TRANSKRIP 🔗
WEBVTT
00:00:00.160 --> 00:00:03.359
Hey, it's Jason, host of the Code with Jason podcast.
00:00:03.520 --> 00:00:04.480
You're a developer.
00:00:04.639 --> 00:00:06.160
You like to listen to podcasts.
00:00:06.400 --> 00:00:07.759
You're listening to one right now.
00:00:07.919 --> 00:00:13.599
Maybe you like to read blogs and subscribe to email newsletters and stuff like that.
00:00:13.839 --> 00:00:14.960
Keep in touch.
00:00:16.079 --> 00:00:23.440
Email newsletters are a really nice way to keep on top of what's going on in the programming world.
00:00:24.239 --> 00:00:26.879
Except they're actually not.
00:00:27.199 --> 00:00:36.479
I don't know about you, but the last thing that I want to do after a long day of staring at the screen is sit there and stare at the screen some more.
00:00:36.640 --> 00:00:40.240
That's why I started a different kind of newsletter.
00:00:40.320 --> 00:00:43.679
It's a snail mail programming newsletter.
00:00:43.920 --> 00:00:44.479
That's right.
00:00:44.560 --> 00:00:51.679
I send an actual envelope in the mail containing a paper newsletter that you can hold in your hands.
00:00:51.840 --> 00:00:59.280
You can read it on your living room couch, at your kitchen table, in your bed, or in someone else's bed.
00:00:59.359 --> 00:01:02.159
And when they say, What are you doing in my bed?
00:01:02.399 --> 00:01:04.879
You can say, I'm reading Jason's newsletter.
00:01:04.959 --> 00:01:06.159
What does it look like?
00:01:06.640 --> 00:01:12.640
You might wonder what you might find in this snail mail programming newsletter.
00:01:12.879 --> 00:01:20.480
You can read about all kinds of programming topics like object-oriented programming, testing, DevOps, AI.
00:01:20.719 --> 00:01:23.760
Most of it's pretty technology agnostic.
00:01:24.239 --> 00:01:42.000
You can also read about other non-programming topics like philosophy, evolutionary theory, business, marketing, economics, psychology, music, cooking, history, geology, language, culture, robotics, and farming.
00:01:42.319 --> 00:01:46.239
The name of the newsletter is Nonsense Monthly.
00:01:46.560 --> 00:01:50.560
Here's what some of my readers are saying about it.
00:01:50.879 --> 00:01:57.120
Helmut Kobler from Los Angeles says thanks much for sending the newsletter.
00:01:57.280 --> 00:02:00.879
I got it about a week ago and read it on my sofa.
00:02:01.120 --> 00:02:06.400
It was a totally different experience than reading it on my computer or iPad.
00:02:06.640 --> 00:02:12.159
It felt more relaxed, more meaningful, something special and out of the ordinary.
00:02:12.960 --> 00:02:18.879
I'm sure that's what you were going for, so just wanted to let you know that you succeeded.
00:02:19.199 --> 00:02:20.800
Looking forward to more.
00:02:21.919 --> 00:02:31.520
Drew Bragg from Philadelphia says, Nonsense Monthly is the only newsletter I deliberately set aside time to read.
00:02:31.759 --> 00:02:44.240
I read a lot of great newsletters, but there's just something about receiving a piece of mail, physically opening it, and sitting down to read it on paper that is just so awesome.
00:02:44.479 --> 00:02:46.319
Feels like a lost luxury.
00:02:47.280 --> 00:02:57.919
Chris Sonnier from Dickinson, Texas says, just finished reading my first nonsense monthly snail mail newsletter and truly enjoyed it.
00:02:58.240 --> 00:03:03.199
Something about holding a physical piece of paper that just feels good.
00:03:03.439 --> 00:03:04.479
Thank you for this.
00:03:04.639 --> 00:03:06.240
Can't wait for the next one.
00:03:06.560 --> 00:03:16.319
Dear listener, if you would like to get letters in the mail from yours truly every month, you can go sign up at nonsense monthly dot com.
00:03:16.960 --> 00:03:20.240
That's nonsensemonthly.com.
00:03:20.719 --> 00:03:25.599
I'll say it one more time nonsense monthly dot com.
00:03:25.759 --> 00:03:29.599
And now without further ado, here is today's episode.
00:03:53.280 --> 00:03:54.719
Eleni, welcome back.
00:03:55.039 --> 00:03:57.680
Thank you so much, Jason, for having me back.
00:03:57.919 --> 00:03:58.560
I'm excited.
00:03:58.800 --> 00:03:59.759
I'm so glad you're here.
00:03:59.840 --> 00:04:00.879
I'm excited too.
00:04:00.960 --> 00:04:05.439
Um, for anybody who didn't catch the first episode, do you want to tell us a little bit about yourself?
00:04:05.840 --> 00:04:06.719
Yeah, for sure.
00:04:06.879 --> 00:04:09.199
Um, so yeah, I'm Eleni Konyor.
00:04:09.280 --> 00:04:12.639
I'm a senior staff software engineer at Cisco Meraki.
00:04:13.120 --> 00:04:15.439
I've worked here for about four years.
00:04:15.680 --> 00:04:25.759
Um outside of my profession, I am a Greek American, first generation um first person to go to college in my family.
00:04:26.079 --> 00:04:31.120
And I don't know, I like the outdoors, I like the bass.
00:04:32.480 --> 00:04:36.800
Um wait, wait, you said you like outdoors and you like what was the other thing?
00:04:37.040 --> 00:04:37.519
The bass.
00:04:37.600 --> 00:04:38.399
We talked about the bass guitar.
00:04:38.720 --> 00:04:40.079
Oh, the bass guitar, of course.
00:04:40.160 --> 00:04:40.319
Yeah.
00:04:40.480 --> 00:04:41.439
Yeah, yeah, yeah.
00:04:41.680 --> 00:04:45.680
Um, and yeah, we talked a little bit about left and right brain.
00:04:46.000 --> 00:04:47.279
So yeah.
00:04:47.439 --> 00:04:49.199
Uh I am biased.
00:04:49.279 --> 00:04:52.879
I would recommend people go hear that recording, but yeah, that's a little bit about it.
00:04:53.120 --> 00:04:54.720
Yeah, I thought that was a great one.
00:04:54.959 --> 00:04:59.759
Um, yeah, and dear listener, if you didn't know, I too work at Cisco Meraki.
00:05:00.720 --> 00:05:04.160
Um I'm a tech lead on a different team.
00:05:04.319 --> 00:05:14.079
You and I, Lenny, don't cross paths a lot in a work capacity at work, but we do complain in the DMs a lot to each other, which is great.
00:05:14.399 --> 00:05:22.959
Um, I often feel like, you know, I have a
Load full transcript
complaint, and I'm like, man, who who would understand this complaint that I need to complain about?
00:05:23.279 --> 00:05:24.319
Lenny would understand it.
00:05:24.399 --> 00:05:25.439
She gets it.
00:05:25.759 --> 00:05:27.759
Uh so I'm I'm glad you're there to.
00:05:28.560 --> 00:05:29.199
Yeah.
00:05:30.240 --> 00:05:33.120
Um, anyway, what's on your mind today?
00:05:33.519 --> 00:05:41.199
Yeah, um, we did talk a little bit about AI last time, and I think you know, AI is great, but there's also a lot of downsides.
00:05:41.439 --> 00:05:50.639
And, you know, right before we were like gathering here, we would talked a little bit about the reinventing of the wheels that is happening.
00:05:50.879 --> 00:05:58.639
Um, so maybe we could start complaining about that and then see see what other topics come to mind in terms of complaining.
00:05:59.439 --> 00:06:03.040
Yeah, and dear listener, I have to share just a little bit of background.
00:06:03.199 --> 00:06:05.360
Um, kind of in jest, I had the idea.
00:06:05.439 --> 00:06:12.240
I'm like, what if we start a podcast called I I forget, do you remember what I said for the podcast name idea?
00:06:12.800 --> 00:06:13.680
It was great.
00:06:13.839 --> 00:06:16.240
I was gonna try and see it in our DMs.
00:06:16.560 --> 00:06:20.399
Well, it it was something to do with you and me just like ranting.
00:06:20.639 --> 00:06:27.439
Uh I'm not gonna start a whole new podcast for that, but we can at least do that here on this podcast.
00:06:27.759 --> 00:06:34.800
Anyway, yeah, tell me tell me what you're telling me a little bit about pre-show where people will reinvent the wheel with AI.
00:06:35.360 --> 00:06:47.680
Yeah, I so because AI is so quick at just churning out code and like thousands of lines of code, and you know, it it gives you something demoable very fast.
00:06:48.160 --> 00:06:58.000
People love creating like bespoke solutions for things that like at least 80% they could just get already out there.
00:06:58.240 --> 00:07:08.720
So one thing I've noticed is that people who don't necessarily like the Jira interface, which you know, I'm I have never worked at Alassian.
00:07:08.959 --> 00:07:10.079
I have no skin in the game.
00:07:10.240 --> 00:07:15.439
I used to be the biggest Jira hater, and they've made so many improvements in the past few years.
00:07:15.600 --> 00:07:19.040
I don't know who's making those decisions, but please keep doing it.
00:07:19.920 --> 00:07:27.759
Um, so I don't think the interface is as bad as it used to be by any means, but still people have this mindset that it's frustrating to use.
00:07:27.920 --> 00:07:30.879
And, you know, software engineers don't like writing tickets.
00:07:30.959 --> 00:07:32.959
I don't like writing tickets, so I get it.
00:07:33.120 --> 00:07:42.079
Um, but they I guess managers want to display it in a very specific way that you can probably just get from a board anyway, if you just configure the board differently.
00:07:42.399 --> 00:07:46.000
So they'll make their own like Jira instance effectively.
00:07:46.160 --> 00:07:50.399
And I can't even tell you how many managers have done this at Cisco alone.
00:07:50.720 --> 00:07:54.560
And they'll be like, look at what I built, and it's so pretty, and I'm so happy.
00:07:55.040 --> 00:07:59.199
Like, okay, so you're just gonna keep maintaining that now?
00:07:59.600 --> 00:08:02.879
Because that's gonna take away from whatever other responsibilities you have.
00:08:02.959 --> 00:08:04.000
So that's one thing.
00:08:04.639 --> 00:08:14.480
And then I think with skill development, like so many people create skills, and then you either put it in like one huge monorepo, or then you have many different scattered repos.
00:08:14.560 --> 00:08:19.360
And it's like, how does everyone get the information that they can use a skill and blah, blah, blah?
00:08:19.600 --> 00:08:30.319
And there's like open source packages that create marketplaces that handle automatic updating and all this stuff that you can configure, and it's quite nice.
00:08:30.480 --> 00:08:31.839
And like I said, open source.
00:08:31.920 --> 00:08:44.799
It does so much more than anyone could possibly be building on their own, but there's at least five at Cisco where people are like, well, I had a very specific need that I wasn't that wasn't being met somewhere else.
00:08:44.879 --> 00:08:50.960
And I'm like, okay, so you just wasted all of those tokens to build something that you didn't need.
00:08:52.320 --> 00:08:55.759
You could have been building something cooler that doesn't exist.
00:08:56.159 --> 00:09:01.279
Um, so yeah, that's like my biggest bright gripe right now around landscape.
00:09:01.840 --> 00:09:03.679
Yeah, it's so entertaining.
00:09:03.759 --> 00:09:07.200
It's it's depressing and entertaining at the same time.
00:09:07.519 --> 00:09:11.120
Um, you know, I've I've talked about this before.
00:09:11.200 --> 00:09:24.639
I don't know if I've talked about it on the podcast, and not to get political, but there were kind of three events in the 21st century which made me change my view of humanity a bit.
00:09:24.960 --> 00:09:29.039
Um one was when Trump got elected in 2016.
00:09:29.200 --> 00:09:30.879
I'm just like, what the fuck?
00:09:31.279 --> 00:09:42.399
And it it it caused me to like rewire my brain and like have a new understanding of people and America and the world and stuff like that.
00:09:42.639 --> 00:09:46.000
Um and that was you know, that was on me.
00:09:46.159 --> 00:09:58.960
Like my my understanding was distorted, and so this this thing that was a big shock to me caused me to to to rethink everything and gain a better understanding.
00:09:59.279 --> 00:10:02.000
Um and then the next thing was COVID.
00:10:02.399 --> 00:10:09.759
There were all sorts of wacky responses to that whole thing on both sides of the political spectrum.
00:10:10.639 --> 00:10:17.759
Um and now AI the the response to and AI is is
less political.
00:10:17.840 --> 00:10:32.879
There's there's some political stuff mixed in, but mostly it's just it's depressing, and I hate to say it, but like the average person is so much dumber than I previously thought.
00:10:33.679 --> 00:10:36.799
Um even supposedly smart people.
00:10:37.039 --> 00:10:49.679
You know, like I used to work at a grocery store in a bad neighborhood, and like I all day, every day I had to deal with not everybody, but I had to deal with a lot of awful people.
00:10:49.919 --> 00:10:51.440
Just awful people.
00:10:51.759 --> 00:11:04.240
Like, quick example, one time a guy stuffed a bunch of steaks down his pants, and he tried to walk out and steal these steaks, and we had to fight him.
00:11:04.559 --> 00:11:05.360
Oh my god.
00:11:05.600 --> 00:11:14.799
Yeah, me and these this other guy fought him, and he like threw me against uh this like brochure rack, and like I cut my head and I bled.
00:11:15.200 --> 00:11:19.039
He tried to this is this is one of the best parts.
00:11:19.279 --> 00:11:25.840
Um the other guy tackled him, and I like jumped on him and put him in a headlock, and we were like wrestling around on the ground.
00:11:26.000 --> 00:11:33.200
The guy put his thumb in my right eye and tried to fucking go gouge my eye out over stakes.
00:11:33.679 --> 00:11:39.679
He he didn't manage to gouge out my eye, but he did manage to scoop my contact lens out of my eye.
00:11:40.399 --> 00:11:57.120
Yeah, so anyway, just that that was like a sample of reality at that point in time where like I grew up in a small town, then I moved to this small city and and had a whole new experience of humanity.
00:11:57.679 --> 00:11:59.600
Yeah, I'm so sorry you had to deal with that.
00:11:59.759 --> 00:12:00.639
That's wild.
00:12:00.960 --> 00:12:02.320
Oh no, it was fun.
00:12:02.559 --> 00:12:16.480
Um and and now it's like okay, I have been like sorted into a different socioeconomic stratum, and now I don't deal with the kind of people who stuff steaks down their pants.
00:12:16.559 --> 00:12:22.320
Uh it's it's all these uh college educated, supposedly smart people.
00:12:23.120 --> 00:12:30.399
But as you have experienced as well as me, a lot of these people are not actually fucking smart.
00:12:30.480 --> 00:12:31.679
It's crazy.
00:12:32.000 --> 00:12:32.240
Yeah.
00:12:32.480 --> 00:12:38.559
And it's like uh it's it's one of those bitter truths that's really hard to accept.
00:12:38.960 --> 00:12:40.720
Yeah, no, I I hear you on that.
00:12:40.799 --> 00:12:50.799
It's there's a huge discrepancy in terms of like excuse me, what kind of college education you're getting and how open-minded you are.
00:12:50.960 --> 00:12:58.240
And like I when I first went to college, I I have lived near in New Jersey, so like I've lived near New York City my whole life.
00:12:58.320 --> 00:13:01.519
I've been there so many times before I ever lived there.
00:13:01.840 --> 00:13:21.360
But when you actually are there every single day and you're around people that you didn't grow up with, and it's like, you know, I went to NYU, and so there's a lot of people who come from international places, and so you get immersed into this lovely like hodgepodge of humanity, right?
00:13:21.519 --> 00:13:23.519
And get exposed to different things.
00:13:23.759 --> 00:13:45.840
And if you're someone who hasn't made an effort, a conscious effort to do that or to learn about other people or their own experiences, or even try to have empathy for their experiences, then no matter how educated you are, you're still gonna be missing all of that stuff that actually teaches you more about life.
00:13:46.080 --> 00:13:59.679
So yeah, you can get A's and and graduate um and and have gone to a college that you still didn't really get exposure to different people or different trains of thought.
00:14:00.240 --> 00:14:04.159
And so then how can you question your own reality?
00:14:04.320 --> 00:14:05.440
You don't, right?
00:14:05.919 --> 00:14:08.240
So it is fascinating.
00:14:08.960 --> 00:14:10.240
Yeah, it is.
00:14:10.399 --> 00:14:15.759
Um it's fascinating and it's frustrating and and all those things.
00:14:16.000 --> 00:14:18.320
Um, but anyway, back to the AI thing.
00:14:18.480 --> 00:14:23.919
Um, just the whole response to this wave of AI has been so irrational.
00:14:24.879 --> 00:14:38.159
We have this incredible tool that is like, you know, right up there with the light bulb and all that stuff in terms of the impact of inventions and what are people doing with it.
00:14:38.480 --> 00:14:45.440
Some people are doing amazing things, and a lot of people are just squandering this incredible power that we now have.
00:14:46.080 --> 00:14:53.120
Yeah, I saw like an 18-year-old is using AI to help cure like some specific kind of cancer.
00:14:53.519 --> 00:14:58.080
And like that to me, it's like, yes, please, let's keep hearing more about that.
00:14:58.480 --> 00:15:06.320
Um, but yeah, no, I I feel like mostly it's let me just make a copy of some website that already exists.
00:15:06.960 --> 00:15:16.399
It's like yeah, I don't know if it's like uh Parkinson's law or whatever, like work will expand to fill up the available time or whatever.
00:15:16.480 --> 00:15:48.000
But you know that thing how like early on in the Industrial Revolution there is a prediction that people would eventually only work like 10 or 15 hours a week and spend the rest of their time on leisure, because it's like, oh, you can make your whole income in just this fraction of the time you used to be able to, and people will spend the balance of their time in all these amazing ways, but people ended up just working the same amount, and now we have more money, and we um we've we filled up that available time.
00:15:49.120 --> 00:15:52.480
Um and I kind of see the same thing with AI.
00:15:52.639 --> 00:16:05.919
It's like we have uh uh I don't know, let's let's just throw out a number and say we have 5x the
productivity capacity that we did before.
00:16:06.960 --> 00:16:20.559
Um but I don't feel like people are creating 5x the value we're just we're we're creating the same amount of value and then using that extra capacity to like waste a bunch of time.
00:16:21.120 --> 00:16:22.559
Yeah, it's so sad.
00:16:22.960 --> 00:16:28.000
Yeah, that's probably overly cynical, but I I think that's probably like directionally correct.
00:16:28.399 --> 00:16:29.840
Yeah, no, I'm with you.
00:16:30.000 --> 00:16:44.879
Um, and I think it's healthy to have cynicism around this because there's so much hype with AI, and there's so much marketing from all of these different tech companies, and you know, they just sneeze out AI and then the stock price goes up, right?
00:16:45.120 --> 00:16:54.480
So it it is important to talk about the limitations and the reality of how we're using it versus the like capabilities and the pros.
00:16:54.799 --> 00:16:58.639
But yeah, it's there's so many things that go into it.
00:16:58.720 --> 00:17:03.279
And I don't know about you, like to bring it back to the political part a bit.
00:17:03.519 --> 00:17:19.680
Um, I've been seeing so much more on like different social media and actual news outlets, um, just reporting on how much uh damage AI is doing.
00:17:19.920 --> 00:17:35.680
Like before Chat GPT, we had companies going out and being like, look at how sustainable we are, and we're gonna meet all of our targets by X date, and like even bragging about meeting the targets earlier than originally planned.
00:17:35.920 --> 00:17:51.200
And now we are like spinning up data centers that kill people's water and just completely destroy the environment, um to a uh at a rate that we have never seen before.
00:17:51.519 --> 00:17:57.119
And none of these companies are kind of learning from the experiences of the past.
00:17:57.279 --> 00:18:01.839
Like, why did we have all these sustainable sustainability efforts to begin with?
00:18:02.079 --> 00:18:04.400
And then it's like, oh, whatever.
00:18:04.640 --> 00:18:08.720
Like we just need we need the tokens and we need everyone to be using this.
00:18:08.960 --> 00:18:26.720
And you know, to me, it's like, yeah, I I do want to keep using AI, but I don't want to be seeing people using it for things that, like, to your point are not contributing to the bottom line or increasing value, whether it's for themselves or for other, like for their companies, whatever.
00:18:26.960 --> 00:18:32.960
Um just a waste of resources, like real resources.
00:18:33.839 --> 00:18:37.599
Yeah, I'd I'd I'm not up on all that yet.
00:18:37.680 --> 00:18:39.599
I'd like to understand it better.
00:18:40.160 --> 00:18:48.319
Um because like I've I've heard about that, the environmental impact of data centers and stuff like that, and the the water usage and that kind of thing.
00:18:48.720 --> 00:18:51.440
I don't quite understand how.
00:18:52.079 --> 00:18:58.240
Um because like one one criticism is just like the sheer volume of water that it uses.
00:18:58.480 --> 00:19:01.279
But then not just water, but fresh water.
00:19:01.759 --> 00:19:02.319
Oh, okay.
00:19:02.880 --> 00:19:04.240
They don't recycle it.
00:19:05.519 --> 00:19:17.119
And then like other uh economic activities like agriculture, of course, use enormous amounts of water, um, like many, many times as much as data centers.
00:19:17.359 --> 00:19:23.039
So I don't quite understand what's different about the data centers versus these other uses.
00:19:23.759 --> 00:19:25.119
Yeah, that's a fair point.
00:19:25.279 --> 00:19:28.079
I haven't looked at that comparison metric either.
00:19:28.319 --> 00:19:34.480
Um, what I've been seeing reported is a data center can take up, I don't know the exact metric.
00:19:34.640 --> 00:19:39.519
I'm in my head, I'm saying 300,000 homes, but that might be off.
00:19:39.920 --> 00:19:43.759
So one data center takes up that many homes of electricity.
00:19:44.480 --> 00:20:05.680
And excuse me, it's it gets to the point where um some I forget what state it was in, but they were saying that a data center, I think it was Facebook's or Meta's, one of Meta's data centers, had opened up and they like completely tore down all the trees in that area to even build the data center.
00:20:06.000 --> 00:20:15.680
And this farm that was right next to them to that data center, they started realizing that their water pressure was very, very low.
00:20:16.319 --> 00:20:22.319
And then they started seeing traces of sediment coming through their water.
00:20:22.720 --> 00:20:25.680
And um, I don't know, I should know more.
00:20:26.079 --> 00:20:29.599
You probably know all of these things because you do so much around your house.
00:20:29.839 --> 00:20:33.680
But no, I mean, like, I is it the water tank or like something else?
00:20:33.759 --> 00:20:40.960
I have no idea what they were referring to, but they had something, they had to replace a whole thing in their house because the sediment was so bad.
00:20:41.119 --> 00:20:48.880
And they were like, this usually lasts like X amount of years, and now it's lasting like only five years, something like that.
00:20:49.119 --> 00:20:51.119
So it's a lot.
00:20:51.279 --> 00:21:08.079
And to see like the dirt that comes through someone's faucet, and no one is doing anything about it, they're just like, well, we need the energy, that to me is kind of gross because it's just telling you that everyone else is expendable for corporate profits.
00:21:08.480 --> 00:21:15.119
So yeah, there's a a real big negative side to AI that I wish we talked about more.
00:21:15.200 --> 00:21:23.519
And it's not gonna be the individual consumers that recycle and do all these things that are gonna make the biggest impact on the environment.
00:21:23.599 --> 00:21:32.720
It's gonna be the corporations and how do they find ways to be more sustainable so that we can still benefit from AI, but we don't destroy people's lives for it.
00:21:33.039 --> 00:21:33.680
Yeah.
00:21:34.319 --> 00:21:36.000
Yeah, that's a good point.
00:21:36.319 --> 00:21:41.759
Um, I really want to learn more about it because I don't understand how it works.
00:21:42.079 --> 00:21:57.279
Um what this is expanding the scope of the conversation wildly, but I really wish that we would get back to nuclear power because that's such a safer and cleaner form of energy than coal.
00:21:57.920 --> 00:21:59.759
Um, and so that could at least help.
00:22:00.160 --> 00:22:01.839
Help address some of this.
00:22:02.000 --> 00:22:07.599
Obviously, that doesn't do anything about the water issue, but at least the energy production part.
00:22:08.319 --> 00:22:08.880
Yeah, yeah.
00:22:08.960 --> 00:22:12.720
No, I I've heard for years that nuclear is cleaner, but it's riskier.
00:22:12.960 --> 00:22:16.880
So if you if something goes wrong, then it goes really wrong.
00:22:17.119 --> 00:22:21.759
Um, but I haven't read up on the latest and that in years.
00:22:22.000 --> 00:22:23.440
So I don't know if that's outdated.
00:22:23.839 --> 00:22:24.400
Yeah.
00:22:24.720 --> 00:22:31.279
Well, the way I look at it is like a per capita point of view.
00:22:31.519 --> 00:22:53.359
Like if if you if you total up all of the cost and human life and health and stuff like that from coal versus nuclear, um like proportionally to the amount that it's been used, um I understand that nuclear is so much safer.
00:22:53.599 --> 00:23:16.559
Um because like coal, you know, we're we're putting out all this uh all these emissions from the coal plants and um all this mercury is getting into the ocean and then the uh the fish the the fish get contaminated with mercury and that has all these and then goes into us.
00:23:16.799 --> 00:23:17.119
Yeah.
00:23:18.799 --> 00:23:25.759
Yeah, and we're not having any anything from that from uh anything like that from nuclear power plants.
00:23:26.000 --> 00:23:40.000
The trouble is like when you have something like Chernobyl or Three Mile Island, that's a big like news headline event rather than coal, which is just doing the same kind of damage every day.
00:23:40.079 --> 00:23:45.920
Like it's not newsworthy that, like, hey, some more tuna were contaminated by coal today.
00:23:46.240 --> 00:23:48.720
There's no um PR about that.
00:23:48.880 --> 00:24:01.119
So it was like really unfortunate that we had these bad accidents early on in the lifetime of nuclear that soured everybody to nuclear.
00:24:01.279 --> 00:24:10.079
And it's kind of a um, you know, most people are uh not very numerate, not very statistically literate.
00:24:10.480 --> 00:24:26.079
And so it was very easy to convince people that nuclear is so dangerous when statistically it's safer, but to our like uh caveman brains, that's that's not so easy to for that lesson to sink in.
00:24:26.640 --> 00:24:28.640
Yeah, that makes a lot of sense.
00:24:28.960 --> 00:24:32.160
It goes back to I feel like everything is marketing and PR.
00:24:33.039 --> 00:24:35.200
Everything is an ad, you know.
00:24:35.359 --> 00:24:37.200
So that's another thing to complain about.
00:24:37.359 --> 00:24:38.799
It gets tiresome.
00:24:40.079 --> 00:24:40.720
Yeah.
00:24:42.000 --> 00:24:43.920
Yeah, I can agree with that.
00:24:44.400 --> 00:24:50.240
Yeah, that's that's another annoying thing about the AI, is is all the hype around it.
00:24:50.880 --> 00:24:53.519
And the AI generated social media posts.
00:24:53.920 --> 00:24:54.720
I can't.
00:24:55.359 --> 00:24:57.039
Even on LinkedIn, right?
00:24:57.680 --> 00:24:58.079
Mm-hmm.
00:24:59.359 --> 00:25:01.920
Oh, I'm so happy you brought this up.
00:25:03.039 --> 00:25:08.319
I see, like sometimes I see like really, really awesome posts, and I'm like, okay, you actually cared.
00:25:08.559 --> 00:25:19.119
And then I see AI generated ones where I'm like, I understand that you wanted to make content, but I'm now just getting something from a model that I could have gotten myself.
00:25:19.279 --> 00:25:24.799
Like, you didn't add value to my life by me reading your post because you didn't really write it.
00:25:24.960 --> 00:25:28.559
You know, you had an inanimate object write it.
00:25:28.720 --> 00:25:34.319
And the way that it writes prose is nonsensical.
00:25:34.480 --> 00:25:38.480
Like it, it could look right, right?
00:25:38.799 --> 00:25:49.920
Um, but when you're reading things, the biggest thing to me is I had had a professor my freshman year who said, like, read every line and like try to see it as an arrow.
00:25:50.079 --> 00:25:54.799
And so every sentence should be an arrow to the next sentence.
00:25:54.880 --> 00:25:56.079
So they should all connect.
00:25:56.319 --> 00:26:01.039
And then every paragraph should, you know, somewhat relate to the next paragraph.
00:26:01.200 --> 00:26:02.799
You can't just go from A to Z.
00:26:03.279 --> 00:26:06.720
Um, and I see AI, like it doesn't do that.
00:26:07.119 --> 00:26:12.799
It could write a couple sentences and then like the next thing has nothing to do with the previous three.
00:26:13.039 --> 00:26:19.279
And maybe those are improving with like more, we just had what we're on Opus 4.8 now.
00:26:19.599 --> 00:26:26.880
Um, so there's improvements, but it still doesn't, the editing is not there.
00:26:27.119 --> 00:26:31.759
And so it's still obvious to me when I read a post that's AI generated.
00:26:31.839 --> 00:26:35.519
And I'm like, I don't, do I unfollow you at this point?
00:26:35.599 --> 00:26:39.519
Because I just want to see what like humans are actually saying.
00:26:39.759 --> 00:26:51.599
Um, like I want to hear about AI and I want to hear how people are using it, but I don't want to read a LinkedIn post or even like a whole, I don't know, what what are those things called now?
00:26:51.759 --> 00:26:54.880
The where people stack something.
00:26:55.440 --> 00:26:57.039
Um Substack.
00:26:57.200 --> 00:27:01.519
I don't want to read a whole Substack article
that is AI generated either.
00:27:01.680 --> 00:27:10.000
Cause it's like I could have just put that, fed that into my own prompts and gotten some result back, and it would have effectively been the same.
00:27:10.240 --> 00:27:14.079
So you know, I think there's a profitable lesson here.
00:27:14.880 --> 00:27:36.799
Um, and I have to think through what exactly it is, but like, okay, so I, as you know, am somebody who I I I hate the term content, um, but I'm somebody who has created content for many years, podcast episodes, blog posts, and stuff like that.
00:27:37.359 --> 00:27:43.440
Um and the advent of AI has made many things obsolete.
00:27:43.599 --> 00:27:45.920
Like, for example, Stack Overflow.
00:27:46.160 --> 00:27:50.000
I don't remember the last time I've even visited Stack Overflow.
00:27:50.240 --> 00:27:56.640
It's kind of just um relegated to the dustbin of history at this point.
00:27:57.039 --> 00:28:08.160
Um and then certain kinds of blog posts, like a blog post about like uh I don't know, documenting some function in Ruby or something like that.
00:28:08.319 --> 00:28:12.079
Like nobody needs that anymore because you can just ask AI.
00:28:12.640 --> 00:28:20.319
And so a big question for me is like, what is still worth writing and what are people still gonna read?
00:28:21.759 --> 00:28:31.200
And it it the things that that you said just now um I think shed some light on the answer to that question.
00:28:32.319 --> 00:28:45.599
Because people don't want I I don't remember your exact words, but like if your social media post is something that I could have conjured up myself with a prompt, then your post is worthless.
00:28:45.920 --> 00:28:49.200
Like I want something that only a person could have come up with.
00:28:50.160 --> 00:28:54.960
So I think that's don't you think there's value in like that documentation example that you gave?
00:28:55.119 --> 00:29:12.079
You know, like I recently I've seen posts that have switched, and it's like, oh, now that all these AI clients are charging, or AI companies are charging by token usage and not whatever subscription model they had before, the bills are way more expensive expensive.
00:29:12.319 --> 00:29:18.240
Um, and so people are like, oh yeah, we just hired an intern because the intern was cheaper than AI.
00:29:18.480 --> 00:29:31.119
Or we I think GitHub Copilot or no Microsoft in general, they canceled their CLUD subscription for all of their uh employees because it was too much of a cost for them.
00:29:31.279 --> 00:29:34.160
Um, they probably just want to use Copilot anyway.
00:29:34.480 --> 00:29:42.480
And so we're like not hiring people who aren't given the chance to actually make the mistakes themselves.
00:29:42.640 --> 00:29:51.119
And so if they're leaning only on AI, the AI is just gonna be very confident and spit something back that might not make sense or be helpful.
00:29:51.279 --> 00:29:56.319
I find a lot of the times, too, if you're iterating, it'll try to give the context of the iteration.
00:29:56.480 --> 00:29:58.559
And I'm like, no one cares about that.
00:29:58.799 --> 00:30:00.720
No one is going to read that part.
00:30:00.960 --> 00:30:07.839
Like, if I'm so if I'm using AI to create a pull request, right?
00:30:07.920 --> 00:30:21.839
And I have like a ticket that's pretty well scoped, and I as an engineer understand what I want to accomplish out of it, I can refine the code with the prompts in a conversation with the agent to get to a certain place.
00:30:22.000 --> 00:30:30.880
But what I find is that agents really love to give historical context in a way that doesn't help.
00:30:31.119 --> 00:30:41.920
So it's there's different, like when you get historical context about an application to understand how you came from A to B and C and D, that is helpful.
00:30:42.240 --> 00:30:50.000
But if I'm writing a Jira ticket with an agent and it's tell and I'm refining it and it's telling me, oh, a previous iteration, blah, blah, blah.
00:30:50.079 --> 00:30:53.599
It's like, if I give that to a fresh agent, why does the fresh agent care?
00:30:54.000 --> 00:30:55.039
Yeah, right.
00:30:55.279 --> 00:31:05.599
If I'm writing a pull request and there's code or a doc string or something in Python, and it's telling me, like, oh, you know, we didn't need this anymore because we decided to do this instead.
00:31:05.680 --> 00:31:09.039
It's like, but this is a new pull request.
00:31:09.359 --> 00:31:15.680
You know, I don't need to give the context of our conversation in the pull request.
00:31:16.160 --> 00:31:16.559
Right.
00:31:16.799 --> 00:31:24.160
I've experienced that exact thing when writing tickets and PR descriptions and stuff like that.
00:31:24.799 --> 00:31:40.799
It seems to be no good, at least not yet, at like putting itself in the shoes of somebody who um doesn't have any context on the thing you're talking about, and imagining what they would need to know from that perspective.
00:31:41.039 --> 00:31:49.759
Which makes sense because like that's a fairly that's kind of a specific and unique human skill.
00:31:50.640 --> 00:31:59.440
Uh and like I think the AI can kind of do that, but it doesn't do it without being prompted specifically to do that.
00:31:59.759 --> 00:32:00.559
Exactly.
00:32:00.799 --> 00:32:08.000
Yeah, and so to my point of these kinds of posts that you said, maybe they're not helpful to people anymore, but how would we know?
00:32:08.240 --> 00:32:08.559
Right?
00:32:08.799 --> 00:32:22.559
Because if these the younger generation of software engineers, if we're even giving them the opportunity to enter the workforce with this profession, how would they be able to learn from those mistakes?
00:32:22.720 --> 00:32:29.200
Especially as we keep moving towards like, oh, now AI can I can generate like 25 PRs in a day.
00:32:29.440 --> 00:32:31.759
And so now I'm gonna send that all to the team.
00:32:31.920 --> 00:32:33.279
That's a lot.
00:32:33.680 -->
00:32:37.519
And so now it becomes, oh, let's use AI to review the code.
00:32:37.680 --> 00:32:43.440
It's like the inmates in the asylum are just like reviewing themselves.
00:32:43.839 --> 00:32:44.160
Right.
00:32:44.400 --> 00:32:44.720
Right.
00:32:44.960 --> 00:32:50.079
So it becomes too much for a human to then it's overwhelming, right?
00:32:50.160 --> 00:32:52.160
Because the sheer volume of the code.
00:32:52.240 --> 00:33:05.839
And then, you know, if you're not someone who is used to has like, you know, early on in my career, I created a PR that was like 3,000 lines of code, and I no one had told me that that was a bad idea until I asked for review.
00:33:06.160 --> 00:33:09.759
And I was being stubborn instead of splitting up the PR.
00:33:09.839 --> 00:33:16.000
So it took like two months for that change to actually go through all of the review iterations and land.
00:33:16.720 --> 00:33:25.200
It was very thoroughly tested, like by the end of it and reviewed, but you know, we still needed to fix some issues after that, understandably.
00:33:25.359 --> 00:33:31.440
And that to me was like a huge landmark in my career of like, this is not something to do.
00:33:31.599 --> 00:33:35.839
I don't want to be sitting in review for something for two months that sucks.
00:33:36.319 --> 00:33:50.880
Um, so to me, like I try to keep my PRs as close to 200 absolute lines, AI generated or not, so that it's easier for a human to actually review it or even an agent, right?
00:33:50.960 --> 00:33:51.440
That's fine.
00:33:51.519 --> 00:33:53.519
I'm not saying don't use those tools.
00:33:54.000 --> 00:34:12.159
But how do the younger people actually learn if no one has capacity to teach them because we're all overwhelmed with work and the stream of PR is coming through to review, and we're all just talking to agents all the time, right?
00:34:12.239 --> 00:34:21.840
So to me, it's like there's still value in teaching people that, even if like two people read that and it made a difference in their career.
00:34:22.000 --> 00:34:26.159
I feel like to me, that would be a win and worth it.
00:34:26.320 --> 00:34:26.639
Yeah.
00:34:27.920 --> 00:34:36.320
Yeah, like the um this this wave of AI is revealing so many interesting things.
00:34:36.719 --> 00:34:59.760
Um like there are these fundamental and very old programming principles that for some reason don't they they don't seem to gain um acceptance or familiarity or whatever over time.
00:35:00.239 --> 00:35:08.159
It's like five percent of the programmer population is aware of these principles and it's a static five percent.
00:35:08.320 --> 00:35:25.119
We we don't as an industry we don't mature and get wiser, it's just uh new people are coming in and not learning these things, and then they get old and retire, and more new people come in and don't learn these things, and blah blah blah.
00:35:25.360 --> 00:35:36.800
Uh I I wish it were the case that our knowledge as an industry would accumulate and we get wiser over time, but sadly that seems not to be the the case.
00:35:37.199 --> 00:35:56.239
Um, but but more specifically, um things like uh feedback loops, for example, um, and that short feedback loops tend to work out a lot better than long feedback loops, like your example with a 3,000-line PR that took two months to get merged.
00:35:56.480 --> 00:36:02.960
You learned from that painful experience, and now you write PRs that are no more than 200 lines.
00:36:03.440 --> 00:36:04.159
Well, I try.
00:36:04.320 --> 00:36:05.840
Let's not give me all the credit there.
00:36:06.000 --> 00:36:08.559
Okay, I tried as best as I can.
00:36:09.679 --> 00:36:32.239
And these things are true whether AI is in the picture or not, but it's like AI is shining a bright spotlight on the fact that a lot of people they're either not aware of these fundamental principles, or they like think for some reason that these principles no longer apply because of AI.
00:36:33.280 --> 00:36:33.599
Yeah.
00:36:34.000 --> 00:36:39.199
Um, and it's again, it's one of those things like Trump, COVID, AI.
00:36:39.440 --> 00:36:47.119
They're like lifting the veil so that we can see these things that were always true, but I never realized them before.
00:36:47.199 --> 00:36:55.280
It's like, whoa, like so many people just don't know what the fuck they're doing at all, and they're behaving in these crazy ways.
00:36:55.760 --> 00:37:00.400
It was always true, but now because of AI, it's it's just so much more clear.
00:37:00.800 --> 00:37:01.360
Yeah.
00:37:01.599 --> 00:37:16.639
To me, it's so obvious that the folks who let's stick with that static 5%, those folks who are using AI, they're using AI in a way that maintains what they would have done beforehand, but doing it faster.
00:37:16.800 --> 00:37:23.199
And so the quality output is roughly the same as it would have been if they were just handwriting the code.
00:37:23.679 --> 00:37:27.440
And to me, those are the artists in software engineering.
00:37:27.679 --> 00:37:32.480
They are the people that actually care not just about the science, but the artistic flair.
00:37:32.719 --> 00:37:34.800
And it doesn't have to be complicated to read.
00:37:34.880 --> 00:37:42.239
Like in fact, I would I would be willing to argue that that static 5% care very much that it's simple code and easy to read.
00:37:42.400 --> 00:37:48.559
Um, but everybody else is just, oh, I don't have to write the code anymore.
00:37:48.719 --> 00:37:49.199
Awesome.
00:37:49.360 --> 00:37:52.960
I'm gonna use AI and just chug this along and get it shipped.
00:37:53.039 --> 00:37:53.760
I don't care.
00:37:53.920 --> 00:37:54.159
Right.
00:37:54.239 --> 00:38:10.639
And that to me is like the most depressing part of AI is that so the people who created all of these, you know, agentic workflows and whatever, and these like CEOs that go and they're like, coding is no longer the bottleneck.
00:38:10.800 --> 00:38:22.159
It's like if you
had actually followed practices that are statistically proven, like studies have been made, you can read about them um online and all of that.
00:38:22.320 --> 00:38:37.440
Even Cisco has done this where the lower amount of lines of code and like the single responsibility principles and good design patterns, you're and testing, very important, having high coverage, you're actually gonna ship things faster.
00:38:37.599 --> 00:38:42.079
And that's always been a thing that people have proven over and over and over again.
00:38:42.239 --> 00:38:51.280
And now we're like not, we're still not listening to it because none of these models have been trained on those practices, unfortunately.
00:38:51.679 --> 00:38:55.519
And I feel like those people who created all this, they just never cared.
00:38:55.679 --> 00:38:58.719
It to them, it was a burden to write the code.
00:38:58.880 --> 00:39:02.320
Whereas to the 5%, it was the thrill.
00:39:03.519 --> 00:39:07.920
Yeah, that's one of the things that I found that has been a bit surprising.
00:39:08.079 --> 00:39:41.920
Like how many people uh had like a like a uh I I don't know the right word, like an antipathy that that feels a little bit too strong, but like a a they they didn't relish the work that they do um and that feels too strong the other direction, but like it this has revealed that a lot of people view a lot of this work as a chore, which you know I think makes sense.
00:39:42.079 --> 00:39:46.960
Okay, I'm just thinking in real time here for the first time about some of the stuff.
00:39:47.280 --> 00:39:58.079
Um you know, okay, so I always say that I'm a testing chauvinist, like I I think that that is the one right way to do it.
00:39:58.480 --> 00:40:01.840
Um because of reasons.
00:40:02.000 --> 00:40:31.519
Like that's not just my opinion, but there are arguments behind this because when you practice uh test-driven development, you're deciding what to do, and then you do it rather than the other way around, which which sounds crazy, but like okay, when I used to do and sorry for like jumping all over, but um when I used to do consulting, people would bring me in often for help with testing.
00:40:32.239 --> 00:40:50.079
And so I would come in and I would see like, okay, I agree, you you have some room for improvement with testing, but let's look into this a bit and see what's happening, and I would sit with programmers and uh observe their work and stuff like that.
00:40:50.639 --> 00:41:05.519
And in all the cases, um in addition to a problem with testing, they their their programmers and managers didn't decide what to do before they did it.
00:41:05.760 --> 00:41:09.280
They would just have a vague idea and just start coding.
00:41:09.519 --> 00:41:15.440
It's like, wait, wait, how the fuck do you think you can accomplish anything if you don't know what you're trying to accomplish?
00:41:15.679 --> 00:41:20.239
Like it it sounds so crazy, like it couldn't possibly be true what I'm describing.
00:41:20.559 --> 00:41:24.880
But that's that's how almost everybody works.
00:41:25.360 --> 00:41:29.679
Um they just get a vague idea and start coding.
00:41:29.760 --> 00:41:38.960
And so, you know, I've I've I've sat with hundreds of different programmers over many, many years and watched people work.
00:41:40.000 --> 00:41:58.000
And quite a lot of people, most of the time they're working, are in a state of confusion and fog and uh frustration because their way of working is so disorganized.
00:41:58.880 --> 00:42:04.719
And often I will stop people and say, Hang on, what are you trying to do right now?
00:42:05.280 --> 00:42:06.719
And they don't have an answer.
00:42:07.679 --> 00:42:09.599
And it's like, what the fuck are you doing?
00:42:09.840 --> 00:42:12.480
Like, you should know what you're trying to do.
00:42:12.719 --> 00:42:14.800
And if you don't know what you're trying to do, stop.
00:42:15.920 --> 00:42:19.599
Stop working because you're not gonna not gonna get anywhere that way.
00:42:20.000 --> 00:42:23.199
Um, anyway, I don't even remember what my point was.
00:42:23.360 --> 00:42:32.239
I think maybe my point was that's why I'm a TDD chauvinist, because it forces you to clearly state what you're going for.
00:42:32.880 --> 00:42:49.039
Um and then you have to encode your intentions into a test, and then you write the code to fulfill um the expectations that your tests, your specifications describe.
00:42:49.599 --> 00:42:52.960
Um, I'll pause there because now I'm just starting to ramble.
00:42:53.280 --> 00:42:54.320
No, this is amazing.
00:42:54.400 --> 00:43:02.880
I see this all the time, uh, and it's only gotten worse with AI because you just prompt whatever and it goes off and does its thing.
00:43:03.199 --> 00:43:12.719
But the way that I've been using AI for so many years is I still spend the longest amount of time in quote unquote the planning phase, right?
00:43:13.039 --> 00:43:16.000
So I'm iterating with like what is it that I want to build?
00:43:16.079 --> 00:43:17.039
What is the point?
00:43:17.199 --> 00:43:21.119
And the code part should take the least amount of time, right?
00:43:21.360 --> 00:43:23.840
And that has been true for years.
00:43:24.000 --> 00:43:30.159
Is like by the time you start writing code, you should have an idea of what it is you're doing.
00:43:30.320 --> 00:43:43.760
And that part should be really fast, and then hopefully, you know, like I said, single responsibility, pull requests, low lines of code diff if you can, and ask for review and keep chugging along.
00:43:43.840 --> 00:43:46.320
Like that stuff is tried and true.
00:43:46.559 --> 00:43:53.760
But for some reason, people get so angry over the testing of it all that they're like, well, we don't have time to test.
00:43:54.000 --> 00:43:57.920
It's like you don't have time to not test.
00:43:59.039 --> 00:43:59.599
That's you.
00:44:00.960 --> 00:44:09.599
Because then you're gonna have bugs and then you're
delaying shipping this product that you're supposedly caring to show to your customers.
00:44:09.760 --> 00:44:14.400
Like, I don't understand it, but there's always been that discrepancy.
00:44:14.639 --> 00:44:20.239
It actually reminds me of I I had um, and back to like the documentation point a little bit too.
00:44:20.400 --> 00:44:30.639
I had a manager in my previous company that would say, like, we're we're not documenting anything, we don't have time, I don't care about tests, all this stuff.
00:44:30.960 --> 00:44:35.760
And I think about him so much now because now it's the inverse.
00:44:35.920 --> 00:44:41.920
It's like, oh, well, the agents need to know why this existed and it has to be really well documented for them.
00:44:42.159 --> 00:44:44.800
Like, wow, this like documentation has shifted.
00:44:44.960 --> 00:44:54.000
Like, people are on the bandwagon for documentation now, um, because it serves AI, not because it mattered for humans.
00:44:54.239 --> 00:44:57.840
They haven't come around to the testing fully though, which is unfortunate.
00:44:58.320 --> 00:44:59.119
Maybe next year.
00:45:00.159 --> 00:45:01.679
Yeah, maybe.
00:45:02.079 --> 00:45:08.960
Um, yeah, it it is interesting, the like good practices that AI is prompting people to adopt.
00:45:09.280 --> 00:45:11.039
That's a very positive thing.
00:45:11.280 --> 00:45:15.280
It's it's amusing to me that this is how this is happening.
00:45:15.760 --> 00:45:19.280
I I didn't expect it to go this way, but it's good.
00:45:19.440 --> 00:45:26.480
It's it's causing people to uh be more interested in testing and apparently documentation.
00:45:26.559 --> 00:45:33.360
I've I don't I I haven't been in places that um that that is relevant.
00:45:33.599 --> 00:45:47.840
Um but the testing stuff I have noticed because like people are like, well, have the AI write the tests and then write the code and then it can uh refactor without breaking the old stuff and stuff like that.
00:45:48.000 --> 00:45:50.400
So that is is good to see.
00:45:50.559 --> 00:45:58.880
Unfortunately, right now, AI is not, in my experience, is not very good at writing tests without a lot of guidance.
00:45:59.360 --> 00:46:04.320
But I have found that with the right guidance, it it can write very good tests.
00:46:04.800 --> 00:46:05.039
Yeah.
00:46:05.199 --> 00:46:09.920
Now I find myself pointing it to Martin Fowler's uh testing.
00:46:10.079 --> 00:46:14.400
He has like a whole testing site on his website um with different resources.
00:46:14.480 --> 00:46:16.800
I'm like, go look at this and do it.
00:46:17.599 --> 00:46:25.760
And then I routinely will have like, if I'm doing a proof of concept and I still want a high level of coverage, I might not care as much as the quality of the test.
00:46:25.920 --> 00:46:49.199
But when I'm actually going back and making sure it's productionized for a customer to see, I will tell the agent, like, look at these resources, including the Martin Fowler ones,
scan the entire testing code base for um low-value tests, things that if you like deleted this, it still would pass the test and delete those or like refactor the test so that they're actually high value.
00:46:49.360 --> 00:46:54.880
And every single time it has found multiple tests where it's like, oh, this is a stupid test.
00:46:55.280 --> 00:47:05.920
And it's actually kind of funny to see the agent evaluate a previous agent's work when you give it this kind of context, because then it's like, wow, what a what a terrible test.
00:47:06.719 --> 00:47:09.840
Like, well, you're the same model, but a different agent.
00:47:10.000 --> 00:47:11.039
So I don't know.
00:47:11.360 --> 00:47:12.719
Yeah, it's funny.
00:47:13.039 --> 00:47:24.719
Well, it's interesting how the model like kind of knows everything, um, but just because it knows everything doesn't mean it's always gonna behave according to what it knows.
00:47:25.119 --> 00:47:44.159
And so, like, if you if you ask it to write, for example, some small program, it might write a piece of garbage, and then you're like, no, no, no, like remember, like use the single responsibility program, uh single responsibility principle, and it's like, oh yeah, of course.
00:47:44.320 --> 00:47:45.920
And then it'll refactor it and it's great.
00:47:46.079 --> 00:47:48.559
It's like, well, why did you do it so bad the first time?
00:47:48.960 --> 00:47:50.320
In the beginning, yeah.
00:47:50.639 --> 00:47:54.719
No, there's you know, Cursor, um, I can't say enough good things about that company.
00:47:54.880 --> 00:47:56.079
I love Cursor so much.
00:47:56.159 --> 00:47:59.599
Um, and I really hope that SpaceX doesn't buy it.
00:47:59.760 --> 00:48:06.719
Um, but they actually exposed their like team toolkit to people so you can install it.
00:48:06.960 --> 00:48:08.880
And they have a DSlop skill.
00:48:08.960 --> 00:48:11.679
It's one of my favorite skills that exists out there.
00:48:12.000 --> 00:48:16.800
And um, some some folks at the company we've been building like different skills for people.
00:48:16.960 --> 00:48:19.440
And so we'll talk about this toolkit.
00:48:19.760 --> 00:48:34.719
And it's like you you do the iteration with the agent and it can do your tasks on your source code, and then you run the dslop and also the code review agents that exist in these clients now, and it will always come back and be like, this was terrible.
00:48:34.960 --> 00:48:37.920
We should fix this, or this, yeah, this was so sloppy.
00:48:38.079 --> 00:48:39.360
Like, let's delete that.
00:48:39.440 --> 00:48:42.800
And I recently, like yesterday, just learned about the slop grenade.
00:48:42.880 --> 00:48:46.480
It's used for messages, but I think it applies to code too.
00:48:46.800 --> 00:48:49.760
I I saw what you wrote on LinkedIn about that, yeah.
00:48:50.079 --> 00:48:51.840
Yeah, I love it so much.
00:48:52.079 --> 00:48:55.599
Um, and what was I trying to make the point?
00:48:55.679 --> 00:49:00.320
Oh, yeah, and we've said to each other, like, why not why do we even need the skill?
00:49:00.480 --> 00:49:04.079
Why can't the model just like deslop itself in the beginning?
00:49:04.239 --> 00:49:06.800
Um, and I guess you know, it's all back to the tokens.
00:49:06.960 --> 00:49:25.440
You you spend more tokens when you have to go through more iterations, but it would be so much nicer if these models just did tried and true programming tactics that have been proven to actually improve the code from the beginning instead of going through these multiple iterations.
00:49:26.559 --> 00:49:28.079
Well, okay.
00:49:28.559 --> 00:49:41.280
So the the the tough thing about the nature of the AI we have, like LLMs, um, is that they're not opinionated.
00:49:41.920 --> 00:50:05.519
They have all this well, okay, and like okay, so they have all this knowledge, but like we should put knowledge in quotes because because okay, it it has all this all these beliefs, um and they are not all compatible with each other and a lot of them are bullshit.
00:50:06.000 --> 00:50:34.000
Like so much so much programming education is just so wrong, um, and the LMs just read all this stuff and they believe it, and if you say like uh make sure to organize everything in service objects, then it will happily do it, even though I think that that's a a really bad idea.
00:50:34.239 --> 00:50:41.679
Um it has read all these blog posts that talk about how good of an idea that is.
00:50:42.719 --> 00:50:54.880
And so I I think we're probably I I don't see how we cannot be stuck with that situation until we have a different kind of intelligence that can be opinionated.
00:50:55.599 --> 00:51:02.320
Otherwise it'll just believe whatever you whatever version of the truth you want it to believe.
00:51:02.400 --> 00:51:02.960
Yeah.
00:51:03.360 --> 00:51:03.920
Yeah.
00:51:04.239 --> 00:51:05.360
Yeah, for sure.
00:51:05.519 --> 00:51:08.000
They can be guided in any conversation.
00:51:08.159 --> 00:51:16.880
They they won't normally like sometimes it'll push back when I ask it questions, and I'll but I have to preface it with like, I don't want you to just say yes to my question.
00:51:17.119 --> 00:51:25.280
I'm literally asking you to see, you know, and I tried to like test it almost be like, can you give me a valid response?
00:51:25.440 --> 00:51:30.000
And I think I'm at the point where it's more trustworthy because of the way that I prompt it.
00:51:30.239 --> 00:51:36.079
But in the beginning, I certainly would go Google because I was like, I don't trust you, you're wrong.
00:51:36.239 --> 00:51:38.320
Um, but they've gotten better in that respect.
00:51:38.400 --> 00:51:53.679
I just wish that they were trained with higher quality, at least the coding agents for sure, like higher quality code, because I'd imagine most of the the code that these models are trained on are whatever's on GitHub that's available.
00:51:53.760 --> 00:52:01.840
And there's so many
people who are just like fucking around and and they should, they should be exploring, but they're not writing production code necessarily.
00:52:01.920 --> 00:52:10.480
Like certainly the open source uh folks are, but everybody else who can have a pro public GitHub uh repo, like they might not be.
00:52:10.559 --> 00:52:19.599
You know, they might just be learning, and you know, they might even look at their code from a year ago and be like, whoa, that was gross, but the models are trained on it.
00:52:20.079 --> 00:52:23.440
So yeah, yeah, yeah.
00:52:23.679 --> 00:52:31.360
Like almost every single code base I've code base I've ever worked on in my life is a complete piece of shit.
00:52:31.519 --> 00:52:35.599
Like it's it's so far from exemplary, you know?
00:52:35.760 --> 00:52:36.400
Yeah.
00:52:36.880 --> 00:52:43.199
Um like it's not even it's not even like acceptable, let alone exemplary.
00:52:43.599 --> 00:52:55.039
And these are the things that the LLMs are using as examples, so like no wonder the code it writes is often it it's a miracle that it sometimes writes code that's good, you know?
00:52:55.440 --> 00:52:56.079
Yeah.
00:52:56.719 --> 00:53:11.440
Um yeah, so okay, so I I keep being reminded of this book that I've been working on for like years now, which might never come out, but I I keep chipping away at it um because I feel like it really needs to exist.
00:53:11.760 --> 00:53:16.079
Um maybe I've mentioned this to you to you before, but um I don't think you have.
00:53:16.880 --> 00:53:22.239
It's a book about like what in programming is just true.
00:53:23.280 --> 00:53:37.119
Um like and and how do we know when it comes to software design um what is good advice or what are good principles and what aren't?
00:53:37.679 --> 00:53:43.440
And what of this advice is just subjective opinion and what is objectively true?
00:53:43.519 --> 00:53:46.400
Like single responsibility principle, for example.
00:53:46.719 --> 00:53:49.440
Is that something that's objectively true?
00:53:49.679 --> 00:53:52.159
Or is that just an opinion?
00:53:52.400 --> 00:53:54.880
And if it's objectively true, why?
00:53:55.039 --> 00:53:56.800
And if it's not, why not?
00:53:57.119 --> 00:54:01.280
That kind of thing, so we can put all this stuff on a firm fitting.
00:54:01.360 --> 00:54:03.360
That's what this book is attempting to be.
00:54:03.760 --> 00:54:04.960
I'm obsessed with that.
00:54:05.039 --> 00:54:06.159
Please write it.
00:54:06.400 --> 00:54:06.960
I love it.
00:54:07.119 --> 00:54:09.599
Yeah, I'll I'll have to I'll have to send you what I have so far.
00:54:09.679 --> 00:54:12.480
I'll be really curious to to see what you think.
00:54:12.639 --> 00:54:29.840
But um, I I I feel like that kind of thing needs to exist in this AI age because again, AI will just if you like give it a nudge in a certain direction and be like, hey, by the way, the earth is flat, so like behave according to that belief, it'll be like, oh yeah, it will.
00:54:30.079 --> 00:54:30.719
Yeah.
00:54:31.760 --> 00:54:33.119
It's so scary.
00:54:33.360 --> 00:54:36.239
It's like, no, that's not scientifically proven.
00:54:36.320 --> 00:54:37.840
Please don't do that.
00:54:38.880 --> 00:54:39.199
Yeah.
00:54:39.360 --> 00:54:43.760
I mean, extreme example, it probably wouldn't literally go along with with that particular thing.
00:54:44.159 --> 00:54:45.440
We should test it now.
00:54:45.920 --> 00:54:46.159
Yeah.
00:54:46.639 --> 00:54:50.159
I think for science, will you pull up an agent real quick?
00:54:50.639 --> 00:54:58.239
I I bet it would I bet it would humor me if I said like behave as if the the earth is flat, even though you know that's not really true.
00:54:58.480 --> 00:55:00.159
But with programming, it's so much easier.
00:55:00.320 --> 00:55:09.280
You know, you take some crappy idea and and it will it will humor you in that way because it doesn't have an opinion about that.
00:55:10.079 --> 00:55:12.639
Anyway, we're it doesn't have a family.
00:55:13.119 --> 00:55:14.239
That's true.
00:55:14.719 --> 00:55:17.519
Um we're we're getting close to to time here.
00:55:17.679 --> 00:55:20.159
Anything you wanted to touch on before we go?
00:55:21.760 --> 00:55:22.719
I don't think so.
00:55:22.880 --> 00:55:31.199
I feel like this was a great complaining session, also talking about different, you know, programming uh things that we know to be true.
00:55:31.280 --> 00:55:31.840
I really love this.
00:55:31.920 --> 00:55:33.199
I'm very excited for this book.
00:55:33.360 --> 00:55:34.960
Please send me whatever you have.
00:55:35.199 --> 00:55:42.400
But I I'm interested to see how AI shifts even in the next year now that everything is more expensive.
00:55:42.639 --> 00:55:49.920
Uh, and maybe that will stop us reinventing the wheel, just to bring it back to what we first started talking about.
00:55:50.480 --> 00:55:50.880
Yeah.
00:55:51.039 --> 00:55:57.119
And I think if we look if we leave the listener with a piece of advice, it should be don't write your own Jira.
00:55:58.079 --> 00:55:59.199
Yeah, definitely.
00:55:59.280 --> 00:55:59.920
Don't do that.
00:56:00.000 --> 00:56:01.280
It's not worth your time.
00:56:01.519 --> 00:56:06.079
If you have a complaint about how Jira works, please go talk to the Atlassian team.
00:56:06.880 --> 00:56:08.000
Um okay.
00:56:08.239 --> 00:56:10.000
Very last question for you, Lenny.
00:56:10.079 --> 00:56:15.039
Um, anything you want to share, uh, your website, online presence, that kind of stuff.
00:56:15.360 --> 00:56:16.000
Oh, for sure.
00:56:16.079 --> 00:56:16.320
Yeah.
00:56:16.400 --> 00:56:21.360
I my personal website is datgreekchick.com, d-a-t greekchick.com.
00:56:21.519 --> 00:56:24.239
I'm on LinkedIn, Eleni Arvanitiskonier.
00:56:24.880 --> 00:56:30.800
You'll have that in the notes because I'm sure people will butcher that if they try to spell it on their own.
00:56:31.039 --> 00:56:38.000
Um, and yeah, I'm definitely every time we meet, I'm thinking I really need to get more of my presence out and write these things.
00:56:38.159 --> 00:56:39.760
So it's always inspiring.
00:56:39.840 --> 00:56:46.320
So I'm I'm gonna intentionally promise to the ether that I actually start doing that again.
00:56:46.639 --> 00:56:47.039
All right.
00:56:47.199 --> 00:56:49.199
Well, we will put that stuff in the show notes.
00:56:49.280 --> 00:56:51.599
And Lenny, thanks so much for coming on the show.
00:56:51.840 --> 00:56:54.400
Thank you so much, Jason, for having me.