> What I wanted was to say “hey Siri, call Claw Phone” and have the audio system in my Toyota become an IDE. So I build it.
Or just focus on driving? Why we are doing it to ourselves? It seems so toxic to fill every possible little moment with… productivity? Is it even productive?
This comment is too emotional but i just felt so sad while reading this
I wonder if these people are just avoiding thinking about the tough things in their lives.
I wonder if these people are just scared of being human, so reaching for any distraction they can get.
I've tried to stop taking my phone with me when I go to the bathroom. When I shower. When I go to bed. Because I think we all have these same addictions. There's things that suck in life. But maybe if we put our phones down we can work together to solve these things.
The author says he has two kids, which would likely constrain what he is able to accomplish in his free time.
Children are financially dependent on the parents to provide for them. There's not really much way around that. It makes sense that if you can do more things within the time that is left that people will try to figure out how to cram those things in. What we would have resigned to give up in the past now seems possible to attain with enough AI credits and tools.
I do know a lot of people who love to talk. I don't think it's a character flaw. It's certainly not what I want, and I would die if I had to talk all day, but it's just the way they prefer to communicate. Same way that some people are introverts and some are extroverts, some people like reading paper books and some people like audiobooks.
I have not very well treated AuADHD and being alone with my thoughts very long is generally not very productive, At least Coding LLMs have helped me get things I wouldn't of had the attention span to make in the past come to life. and a good bit of vibe coding is just yelling at the LLM that what its doing sounds good on paper so keep going, please do the needful, make no mistakes :V
I was a workaholic from 18-26. 12+ hour days for months/years on end. It absolutely was not healthy. Toxic is not an inaccurate label.
But I don't regret it. Those years are the foundation of the career I have in my 30's.
Back in those days, when I wasn't at a computer, I was listening to non-fiction audiobooks on business and software. I don't know how I had such motivation bvack then, but I'm glad I capitalized on it while I had it.
In other words, to people reading questioning if they're working too much: it's okay to work hard as long as you're doing it for the right reasons. (I'll purposely leave "right reasons" undefined, that's on you to evaluate)
I'm just generally not a fan of people putting other people down for wanting to be productive. It's okay to work hard, and it's okay if your identity is your work at least for a short time in your life.
> I was a workaholic from 18-26. 12+ hour days for months/years on end. It absolutely was not healthy. Toxic is not an inaccurate label.
But I don't regret it. Those years are the foundation of the career I have in my 30's.
I'm glad this worked out for you
As a small counter anecdote I guess, I was this person in my 20s too. I arranged my whole life around work, constantly trying to get that next rung. Then I burned out, quit my job, moved to a new city and was unemployed for a year. My career has been pretty decent since then, but it almost had nothing to do with the hard work in my 20s. It's just that where I was working before didn't reward the hard work and where I am now rewards the work I do even though I don't work nearly as hard as I used to
Anyways. All I'm really saying is if you're going to work yourself to the bone trying to get ahead, make sure to take a breath once in a while and look around. Check in with yourself to ensure that the hard work is actually paying off, building the life you want. Otherwise it's just trading your youth and getting nothing in return
I learned a lot during those years too, and in some ways had to learn those things no matter what role or opportunity I chose.
I received some advice to simply add 15 minute of additional "work" a week, and not any more until I could handle it to my baseline... and then be sure to add 15 minutes of "balance" a week as well. Where my work days would go long, I found I was able to tie in habits to go for a walk, eat, etc. This did let me stretch quite far for a longer time, and burn out was a much lower risk.
How efficiently or effectively I learned those lessons could be debatable, but putting in sheer hours on learning and learning to apply things has compounded in some areas very strongly.
At the same time it must be acknowledged that doing this in a way that is not balanced can naturally lead to under development in other areas and it's worth trying to stay mindful of.
Hard work isn't a bad thing, it's the gap of not learning, not improving, not reflecting. There's no shortcut to putting in the work or learning the learnings.
I find driving to be one of the most useless ways of spending my time, and if it's for more than half an hour, I do try to figure out some way to increase the value of that time.
I have a weekly commitment that leaves me driving home (~40min) at 9pm, and I usually eat dinner (just a sandwich) while I drive. That also has the advantage of making it so that I'm not eating an hour before bed.
If I know that I need to call someone, I'll usually try to schedule that call while I'm driving. I used to take meetings while driving as well, though I stopped because it was perceived poorly by others.
What's sort of sad is that I can take public transit to all of my regular commitments, and that lets me keep doing something (reading, working, whatever). The schedules are poor, though, and they blow my commute times completely out of the water. For example, I've got a 5-7pm commitment that is a 15-minute drive one way, but if I wanted to go by bus, I'd have to leave at 3:30pm (latest it comes before I need to be there), and get back on it at 8pm (the earliest it comes after I'm done).
It’s not useless though. It allows you to engage your default mode network, which is otherwise insanely suppressed in the barrage of constant stimulation that is modern life.
I think you should just focus on the road because most of us are just trying to get home safely to our families. Some of us are even biking beside the road on a lightly-protected bike lane.
My main use case is that I'm driving and think of something I want to remember, and want to record it hands-free without taking my eyes off of the road
In my experience the driving-behavior part of my brain can run virtually autonomously, like how you don't really have to spend 100% of your brain to walk down the street. This means that the words-thinking part of my brain is almost completely free, with the exception of short high-attention spikes for risky maneuvers like onramp merging. This is why listening to music or podcasts is a very popular driving activity. In many places even handsfree phone calls are allowed as long as both hands are available and your vision isn't obstructed.
I would contend that listening to a podcast or being on a handsfree phone call would be on par with the Claw Phone.
I find there's an asymmetry between listening and speaking. It's fine for someone else to talk about their week, but don't ask me (driving) to do any deep descriptions about my own.
> In my experience the driving-behavior part of my brain can run virtually autonomously
It can, but I've heard quite plausible claims in the past [1] that you shouldn't let it - because that's one of the things that kills motorcyclists. Your autopilot brain is looking out for other cars quite effectively - but a motorcycle isn't a car, and can slip through un-noticed if you're mind is engaged elsewhere.
I started reading the first part of your comment before the article and thought you were mocking AI bros. I then read the rest of your comment and was sure you're misrepresenting TFA. I clicked on the article and started at it in disbelief.
I get that many people are tired of too many AI posts and there's an influx of negative comments but I think this is genuinely amazing. Think about watching Star Trek in the 60s and seeing people talk to computers and them understanding and being able to communicate back. We're literally living in the future!
The best time to solve personal problems with those techniques, perhaps. That is not the same as (and might be opposed to) the best time to seek employment or go into business using those techniques; there isn't going to be much of a market for things that your (employer's) potential customers could trivially do themselves.
I see this sentiment constantly. AI tooling is better than ever and its making building things easier than ever. I have respected coworkers who say that are maxing out multiple $200/month subscriptions.
But I have yet to see any results? Where is the useful stuff?
I don't know what those people are doing, but I built a personal day-to-day notes manager at work, for work, for under $20 in credits. Yes, I could have just used text files but this is less friction which means I'll actually stick to it. Nothing exactly like this already existed. It was built in under a week in small portions of spare time, and it probably would have been more like a month if I had to choose all the libraries and write the whole thing myself.
Search Ask HN threads, there are lots asking the same question and it looks like people do make useful stuff, it's just personal software not distributed to the public. I find that nice actually, because it's nice to make something just for yourself and is essentially what software is good for, solving your own problem.
I do think people are seeing useful results, but it’s at least several orders of magnitude less than what is claimed.
My metric is: how much code that I create today do I depend on in 3 months (incl learnings and one off data pulls etc.) and its waaay less than what I generate. A lot of it is frankly noise.
The results are in existing products being built out faster, in more internal tooling that would have previously not been cost-effective. Almost every software engineering shop is just doing the same thing as before but faster, as AI doesn't really give you an edge in the product side of things.
This is just an advertisement, it's not about being a "duct tape engineer", and the various coding agents are already great duct tape engineers, so I can't imagine someone writing a compelling blog post about it anyway.
Agreed. I was expecting something more along the lines of "now is the best time to be somebody capable of glueing together and fixing all the messes that AI agents have created, on top of being aware enough of security issues.
This has been the the case all the time: most of our work are connecting pipes using glue code/duct tape so to speak. But now, we are delegating this to AI. Nothing new for me.
I feel as if a lot of this what Google home (or other "home like" products) could have been and they have failed miserably. As a Google home user I find it can't answer the simplest questions that would require even the hint of an integration within Google's own ecosystem.
The good times are yet to come though: when all the slop held together by spaghetti, duct tape, chewing gum and hairballs starts falling apart and someone needs to fix it. If the slop bubble doesn't start popping soon, in 10 years a handful of people will end up being better paid than COBOL developers are now cause they'd be the only one that know what a compiler is. Personally I'm not too enthusiastic about the prospect so if I'm lucky, I'll be enjoying early retirement and watching all hell break loose from a camper van near the sea somewhere.
Have you used AI lately? Yes, this was the case a year ago but I've been using Claude daily for the past month and the quality is on par with what a senior engineer would be producing - often times better as it's more thorough and can think through all logical edge cases much more reliably. I do review all the code it writes. There are some suggestions I have but I'd say overall, 99% of it is solid.
I tend to call this sort of "I glued a bunch of external services together to make a useful tool" Software Plumbing, not Engineering.
Anyways I think what you've demonstrated that it's actually a really bad time to be a "Duct Tape Engineer" because anyone with a bit of knowhow can coax the AI to build them some pile of loose data pipes and leaky abstractions that appears useful. The market for this sort of software builder is about to get very crowded
51 comments:
> What I wanted was to say “hey Siri, call Claw Phone” and have the audio system in my Toyota become an IDE. So I build it.
Or just focus on driving? Why we are doing it to ourselves? It seems so toxic to fill every possible little moment with… productivity? Is it even productive?
This comment is too emotional but i just felt so sad while reading this
I wonder if these people just need to talk.
I wonder if these people are just avoiding thinking about the tough things in their lives.
I wonder if these people are just scared of being human, so reaching for any distraction they can get.
I've tried to stop taking my phone with me when I go to the bathroom. When I shower. When I go to bed. Because I think we all have these same addictions. There's things that suck in life. But maybe if we put our phones down we can work together to solve these things.
- Written on godelski's iPhone while pooping
The author says he has two kids, which would likely constrain what he is able to accomplish in his free time.
Children are financially dependent on the parents to provide for them. There's not really much way around that. It makes sense that if you can do more things within the time that is left that people will try to figure out how to cram those things in. What we would have resigned to give up in the past now seems possible to attain with enough AI credits and tools.
I do know a lot of people who love to talk. I don't think it's a character flaw. It's certainly not what I want, and I would die if I had to talk all day, but it's just the way they prefer to communicate. Same way that some people are introverts and some are extroverts, some people like reading paper books and some people like audiobooks.
Excrementalist Philosophy
I have not very well treated AuADHD and being alone with my thoughts very long is generally not very productive, At least Coding LLMs have helped me get things I wouldn't of had the attention span to make in the past come to life. and a good bit of vibe coding is just yelling at the LLM that what its doing sounds good on paper so keep going, please do the needful, make no mistakes :V
I was a workaholic from 18-26. 12+ hour days for months/years on end. It absolutely was not healthy. Toxic is not an inaccurate label.
But I don't regret it. Those years are the foundation of the career I have in my 30's.
Back in those days, when I wasn't at a computer, I was listening to non-fiction audiobooks on business and software. I don't know how I had such motivation bvack then, but I'm glad I capitalized on it while I had it.
In other words, to people reading questioning if they're working too much: it's okay to work hard as long as you're doing it for the right reasons. (I'll purposely leave "right reasons" undefined, that's on you to evaluate)
I'm just generally not a fan of people putting other people down for wanting to be productive. It's okay to work hard, and it's okay if your identity is your work at least for a short time in your life.
> I was a workaholic from 18-26. 12+ hour days for months/years on end. It absolutely was not healthy. Toxic is not an inaccurate label. But I don't regret it. Those years are the foundation of the career I have in my 30's.
I'm glad this worked out for you
As a small counter anecdote I guess, I was this person in my 20s too. I arranged my whole life around work, constantly trying to get that next rung. Then I burned out, quit my job, moved to a new city and was unemployed for a year. My career has been pretty decent since then, but it almost had nothing to do with the hard work in my 20s. It's just that where I was working before didn't reward the hard work and where I am now rewards the work I do even though I don't work nearly as hard as I used to
Anyways. All I'm really saying is if you're going to work yourself to the bone trying to get ahead, make sure to take a breath once in a while and look around. Check in with yourself to ensure that the hard work is actually paying off, building the life you want. Otherwise it's just trading your youth and getting nothing in return
I learned a lot during those years too, and in some ways had to learn those things no matter what role or opportunity I chose.
I received some advice to simply add 15 minute of additional "work" a week, and not any more until I could handle it to my baseline... and then be sure to add 15 minutes of "balance" a week as well. Where my work days would go long, I found I was able to tie in habits to go for a walk, eat, etc. This did let me stretch quite far for a longer time, and burn out was a much lower risk.
How efficiently or effectively I learned those lessons could be debatable, but putting in sheer hours on learning and learning to apply things has compounded in some areas very strongly.
At the same time it must be acknowledged that doing this in a way that is not balanced can naturally lead to under development in other areas and it's worth trying to stay mindful of.
Hard work isn't a bad thing, it's the gap of not learning, not improving, not reflecting. There's no shortcut to putting in the work or learning the learnings.
I find driving to be one of the most useless ways of spending my time, and if it's for more than half an hour, I do try to figure out some way to increase the value of that time.
I have a weekly commitment that leaves me driving home (~40min) at 9pm, and I usually eat dinner (just a sandwich) while I drive. That also has the advantage of making it so that I'm not eating an hour before bed.
If I know that I need to call someone, I'll usually try to schedule that call while I'm driving. I used to take meetings while driving as well, though I stopped because it was perceived poorly by others.
What's sort of sad is that I can take public transit to all of my regular commitments, and that lets me keep doing something (reading, working, whatever). The schedules are poor, though, and they blow my commute times completely out of the water. For example, I've got a 5-7pm commitment that is a 15-minute drive one way, but if I wanted to go by bus, I'd have to leave at 3:30pm (latest it comes before I need to be there), and get back on it at 8pm (the earliest it comes after I'm done).
It’s not useless though. It allows you to engage your default mode network, which is otherwise insanely suppressed in the barrage of constant stimulation that is modern life.
I think you should just focus on the road because most of us are just trying to get home safely to our families. Some of us are even biking beside the road on a lightly-protected bike lane.
Always relevant https://youtu.be/_o7qjN3KF8U?is=9aGmOhHqGt2KwRk8
My main use case is that I'm driving and think of something I want to remember, and want to record it hands-free without taking my eyes off of the road
In my experience the driving-behavior part of my brain can run virtually autonomously, like how you don't really have to spend 100% of your brain to walk down the street. This means that the words-thinking part of my brain is almost completely free, with the exception of short high-attention spikes for risky maneuvers like onramp merging. This is why listening to music or podcasts is a very popular driving activity. In many places even handsfree phone calls are allowed as long as both hands are available and your vision isn't obstructed.
I would contend that listening to a podcast or being on a handsfree phone call would be on par with the Claw Phone.
I find there's an asymmetry between listening and speaking. It's fine for someone else to talk about their week, but don't ask me (driving) to do any deep descriptions about my own.
> In my experience the driving-behavior part of my brain can run virtually autonomously
It can, but I've heard quite plausible claims in the past [1] that you shouldn't let it - because that's one of the things that kills motorcyclists. Your autopilot brain is looking out for other cars quite effectively - but a motorcycle isn't a car, and can slip through un-noticed if you're mind is engaged elsewhere.
[1] Citation needed, but lacking I'm afraid!
People like different things than you do, not sure why you have to get sad about it.
Driving is a good time to decompress or hammock based engineer imo
Being a hammock-deployed engineer is really the career goal.
Some folks might be trying to empty what's on their mind.
Very well could be a productivity habit bordering on obsession too.
So a lot of slop out there is just undiagnosed ADHD.
Yeah but what if I do this so I have the time in my workday to drive to the beach.
I started reading the first part of your comment before the article and thought you were mocking AI bros. I then read the rest of your comment and was sure you're misrepresenting TFA. I clicked on the article and started at it in disbelief.
I assumed they meant the 15 minutes waiting in between kind of slots. Not... Actually while driving I hope
> I didn’t build Twilio. I didn’t build the Realtime API. I didn’t build Claude Code or MCP.
I didn't write a blog post.
Most innovation is just connecting the works of others together with a touch of individual creativity.
Mea culpa. But I _did_ record a video!
Thank you, this quip really cracked me up. :))
That time in the car could have been spent thinking of something worthwhile enough to write about.
I get that many people are tired of too many AI posts and there's an influx of negative comments but I think this is genuinely amazing. Think about watching Star Trek in the 60s and seeing people talk to computers and them understanding and being able to communicate back. We're literally living in the future!
The best time to solve personal problems with those techniques, perhaps. That is not the same as (and might be opposed to) the best time to seek employment or go into business using those techniques; there isn't going to be much of a market for things that your (employer's) potential customers could trivially do themselves.
It is never sufficiently trivial if you don't have the technical know-how or the ability to do it in a time-efficient manner.
I see this sentiment constantly. AI tooling is better than ever and its making building things easier than ever. I have respected coworkers who say that are maxing out multiple $200/month subscriptions.
But I have yet to see any results? Where is the useful stuff?
I don't know what those people are doing, but I built a personal day-to-day notes manager at work, for work, for under $20 in credits. Yes, I could have just used text files but this is less friction which means I'll actually stick to it. Nothing exactly like this already existed. It was built in under a week in small portions of spare time, and it probably would have been more like a month if I had to choose all the libraries and write the whole thing myself.
Search Ask HN threads, there are lots asking the same question and it looks like people do make useful stuff, it's just personal software not distributed to the public. I find that nice actually, because it's nice to make something just for yourself and is essentially what software is good for, solving your own problem.
Yup, that's a sentiment I wrote about last year: building software for personal use that doesn't need to scale
I do think people are seeing useful results, but it’s at least several orders of magnitude less than what is claimed.
My metric is: how much code that I create today do I depend on in 3 months (incl learnings and one off data pulls etc.) and its waaay less than what I generate. A lot of it is frankly noise.
The results are in existing products being built out faster, in more internal tooling that would have previously not been cost-effective. Almost every software engineering shop is just doing the same thing as before but faster, as AI doesn't really give you an edge in the product side of things.
This is just an advertisement, it's not about being a "duct tape engineer", and the various coding agents are already great duct tape engineers, so I can't imagine someone writing a compelling blog post about it anyway.
Agreed. I was expecting something more along the lines of "now is the best time to be somebody capable of glueing together and fixing all the messes that AI agents have created, on top of being aware enough of security issues.
This was the exact opposite.
This has been the the case all the time: most of our work are connecting pipes using glue code/duct tape so to speak. But now, we are delegating this to AI. Nothing new for me.
All modern SaaS is just other SaaS glued together
I feel as if a lot of this what Google home (or other "home like" products) could have been and they have failed miserably. As a Google home user I find it can't answer the simplest questions that would require even the hint of an integration within Google's own ecosystem.
I hope he does not use it and just wanted to advertise his project to get some Github stars...
The good times are yet to come though: when all the slop held together by spaghetti, duct tape, chewing gum and hairballs starts falling apart and someone needs to fix it. If the slop bubble doesn't start popping soon, in 10 years a handful of people will end up being better paid than COBOL developers are now cause they'd be the only one that know what a compiler is. Personally I'm not too enthusiastic about the prospect so if I'm lucky, I'll be enjoying early retirement and watching all hell break loose from a camper van near the sea somewhere.
Have you used AI lately? Yes, this was the case a year ago but I've been using Claude daily for the past month and the quality is on par with what a senior engineer would be producing - often times better as it's more thorough and can think through all logical edge cases much more reliably. I do review all the code it writes. There are some suggestions I have but I'd say overall, 99% of it is solid.
And when you get home to check out the results, you won't understand any of the code :)
This is a completely insane way to check how many emails I have in my inbox I love it.
It's the spaghetti code years all over again but with ai. :)
I tend to call this sort of "I glued a bunch of external services together to make a useful tool" Software Plumbing, not Engineering.
Anyways I think what you've demonstrated that it's actually a really bad time to be a "Duct Tape Engineer" because anyone with a bit of knowhow can coax the AI to build them some pile of loose data pipes and leaky abstractions that appears useful. The market for this sort of software builder is about to get very crowded