I have tried to research what "meditation" really means. I discovered that its meaning is somewhere between "doing nothing" and "processing ceremony". Now it easier for me to analyze those articles with such an optics.
I have certainly noticed my stress skyrocket in this new mode of working. I was used to getting a lot done very quickly, with intense pockets of work followed downtime. Now it feels more like a steady stream of medium stress, and there is no opportunity to stop or drop the thread.
I must admit, if this is the new way of doing software development (eg: not actually programming but working with LLMs) I am not going to stick around for that long. It's not what I fell on love with, it's not what I trained for etc. I may as well do a job I don't enjoy that lets me rest my brain for later.
Yeah, same thoughts. And this industry is becoming so volatile, I'm not sure what will happen tomorrow. I mean it's highly unlikely that AI will replace developers at least in the next 10 years, but I'm not sure what will "software developer" become. Certain people love to work with details. If AI is taking away this joy, I'll rather retire as early as possible from this volatile industry.
Maybe we just aren't far enough in the vibe coding side of things and there are still too many people in the industry who still pay attention to details, so no major catastrophes haven't happened yet because of vibe coding. So the people who pay attention to details are still carrying their organizations, but I do wonder how long it is going to be sustainable.
When it comes to joy killers because of AI, then it is dismal how plagiarism (going by the definition of "presenting someone else's work without attribution") suddenly became widely accepted. When I see long lists of bullet points with interspersed bold text, I know that it is something the sender did not write or bother reviewing. Absolute cherry on top when in the end of that text you see the typical LLM suggestion that you can ask for more information, which the sender didn't even bother removing.
They crashed yes, but not for too long and they did recover. And was it ever confirmed it was because of vibe coding? Not sure how much if any it even impacted their stock.
I can confirm that nuclear power plant software has much higher quality level than normal commercial software and extremly extensive testing. In addition, lot of nuclear safety is checked below the software level on hardware level.
Developement of nuclear power plant software is very conservative, it will use LLMs maybe in 10-15 years.
I’m trying to get a bit away from the business stakeholders, into more technically required roles. Eventually my goal is to get into a system programming role.
The issue with roles close to business is that it doesn’t provide the right soil for good engineering . Your stakeholders have no concept of engineering and wants everything ASAP; Your manager is just a yes man who takes all tickets, and want you to use AI for everything because it’s so easy and quick; Your VP thinks your team is not moving quickly enough; Your VP puts speed before quality literally.
The thing is, I believe that some roles and some industries just don’t care about good engineering. If you want to be a good engineer, you have to stay away those, even if they are high paying, and get yourself into a system programming role, in a company that fails you if you do not have good engineering practices. The only way to be a good engineer is to put yourself in such an environment that you will almost surely fail if you are not a good one.
Those roles and companies can die and I don’t give a fuck about those business clowns.
It’s not just that. Working with multiple agents and tasks switching will increase cognitive load significantly leading to both poor decision making and increased stress.
10 years is a long time. 10 years ago the Transformer architecture didn't exist. I would call it moderately unlikely at best. At the very least, I would say it's likely that development will require an entirely different skillet 10 years from now.
One idea to consider might be going into safety critical embedded work (e.g. brake controllers, critical systems for airplanes/trains, medical devices, some industrial systems, ...). AI hasn't penetrated much here yet. It isn't at all clear how or if you would be able to certify the process for example.
That might change with time, but for now, all I see AI used for is additional code review and side scripts/tooling that don't need to be safety rated.
Of course, that might mean entirely switching language (C, C++ or increasingly but still in minority Rust), learning entirely different skills (control system theory, real time systems, possibly formal verification but usually not), etc.
The move-fast-break-things crowd is going to come after these as well, long with medical and defense software where lives are fully on the line. Sure, there will be failures and needless deaths and bombings of elementary schools, but that's just the price of being on the bandwagon.
Not sound harsh but that the people who solved problems with code just because they love coding disappears from problem-solving environments does sounds like a win-win for everyone involved. I've both been in situations where I loved coding the solution more than I want the problem solved, and I got in the way of people who just wanted the solution, and vice-versa where architect-astronauts are more interested in coding that solving things so they get in the way. If these could be better separated, that feels like the right direction.
This isn't the worst article, and it's triggered a decent amount of discussion (despite being very short). However, I really dislike "What you're doing wrong/failing to do" titles. They are intended to trigger anxiety, which is manipulative and (in this case) precisely contradicts the concern the author is purporting to have for the rest of us.
On the subject: some people find meditation very helpful, others find it a net negative, or useless, or impossible to do. So a categorical "you should do this" isn't correct or particularly helpful. Try it, if it works for you, great; but don't put it about that people who aren't doing it are being negligent in some way.
> On the subject: some people find meditation very helpful, others find it a net negative, or useless, or impossible to do. So a categorical "you should do this" isn't correct or particularly helpful. Try it, if it works for you, great; but don't put it about that people who aren't doing it are being negligent in some way
Absolutely. I've tried mediation in many situations and some classes but it's just not for me. My ADHD brain doesn't work that way. It's painfully boring and not relaxing at all. What does work for me is a walk through nature after a stressful day. There's another thing that works even better but too fringey and a bit nsfw to go into detail :) But anyway mediation definitely does not.
Relaxation isn't really a goal of meditation. When you do it you cultivate a kind of meta-cognition, an awareness of - and control over - the kind of invasive thinking that usually dominates our awareness.
As a fellow ADHD person I didn't get out the first few times I tried, but now find it quite helpful.
A most elementary form of meditation, is getting used to placing your attention on a sensation and keeping it anchored there - even when other sensations or thoughts arise.
Following the breath- place your awareness, your attention, on the sensation of air passing through your nostrils. Count one inbreath and outbreath cycle as «1», and count until 10 or 21. Decide before you start, how many repetitions of 10 or 21 you will do.
If at any point your attention has drifted to a different sensation - seeing, hearing etc, or thinking, visual imagery etc, then congratulate yourself for noticing, and restart from «1».
I recommend «The attention revolution» by Alan B. Wallace
Thank you. I like the comparison of "meditation" with "sport": it is not all the same, even if there are commonalities between some disciplines.
It is rare to see laypeople discuss some of the different types and which one may be best suited for a particular goal.
If the goal is simply relieving stress, performing some sport outdoors —especially team sports— is probably more effective than any meditation, for most people.
>> I’m clearly much more productive now. I’m doing five things at once very effectively, switching between multiple agent sessions from morning to night.
I feel like it depends on the task, and that's why people seem to disagree on this. Think about a manager managing 5 devs. If he is working on planning and managing work for his dev team, we don't say he is task switching, he's just taking a management role where he takes a high level view of the task at hand and then delegates the deep dive. Where it differs for devs is that we could in theory run multiple agents concurrently, but frequently, currently, we have to dive in and give the agents significant steers and this pulls us in to the detail. The same will happen for managers. The variables are the complexity of the task, the capability of the agent and the number of tasks. There are lots of scenarios where devs can run multiple tasks without too much mental overload, but I think what is hard is that we don't know when an agent will underperform on a task and we will get pulled back into developer mode. Maybe it's a case of running for as long as you can in manager mode and then accept that when one agent needs help, you have to single task with that agent (I think this is what makes us feel like we are the bottleneck, and that's where the feeling of stress creeps in). I thought about this a lot while working on https://www.agentkanban.io which I use to help me partition agent chats by task, run separate worktrees etc
Worth noting that this article is 25 years old. The world was very very different back then, especially when it comes to software engineering.
Context switching is a problem when the cost of switching contexts is non-negligible -- but in the age of agentic development is that still really true? Surely yes for some problems, but for many others I would argue it no longer is.
A personal anecdote for you:
At my company we have a local development CLI our devX team built, it allows for agents to interact with standing up, tearing down and managing local stacks for our software suite. When I receive customer feedback about a broken button, or a poor UX experience, I simply start up a prompt:
/metal user X reported an issue on the trial balance page, they encountered a blank page when using the inception to date filter. We need to investigate the root cause, spin up a new stack, and resolve the bug.
Then off to the next task, maybe some few hours later I'll check back in on the session and I'll see:
After a quick QA session I validate the fix, confirm that our claude reviewer has approved the PR and merge the PR to deploy. The mental burden of switching to this task is quite low, orders of magnitude lower than it would be 25 years ago.
I think the more stressful part is the management expectation that things will speed up more, especially when you can generate plausible looking frontends relatively quickly. And if you have out of touch control-freak management without any technical experience, you waste more life time arguing with them.
Of course you also might exhaust yourself to some degree, as your own expectation might be that you can develop multiple things in parallel, while also having to review a lot of code where you might not have context, so in a way you have to hold more high level context in your brain state, what might be somewhat stressful. However, when you have been tech lead once, all of that is somewhat familiar.
As someone brought up in a Hindu household (with Brahmin orthodoxy at that and all the casteism that came with it) and having learnt to shun all of that culture, and the religious indoctrination, here's the essence of mindfulness meditation that I was taught that I still practice and find useful.
1. Sit somewhere comfortable. Sitting "cross legged" or with your "back straight" as the guide linked to above advocates is not necessary. A comfortable chair/couch is fine.
2. The room should preferably be quiet. Though if you have the privilege of access to an outdoor courtyard that's quiet other than birdsong and chirp of insects, you'll probably enjoy it more. But a quiet room is good enough.
3. Phase 1: Set a timer on your watch/phone for 5 mins. Close your eyes. And let your mind wander. Doesn't matter what your mind drifts towards.
4. Phase 2: Restart the 5 min timer. Now, try quieten your mind of thoughts and focus instead on just your breathing. Be gentle with yourself. Your mind will wander again and that's fine. Just gently nudge it back to your breathing.
That's pretty much it. Slowly, over months try and increase Phase 2 from 5 to 10 mins.
When I described this to my partner, I used the analogy of treating your mind like a curious eager pup. In the first phase, cutting of external stimulus of sight by closing your eyes is like having the pup with you in a closed room.
In phase 2, you gently hold the puppy near you and get it to quiet down and stay still.
She mentioned that this analogy helped her a lot.
Honestly, this is pretty much the gist of it. I suspect that you will likely get most of the benefits of advanced meditative techniques with just the 2 simple steps from above. YMMV.
Be patient though. Getting to a fully calm state of mind takes months of practice.
The Mahasi method is quite different. You don't try to calm or control your mind. You observe and note your experiences as they're happening. Over time the calmness comes (and goes) but its not the goal. The goal is to see reality clearly. This clear seeing (which is where the word Vipassana comes from) leads to a change in the habit patterns that cause our stress and suffering.
You're right. This is a different technique. This is my simplification of the TM technique along with "japa" (repetition of a phrase) as is typically taught in the Brahmin scripture school mileu.
Since the OP was about achieving flow state and focus, I thought this was relevant.
So far I see it more like "you buy a car to take you between cities, but you end up routinely driving even just 1 km to a store, +50 kg overweight and prematurely dead due to a heart attack."
But sure, if the most important thing is to mass produce tons of shitty code, it's your life - just don't give people dumb advice on what they NEED to do. :)
I try not to context switch when doing agentic programming. Instead, I use a single agent thread (in pi) and pay extra for faster inference (GLM 5.2 from fireworks.ai, currently; around 100 tokens per second). I rarely spend more than $25 per working week, which is a fraction of a percent of my own fee (I’m a specialist consultant). I also keep an Anthropic subscription and use that for longer research and design tasks.
I’m sure many people produce more than me, but I retain my sanity as well as a high level of understanding of the code that I produce, which in my domain I feel is still important. I’ve tried ultracode-style subagent workflows and find that they rapidly produce reams of slop that I don’t have the patience or energy to properly review.
I’ve started doing mornings without any llm assisted work, and keeping it only for after 11. I find it gives me back the joy of designing my systems in a highly focused state, while keeping the later part of the day for persisting those well thought out ideas into code.
I noticed how relaxing and meditative programming can be. It might sound that after day job basically solving other people pronlems I sit down late at noght to just write code for hours on end. But I really enjoy it. Using LLM’s to generate the code ruins it.
I have also done meditation, but I struggle to keep it up for long. I think you should really do it consistently to get majority of effects. Coding, exercising, drawing has always been an easier form of meditation for me.
My favorite metaphor for programming is playing chess. Your opponent in programming is the complexity, you don't see its moves before the coding and design progress, before you make your choices/moves. You solve a problem by writing some code but that causes new problems down the line you didn't know existed before you made your choice of writing some specific code. or choosing a specific design.
Chess-players too are in a very "meditative" state when they play, and they enjoy it, I assume because it let's them focus on the game and forget about everything else.
I don’t think this article is suggesting really going for it in terms of meditation. But, as a warning to people, there is evidence that meditation can be dangerous for some people.
You say programming used to be a meditative activity.
Then why get overwhelmed by LLMs and meditate to calm down, when you can just write the code yourself at a healthier pace? Tools are supposed to be designed around humans, it’s not the human that has to adapt to the machine.
In any case, meditating with an end to destress or to reach higher levels of productivity is missing the point of meditation.
This is a common thing to say, but when during the development of human civilization has this actually been the case? Is agriculture designed around humans more than hunting/gathering? Is industrialized work more designed around humans than agrarian society?
I don't mean to sound pessimistic or technocratic; quite the contrary. But I think we shouldn't project our desire for equanimity onto romantized versions of civilization.
It's fine for your pet projects. But for most of professional programming it's no longer feasible as you'll be at a small fraction of your machine assisted performance.
If you think performance relates to speed and amount of code per unit of time yes. If you're more grounded with the reality of software engineering then no
I have in fact masters in SE and three decades experience of commercial programming. Loved every minute of it (well except the burnout episode) and still do my hobby projects. So I would say no, you are wrong. The models decimate not just the coding (the best and the most fun part of development) but all the pseudo-engineering roles like architects or product managers too. Simply because there's less need for communication in the team as the surface of work for each dev is now quite enormous.
My performance in writing code was never once the problem. I don’t get why I should increase the amount of output by depending on a third party tool to do my thinking to whom I have to explain my very abstract thought process in words.
The point of being an experienced programmer is thinking in data structures and transformations, not in prose. Why would I introduce all that friction?
I was so stressed at work a few years ago. Burnt out. Exhausted. I started meditating. Shared with my manager that I started, and it’s been helping me process all the chaos at work.
He told me that wasn’t normal, and I shouldn’t have to meditate just to function at work :’)
He was a smartass, but also very blunt - unsparingly.
I did not encourage him to, this was just during a weekly 1:1 where I was sharing with him how I’ve been coping with the amount of workload and chaos happening among the team/myself.
He was wanting to empathize me that it’s not normal to have to do that to be functional at work, acknowledging how rough things were at the time.
I kept doing it, but fell out of practice. Also left and no longer work there, due to stress and poor support. Shocker.
> I’m clearly much more productive now. I’m doing five things at once very effectively, switching between multiple agent sessions from morning to night. After working full-time like this for ~8 months, one thing I’m sure of is that this way of working involves much less time spent in a flow state.
What an utter piece of BS. AI goons really like to smell their own crap
I was discussing Buddhism with a few Buddhist friends this past weekend, and I randomly had an enlightenment. It was a very odd experience, I felt like I understood all the weird things I'd heard from them, and I suddenly became very calm and accepting of everything. I also had a sense of sort of "watching" what I was experiencing through my own eyes.
I'm generally hyper rationalist, so this was a very interesting experience, and it happened because a random thing one of my friends said about meditation made something "click" in me.
It lasted about a day, I can't say I have any lasting effects from it now. It'd be interesting to see if I can make it happen again, but when I was in that state, I thought that trying to make it happen would defeat the purpose.
I asked my friend "is the purpose of meditation just to feel existence?" and he said "yes, and also taking your fears, insecurities, etc and throwing them away", and something just clicked.
Personally, I feel that as an individual, it's the right time to complete a program, but as a team, it's become harder.
It's true that the proportion of founders has increased both in the US and in my country, Korea.
And unlike the old days, it feels like what's needed now isn't so much deep, concentrated programming knowledge in one area, but rather broad knowledge across many fields. The claim that "productivity has increased" really only applies to freelancers. In fact, there's been a noticeable increase in freelance outsourcing requests that would be hard to handle without AI, lots of short deadline gigs compared to before. And of course, that makes it harder to charge appropriately.
For teams, on the other hand, you still need things like code reviews and team decision making.
As an individual, I've practically become someone who just writes up a gate, lets AI handle the code, checks that the core domain doesn't break, watches the gate's rules, and pulls the lever.
The reason team work slows down is mainly because Agile methodologies and code review processes are still human centric and consensus driven, and human cognitive speed itself becomes the bottleneck.
So I can understand a lot of the arguments that come up in the comments. The important thing is that most people tend to only see their own situation and their own context, which makes it hard for them to understand others.
Bros "discuss on hacker news" link takes you to submit the article here. that really rustles my jimmies. its unfortunate that bro couldnt csrf the submit link thanks to submit tokens. I have no doubt he would have tried that too.
I have tried to research what "meditation" really means. I discovered that its meaning is somewhere between "doing nothing" and "processing ceremony". Now it easier for me to analyze those articles with such an optics.
I have certainly noticed my stress skyrocket in this new mode of working. I was used to getting a lot done very quickly, with intense pockets of work followed downtime. Now it feels more like a steady stream of medium stress, and there is no opportunity to stop or drop the thread.
I must admit, if this is the new way of doing software development (eg: not actually programming but working with LLMs) I am not going to stick around for that long. It's not what I fell on love with, it's not what I trained for etc. I may as well do a job I don't enjoy that lets me rest my brain for later.
Yeah, same thoughts. And this industry is becoming so volatile, I'm not sure what will happen tomorrow. I mean it's highly unlikely that AI will replace developers at least in the next 10 years, but I'm not sure what will "software developer" become. Certain people love to work with details. If AI is taking away this joy, I'll rather retire as early as possible from this volatile industry.
Maybe we just aren't far enough in the vibe coding side of things and there are still too many people in the industry who still pay attention to details, so no major catastrophes haven't happened yet because of vibe coding. So the people who pay attention to details are still carrying their organizations, but I do wonder how long it is going to be sustainable.
When it comes to joy killers because of AI, then it is dismal how plagiarism (going by the definition of "presenting someone else's work without attribution") suddenly became widely accepted. When I see long lists of bullet points with interspersed bold text, I know that it is something the sender did not write or bother reviewing. Absolute cherry on top when in the end of that text you see the typical LLM suggestion that you can ask for more information, which the sender didn't even bother removing.
programmers were always against "software patents" - the idea of copyrighting algorithms and implementations
> major catastrophes haven't happened yet because of vibe coding
Didn't Azure, AWS and Cloudflare crash a few times in the second half of 2025 because of vibe coding?
They crashed yes, but not for too long and they did recover. And was it ever confirmed it was because of vibe coding? Not sure how much if any it even impacted their stock.
It was confirmed each was because of vibe coding.
Catastrophies would be we vibe coded a nuclear plant or space rocket system and we blew up thousands of people due to a vibe coding error.
I can confirm that nuclear power plant software has much higher quality level than normal commercial software and extremly extensive testing. In addition, lot of nuclear safety is checked below the software level on hardware level.
Developement of nuclear power plant software is very conservative, it will use LLMs maybe in 10-15 years.
Bringing most of the western world economy to a standstill isn't one? When I say AWS was down I mean AWS was down.
I’m trying to get a bit away from the business stakeholders, into more technically required roles. Eventually my goal is to get into a system programming role.
The issue with roles close to business is that it doesn’t provide the right soil for good engineering . Your stakeholders have no concept of engineering and wants everything ASAP; Your manager is just a yes man who takes all tickets, and want you to use AI for everything because it’s so easy and quick; Your VP thinks your team is not moving quickly enough; Your VP puts speed before quality literally.
The thing is, I believe that some roles and some industries just don’t care about good engineering. If you want to be a good engineer, you have to stay away those, even if they are high paying, and get yourself into a system programming role, in a company that fails you if you do not have good engineering practices. The only way to be a good engineer is to put yourself in such an environment that you will almost surely fail if you are not a good one.
Those roles and companies can die and I don’t give a fuck about those business clowns.
It’s not just that. Working with multiple agents and tasks switching will increase cognitive load significantly leading to both poor decision making and increased stress.
https://pmc.ncbi.nlm.nih.gov/articles/PMC7075496/ https://pmc.ncbi.nlm.nih.gov/articles/PMC7614709/
10 years is a long time. 10 years ago the Transformer architecture didn't exist. I would call it moderately unlikely at best. At the very least, I would say it's likely that development will require an entirely different skillet 10 years from now.
One idea to consider might be going into safety critical embedded work (e.g. brake controllers, critical systems for airplanes/trains, medical devices, some industrial systems, ...). AI hasn't penetrated much here yet. It isn't at all clear how or if you would be able to certify the process for example.
That might change with time, but for now, all I see AI used for is additional code review and side scripts/tooling that don't need to be safety rated.
Of course, that might mean entirely switching language (C, C++ or increasingly but still in minority Rust), learning entirely different skills (control system theory, real time systems, possibly formal verification but usually not), etc.
> going into safety critical embedded work
The move-fast-break-things crowd is going to come after these as well, long with medical and defense software where lives are fully on the line. Sure, there will be failures and needless deaths and bombings of elementary schools, but that's just the price of being on the bandwagon.
"Switch to a field that involves many people dying if you write a bug" doesn't sound like the less stressful alternative to me.
it was impossible to write code for 8 hours straight, you naturally had to stop
but you can prompt for 8 hours more or less
like running versus cycling - you can cover more distance by cycling and it's less intensive (I'm talking casual running/cycling, not racing
agents are a bicycle for the mind
The point was they trained to be a runner, not a cyclist.
Not sound harsh but that the people who solved problems with code just because they love coding disappears from problem-solving environments does sounds like a win-win for everyone involved. I've both been in situations where I loved coding the solution more than I want the problem solved, and I got in the way of people who just wanted the solution, and vice-versa where architect-astronauts are more interested in coding that solving things so they get in the way. If these could be better separated, that feels like the right direction.
This isn't the worst article, and it's triggered a decent amount of discussion (despite being very short). However, I really dislike "What you're doing wrong/failing to do" titles. They are intended to trigger anxiety, which is manipulative and (in this case) precisely contradicts the concern the author is purporting to have for the rest of us.
On the subject: some people find meditation very helpful, others find it a net negative, or useless, or impossible to do. So a categorical "you should do this" isn't correct or particularly helpful. Try it, if it works for you, great; but don't put it about that people who aren't doing it are being negligent in some way.
> On the subject: some people find meditation very helpful, others find it a net negative, or useless, or impossible to do. So a categorical "you should do this" isn't correct or particularly helpful. Try it, if it works for you, great; but don't put it about that people who aren't doing it are being negligent in some way
Absolutely. I've tried mediation in many situations and some classes but it's just not for me. My ADHD brain doesn't work that way. It's painfully boring and not relaxing at all. What does work for me is a walk through nature after a stressful day. There's another thing that works even better but too fringey and a bit nsfw to go into detail :) But anyway mediation definitely does not.
You need to find what works for you.
Relaxation isn't really a goal of meditation. When you do it you cultivate a kind of meta-cognition, an awareness of - and control over - the kind of invasive thinking that usually dominates our awareness.
As a fellow ADHD person I didn't get out the first few times I tried, but now find it quite helpful.
This. It's like you end up growing your own PAUSE button for the rest of your day and you can break your own fourth wall.
Meditation - «getting used to»
A most elementary form of meditation, is getting used to placing your attention on a sensation and keeping it anchored there - even when other sensations or thoughts arise.
Following the breath- place your awareness, your attention, on the sensation of air passing through your nostrils. Count one inbreath and outbreath cycle as «1», and count until 10 or 21. Decide before you start, how many repetitions of 10 or 21 you will do.
If at any point your attention has drifted to a different sensation - seeing, hearing etc, or thinking, visual imagery etc, then congratulate yourself for noticing, and restart from «1».
I recommend «The attention revolution» by Alan B. Wallace
Thank you. I like the comparison of "meditation" with "sport": it is not all the same, even if there are commonalities between some disciplines.
It is rare to see laypeople discuss some of the different types and which one may be best suited for a particular goal.
If the goal is simply relieving stress, performing some sport outdoors —especially team sports— is probably more effective than any meditation, for most people.
So attention is all we need?
So you can place your attention on a single session of Claude Code, count to 21, and switch to another? :)
Why 21?
Because is half of 42
thanks
>> I’m clearly much more productive now. I’m doing five things at once very effectively, switching between multiple agent sessions from morning to night.
Joel Spolsky disagrees here: https://www.joelonsoftware.com/2001/02/12/human-task-switche...
I feel like it depends on the task, and that's why people seem to disagree on this. Think about a manager managing 5 devs. If he is working on planning and managing work for his dev team, we don't say he is task switching, he's just taking a management role where he takes a high level view of the task at hand and then delegates the deep dive. Where it differs for devs is that we could in theory run multiple agents concurrently, but frequently, currently, we have to dive in and give the agents significant steers and this pulls us in to the detail. The same will happen for managers. The variables are the complexity of the task, the capability of the agent and the number of tasks. There are lots of scenarios where devs can run multiple tasks without too much mental overload, but I think what is hard is that we don't know when an agent will underperform on a task and we will get pulled back into developer mode. Maybe it's a case of running for as long as you can in manager mode and then accept that when one agent needs help, you have to single task with that agent (I think this is what makes us feel like we are the bottleneck, and that's where the feeling of stress creeps in). I thought about this a lot while working on https://www.agentkanban.io which I use to help me partition agent chats by task, run separate worktrees etc
Uh, I am an EM, and you have to treat context switching as the enemy or nothing gets done.
The programs we call agents are nothing like people.
That was 2001 today Joel seems to think this is the future: https://hash.ai/
Does Joel still disagree today?
Worth noting that this article is 25 years old. The world was very very different back then, especially when it comes to software engineering.
Context switching is a problem when the cost of switching contexts is non-negligible -- but in the age of agentic development is that still really true? Surely yes for some problems, but for many others I would argue it no longer is.
A personal anecdote for you:
At my company we have a local development CLI our devX team built, it allows for agents to interact with standing up, tearing down and managing local stacks for our software suite. When I receive customer feedback about a broken button, or a poor UX experience, I simply start up a prompt:
/metal user X reported an issue on the trial balance page, they encountered a blank page when using the inception to date filter. We need to investigate the root cause, spin up a new stack, and resolve the bug.
Then off to the next task, maybe some few hours later I'll check back in on the session and I'll see:
> PR created: https://github.com/company/repo/pull/12758295 > QA URL: http://localhost:8400/<url> > Summary of root cause and fix: lorem ipsum lorem ipsum
After a quick QA session I validate the fix, confirm that our claude reviewer has approved the PR and merge the PR to deploy. The mental burden of switching to this task is quite low, orders of magnitude lower than it would be 25 years ago.
I rate Joel immensely, however, that post is 25 years old.
Also neuroscience disagrees.
This isn’t a debate. OP is wrong.
I think the more stressful part is the management expectation that things will speed up more, especially when you can generate plausible looking frontends relatively quickly. And if you have out of touch control-freak management without any technical experience, you waste more life time arguing with them.
Of course you also might exhaust yourself to some degree, as your own expectation might be that you can develop multiple things in parallel, while also having to review a lot of code where you might not have context, so in a way you have to hold more high level context in your brain state, what might be somewhat stressful. However, when you have been tech lead once, all of that is somewhat familiar.
I've been doing this for 25 years professionally and let's just say I'm more the 3 coffees, 1 redbull, headphones and bassdrive kind of programmer.
So no, I will not be "meditating". My meditative states tend to be beard stroking and occasional F bomb.
For anyone interested in Vipasanna mediation in the tradition of Mahasi Sayadaw: https://sirimangalo.org/text/how-to-meditate/
As someone brought up in a Hindu household (with Brahmin orthodoxy at that and all the casteism that came with it) and having learnt to shun all of that culture, and the religious indoctrination, here's the essence of mindfulness meditation that I was taught that I still practice and find useful.
1. Sit somewhere comfortable. Sitting "cross legged" or with your "back straight" as the guide linked to above advocates is not necessary. A comfortable chair/couch is fine.
2. The room should preferably be quiet. Though if you have the privilege of access to an outdoor courtyard that's quiet other than birdsong and chirp of insects, you'll probably enjoy it more. But a quiet room is good enough.
3. Phase 1: Set a timer on your watch/phone for 5 mins. Close your eyes. And let your mind wander. Doesn't matter what your mind drifts towards.
4. Phase 2: Restart the 5 min timer. Now, try quieten your mind of thoughts and focus instead on just your breathing. Be gentle with yourself. Your mind will wander again and that's fine. Just gently nudge it back to your breathing.
That's pretty much it. Slowly, over months try and increase Phase 2 from 5 to 10 mins.
When I described this to my partner, I used the analogy of treating your mind like a curious eager pup. In the first phase, cutting of external stimulus of sight by closing your eyes is like having the pup with you in a closed room.
In phase 2, you gently hold the puppy near you and get it to quiet down and stay still.
She mentioned that this analogy helped her a lot.
Honestly, this is pretty much the gist of it. I suspect that you will likely get most of the benefits of advanced meditative techniques with just the 2 simple steps from above. YMMV.
Be patient though. Getting to a fully calm state of mind takes months of practice.
The Mahasi method is quite different. You don't try to calm or control your mind. You observe and note your experiences as they're happening. Over time the calmness comes (and goes) but its not the goal. The goal is to see reality clearly. This clear seeing (which is where the word Vipassana comes from) leads to a change in the habit patterns that cause our stress and suffering.
You're right. This is a different technique. This is my simplification of the TM technique along with "japa" (repetition of a phrase) as is typically taught in the Brahmin scripture school mileu.
Since the OP was about achieving flow state and focus, I thought this was relevant.
There is also a simpler approach: just stop using AI.
And if you can't, THAT should be a big red warning sign for you.
that's like "stop using a car, you can walk between cities and its healthier"
So far I see it more like "you buy a car to take you between cities, but you end up routinely driving even just 1 km to a store, +50 kg overweight and prematurely dead due to a heart attack."
But sure, if the most important thing is to mass produce tons of shitty code, it's your life - just don't give people dumb advice on what they NEED to do. :)
(putting aside the negative impact of the data centers on the planet, which is not "your life" anymore)
I try not to context switch when doing agentic programming. Instead, I use a single agent thread (in pi) and pay extra for faster inference (GLM 5.2 from fireworks.ai, currently; around 100 tokens per second). I rarely spend more than $25 per working week, which is a fraction of a percent of my own fee (I’m a specialist consultant). I also keep an Anthropic subscription and use that for longer research and design tasks.
I’m sure many people produce more than me, but I retain my sanity as well as a high level of understanding of the code that I produce, which in my domain I feel is still important. I’ve tried ultracode-style subagent workflows and find that they rapidly produce reams of slop that I don’t have the patience or energy to properly review.
I also meditate quite a bit.
I’ve started doing mornings without any llm assisted work, and keeping it only for after 11. I find it gives me back the joy of designing my systems in a highly focused state, while keeping the later part of the day for persisting those well thought out ideas into code.
I noticed how relaxing and meditative programming can be. It might sound that after day job basically solving other people pronlems I sit down late at noght to just write code for hours on end. But I really enjoy it. Using LLM’s to generate the code ruins it.
I have also done meditation, but I struggle to keep it up for long. I think you should really do it consistently to get majority of effects. Coding, exercising, drawing has always been an easier form of meditation for me.
My favorite metaphor for programming is playing chess. Your opponent in programming is the complexity, you don't see its moves before the coding and design progress, before you make your choices/moves. You solve a problem by writing some code but that causes new problems down the line you didn't know existed before you made your choice of writing some specific code. or choosing a specific design.
Chess-players too are in a very "meditative" state when they play, and they enjoy it, I assume because it let's them focus on the game and forget about everything else.
On the contrary, many still need to learn how to say no.
well, gurus are supposed to meditate, once in a while.
per https://en.wikipedia.org/wiki/Guru_Meditation
I don’t think this article is suggesting really going for it in terms of meditation. But, as a warning to people, there is evidence that meditation can be dangerous for some people.
You say programming used to be a meditative activity.
Then why get overwhelmed by LLMs and meditate to calm down, when you can just write the code yourself at a healthier pace? Tools are supposed to be designed around humans, it’s not the human that has to adapt to the machine.
In any case, meditating with an end to destress or to reach higher levels of productivity is missing the point of meditation.
> Tools are supposed to be designed around humans
This is a common thing to say, but when during the development of human civilization has this actually been the case? Is agriculture designed around humans more than hunting/gathering? Is industrialized work more designed around humans than agrarian society?
I don't mean to sound pessimistic or technocratic; quite the contrary. But I think we shouldn't project our desire for equanimity onto romantized versions of civilization.
It's fine for your pet projects. But for most of professional programming it's no longer feasible as you'll be at a small fraction of your machine assisted performance.
If you think performance relates to speed and amount of code per unit of time yes. If you're more grounded with the reality of software engineering then no
I have in fact masters in SE and three decades experience of commercial programming. Loved every minute of it (well except the burnout episode) and still do my hobby projects. So I would say no, you are wrong. The models decimate not just the coding (the best and the most fun part of development) but all the pseudo-engineering roles like architects or product managers too. Simply because there's less need for communication in the team as the surface of work for each dev is now quite enormous.
My performance in writing code was never once the problem. I don’t get why I should increase the amount of output by depending on a third party tool to do my thinking to whom I have to explain my very abstract thought process in words.
The point of being an experienced programmer is thinking in data structures and transformations, not in prose. Why would I introduce all that friction?
I was so stressed at work a few years ago. Burnt out. Exhausted. I started meditating. Shared with my manager that I started, and it’s been helping me process all the chaos at work.
He told me that wasn’t normal, and I shouldn’t have to meditate just to function at work :’)
What a strange opinion. If it helps you do better at work, why wouldn't it be something to encourage?
Was he a judgmental person in general? Or do you think he had an aversion to meditating?
I do have to say, if you were encouraging him to ALSO start meditating, I'd hate that too.
He was a smartass, but also very blunt - unsparingly.
I did not encourage him to, this was just during a weekly 1:1 where I was sharing with him how I’ve been coping with the amount of workload and chaos happening among the team/myself.
He was wanting to empathize me that it’s not normal to have to do that to be functional at work, acknowledging how rough things were at the time.
I kept doing it, but fell out of practice. Also left and no longer work there, due to stress and poor support. Shocker.
> I’m clearly much more productive now. I’m doing five things at once very effectively, switching between multiple agent sessions from morning to night. After working full-time like this for ~8 months, one thing I’m sure of is that this way of working involves much less time spent in a flow state.
What an utter piece of BS. AI goons really like to smell their own crap
I was discussing Buddhism with a few Buddhist friends this past weekend, and I randomly had an enlightenment. It was a very odd experience, I felt like I understood all the weird things I'd heard from them, and I suddenly became very calm and accepting of everything. I also had a sense of sort of "watching" what I was experiencing through my own eyes.
I'm generally hyper rationalist, so this was a very interesting experience, and it happened because a random thing one of my friends said about meditation made something "click" in me.
It lasted about a day, I can't say I have any lasting effects from it now. It'd be interesting to see if I can make it happen again, but when I was in that state, I thought that trying to make it happen would defeat the purpose.
What was the thing that made you click?
I asked my friend "is the purpose of meditation just to feel existence?" and he said "yes, and also taking your fears, insecurities, etc and throwing them away", and something just clicked.
Personally, I feel that as an individual, it's the right time to complete a program, but as a team, it's become harder.
It's true that the proportion of founders has increased both in the US and in my country, Korea.
And unlike the old days, it feels like what's needed now isn't so much deep, concentrated programming knowledge in one area, but rather broad knowledge across many fields. The claim that "productivity has increased" really only applies to freelancers. In fact, there's been a noticeable increase in freelance outsourcing requests that would be hard to handle without AI, lots of short deadline gigs compared to before. And of course, that makes it harder to charge appropriately.
For teams, on the other hand, you still need things like code reviews and team decision making.
As an individual, I've practically become someone who just writes up a gate, lets AI handle the code, checks that the core domain doesn't break, watches the gate's rules, and pulls the lever.
The reason team work slows down is mainly because Agile methodologies and code review processes are still human centric and consensus driven, and human cognitive speed itself becomes the bottleneck.
So I can understand a lot of the arguments that come up in the comments. The important thing is that most people tend to only see their own situation and their own context, which makes it hard for them to understand others.
“I’m doing five things at once very effectively”
…sure you are buddy, sure you are…
Note to self: book appointment with Optometrist ASAP to correct how far my eyes have rolled back into my head.
hehe
Bros "discuss on hacker news" link takes you to submit the article here. that really rustles my jimmies. its unfortunate that bro couldnt csrf the submit link thanks to submit tokens. I have no doubt he would have tried that too.