46:32.789
ArtificialRuby.ai, and I think that makes sense.
00:46:33.429 --> 00:46:34.150
Yeah, shocking.
00:46:34.389 --> 00:46:36.389
Dot AI for the AI Ruby meetup.
00:46:36.550 --> 00:46:37.190
Yep, that makes sense.
00:46:37.509 --> 00:46:38.150
We also have the document.
00:46:38.230 --> 00:46:39.029
So either one, either one.
00:46:39.269 --> 00:46:39.829
Okay, there you go.
00:46:39.989 --> 00:46:40.150
Yeah.
00:46:40.309 --> 00:46:41.349
Covering the bases.
00:46:41.750 --> 00:46:44.070
Domain addict, but aren't we all?
00:46:44.230 --> 00:46:44.869
Isn't that a thing?
00:46:45.029 --> 00:46:47.190
Isn't that like a prerequisite of being a developer?
00:46:47.349 --> 00:46:51.349
Is just owning domains and potentially never doing anything with them.
00:46:51.590 --> 00:46:54.389
Although you are doing stuff with them, so you're a step above.
00:46:54.710 --> 00:46:59.110
Any place on the internet that's best to find you specifically?
00:47:00.150 --> 00:47:04.949
Me specifically, subler.com will get you to kind of everything we're doing.
00:47:05.190 --> 00:47:09.269
Most of the writing that I do is works on mymachine.ai.
00:47:10.150 --> 00:47:11.670
I try to do it weekly.
00:47:11.829 --> 00:47:17.909
Some days, sometimes if the project's a little bit bigger, it takes a couple weeks, but usually there.
00:47:18.070 --> 00:47:22.309
And then from there, usually hanging out in the sublayer Discord.
00:47:22.469 --> 00:47:25.190
So if you chat, have some ideas, come there.
00:47:25.509 --> 00:47:25.909
Cool.
00:47:26.070 --> 00:47:26.630
Very cool.
00:47:26.869 --> 00:47:29.989
Well, is there anything we missed before we do our wrap-up?
00:47:30.150 --> 00:47:36.789
Like anything that you were hoping we'd talk about that we didn't, or that you want to at least touch on before we bounce?
00:47:37.269 --> 00:47:42.230
By the time this episode's published, latent library will be should be live.
00:47:42.309 --> 00:47:45.750
So that'll be at latent library.xyz.
00:47:46.150 --> 00:47:47.829
We can add that to the show notes too.
00:47:47.989 --> 00:47:56.550
And I think by then, you know, I mentioned earlier that I'm gonna be putting out kind of Railscasty style five to ten to fifteen minute videos.
00:47:56.789 --> 00:48:02.230
I think that should also be launched by the time this episode is published.
00:48:02.550 --> 00:48:05.670
I'm gonna add that to the works on my machine substack.
00:48:05.909 --> 00:48:26.309
So keep the essays and the open source stuff and then add like kind of a new$15 a month, two videos a month of here's a really focused technique on solving a problem or doing something with the agentic coding, agenc programming agents, like clock code, code I, yeah, Gemini.
00:48:26.949 --> 00:48:27.829
Do we call these things?
00:48:27.909 --> 00:48:29.829
Yeah, naming is hard.
00:48:30.550 --> 00:48:35.429
Everyone who's followed me doing anything ever should know I struggle with naming.
00:48:35.670 --> 00:48:35.989
Cool.
00:48:36.150 --> 00:48:36.869
Well, thanks, Scott.
00:48:36.949 --> 00:48:42.789
I really appreciate you coming on and talking about all that cool AI stuff and looking forward to having you in Philly.
00:48:42.869 --> 00:49:00.389
And hopefully I can make it up to an artificial here soon, because it definitely sounds like a cool place to talk to people and find out more about this very broad and weird space of AI that has no clear path.
00:49:00.469 --> 00:49:03.349
And that's both exciting and a little daunting.
00:49:03.590 --> 00:49:07.429
I do want to come up and check it out because I got the Ruby part down.
00:49:07.509 --> 00:49:09.670
It's the AI part I'm still figuring out.
00:49:09.989 --> 00:49:11.269
Yeah, we'd love to have you.
00:49:11.429 --> 00:49:12.710
It's definitely a great time.
00:49:12.789 --> 00:49:16.630
And yeah, I'm excited to come down to Philly and meet the Philly crew too.
00:49:16.789 --> 00:49:16.949
Yeah.
00:49:17.029 --> 00:49:17.110
Yeah.
00:49:17.909 --> 00:49:18.869
Thanks so much for having me on.
00:49:18.949 --> 00:49:19.829
This was a lot of fun.
00:49:20.070 --> 00:49:20.949
Absolutely, man.
00:49:21.110 --> 00:49:22.710
Check out Scott at all the places.
00:49:22.949 --> 00:49:27.909
Check out the show notes for links, and I will see you all in the next episode.
00:49:28.230 --> 00:49:28.550
Bye.