The title is doing a lot of work here. What resonated with me is the shift from “writing code” to “steering systems” rather than the hype framing. Senior devs already spend more time constraining, reviewing, and shaping outcomes than typing syntax. AI just makes that explicit. The real skill gap isn’t prompt cleverness, it’s knowing when the agent is confidently wrong and how to fence it in with tests, architecture, and invariants. That part doesn’t scale magically.
That's kind of the point here. Once a dev reached a certain level, they often weren't doing much "relaxing code typing" anyways before the AI movement. I don't find it to be much different than being a tech lead, architect, or similar role.
Ya know, I have to admit feeling something like this. Normally, the amount of stuff I put together in a work day offers a sense of completion or even a bit of a dopamine bump because of a "job well done". With this recent work I've been doing, it's instead felt like I've been spending a multiplier more energy communicating intent instead of doing the work myself; that communication seems to be making me more tired than the work itself. Similar?
Nah, I don’t miss at all typing all the tests, CLIs, and APIs I’ve created hundreds of times before. I dunno if I it’s because I do ML stuff, but it’s almost all “think a lot about something, do some math, and and then type thousands of lines of the same stuff around the interesting work.”
It's difficult to steer complex systems correctly, because no one has a complete picture of the end goal at the outset. That's why waterfall fails. Writing code agentically means you have to go out of your way to think deeply about what you're building, because it won't be forced on you by the act of writing code. If your requirements are complex, they might actually be a hindrance because you're going have to learn those lessons from failed iterations instead of avoiding them preemptively.
This is pretty recent - the survey they ran (99 respondents) was August 18 to September 23 2025 and the field observations (watching developers for 45 minute then a 30 minute interview, 13 participants) were August 1 to October 3.
The models were mostly GPT-5 and Claude Sonnet 4. The study was too early to catch the 5.x Codex or Claude 4.5 models (bar one mention of Sonnet 4.5.)
This is notable because a lot of academic papers take 6-12 months to come out, by which time the LLM space has often moved on by an entire model generation.
Depends on the participants. If they're cutting-edge LLM users then yes, I think so. If they continue to use LLMs like they would have back in the first half of 2025 I'm not sure if a difference would be noticeable.
we've never seen a profession drive themselves so aggressively to irrelevance. software engineering will always exist, but it's amazing the pace to which pressure against the profession is rising. 2026 will be a very happy new year indeed for those paying the salaries. :)
We've been giving our work away to each other for free as open source to help improve each other's productivity for 30+ years now and that's only made our profession more valuable.
I see little proof open source has resulted in higher wages and not the fact that everything is being digitized and the subsequent demand for such people to assist in such.
I'm not sure how I can prove it, but ~25 years ago building software without open source sucked. You had to build everything from scratch! It took months to get even the most basic things up and running.
I think open source is the single most important productivity boost to our industry that's ever existed. Automated testing is a close second.
Google, Facebook, many others would not have existed without open source to build on.
And those giants and others like them that were enabled by open source employed a TON of people, at competitive rates that greatly increased our salaries.
Indeed it did. All else being equal I still think SWE salaries on average would of been more if we kept it like that given basic economics - there would of been a lot less people capable of doing it but the high ROI automation opportunities would of still been there. The fact that "it sucked" usually creates more scarcity on the supply side; which all being equal means higher wages and in our capitalist society - status. Anecdotally with AI I'm seeing the opposite now - less hiring, less wage pressure and in social circles a lot less status when I mention I'm a SWE (almost sympathy these days vs respect only 5 years ago).
At least locally inflation adjusted in my city SWE wages bought more and were higher in general compared to others in the 90's-2000's than on wards (ex big tech). Partly because this difficulty and low level knowledge meant only very skilled people could participate.
Also it really baffles me how many are actually in on the hype train. Its a lot more than the crypto bros back in the day. Good thing AI still cant reason and innovate stuff. Also leaking credentials is a felony in my country so I also wont ever attach it to my codebases.
I think the issue is folks talk past each other. People who find coding agents useful or enjoyable are labeled “on the hype train” and folks for which coding agents don’t work for them or their workflow are considered luddites. There are an incredible number of contradicting claims and predictions out there as well, and I believe what we see is folks projecting their reaction to some amalgamation of them onto others. I see a lot of “they” language, and a lot of viral articles about business leadership “shoving AI down our throats” and it becomes a divisive issue like American political scene with really no one having a real conversation
I think the reason for the varying claims and predictions is because developers have wildly different standards for what constitutes working code. For the developers with a lower threshold, AI is like crack to them because gen ai's output is similar to what they would produce, and it really is a 10x speedup. For others, especially those who have to fix and maintain that code, it's more like a 10x slowdown.
Hence why you have in the same thread, some developer who claims that Claude writes 99% of their code and another developer who finds it totally useless. And of course others who are somewhere in the middle.
Its all a hype train though. People still believe in the AI gonna bring utopia bullshit while the current infra is being built on debt. The only reason it still exists is that all these AI companies believe in some kind of revenue outside of subscriptions. So its all about:
Owning the infrastructure and enshittify (ads) once enough products are based on AI.
.env files are used to develop as well, for some things like PayPal u dont have to change the credentials, you just enable sandbox mode. If I had some LLM attached to my codebase, it would be able to read those credentials from the .env file.
This has nothing to do with deployment. I never talked about deployment.
That’s not how LLMs work, it’s part of the reinforcement learning or SFT dataset, data labelers would have written or generated tons of examples using this and other patterns (all the emoji READMEs for example) that the models emulate. The early ones had very formulaic essay style outputs that always ended with “in conclusion”, lots of the same kind of bullet lists, and a love of adjectives and delving, all of which were intentionally trained in. It’s more subtle now but it’s still there.
Maybe I was being imprecise, but I’m not sure what you mean by “not how LLMs work” - discovering patterns of how humans write is exactly the signal they are trained against. Either explicitly curated like SFT or coaxed out during RLHF, no?
It could even have been picked up in pretraining and then rewarded during rlhf when the output domain was being refined; I haven’t used enough LLMs before post training to know what step it usually becomes noticeable.
You know what. After seeing all these articles about AI/LLM for these past 4 years, about how they are going to replace me as software developers and about how I am not productive enough without using 5 agents and being a project manager.
I. Don't. Care.
I don't even care about those debates outside. Debates about do LLM work and replace programmers? Say they do, ok so what?
I simply have too much fun programming. I am just a mere fullstack business line programmer, generic random replaceable dude, you can find me dime a dozen.
I do use LLM as Stack Overflow/docs replacement, but I always code by hand all my code.
If you want to replace me, replace me. I'll go to companies that need me. If there are no companies that need my skill, fine, then I'll just do this as a hobby, and probably flip burgers outside to make a living.
I don't care about your LLM, I don't care about your agent, I probably don't even care about the job prospects for that matter if I have to be forced to use tools that I don't like and to use workflows I don't like. You can go ahead find others who are willing to do it for you.
As for me, I simply have too much fun programming. Now if you excuse me, I need to go have fun.
I simply will not spend my life begging and coaxing a machine to output working code. If that is what becomes of this profession, I will just do something else :)
Until you realize you're just begging and coaxing a human to better beg and coax a machine to output working code - when you could just beg and coax the machine yourself.
It would definitely be the profession if we stopped developing things today. Think about the idea of coding agents 2 years ago, I personally found them very unrealistic and am now coding exclusively with them despite them being either a neutral or net negative to my development time simply because I see the writing on the wall that in 6 mos to a year they will probably be a huge net positive and in 2-3 years the dismissive attitude towards adoption will start to look kind of silly (no offense). To me we are _just_ at the inflection point where using and not using coding agents are both totally sensible decisions.
Hear hear. I didn't spend half my life getting an education, competing in the corporate crab bucket, retraining and upskilling just to turn into a robot babysitter.
Why? It is a matter of values. Fun can be a driving force just like money and stability is. It is simply a matter of your values (and your sacrifices).
Like I said, I am just a generic replaceable dime a dozen programmer dude.
Idk, I still mostly avoid using it and if I do, I just copy and paste shit into the Claude web version. I wont ever manage agents as that sounds just as complicated as coding shit myself.
It's not complicated at all. You don't "manage agents". You just type your prompt into an terminal application that can update files, read your docs and run your tests.
As with every new tech there's a hell of a lot of noise (plugins, skills, hooks, MCP, LSP - to quote Kaparthy) but most of it can just be disregarded. No one is "behind" - it's all very easy to use.
The title is doing a lot of work here. What resonated with me is the shift from “writing code” to “steering systems” rather than the hype framing. Senior devs already spend more time constraining, reviewing, and shaping outcomes than typing syntax. AI just makes that explicit. The real skill gap isn’t prompt cleverness, it’s knowing when the agent is confidently wrong and how to fence it in with tests, architecture, and invariants. That part doesn’t scale magically.
Is anyone else getting more mentally exhausted by this? I get more done, but I also miss the relaxing code typing in the middle of the process.
That's kind of the point here. Once a dev reached a certain level, they often weren't doing much "relaxing code typing" anyways before the AI movement. I don't find it to be much different than being a tech lead, architect, or similar role.
For me it's the opposite, I'm wasting less energy over debugging silly bugs and fighting/figuring out some annoying config.
But it does feel less fulfilling I suppose.
Ya know, I have to admit feeling something like this. Normally, the amount of stuff I put together in a work day offers a sense of completion or even a bit of a dopamine bump because of a "job well done". With this recent work I've been doing, it's instead felt like I've been spending a multiplier more energy communicating intent instead of doing the work myself; that communication seems to be making me more tired than the work itself. Similar?
It feels like we all signed up to be ICs, but now we’re middle managers and our reports are bots.
Yes, absolutely, I can be mentally wiped out by lunch.
Nah, I don’t miss at all typing all the tests, CLIs, and APIs I’ve created hundreds of times before. I dunno if I it’s because I do ML stuff, but it’s almost all “think a lot about something, do some math, and and then type thousands of lines of the same stuff around the interesting work.”
I like to alternate focusing on AI wrangling and writing code the old fashioned way.
It's difficult to steer complex systems correctly, because no one has a complete picture of the end goal at the outset. That's why waterfall fails. Writing code agentically means you have to go out of your way to think deeply about what you're building, because it won't be forced on you by the act of writing code. If your requirements are complex, they might actually be a hindrance because you're going have to learn those lessons from failed iterations instead of avoiding them preemptively.
Does using an LLM to craft Hackernews comments count as "steering systems"?
You're totally right! It's not steering systems -- it's cooking, apparently
This is pretty recent - the survey they ran (99 respondents) was August 18 to September 23 2025 and the field observations (watching developers for 45 minute then a 30 minute interview, 13 participants) were August 1 to October 3.
The models were mostly GPT-5 and Claude Sonnet 4. The study was too early to catch the 5.x Codex or Claude 4.5 models (bar one mention of Sonnet 4.5.)
This is notable because a lot of academic papers take 6-12 months to come out, by which time the LLM space has often moved on by an entire model generation.
Thanks Simon - always quick on the draw.
Off your intuition, do you think the same study with Codex 5.2 and Opus 4.5 would see even better results?
Depends on the participants. If they're cutting-edge LLM users then yes, I think so. If they continue to use LLMs like they would have back in the first half of 2025 I'm not sure if a difference would be noticeable.
> academic papers take 6-12 months to come out
It takes about 6 months to figure out how to get LaTeX to position figures where you want them, and then another 6 months to fight with reviewers
> Most Recent Task for Survey
> Number of Survey Respondents
> Building apps 53
> Testing 1
I think this sums up everybody complaints about AI generated code. Don't ask me to be the one to review work you didn't even check.
Yea. Nobody wants to be a full-time code reviewer.
Hi it's me, the guy who wants to be a full-time code reviewer.
Be careful what you wish for.
we've never seen a profession drive themselves so aggressively to irrelevance. software engineering will always exist, but it's amazing the pace to which pressure against the profession is rising. 2026 will be a very happy new year indeed for those paying the salaries. :)
We've been giving our work away to each other for free as open source to help improve each other's productivity for 30+ years now and that's only made our profession more valuable.
I see little proof open source has resulted in higher wages and not the fact that everything is being digitized and the subsequent demand for such people to assist in such.
I'm not sure how I can prove it, but ~25 years ago building software without open source sucked. You had to build everything from scratch! It took months to get even the most basic things up and running.
I think open source is the single most important productivity boost to our industry that's ever existed. Automated testing is a close second.
Google, Facebook, many others would not have existed without open source to build on.
And those giants and others like them that were enabled by open source employed a TON of people, at competitive rates that greatly increased our salaries.
Indeed it did. All else being equal I still think SWE salaries on average would of been more if we kept it like that given basic economics - there would of been a lot less people capable of doing it but the high ROI automation opportunities would of still been there. The fact that "it sucked" usually creates more scarcity on the supply side; which all being equal means higher wages and in our capitalist society - status. Anecdotally with AI I'm seeing the opposite now - less hiring, less wage pressure and in social circles a lot less status when I mention I'm a SWE (almost sympathy these days vs respect only 5 years ago).
At least locally inflation adjusted in my city SWE wages bought more and were higher in general compared to others in the 90's-2000's than on wards (ex big tech). Partly because this difficulty and low level knowledge meant only very skilled people could participate.
even if that's true it's clear enough AI will reduce the demand for swe
Then shit suckers like you scraped it all, ignored the licensing, and sold it back to the very people you took from for a premium.
Also it really baffles me how many are actually in on the hype train. Its a lot more than the crypto bros back in the day. Good thing AI still cant reason and innovate stuff. Also leaking credentials is a felony in my country so I also wont ever attach it to my codebases.
I think the issue is folks talk past each other. People who find coding agents useful or enjoyable are labeled “on the hype train” and folks for which coding agents don’t work for them or their workflow are considered luddites. There are an incredible number of contradicting claims and predictions out there as well, and I believe what we see is folks projecting their reaction to some amalgamation of them onto others. I see a lot of “they” language, and a lot of viral articles about business leadership “shoving AI down our throats” and it becomes a divisive issue like American political scene with really no one having a real conversation
I think the reason for the varying claims and predictions is because developers have wildly different standards for what constitutes working code. For the developers with a lower threshold, AI is like crack to them because gen ai's output is similar to what they would produce, and it really is a 10x speedup. For others, especially those who have to fix and maintain that code, it's more like a 10x slowdown.
Hence why you have in the same thread, some developer who claims that Claude writes 99% of their code and another developer who finds it totally useless. And of course others who are somewhere in the middle.
Its all a hype train though. People still believe in the AI gonna bring utopia bullshit while the current infra is being built on debt. The only reason it still exists is that all these AI companies believe in some kind of revenue outside of subscriptions. So its all about:
Owning the infrastructure and enshittify (ads) once enough products are based on AI.
Its the same chokehold Amazon has on its Vendors.
your credentials shouldn't be in your codebase to begin with!
.env files are a thing in tons of codebases
but thats at runtime, secrets are going to be deployed in a secure manner after the code is released
.env files are used to develop as well, for some things like PayPal u dont have to change the credentials, you just enable sandbox mode. If I had some LLM attached to my codebase, it would be able to read those credentials from the .env file.
This has nothing to do with deployment. I never talked about deployment.
If you have your PayPal creds in your repository, you are doing it wrong.
Is the title an ironic play on AI’s trademark writing style, is it AI generated, or is the style just rubbing off on people?
I think it’s a popular style before gen ai and the training process of LLMs picked up on that.
That’s not how LLMs work, it’s part of the reinforcement learning or SFT dataset, data labelers would have written or generated tons of examples using this and other patterns (all the emoji READMEs for example) that the models emulate. The early ones had very formulaic essay style outputs that always ended with “in conclusion”, lots of the same kind of bullet lists, and a love of adjectives and delving, all of which were intentionally trained in. It’s more subtle now but it’s still there.
Maybe I was being imprecise, but I’m not sure what you mean by “not how LLMs work” - discovering patterns of how humans write is exactly the signal they are trained against. Either explicitly curated like SFT or coaxed out during RLHF, no?
It could even have been picked up in pretraining and then rewarded during rlhf when the output domain was being refined; I haven’t used enough LLMs before post training to know what step it usually becomes noticeable.
You know what. After seeing all these articles about AI/LLM for these past 4 years, about how they are going to replace me as software developers and about how I am not productive enough without using 5 agents and being a project manager.
I. Don't. Care.
I don't even care about those debates outside. Debates about do LLM work and replace programmers? Say they do, ok so what?
I simply have too much fun programming. I am just a mere fullstack business line programmer, generic random replaceable dude, you can find me dime a dozen.
I do use LLM as Stack Overflow/docs replacement, but I always code by hand all my code.
If you want to replace me, replace me. I'll go to companies that need me. If there are no companies that need my skill, fine, then I'll just do this as a hobby, and probably flip burgers outside to make a living.
I don't care about your LLM, I don't care about your agent, I probably don't even care about the job prospects for that matter if I have to be forced to use tools that I don't like and to use workflows I don't like. You can go ahead find others who are willing to do it for you.
As for me, I simply have too much fun programming. Now if you excuse me, I need to go have fun.
I simply will not spend my life begging and coaxing a machine to output working code. If that is what becomes of this profession, I will just do something else :)
If I wanted to do that, I'd just move into engineering management and work with something less temperamental and predictable - humans.
I'd at least be more likely to get a boost in impact and ability to affect decision making, maybe.
Until you realize you're just begging and coaxing a human to better beg and coax a machine to output working code - when you could just beg and coax the machine yourself.
At least I'd be the one interfacing with a human instead of a machine :P
It would definitely be the profession if we stopped developing things today. Think about the idea of coding agents 2 years ago, I personally found them very unrealistic and am now coding exclusively with them despite them being either a neutral or net negative to my development time simply because I see the writing on the wall that in 6 mos to a year they will probably be a huge net positive and in 2-3 years the dismissive attitude towards adoption will start to look kind of silly (no offense). To me we are _just_ at the inflection point where using and not using coding agents are both totally sensible decisions.
Hear hear. I didn't spend half my life getting an education, competing in the corporate crab bucket, retraining and upskilling just to turn into a robot babysitter.
having fun isn't tied to employment unless you are self-employed even then what's fun should not be the driving force
"get a job doing something you enjoy and you'll never work a day in your life"
or something like that
That sounds miserable to me :(
you work on somebody's dime, its no longer your choice
it's your choice whose dime you work on. they can compete for your work by making it fun for you.
It's my life, it's my choice.
Why? It is a matter of values. Fun can be a driving force just like money and stability is. It is simply a matter of your values (and your sacrifices).
Like I said, I am just a generic replaceable dime a dozen programmer dude.
you dont get paid to have fun but to produce as a laborer
a job isn't supposed to be fun its nice when it is but it shouldn't be what drives decisions
You mean it shouldn't be the driving force of your employer to make decision. Yes I agree 10000%
I meant it can be your (not necessarily your employer) driving decision in life.
Of course, you need to suffer. That's about having tradeoffs.
Easy to say if you either:
(1) already have enough money to survive without working, or
(2) don't realize how hard of a life it would be to "flip burgers" to make a living in 2026.
We live very good lives as software developers. Don't be a fool and think you could just "flip burgers" and be fine.
Ah, I actually did flip burgers. So I know.
I also did dry cleaning, cleaning service, deli, delivery guy, etc.
Yup I now have enough money to survive without working.
But I also am very low maintenance, thanks to my early life being raised in harsh conditions.
I am not scared to go back flipping burgers again.
I haven't seen the definition of an agent, in the paper. Do they differentiate agents from generic online chat interfaces?
> Through field observations (N=13) and qualitative surveys (N=99)...
Not a statistically significant sample size.
97 samples is enough to get a 95% confidence level if you accept a 10% margin of error. 99 is not so bad, at least.
https://www.surveymonkey.com/mp/sample-size-calculator/
Significance depends on effect size.
Same thoughts exactly.
I like to think of it as "maintaining fertile soil"
Idk, I still mostly avoid using it and if I do, I just copy and paste shit into the Claude web version. I wont ever manage agents as that sounds just as complicated as coding shit myself.
It's not complicated at all. You don't "manage agents". You just type your prompt into an terminal application that can update files, read your docs and run your tests.
As with every new tech there's a hell of a lot of noise (plugins, skills, hooks, MCP, LSP - to quote Kaparthy) but most of it can just be disregarded. No one is "behind" - it's all very easy to use.