FR version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
60% Positive
Analyzed from 2773 words in the discussion.
Trending Topics
#code#more#writing#team#lines#bottleneck#software#long#week#isn
Discussion (32 Comments)Read Original on HackerNews
I only work on it for a few hours during the week. And it’s progressing at a reasonable pace that I’m happy with. I got cross-compilation from Linux to Windows going early on in a couple of hours. Wasn’t that hard.
I’ve had to rework parts of the code as I’ve progressed. I’ve had to live with decisions I made early on. It’s code. It’s fine.
I don’t really understand the, “more, better, faster,” cachet to be honest. Writing the code hasn’t been the bottle neck to developing software for a long time. It’s usually the thinking that takes most of the time and if that goes away well… I dunno, that’s weird. I will understand it even less.
Agree with writing less code though. The economics of throwing out 37k lines of code a week is… stupid in the extreme. If we get paid by the line we could’ve optimized for this long before LLM’s were invented. It’s not like more lines of code means more inventory to sell. It’s usually the opposite: the more bugs to fix, the more frustrated customers, the higher churn of exhausted developers.
This is what I've always found confusing as well about this push for AI. The act of typing isn't the hard part - its understanding what's going on, and why you're doing it. Using AI to generate code is only faster if you try and skip that step - which leads to an inevitable disaster
It’s more than just typing though. A simple example remembering the exact incantation of CSS classes to style something that you can easily describe in plain English.
Yes, you could look them up or maybe even memorize them. But there’s no way you can make wholesale changes to a layout faster than a machine.
It lowers the cost for experimentation. A whole series of “what if this was…” can be answered with an implementation in minutes. Not a whole afternoon on one idea that you feel a sunk cost to keep.
You lost me here. I can make changes very quickly once I understand both the problem and the solution I want to go with. Modifying text is quite easy. I spend very little time doing it as a developer.
Nobody writing production CSS for a serious web page can avoid rewriting it. Nobody is memorizing anything. It's deeply intertwined with the requirements as they change. You will eventually be forced to review every line of it carefully as each new test is added or when the HTML is changed. No AI is doing that level of testing or has the training data to provide those answers.
It sounds like you're better off not using a web page at all if this bothers you. This isn't a deficiency of CSS. It's the main feature. It's designed to provide tools that can cover all cases.
If you only have one rendering case, you want an image. If you want to skip the code, you can just not write code. Create a mockup of images and hand it off to your web devs.
Does your coding not involve thinking? And if not, why are you not delighted to have AI take that over? Writing unthinking boilerplate is tedious garbage work.
Today I wanted to address a bug I found on a product I work on. At the intersection of platform migration and backwards compatibility I found some customers getting neither. I used an LLM to research the code paths and ensure that my understanding of the break was correct and what the potential side effects of my proposed fix would be. AI saved me stepping through code for hours to understand the side effects. I asked it for a nice description of the flow and it gave it to me, including the pieces I didn’t really know because I’d never even touched that code before. I could have done this. Would it have been a better use of my time than moving on to the next thing? Probably not. Stepping through function calls in an IDE is not my idea of good “thinking” work. Tracing through glue to understand how a magical property gets injected is a great job for a machine.
Then we're doing different things.
I didn't like GitHub so I wrote my own. 60k lines of code later... yes writing code was the bottleneck which has been eliminated. The bottleneck is now design, review, and quality assessments that can't be done trivially.
This isn't even the project I wanted to be doing, the tools that were available were holding me back so I wrote my own. It also consumes a few hours a week.
If you think writing code isn't the bottleneck then you aren't thinking big enough. If you don't WANT to think big enough, that's fine, I also do things for the joy of doing them.
I see this on HN just so much and I am not sure what this is, almost seems like a political slogan that followers keep repeating.
I had to do some rough math in my head but in the last 5 years I have been involved with hiring roughly 40 SWEs. Every single one of them was hired because writing the code was THE bottleneck (the only one) and we needed more people to write the code
I’ve seen it time and again: startups move from their market-fit phase into an operational excellence phase on the backing of VC funding and they start hiring a ton of people. Most of those developers are highly educated, specialized people with deep technical skills and they’re often put to work making the boxes more blue or sitting in meetings with PMs for hours. Teams slow down output when you add more people.
You don’t have a quota. It’s not like you’ll have fewer units to sell if you don’t add that 30k lines of code by Friday.
This is knowledge work. The work is understanding problems and knowing how to develop solutions to them. You add more people and you end up adding overhead. Communication, co-ordination, operations overhead.
The real bottle necks are people and releasing systems into production. Every line of code change is a liability. There’s risk tolerance to manage in order to achieve five-nines.
A well-sized team that has worked together a long time can outperform a massive team any day in my experience.
Haha, this is exactly my experience.
I'll never forget the best candidate I ever interviewed - my feedback was to absolutely hire him and put him on the most interesting and challenging problems. They put him in a marketing team tweaking upsell popups. He left after 2 months.
I've been doing this for 30-years and this is another political slogan of sorts. this is true in every single imaginable job - new people slow you down, until they do not and become part of the well-oiled machine that is hopefully your team. not sure why people insist on saying this, it is like saying "read this book, says that that Sun will rise tomorrow morning"
> I’ve seen it time and again: startups move from their market-fit phase into an operational excellence phase on the backing of VC funding and they start hiring a ton of people. Most of those developers are highly educated, specialized people with deep technical skills and they’re often put to work making the boxes more blue or sitting in meetings with PMs for hours. Teams slow down output when you add more people.
I wasn't talking about startups or developers making boxes more blue, I was talking about personal experience. The bottleneck, if you are doing amazing shit and not burning some billionaries money on some silly "startup" is always the code which is why we hire developers to write the code. Everything else is just coming up with some silly unrelated examples - of course there are people (at every job again) doing nothing or menial tasks - this isn't what I was talking about.
> You don’t have a quota. It’s not like you’ll have fewer units to sell if you don’t add that 30k lines of code by Friday.
I do have customers that want features that would make their lives easier and are willing to handsomely pay for it, that good enough?
> This is knowledge work. The work is understanding problems and knowing how to develop solutions to them. You add more people and you end up adding overhead. Communication, co-ordination, operations overhead.
This is only on super shitty teams with super shitty co-workers (especially senior ones) and super shitty managers. I feel for the careers in this industry where this is/was the case. A whole lot of people are terrible at their jobs in places like this - a whole lot of people...
> A well-sized team that has worked together a long time can outperform a massive team any day in my experience.
a well-sized team was at one point (well-sized team - 1) and (well-sized team - 2) and (well-sized team - 3) and in the future if it is right team will be even more amazing as well (well-sized team + 1), (well-sized team + 2)
The difference, I think is:
- Code factories where everything is moving fast - there's no time to think about how to simplify a problem, just gotta get it done. These companies tended to hire their way out of slowness, which led to more code, more complexity, and more code needed to deal with and resolve edge cases introduced by the complexity. I can count many times I was handed directives to implement something that I knew was far more complex than it had to be, but because of the pressure to move forward it was virtually impossible to push back. Maybe it's the only way they can make the business case work, but IMO it undoubtedly led to far, far more code than would've been necessary if it were possible to consider problems more carefully and if engineers had more autonomy. In these companies also a lot of time was consumed by meetings trying to "sync up" with the 100 other people moving in one direction.
- Smaller shops, open source projects, or indie development where there isn't a rush to get something out the door. Here, it's possible to think through a problem and come up with a solution that reduces code surface area. This was about solving the largest number of problems with the least amount of complexity. Most of my time at this company was spent thinking through how to solve the problem and considering edge cases and exploratory coding, the actual implementation was really quick to write. It really helped that I had a boss who understood and encouraged this, and we were working on safety critical systems. My boss liked to say "you can't birth a baby in less than 9 months just by adding another woman".
I think most of the difference is in team size. A larger team inherently results in more code to do less, because of the n*(n-1)/2 communication overhead [1].
Recently I learned the Navy SEALs saying "Slow is smooth, smooth is fast" which I feel sums up my experience well.
[1] https://en.wikipedia.org/wiki/The_Mythical_Man-Month
The third environment is a large business maintaining services long term. These services do not change in fundamental ways for well over a decade and they make a shit ton of money, yet the requirements never stop changing in subtle ways for the clients. Bugs pop up constantly, but there's more than enough time to fix them the right way as outlined by their contract where expectations have been corrected over the years. There's no choice to do it any other way. The requirements and deadlines are firm. Reliability is the priority.
These are the stable businesses of the broader working world and they're probably what will remain after AI has driven the tech industry into the ground.
On the extreme end to prove the point, the suits intentionally abstract out reality into neat forecasts and spreadsheet cells.
It's hard for me to think of something concrete that will convince you. Does code map directly to business outcomes in your experience? Because it's overwhelmingly not even remotely true in my experience.
even just "all lines of code are not created equal" tells me there's no direct correlation with business value.
so I’ll do what I was thought in first grade to never do and answer a question with a question - how much time per week does a brick layer spend laying bricks? they are looking at these new “robots” laying bricks automatically and talking on BrickLayerNews “man, the brick laying has not been a bottleneck for a long time.”
But to answer your question directly, a lot of time if other people do their job well. Last week I had about 7 hours of meetings, the rest of the time I was coding (so say 35 hours) minus breaks I had to take to stretch and rest my eyes
There is some truth to it, like Brooks' Law (https://en.wikipedia.org/wiki/Brooks's_law) about how adding people to an already late project will just make it later. There are many factors in how long a software engineering task takes beyond pure typing speed, which suggests there are factors beyond code produced per day as well. But some typing has to be done, and some code has to be produced, and those can absolutely be bottlenecks.
Another way of looking at it that I like is Hickey's hierarchy of the problems of programming and their relative costs, from slide 22: https://github.com/matthiasn/talk-transcripts/blob/master/Hi... If you have inherent domain complexity, or a misconception on how to apply programming to a domain, those are 10x worse costs than any day-to-day practice of programming concerns ("the code"), and there's a 10x further reduction for trivialisms like typos.
I think some of it must be cope since so many are in organizations where the more they get promoted the less they program, trending towards (and sometimes reaching) 0. In such an organization sure, code isn't the bottleneck per se, it's a symptom of an underlying cause. The bottleneck would be the bad incentives that get people to schedule incessant unnecessary meetings with as many people as they can to show leadership of stakeholders for promotion doc material, and other questionable things shoved on the best engineers that take them away from engineering. Remove those, and suddenly productivity can go way up, and code produced will go up as well.
I've also always been amused by estimates of what constitutes "good" productivity if you try to quantify it in lines of code. There's a paper from 1994 by Jim Coplien, "Borland Software Craftsmanship: A New Look at Process, Quality, and Productivity". It's summarized in the free book by Richard Gabriel, "Patterns of Software". (https://www.dreamsongs.com/Files/PatternsOfSoftware.pdf pg 135) They were making new spreadsheet software for Windows, and had a group of "very high caliber" professionals, with a core group of 4 people (2 with important prior domain expertise) and then 4 more team members added after a year. "The QPW group, consisting of about eight people, took 31 months to produce a commercial product containing 1 million lines of code. This elapsed time includes the prototypes, but the line count does not. That is, each member of this group produced 1,000 lines of final code per week."
Later on, Coplien was asked "what he thought was a good average for US software productivity", and the answer was "1000 to 2000 non-commentary source lines per programmer per year". Also: "this number was constant for a large in-house program over its 15-year lifetime -- so that original development and maintenance moved at the same pace: slowly". An average of 1k lines a year is 19 lines a week, or about 4 lines a day for a work-week. This was considered acceptable for an average, whereas for an exceptional team you could get 200 a day. Might not there be ways to boost the average from 4 to something like 12 or 20? If your organization is at 4, there is clearly a bottleneck. (For extra context, the QPW group was in C++, and Gabriel notes he had personal experience with several groups demonstrating similar productivity levels. "I watched Lisp programmers produce 1000 lines of Lisp/CLOS code per month per person, which is roughly equivalent to 350 to 1000 lines of C++ code per week." Of course language matters in lines of code comparisons.)
https://avilpage.com/2026/03/config-first-tools.html
There are still consequences, however. Even with an agent, development slows, cost increases, bugs emerge at a higher rate, etc. It's still beneficial to focus on code quality instead of raw output. I don't think this is limited writing it yourself, mind - but you need to actually have an understanding of what's being generated so you can critique and improve it.
Personally, I've found the accessibility aspect to be the most beneficial. I'm not always writing more code, but I can do much more of it on my phone, just prompting the agent, which has been so freeing. I don't feel this is talked about enough!