The post touches very briefly on linting in 7. For me, setting up a large number of static code analysis checks has had the highest impact on code quality.
My hierarchy of static analysis looks like this (hierarchy below is Typescript focused but in principle translatable to other languages):
9. Custom script to ensure shared/util directories are not over stuffed (built this using dependency-cruiser as a library rather than an exec)
10. Security check (semgrep)
I stitch all the above in a single `pnpm check` command and defined an agent rule to run this before marking task as complete.
Finally, I make sure `pnpm check` is run as part of a pre-commit hook to make sure that the agent has indeed addressed all the issues.
This makes a dramatic improvement in code quality to the point where I'm able to jump in and manually modify the code easily when the LLM slot machine gets stuck every now and then.
(Edit: added mention of pre-commit hook which I missed mention of in initial comment)
I use a pre-commit hook to run `pnpm check`. I missed mentioning it in the original comment. Your reply reminded me of it and I have now added it. Thanks.
I wonder at the end of this if it's the still worth the risk?
A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations.
Maybe it's the kind of work I'm doing, or maybe I just suck, but the code to me is a forcing mechanism into ironing out the details, and I don't get that when I'm writing a specification.
I second this. This* is the matter against which we form understanding. This here is the work at hand, our own notes, discussions we have with people, the silent walk where our brain kinda process errors and ideas .. it's always been like this since i was a kid, playing with construction toys. I never ever wanted somebody to play while I wait to evaluate if it fits my desires. Desires that often come from playing.
Outsourcing this to an LLM is similar to an airplane stall .. I just dip mentally. The stress goes away too, since I assume the LLM will get rid of the "problem" but I have no more incentives to think, create, solve anything.
Still blows my mind how different people approach some fields. I see people at work who are drooling about being able to have code made for them .. but I'm not in that group.
I'll push it back against this a little bit. I find any type of deliberative thinking to be a forcing function. I've recently been experimenting with writing very detailed specifications and prompts for an LLM to process. I find that as I go through the details, thoughts will occur to me. Things I hadn't thought about in the design will come to me. This is very much the same phenomenon when I was writing the code by hand. I don't think this is a binary either or. There are many ways to have a forcing function.
I think it's analogous to writing and refining an outline for a paper. If you keep going, you eventually end up at an outline where you can concatenate what are basically sentences together to form paragraphs. This is sort of where you are now, if you spec well you'll get decent results.
I agree, I felt this a bit. The LLM can be a modeling peer in a way. But the phase where it goes to validate / implement is also key to my brain. I need to feel the details.
Everything you have said here is completely true, except for "not in that group": the cost-benefit analysis clearly favors letting these tools rip, even despite the drawbacks.
But it's also likely that these tools will produce mountains of unmaintainable code and people will get buried by the technical debt. It kind of strikes me as similar to the hubris of calling the Titanic "unsinkable." It's an untested claim with potentially disastrous consequences.
> But it's also likely that these tools will produce mountains of unmaintainable code and people will get buried by the technical debt.
It's not just likely, but it's guaranteed to happen if you're not keeping an eye on it. So much so, that it's really reinforced my existing prejudice towards typed and compiled languages to reduce some of the checking you need to do.
Using an agent with a dynamic language feels very YOLO to me. I guess you can somewhat compensate with reams of tests though. (which begs the question, is the dynamic language still saving you time?)
Static type checking is even faster than running the code. It doesn't catch everything, but if finding a type error in a fast test is good, then finding it before running any tests seems like it would be even better.
Oh I'm well aware of this. I admitted defeat in a way.. I can't compete. I'm just at loss, and unless LLM stall and break for some reason (ai bubble, enshittification..) I don't see a future for me in "software" in a few years.
Somehow I appreciate this type of attitude more than the one which reflects total denial of the current trajectory. Fervent denial and AI trash-talking being maybe the single most dominant sentiment on HN over the last year, by all means interspersed with a fair amount of amazement at our new toys.
But it is sad if good programmers should loose sight of the opportunities the future will bring (future as in the next few decades). If anything, software expertise is likely to be one of the most sought-after skills - only a slightly different kind of skill than churning out LOCs on a keyboard faster than the next person: People who can harness the LLMs, design prompts at the right abstraction level, verify the code produced, understand when someone has injected malware, etc. These skills will be extremely valuable in the short to medium term AFAICS.
But ultimately we will obviously become obsolete if nothing (really) catastrophic happens, but when that happens then likely all human labor will be obsolete too, and society will need to be organized differently than exchanging labor for money for means of sustenance.
I get crazy over the 'engineer are not paid to write loc', nobody is sad because they don't have to type anymore. My two issues are it levels the delivery game, for the average web app, anybody can now output something acceptable, and then it doesn't help me conceptualize solution better, so I revert to letting it produce stuff that is not maleable enough.
If the world comes to that it will be absolutely catastrophic, and it’s a failure of grappling with the implications that many of the executives of AI companies think you can paper over the social upheaval with some UBI. There will be no controlling what happens, and you don’t even need to believe in some malicious autonomous AI to see that.
i'm sorry if I pulled everybody down .. but it's been many months since gemini and claude became solid tools, and regularly i have this strong gut feeling. i tried reevaluating my perception of my work, goals, value .. but i keep going back to nope.
I think you have every right to doubt those telling us that they run 5 agents to generate a new SAAS-product while they are sipping latté in a bar. To work like that I believe you'll have to let go of really digging into the code, which in my experience is needed if want good quality.
Yet I think coding agents can be quite a useful help for some of the trivial, but time consuming chores.
For instance I find them quite good at writing tests. I still have to tweak the tests and make sure that they do as they say, but overall the process is faster IMO.
They are also quite good at brute-forcing some issue with a certain configuration in a dark corner of your android manifest. Just know that they WILL find a solution even if there is none, so keep them on a leash!
Today I used Claude for bringing a project I abandoned 5 years ago up to speed. It's still at work in progress, but the task seemed insurmountable (in my limited spare time) without AI, now it feels like I'm half-way there in 2-3 hours.
I think we really need to have a serious think of what is "good quality" in the age of coding agents. A lot of the effort we put into maintaining quality has to do with maintainability, readability etc. But is it relevant if the code isn't for humans? What is good for a human is not what is good for an AI necessarily (not to say there is no overlap). I think there are clearly measurable things we can agree still apply around bugs, security etc, but I think there are also going to be some things we need to just let go of.
You can’t drop anything as long as a programmer is expected to edit the source code directly. Good luck investigating a bug when the code is unclear semantically, or updating a piece correctly when you’re not really sure it’s the only instance.
I think that's the question. Is a programmer expected to ever touch the source code? Or will AI -- and AI alone -- update the code that it generated?
Not entirely unlike other code generation mechanisms, such as tools for generating HTML based on a graphical design. A human could edit that, but it may not have been the intent. The intent was that, if you want a change, go back to the GUI editor and regenerate the HTML.
So like we went from assembler to higher level programming languages, we will now move to specifications for LLMs? Interesting thought... Maybe, once the "compilers" get good enough, but for mission critical systems they are not nearly good enough yet.
Right. I work in aerospace software, and I do not know if this option would ever be on the table. It certainly isn't now.
So I think this question needs to be asked in the context of particular projects, not as an industry-wide yes or no answer. Does your particular project still need humans involved at the code level? Even just for review? If so, then you probably ought to retain human-oriented software design and coding techniques. If not, then, whatever. Doesn't matter. Aim for whatever efficiency metric you like.
It’s also pretty close to Steve Jobs initial vision of computing in the future (https://stevejobsarchive.com/stories/objects-of-our-life, 1983) but my point is that whatever it is we call AI now became reality so much faster than anyone really saw coming. Even if the pace slows down, and it didn’t yet, things are improving so massively all the time that the world can’t keep up changing to accommodate.
> I think you have every right to doubt those telling us that they run 5 agents to generate a new SAAS-product while they are sipping latté in a bar. To work like that I believe you'll have to let go of really digging into the code, which in my experience is needed if want good quality.
Also we live in a capitalist society. The boss will soon ask: "Why the fuck am I paying you to sip a latte in a bar? While am machine does your work? Use all your time to make money for me, or you're fired."
AI just means more output will be expected of you, and they'll keep pushing you to work as hard as you can.
> AI just means more output will be expected of you, and they'll keep pushing you to work as hard as you can.
That’s a bit too cynical for me. After all, yes, your boss is not paying you for sipping lattes, but for producing value for the company. If there is a tool that maximises your output, why wouldn’t he want you to use that to great efficiency?
Put differently, would a carpenter shop accept employees rejecting the power saw in favour of a hand saw to retain their artisanal capability?
I still do this, but when I'm reviewing what's been written and / or testing what's been built.
How I see it is we've reverted back to a heavier spec type approach, however the turn around time is so fast with agents that it still can feel very iterative simply because the cost of bailing on an approach is so minimal. I treat the spec (and tests when applicable) as the real work now. I front load as much as I can into the spec, but I also iterate constantly. I often completely bail on a feature or the overall approach to a feature as I discover (with the agent) that I'm just not happy with the gotchas that come to light.
AI agents to me are a tool. An accelerator. I think there are people who've figured out a more vibey approach that works for them, but for now at least, my approach is to review and think about everything we're producing, which forms my thoughts as we go.
> A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations.
If you need that, don't use AI for it. What is it that you don't enjoy coding or think it's tangential to your thinking process? Maybe while you focus on the code have an agent build a testing pipeline, or deal with other parts of the system that is not very ergonomic or need some cleanup.
That's because many developers are used to working like this.
With AI, the correct approach is to think more like a software architect.
Learning to plan things out in your head upfront without to figure things out while coding requires a mindset shift, but is important to work effectively with the new tools.
To some this comes naturally, for others it is very hard.
I think what GP is referring too are technical semantics and accidental complexity. You can’t plan for those.
The same kind of planning you’re describing can and do happen sans LLM, usually on the sofa, or in front of a whiteboard. Or by reading some research materials. No good programmer rushes to coding without a clear objective.
But the map is not the territory. A lot of questions surface during coding. LLMs will guess and the result may be correct according to the plan, but technically poor, unreliable, or downright insecure.
I also second this. I find that I write better by hand, although I work on niche applications it’s not really standard crud or react apps. I use LLMs in the same way i used to used stack overflow, if I go much farther to automate my work than that I spend more time on cleanup compared to if I just write code myself.
Sometimes the AI does weird stuff too. I wrote a texture projection for a nonstandard geometric primitive, the projection used some math that was valid only for local regions… long story. Claude kept on wanting to rewrite the function to what it thought was correct (it was not) even when I directed to non related tasks. Super annoying. I ended up wrapping the function in comments telling it to f#=% off before it would leave it alone.
Using AI or writing your own code isn't an xor thing. You can still write the code but have a coding assistant or something an alt/cmd-tab away. I enjoy writing code, it relaxes me so that's what I do but when I need to look something up or i'm not clear on the syntax for some particular operation instead of tabbing to a browser and google.com I tab to the agent and ask it to take a look. For me, this is especially helpful for CSS and UI because I really suck at and dislike that part of development.
I also use these things to just plan out an approach. You can use plan mode for yourself to get an idea of the steps required and then ask the agent to write it to a file. Pull up the file and then go do it yourself.
I sometimes wonder if the economics of AI coding agents only work if you totally ignore all the positive externalities that come with writing code.
Is the entire AI bubble just the result of taking performance metrics like "lines of code written per day" to their logical extreme?
Software quality and productivity have always been notoriously difficult to measure. That problem never really got solved in a way that allowed non technical management to make really good decisions from the spreadsheet level of abstraction... but those are the same people driving adoption of all these AI tools.
Engineers sometimes do their jobs in spite of poor incentives, but we are eliminating that as an economic inefficiency.
In 1987 when I first started coding, I would either write my first attempt in BASIC and see it was too slow and rewrite parts in assembly or I would know that I had to write what I wanted from the get go in assembly because the functionality wasn’t exposed at all in BASIC (using the second 64K of memory or using double hires graphics).
This past week, I spent a couple of days modifying a web solution written by someone else + converting it from a Terraform based deployment to CloudFormation using Codex - without looking at the code as someone who hasn’t done front in development in a decade - I verified the functionality.
More relevantly but related, I spent a couple of hours thinking through an architecture - cloud + an Amazon managed service + infrastructure as code + actual coding, diagramming it, labeling it , and thinking about the breakdown and phases to get it done. I put all of the requirements - that I would have done anyway - into a markdown file and told Claude and Codex to mark off items as I tested each item and summarize what it did.
Looking at the amount of work, between modifying the web front end and the new work, it would have taken two weeks with another developer helping me before AI based coding. It took me three or four days by myself.
The real kicker though is while it worked as expected for a couple of hundred documents, it fell completely to its knees when I threw 20x documents into the system. Before LLMs, this would have made me look completely incompetent telling the customer I now wasted two weeks worth of time and 2 other resources.
Now, I just went back to the literal drawing board, rearchitected it, did all of the things with code that the managed services abstracted away with a few tweaks, created a new mark down file and was done in a day. That rework would have taken me a week by itself. I knew the theory behind what the managed service was doing. But in practice I had never done it.
It’s been over a decade where I was responsable for a delivery that I could do by myself without delegating to other people or that was simple enough that I wouldn’t start with a design document for my own benefit. Now within the past year, I can take on larger projects by myself without the coordination/“mythical man Month” overhead.
I can also in a moment of exasperation say to Codex “what you did was an over complicated stupid mess, rethink your implementation from first principles” without getting reported to HR.
There is also a lot of nice to have gold plating that I will do now knowing that it will be a lot faster
I was just thinking this the other day after I did a coding screen and didn't do well. I know the script for the interviewee is your not suppsed to write any code until you talk through the whole thing, but I think i woukd have done better if I could have just wrote a bunch of throw away code to iterate on.
Are there still people under the impression that the correct way to use Stack Overflow all these years was to copy & paste without analyzing what the code did and making it fit for purpose?
If I have to say, we're just waiting for the AI concern caucus to get tired of performing for each other and justifying each other's inaction in other facets of their lives.
The real value that AI provides is the speed at which it works, and its almost human-like ability to “get it” and reasonably handle ambiguity. Almost like tasking a fellow engineer. That’s the value.
By the time you do everything outlined here you’ve basically recreated waterfall and lost all speed advantage. Might as well write the code yourself and just use AI as first-pass peer review on the code you’ve written.
A lot of the things the writer points out also feel like safeguards against the pitfalls of older models.
I do agree with their 12th point. The smaller your task the easier to verify that the model hasn’t lost the plot. It’s better to go fast with smaller updates that can be validated, and the combination of those small updates gives you your final result. That is still agile without going full “specifications document” waterfall.
It’s a solid post overall and even for people with a lot of experience there’s some good ideas in here. “Identify and mark functions that have a high security risk, such as authentication, authorization” is one such good idea - I take more time when the code is in these areas but an explicit marking system is a great suggestion. In addition to immediate review benefits, it means that future updates will have that context.
“Break things down” is something most of us do instinctively now but it’s something I see less experienced people fail at all the time.
I can't help but keep finding it ridiculous how everyone now discovers basic best practices (linting, documentation, small incremental changes) that have been known for ages. It's not needed because of AI, you should have been doing it like this before as well.
Anyone who’s been a developer for more than 10 minutes knows that best practices are hard to always follow through on when there’s pressure to ship.
But there’s more time to do some of these other things if the actual coding time is trending toward zero.
And the importance of it can go up with AI systems because they do actually use the documentation you write as part of their context! Direct visible value can lead people to finally take more seriously things that previously felt like luxuries they didn’t have time for.
Again if you’ve been a developer for more than 10 minutes, you’ve had the discouraging experience of pain-stakingly writing very good documentation only for it to be ignored by the next guy. This isn’t how LLMs work. They read your docs.
Remember having to write detailed specs before coding? Then folks realized it was faster and easier to skip the specs and write the code? So now are we back to where we were?
One of the problems with writing detailed specs is it means you understand the problem, but often the problem is not understand - but you learn to understand it through coding and testing.
We’re not „thinking with portals” about these things enough yet. Typically we’d want a detailed spec beforehand, as coding is expensive and time consuming, thus we want to make sure we’re coding the right thing. With AI though, coding is cheap. So let AI skip the spec and write the code badly. Then have it review the solution, build understanding, design a spec for better solution and have it write it again. Rinse and repeat as many times you need.
It’s also nothing new, as it’s basically Joe Armstrong's programming method. It’s just not prohibitively expensive for the first time in history.
The first rule is an antipattern. I think describing your architecture or ANY kind of documentation for your AI is an anti-pattern and blows the context window leading to worse results, and actual more deviation.
The controlling systems are not give it more words at the start. Agentic coding needs to work in loop with dedicated context.
You need to think about how can i give as much intent as possible with as little words.
You can built a tremendous amount of custom lint rules ai never needs to read except they miss it.
Every pattern in your repo gets repeated, repo will always win over documentation and when your repo is good structured you don’t need to repeat this to AI
It’s like dev always has been, watch what has gone wrong and make sure the whole type or error can’t happen again.
1. Keep things small and review everything AI written, or
2. Keep things bloated and let AI do whatever it wants within the designated interface.
Initially I drew this line for API service / UI components, but it later expanded to other domains. e.g. For my hobby rust project I try to keep "trait"s to be single responsible, never overlap, easy to understand etc etc. but I never look at AI generated "impl"s as long as it passes some sensible tests and conforming the traits.
I find rust generally easier to reason about, but can't stand writing it.
The compiler works well with LLMs plenty of good tooling and LSPs.
If I'm happy with the shape of the code and I usually write the function signatures/ Module APIs. And the compiler is happy with it compiling. Usually the errors if any are logical ones I should catch in reviews.
So I focus on function, compiler focuses on correctness and LLM just does the actual writing.
Same here. I had to do a lot of being in the loop with Python, but with rust - compiler gives Claude all the information it may need and then it figures things out without me.
Writing rust scares me, but I can read it just fine. I've come up with super masochistic linting rules that claude isn't allowed to change and that has improved things quite a bit.
I wish there was a mature framework for frontend that can be configured to be as strict as rust.
I’m finding it to be the opposite. I used to love writing everything by hand but now Claude is giving me the ability to focus more on architecture. I like just sitting down with my coffee and thinking about the next part of my project, how I’d like it to be written and Claude just fills it in for me. It makes mistakes at times but it also finds a lot of mine that I hadn’t even realized were in my code base.
Yep, I get that some people love the act of literally typing "x = 2;" but to me coding is first and foremost problem solving. I have a problem (either truly mine or someone else's), I come up with a solution in my head and slowly implement it.
Before I also had to code it and then make sure it had no issues.
Now I can skip the coding and then just have something spit out something which I can evaluate whether I believe is a good implementation of my solution or not.
Of course, you need the skill to know good from bad but for medium to senior devs, AI is incredibly useful to get rid of the mundane task of actually writing code, while focusing on problem solving with critical review of magically generated code.
Too bad that software developers are carrying water for those who hate them and mock them for being obsolete in 6-12 months, while they are eating caviar (probably evading sanctions) and clink the champagne glasses in Davos:
Define data structures manually, ask AI to implement specific state changes. So JSON, C .h or other source files of func sigs and put prompts in there. Never tried the Agents.md monolithic definition file approach
Also I demand it stick to a limited set of processing patterns. Usually dynamic, recursive programming techniques and functions. They just make the most sense to my head and using one style I can spot check faster.
I also demand it avoid making up abstractions and stick to mathematical semantics. Unique namespaces are not relevant to software in the AI era. It's all
about using unique vectors as keys to values.
Stick to one behavior or type/object definition per file.
Only allow dependencies that are designed as libraries to begin with. There is a ton of documentation to implement a Vulkan pipeline so just do that. Don't import an entire engine like libgodot.
And for my own agent framework I added observation of my local system telemetry via common Linux files and commands. This data feeds back in to be used to generate right-sized sched_ext schedules and leverage bpf for event driven responses.
Am currently experimenting with generation of small models of my own data. A single path of images for example not the entire Pictures directory. Each small model is spun akin to a Docker container.
LLMs are monolithic (massive) zip files of the entire web. No one really asking for that. And anyone who needs it already has access to the web itself
small agents.md files are worth it, at least for holding some basic information (look at build.md to read how to build, the file structure looks like so), rather than have whatever burn double the amount of tokens searching for whatever anyways.
I found an easier way that Works For Me (TM). I describe the problem to LLM and ask it to solve it step by step, but strictly in the Ask mode, not Agent. Then I copy or even type the linws to the code. If I wouldn't write the line myself, it doesn't go in, and I iterate some more.
I do allow it to write the tests (lots of typing there), but I break them manually to see how they fail. And I do think about what the tests should cover before asking LLM to tell me (it does come up with some great ideas, but it also doesn't cover all the aspects I find important).
Great tool, but it is very easy to be led astray if you are not careful.
Every engineering org should be pleading devs to not let AI write tests. They're awful and sometimes they literally don't even assert the code that was generated and instead assert the code in tests.
Same. Small units if work, iterate in it till it's right, commit it, push it, then do the next increment of work. It's how I've always worked like that, except now, I sometimes let someone else figure the exact API calls (I'm still learning react, but Claude helps get the basics in place for me). If the AI just keeps screwing up, I'll grab the wheel and do it myself. It sometimes helps me get things going, but it hasn't been a huge increase in productivity, but I'm not paying the bill so whatever.
You still need to know the hard parts: precisely what you want to build, all domain/business knowledge questions solved, but this tool automates the rest of the coding and documentation and testing.
It's going to be a wild future for software development...
First article about writing code with AI i can get behind 100%. Stuff i already do, stuff i've thought about doing, and at ideas i've never thought doing ("Mark code review levels" especially is a _great_ idea)
Hi i5heu. Given that you seem to use AI tools for generating images and audio versions of your posts, I hope it is not too rude to ask: how much of the post was drafted, written or edited with AI?
The suggestions you make are all sensible but maybe a little bit generic and obvious. Asking ChatGPT to generate advice on effectively writing quality code with AI generates a lot of similar suggestions (albeit less well written).
If this was written with help of AI, I'd personally appreciate a small notice above the blog post. If not, I'd suggest to augment the post with practical examples or anecdotal experience. At the moment, the target group seems to be novice programmers rather than the typical HN reader.
i have written this text by myself except like 2 or 3 sentences which i iterated with an LLM to nail down flow and readability. I would interpret that as completely written by me.
> The suggestions you make are all sensible but maybe a little bit generic and obvious. Asking ChatGPT to generate advice on effectively writing quality code with AI generates a lot of similar suggestions (albeit less well written).
Before i wrote this text, i also asked Gemini Deep Research but for me the results where too technical and not structural or high level as i describe them here. Hence the blogpost to share what i have found works best.
> If not, I'd suggest to augment the post with practical examples or anecdotal experience. At the moment, the target group seems to be novice programmers rather than the typical HN reader.
I have pondered the idea and also wrote a few anecdotal experiences but i deleted them again because i think it is hard to nail the right balance down and it is also highly depended on the project, what renders examples a bit useless.
And i also kind of like the short and lean nature of it the last few days when i worked on the blogpost.
I might will make a few more blogposts about that, that will expand a few points.
> Use strict linting and formatting rules to ensure code quality and consistency. This will help you and your AI to find issues early.
I've always advocated for using a linter and consistent formatting. But now I'm not so sure. What's the point? If nobody is going to bother reading the code anymore I feel like linting does not matter. I think in 10 years a software application will be very obfuscated implementation code with thousands of very solidly documented test cases and, much like compiled code, how the underlying implementation code looks or is organized won't really matter
That's the opposite. I've never read and re-read code more than i do today. The new hires generate 50 more code than they use to, and you _have_ to check it or have compounding production issues (been there, done that). And the errors can now be anywhere, when before you more or less knew what the person writing code is thinking and can understand why some errors are made. LLMs errors could hide _anywhere_, so you have to check it all.
Isn't that a losing proposition? Or do you get 50 times the value out of it too? In my experience the more verbose the code is, the less thought out it is. Lots of changes? Cool, now polish some more and come back when it's below 100 lines change, excluding tests and docs. I don't dare touch it before.
That sounds like the advice of someone who doesn't actually write high-quality code. Perhaps a better title would be "how to get something better than pure slop when letting a chatbot code for you" - and then it's not bad advice I suppose. I would still avoid such code if I can help it at all.
Man, you are really missing out of the biggest revolution of my life.
This is the opinion of someone who has not tried to use Claude Code, in a brand new project with full permissions enabled, and with a model from the last 3 months.
Its only revolutionary if you think engineers were slow before or software was not being delivered fast enough. Its revolutionary for some people sure, but everyone is in a different situation, so one man's trash can be other man's treasure. Most people are treading both paths as automation threatens their livelihood and work they loved, also still not able to understand why would people pay to companies that are actively trying to convince your employer that your job is worthless.
Even If I like this tech, I still dont want to support the companies who make it. Yet to pay a cent to these companies, still using the credits given to me by my employer.
It's insane! We are so far beyond gpt-3.5 and gpt-4. If you're not approaching Claude Code and other agentic coding agents with an open mind with the goal of deriving as much value from them as possible, you are missing out on super powers.
On the flip side, anyone who believes you can create quality products with these tools without actually working hard is also deluded. My productivity is insane, what I can create in a long coding session is incredible, but I am working hard the whole time, reviewing outputs, devising GOOD integration/e2e tests to actually test the system, manually testing the whole time, keeping my eyes open for stereotypically bad model behaviors like creating fallbacks, deleting code to fulfill some objective.
It's actually downright a pain in the ass and a very unpleasant experience working in this way. I remember the sheer flow state I used to get into when doing deep programming where you are so immersed in managing the states and modeling the system. The current way of programming for me doesn't seem to provide that with the models. So there are aspects of how I have programmed my whole life that I dearly miss. Hours used to fly past me without me being the wiser due to flow. Now that's no longer the case most of the times.
This take is pretty uncharitable. I write high quality code, but also there's a bunch of code that could be useful, but that I don't write because it's not worth the effort. AI unlocks a lot of value in that way. And if there's one thing my 25 years as a software engineer has taught me is that while code quality and especially system architecture matter a lot, being super precious about every line of code really does not.
Don't get me wrong, I do think AI coding is pretty dangerous for those without the right expertise to harness it with the right guardrails, and I'm really worried about what it will mean for open source and SWE hiring, but I do think refusing to use AI at this point is a bit like the assembly programmer saying they'll never learn C.
The article did not provide a constructive suggestion on how to write quality code, either. Nor even empirical proof in the form of quality code written by LLMs/agents via the application of those principles.
The post touches very briefly on linting in 7. For me, setting up a large number of static code analysis checks has had the highest impact on code quality.
My hierarchy of static analysis looks like this (hierarchy below is Typescript focused but in principle translatable to other languages):
1. Typesafe compiler (tsc)
2. Basic lint rules (eslint)
3. Cyclomatic complexity rules (eslint, sonarjs)
4. Max line length enforcement (via eslint)
5. Max file length enforcement (via eslint)
6. Unused code/export analyser (knip)
7. Code duplication analyser (jscpd)
8. Modularisation enforcement (dependency-cruiser)
9. Custom script to ensure shared/util directories are not over stuffed (built this using dependency-cruiser as a library rather than an exec)
10. Security check (semgrep)
I stitch all the above in a single `pnpm check` command and defined an agent rule to run this before marking task as complete.
Finally, I make sure `pnpm check` is run as part of a pre-commit hook to make sure that the agent has indeed addressed all the issues.
This makes a dramatic improvement in code quality to the point where I'm able to jump in and manually modify the code easily when the LLM slot machine gets stuck every now and then.
(Edit: added mention of pre-commit hook which I missed mention of in initial comment)
My setup has some of the things mentioned and I found that occasionally the LLM will lie that something passes, when it doesn't.
Yup I have run into the same.
I use a pre-commit hook to run `pnpm check`. I missed mentioning it in the original comment. Your reply reminded me of it and I have now added it. Thanks.
I wonder at the end of this if it's the still worth the risk?
A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations.
Maybe it's the kind of work I'm doing, or maybe I just suck, but the code to me is a forcing mechanism into ironing out the details, and I don't get that when I'm writing a specification.
I second this. This* is the matter against which we form understanding. This here is the work at hand, our own notes, discussions we have with people, the silent walk where our brain kinda process errors and ideas .. it's always been like this since i was a kid, playing with construction toys. I never ever wanted somebody to play while I wait to evaluate if it fits my desires. Desires that often come from playing.
Outsourcing this to an LLM is similar to an airplane stall .. I just dip mentally. The stress goes away too, since I assume the LLM will get rid of the "problem" but I have no more incentives to think, create, solve anything.
Still blows my mind how different people approach some fields. I see people at work who are drooling about being able to have code made for them .. but I'm not in that group.
I'll push it back against this a little bit. I find any type of deliberative thinking to be a forcing function. I've recently been experimenting with writing very detailed specifications and prompts for an LLM to process. I find that as I go through the details, thoughts will occur to me. Things I hadn't thought about in the design will come to me. This is very much the same phenomenon when I was writing the code by hand. I don't think this is a binary either or. There are many ways to have a forcing function.
I think it's analogous to writing and refining an outline for a paper. If you keep going, you eventually end up at an outline where you can concatenate what are basically sentences together to form paragraphs. This is sort of where you are now, if you spec well you'll get decent results.
I agree, I felt this a bit. The LLM can be a modeling peer in a way. But the phase where it goes to validate / implement is also key to my brain. I need to feel the details.
> I see people at work who are drooling about being able to have code made for them .. but I'm not in that group.
people seem to have a inability to predict second and third order effects
the first order effect is "I can sip a latte while the bot does my job for me"... well, great I suppose, while it lasts
but the second order effect is: unless you're in the top 10%, you will now lose your job, permanently
and the third order effect is the economy collapses as it is built on consumer spending
I wonder over the long term how programmers are going to maintain the proficiency to read and edit the code that the LLM produces.
Personally I planned to allocate weekly challenges to stay sharp.
Everything you have said here is completely true, except for "not in that group": the cost-benefit analysis clearly favors letting these tools rip, even despite the drawbacks.
Maybe.
But it's also likely that these tools will produce mountains of unmaintainable code and people will get buried by the technical debt. It kind of strikes me as similar to the hubris of calling the Titanic "unsinkable." It's an untested claim with potentially disastrous consequences.
> But it's also likely that these tools will produce mountains of unmaintainable code and people will get buried by the technical debt.
It's not just likely, but it's guaranteed to happen if you're not keeping an eye on it. So much so, that it's really reinforced my existing prejudice towards typed and compiled languages to reduce some of the checking you need to do.
Using an agent with a dynamic language feels very YOLO to me. I guess you can somewhat compensate with reams of tests though. (which begs the question, is the dynamic language still saving you time?)
Companies aren't evaluating on "keeping an eye on technical debt", but then ARE directly evaluating on whether you use AI tools.
Meanwhile they are hollowing out work forces based on those metrics.
If we make doing the right thing career limiting this all gets rather messy rather quickly.
Tests make me faster. Dynamic or not feels irrelevant when I consider how much slower I’d be without the fast feedback loop of tests.
Static type checking is even faster than running the code. It doesn't catch everything, but if finding a type error in a fast test is good, then finding it before running any tests seems like it would be even better.
Oh I'm well aware of this. I admitted defeat in a way.. I can't compete. I'm just at loss, and unless LLM stall and break for some reason (ai bubble, enshittification..) I don't see a future for me in "software" in a few years.
Somehow I appreciate this type of attitude more than the one which reflects total denial of the current trajectory. Fervent denial and AI trash-talking being maybe the single most dominant sentiment on HN over the last year, by all means interspersed with a fair amount of amazement at our new toys.
But it is sad if good programmers should loose sight of the opportunities the future will bring (future as in the next few decades). If anything, software expertise is likely to be one of the most sought-after skills - only a slightly different kind of skill than churning out LOCs on a keyboard faster than the next person: People who can harness the LLMs, design prompts at the right abstraction level, verify the code produced, understand when someone has injected malware, etc. These skills will be extremely valuable in the short to medium term AFAICS.
But ultimately we will obviously become obsolete if nothing (really) catastrophic happens, but when that happens then likely all human labor will be obsolete too, and society will need to be organized differently than exchanging labor for money for means of sustenance.
I get crazy over the 'engineer are not paid to write loc', nobody is sad because they don't have to type anymore. My two issues are it levels the delivery game, for the average web app, anybody can now output something acceptable, and then it doesn't help me conceptualize solution better, so I revert to letting it produce stuff that is not maleable enough.
If the world comes to that it will be absolutely catastrophic, and it’s a failure of grappling with the implications that many of the executives of AI companies think you can paper over the social upheaval with some UBI. There will be no controlling what happens, and you don’t even need to believe in some malicious autonomous AI to see that.
I feel the same.
Frankly, I am not sure there is a place in the world at all for me in ten years.
I think the future might just be a big enough garden to keep me fed while I wait for lack of healthcare access to put me out of my misery.
I am glad I am not younger.
Yep, its a rather depressing realization isnt it. Oh well, life moves on i suppose.
I think we realistically have a few years of runway left though. Adoption is always slow outside of the far right of the bell curve.
i'm sorry if I pulled everybody down .. but it's been many months since gemini and claude became solid tools, and regularly i have this strong gut feeling. i tried reevaluating my perception of my work, goals, value .. but i keep going back to nope.
That's also how I feel.
I think you have every right to doubt those telling us that they run 5 agents to generate a new SAAS-product while they are sipping latté in a bar. To work like that I believe you'll have to let go of really digging into the code, which in my experience is needed if want good quality.
Yet I think coding agents can be quite a useful help for some of the trivial, but time consuming chores.
For instance I find them quite good at writing tests. I still have to tweak the tests and make sure that they do as they say, but overall the process is faster IMO.
They are also quite good at brute-forcing some issue with a certain configuration in a dark corner of your android manifest. Just know that they WILL find a solution even if there is none, so keep them on a leash!
Today I used Claude for bringing a project I abandoned 5 years ago up to speed. It's still at work in progress, but the task seemed insurmountable (in my limited spare time) without AI, now it feels like I'm half-way there in 2-3 hours.
I think we really need to have a serious think of what is "good quality" in the age of coding agents. A lot of the effort we put into maintaining quality has to do with maintainability, readability etc. But is it relevant if the code isn't for humans? What is good for a human is not what is good for an AI necessarily (not to say there is no overlap). I think there are clearly measurable things we can agree still apply around bugs, security etc, but I think there are also going to be some things we need to just let go of.
You can’t drop anything as long as a programmer is expected to edit the source code directly. Good luck investigating a bug when the code is unclear semantically, or updating a piece correctly when you’re not really sure it’s the only instance.
I think that's the question. Is a programmer expected to ever touch the source code? Or will AI -- and AI alone -- update the code that it generated?
Not entirely unlike other code generation mechanisms, such as tools for generating HTML based on a graphical design. A human could edit that, but it may not have been the intent. The intent was that, if you want a change, go back to the GUI editor and regenerate the HTML.
So like we went from assembler to higher level programming languages, we will now move to specifications for LLMs? Interesting thought... Maybe, once the "compilers" get good enough, but for mission critical systems they are not nearly good enough yet.
This is exactly what is happening from a levels of abstraction standpoint.
The difference being that compilers and related tools are deterministic, and we can manage the outputs using mathematical proof of correctness.
The LLM's driving this new abstraction layer are another beast entirely.
Right. I work in aerospace software, and I do not know if this option would ever be on the table. It certainly isn't now.
So I think this question needs to be asked in the context of particular projects, not as an industry-wide yes or no answer. Does your particular project still need humans involved at the code level? Even just for review? If so, then you probably ought to retain human-oriented software design and coding techniques. If not, then, whatever. Doesn't matter. Aim for whatever efficiency metric you like.
Then again, would anyone have guessed we’d even be seriously discussing this topic 10, 20, 40 years ago?
Maybe. This book from 1990
https://mitpress.mit.edu/9780262526401/artificial-intelligen...
envisions a future of AI assistance that looks not too far off from today.
It’s also pretty close to Steve Jobs initial vision of computing in the future (https://stevejobsarchive.com/stories/objects-of-our-life, 1983) but my point is that whatever it is we call AI now became reality so much faster than anyone really saw coming. Even if the pace slows down, and it didn’t yet, things are improving so massively all the time that the world can’t keep up changing to accommodate.
> I think you have every right to doubt those telling us that they run 5 agents to generate a new SAAS-product while they are sipping latté in a bar. To work like that I believe you'll have to let go of really digging into the code, which in my experience is needed if want good quality.
Also we live in a capitalist society. The boss will soon ask: "Why the fuck am I paying you to sip a latte in a bar? While am machine does your work? Use all your time to make money for me, or you're fired."
AI just means more output will be expected of you, and they'll keep pushing you to work as hard as you can.
> AI just means more output will be expected of you, and they'll keep pushing you to work as hard as you can.
That’s a bit too cynical for me. After all, yes, your boss is not paying you for sipping lattes, but for producing value for the company. If there is a tool that maximises your output, why wouldn’t he want you to use that to great efficiency?
Put differently, would a carpenter shop accept employees rejecting the power saw in favour of a hand saw to retain their artisanal capability?
If the power saw ran itself without any oversight, the carpenter shop wouldn't accept any type of employees.
But that’s the exact opposite of what the GP was arguing; you will be expected to stick with the agent more, not less.
I still do this, but when I'm reviewing what's been written and / or testing what's been built.
How I see it is we've reverted back to a heavier spec type approach, however the turn around time is so fast with agents that it still can feel very iterative simply because the cost of bailing on an approach is so minimal. I treat the spec (and tests when applicable) as the real work now. I front load as much as I can into the spec, but I also iterate constantly. I often completely bail on a feature or the overall approach to a feature as I discover (with the agent) that I'm just not happy with the gotchas that come to light.
AI agents to me are a tool. An accelerator. I think there are people who've figured out a more vibey approach that works for them, but for now at least, my approach is to review and think about everything we're producing, which forms my thoughts as we go.
> A lot of how I form my thoughts is driven by writing code, and seeing it on screen, running into its limitations.
If you need that, don't use AI for it. What is it that you don't enjoy coding or think it's tangential to your thinking process? Maybe while you focus on the code have an agent build a testing pipeline, or deal with other parts of the system that is not very ergonomic or need some cleanup.
Exactly. 30 years ago a mathematician I knew said to me: "The one thing that you can say for programming is that it forces you to be precise."
We vibe around a lot in our heads and that's great. But it's really refreshing, every so often, to be where the rubber meets the road.
That's because many developers are used to working like this.
With AI, the correct approach is to think more like a software architect.
Learning to plan things out in your head upfront without to figure things out while coding requires a mindset shift, but is important to work effectively with the new tools.
To some this comes naturally, for others it is very hard.
I think what GP is referring too are technical semantics and accidental complexity. You can’t plan for those.
The same kind of planning you’re describing can and do happen sans LLM, usually on the sofa, or in front of a whiteboard. Or by reading some research materials. No good programmer rushes to coding without a clear objective.
But the map is not the territory. A lot of questions surface during coding. LLMs will guess and the result may be correct according to the plan, but technically poor, unreliable, or downright insecure.
I also second this. I find that I write better by hand, although I work on niche applications it’s not really standard crud or react apps. I use LLMs in the same way i used to used stack overflow, if I go much farther to automate my work than that I spend more time on cleanup compared to if I just write code myself.
Sometimes the AI does weird stuff too. I wrote a texture projection for a nonstandard geometric primitive, the projection used some math that was valid only for local regions… long story. Claude kept on wanting to rewrite the function to what it thought was correct (it was not) even when I directed to non related tasks. Super annoying. I ended up wrapping the function in comments telling it to f#=% off before it would leave it alone.
Using AI or writing your own code isn't an xor thing. You can still write the code but have a coding assistant or something an alt/cmd-tab away. I enjoy writing code, it relaxes me so that's what I do but when I need to look something up or i'm not clear on the syntax for some particular operation instead of tabbing to a browser and google.com I tab to the agent and ask it to take a look. For me, this is especially helpful for CSS and UI because I really suck at and dislike that part of development.
I also use these things to just plan out an approach. You can use plan mode for yourself to get an idea of the steps required and then ask the agent to write it to a file. Pull up the file and then go do it yourself.
I sometimes wonder if the economics of AI coding agents only work if you totally ignore all the positive externalities that come with writing code.
Is the entire AI bubble just the result of taking performance metrics like "lines of code written per day" to their logical extreme?
Software quality and productivity have always been notoriously difficult to measure. That problem never really got solved in a way that allowed non technical management to make really good decisions from the spreadsheet level of abstraction... but those are the same people driving adoption of all these AI tools.
Engineers sometimes do their jobs in spite of poor incentives, but we are eliminating that as an economic inefficiency.
In 1987 when I first started coding, I would either write my first attempt in BASIC and see it was too slow and rewrite parts in assembly or I would know that I had to write what I wanted from the get go in assembly because the functionality wasn’t exposed at all in BASIC (using the second 64K of memory or using double hires graphics).
This past week, I spent a couple of days modifying a web solution written by someone else + converting it from a Terraform based deployment to CloudFormation using Codex - without looking at the code as someone who hasn’t done front in development in a decade - I verified the functionality.
More relevantly but related, I spent a couple of hours thinking through an architecture - cloud + an Amazon managed service + infrastructure as code + actual coding, diagramming it, labeling it , and thinking about the breakdown and phases to get it done. I put all of the requirements - that I would have done anyway - into a markdown file and told Claude and Codex to mark off items as I tested each item and summarize what it did.
Looking at the amount of work, between modifying the web front end and the new work, it would have taken two weeks with another developer helping me before AI based coding. It took me three or four days by myself.
The real kicker though is while it worked as expected for a couple of hundred documents, it fell completely to its knees when I threw 20x documents into the system. Before LLMs, this would have made me look completely incompetent telling the customer I now wasted two weeks worth of time and 2 other resources.
Now, I just went back to the literal drawing board, rearchitected it, did all of the things with code that the managed services abstracted away with a few tweaks, created a new mark down file and was done in a day. That rework would have taken me a week by itself. I knew the theory behind what the managed service was doing. But in practice I had never done it.
It’s been over a decade where I was responsable for a delivery that I could do by myself without delegating to other people or that was simple enough that I wouldn’t start with a design document for my own benefit. Now within the past year, I can take on larger projects by myself without the coordination/“mythical man Month” overhead.
I can also in a moment of exasperation say to Codex “what you did was an over complicated stupid mess, rethink your implementation from first principles” without getting reported to HR.
There is also a lot of nice to have gold plating that I will do now knowing that it will be a lot faster
Any sufficiently detailed specification converges on code.
I couldn't agree more. It's often when you are in the depth of the details that I make important decisions on how to engineer the continuation.
Yes, I look at this in a similar vein to the (Eval <--> Appply) Cycle in SICP textbook, as a (Design <--> Implement) cycle.
Sounds like the coders equivalent of the Whorfian hypothesis.
I was just thinking this the other day after I did a coding screen and didn't do well. I know the script for the interviewee is your not suppsed to write any code until you talk through the whole thing, but I think i woukd have done better if I could have just wrote a bunch of throw away code to iterate on.
Are there still people under the impression that the correct way to use Stack Overflow all these years was to copy & paste without analyzing what the code did and making it fit for purpose?
If I have to say, we're just waiting for the AI concern caucus to get tired of performing for each other and justifying each other's inaction in other facets of their lives.
Lab-grown meat slop producer defends AI slop.
So now we're pro-slaughter and low-yield agriculture as long as we get to ride the keyboard eh?
The real value that AI provides is the speed at which it works, and its almost human-like ability to “get it” and reasonably handle ambiguity. Almost like tasking a fellow engineer. That’s the value.
By the time you do everything outlined here you’ve basically recreated waterfall and lost all speed advantage. Might as well write the code yourself and just use AI as first-pass peer review on the code you’ve written.
A lot of the things the writer points out also feel like safeguards against the pitfalls of older models.
I do agree with their 12th point. The smaller your task the easier to verify that the model hasn’t lost the plot. It’s better to go fast with smaller updates that can be validated, and the combination of those small updates gives you your final result. That is still agile without going full “specifications document” waterfall.
It’s a solid post overall and even for people with a lot of experience there’s some good ideas in here. “Identify and mark functions that have a high security risk, such as authentication, authorization” is one such good idea - I take more time when the code is in these areas but an explicit marking system is a great suggestion. In addition to immediate review benefits, it means that future updates will have that context.
“Break things down” is something most of us do instinctively now but it’s something I see less experienced people fail at all the time.
I can't help but keep finding it ridiculous how everyone now discovers basic best practices (linting, documentation, small incremental changes) that have been known for ages. It's not needed because of AI, you should have been doing it like this before as well.
Anyone who’s been a developer for more than 10 minutes knows that best practices are hard to always follow through on when there’s pressure to ship.
But there’s more time to do some of these other things if the actual coding time is trending toward zero.
And the importance of it can go up with AI systems because they do actually use the documentation you write as part of their context! Direct visible value can lead people to finally take more seriously things that previously felt like luxuries they didn’t have time for.
Again if you’ve been a developer for more than 10 minutes, you’ve had the discouraging experience of pain-stakingly writing very good documentation only for it to be ignored by the next guy. This isn’t how LLMs work. They read your docs.
Remember having to write detailed specs before coding? Then folks realized it was faster and easier to skip the specs and write the code? So now are we back to where we were?
One of the problems with writing detailed specs is it means you understand the problem, but often the problem is not understand - but you learn to understand it through coding and testing.
So where are we now?
We’re not „thinking with portals” about these things enough yet. Typically we’d want a detailed spec beforehand, as coding is expensive and time consuming, thus we want to make sure we’re coding the right thing. With AI though, coding is cheap. So let AI skip the spec and write the code badly. Then have it review the solution, build understanding, design a spec for better solution and have it write it again. Rinse and repeat as many times you need.
It’s also nothing new, as it’s basically Joe Armstrong's programming method. It’s just not prohibitively expensive for the first time in history.
Astronaut 1, AI-assisted developers: You mean, it's critical to plan and spec out what you want to write before you start in on code?
Astronaut 2, Tim Bryce: Always has been...
The first rule is an antipattern. I think describing your architecture or ANY kind of documentation for your AI is an anti-pattern and blows the context window leading to worse results, and actual more deviation.
The controlling systems are not give it more words at the start. Agentic coding needs to work in loop with dedicated context.
You need to think about how can i give as much intent as possible with as little words.
You can built a tremendous amount of custom lint rules ai never needs to read except they miss it.
Every pattern in your repo gets repeated, repo will always win over documentation and when your repo is good structured you don’t need to repeat this to AI
It’s like dev always has been, watch what has gone wrong and make sure the whole type or error can’t happen again.
I also made a list of tips on writing code with AI, with a special focus on security. Others may find the tips useful. Here they are: https://openssf.org/blog/2026/01/05/ai-software-development-...
Some pattern I found from my hobby project.
1. Keep things small and review everything AI written, or 2. Keep things bloated and let AI do whatever it wants within the designated interface.
Initially I drew this line for API service / UI components, but it later expanded to other domains. e.g. For my hobby rust project I try to keep "trait"s to be single responsible, never overlap, easy to understand etc etc. but I never look at AI generated "impl"s as long as it passes some sensible tests and conforming the traits.
I'm finding Rust is perfect for me with LLMs.
I find rust generally easier to reason about, but can't stand writing it.
The compiler works well with LLMs plenty of good tooling and LSPs.
If I'm happy with the shape of the code and I usually write the function signatures/ Module APIs. And the compiler is happy with it compiling. Usually the errors if any are logical ones I should catch in reviews.
So I focus on function, compiler focuses on correctness and LLM just does the actual writing.
Do you think Rust will end up getting a boost from LLM adoption?
It definitely has for me! I just replied to the parent explaining why.
Tl;Dr I don't mind reading rust I hate writing it and the compiler meets me in the middle.
Same here. I had to do a lot of being in the loop with Python, but with rust - compiler gives Claude all the information it may need and then it figures things out without me.
Writing rust scares me, but I can read it just fine. I've come up with super masochistic linting rules that claude isn't allowed to change and that has improved things quite a bit.
I wish there was a mature framework for frontend that can be configured to be as strict as rust.
Sounds like an awful lot of work and nannying just to avoid writing code yourself. Coding used to be fun and enjoyable once...
I’m finding it to be the opposite. I used to love writing everything by hand but now Claude is giving me the ability to focus more on architecture. I like just sitting down with my coffee and thinking about the next part of my project, how I’d like it to be written and Claude just fills it in for me. It makes mistakes at times but it also finds a lot of mine that I hadn’t even realized were in my code base.
Yep, I get that some people love the act of literally typing "x = 2;" but to me coding is first and foremost problem solving. I have a problem (either truly mine or someone else's), I come up with a solution in my head and slowly implement it.
Before I also had to code it and then make sure it had no issues.
Now I can skip the coding and then just have something spit out something which I can evaluate whether I believe is a good implementation of my solution or not.
Of course, you need the skill to know good from bad but for medium to senior devs, AI is incredibly useful to get rid of the mundane task of actually writing code, while focusing on problem solving with critical review of magically generated code.
Too bad that software developers are carrying water for those who hate them and mock them for being obsolete in 6-12 months, while they are eating caviar (probably evading sanctions) and clink the champagne glasses in Davos:
https://xcancel.com/hamptonism/status/2019434933178306971
And all that after stealing everyone's output.
Underground Resistance Aims To Sabotage AI With Poisoned Data
https://news.ycombinator.com/item?id=46827777
Textile workers sabotage mechanical looms. History repeats itself.
My tricks:
Define data structures manually, ask AI to implement specific state changes. So JSON, C .h or other source files of func sigs and put prompts in there. Never tried the Agents.md monolithic definition file approach
Also I demand it stick to a limited set of processing patterns. Usually dynamic, recursive programming techniques and functions. They just make the most sense to my head and using one style I can spot check faster.
I also demand it avoid making up abstractions and stick to mathematical semantics. Unique namespaces are not relevant to software in the AI era. It's all about using unique vectors as keys to values.
Stick to one behavior or type/object definition per file.
Only allow dependencies that are designed as libraries to begin with. There is a ton of documentation to implement a Vulkan pipeline so just do that. Don't import an entire engine like libgodot.
And for my own agent framework I added observation of my local system telemetry via common Linux files and commands. This data feeds back in to be used to generate right-sized sched_ext schedules and leverage bpf for event driven responses.
Am currently experimenting with generation of small models of my own data. A single path of images for example not the entire Pictures directory. Each small model is spun akin to a Docker container.
LLMs are monolithic (massive) zip files of the entire web. No one really asking for that. And anyone who needs it already has access to the web itself
small agents.md files are worth it, at least for holding some basic information (look at build.md to read how to build, the file structure looks like so), rather than have whatever burn double the amount of tokens searching for whatever anyways.
I found an easier way that Works For Me (TM). I describe the problem to LLM and ask it to solve it step by step, but strictly in the Ask mode, not Agent. Then I copy or even type the linws to the code. If I wouldn't write the line myself, it doesn't go in, and I iterate some more.
I do allow it to write the tests (lots of typing there), but I break them manually to see how they fail. And I do think about what the tests should cover before asking LLM to tell me (it does come up with some great ideas, but it also doesn't cover all the aspects I find important).
Great tool, but it is very easy to be led astray if you are not careful.
Every engineering org should be pleading devs to not let AI write tests. They're awful and sometimes they literally don't even assert the code that was generated and instead assert the code in tests.
My approach:
1. Have the LLM write code based on a clear prompt with limited scope 2. Look at the diff and fix everything it got wrong
That's it. I don't gain a lot in velocity, maybe 10-20%, but I've seen the code, and I know it's good.
Same. Small units if work, iterate in it till it's right, commit it, push it, then do the next increment of work. It's how I've always worked like that, except now, I sometimes let someone else figure the exact API calls (I'm still learning react, but Claude helps get the basics in place for me). If the AI just keeps screwing up, I'll grab the wheel and do it myself. It sometimes helps me get things going, but it hasn't been a huge increase in productivity, but I'm not paying the bill so whatever.
The GSD tool (get-shit-done) automates a very similar process to this, and has been mind-blowing for larger projects and refactors.
https://github.com/glittercowboy/get-shit-done
You still need to know the hard parts: precisely what you want to build, all domain/business knowledge questions solved, but this tool automates the rest of the coding and documentation and testing.
It's going to be a wild future for software development...
First article about writing code with AI i can get behind 100%. Stuff i already do, stuff i've thought about doing, and at ideas i've never thought doing ("Mark code review levels" especially is a _great_ idea)
All this boils down to is that AI wins when it amplifies engineers, not replaces them. And the best code still comes from devs who ultrathink.
Hi i5heu. Given that you seem to use AI tools for generating images and audio versions of your posts, I hope it is not too rude to ask: how much of the post was drafted, written or edited with AI?
The suggestions you make are all sensible but maybe a little bit generic and obvious. Asking ChatGPT to generate advice on effectively writing quality code with AI generates a lot of similar suggestions (albeit less well written).
If this was written with help of AI, I'd personally appreciate a small notice above the blog post. If not, I'd suggest to augment the post with practical examples or anecdotal experience. At the moment, the target group seems to be novice programmers rather than the typical HN reader.
Hi raphman,
i have written this text by myself except like 2 or 3 sentences which i iterated with an LLM to nail down flow and readability. I would interpret that as completely written by me.
> The suggestions you make are all sensible but maybe a little bit generic and obvious. Asking ChatGPT to generate advice on effectively writing quality code with AI generates a lot of similar suggestions (albeit less well written).
Before i wrote this text, i also asked Gemini Deep Research but for me the results where too technical and not structural or high level as i describe them here. Hence the blogpost to share what i have found works best.
> If not, I'd suggest to augment the post with practical examples or anecdotal experience. At the moment, the target group seems to be novice programmers rather than the typical HN reader.
I have pondered the idea and also wrote a few anecdotal experiences but i deleted them again because i think it is hard to nail the right balance down and it is also highly depended on the project, what renders examples a bit useless.
And i also kind of like the short and lean nature of it the last few days when i worked on the blogpost. I might will make a few more blogposts about that, that will expand a few points.
Thank you for your feedback!
How to write good code with AI -> put in as much effort as you did before on 20% more code than you used to work with.
In her defence, I use most of those strategies myself as well...
https://bcantrill.dtrace.org/2025/12/05/your-intellectual-fl...
How to write quality code with AI? Don't let it write the code.
> Use strict linting and formatting rules to ensure code quality and consistency. This will help you and your AI to find issues early.
I've always advocated for using a linter and consistent formatting. But now I'm not so sure. What's the point? If nobody is going to bother reading the code anymore I feel like linting does not matter. I think in 10 years a software application will be very obfuscated implementation code with thousands of very solidly documented test cases and, much like compiled code, how the underlying implementation code looks or is organized won't really matter
That's the opposite. I've never read and re-read code more than i do today. The new hires generate 50 more code than they use to, and you _have_ to check it or have compounding production issues (been there, done that). And the errors can now be anywhere, when before you more or less knew what the person writing code is thinking and can understand why some errors are made. LLMs errors could hide _anywhere_, so you have to check it all.
Isn't that a losing proposition? Or do you get 50 times the value out of it too? In my experience the more verbose the code is, the less thought out it is. Lots of changes? Cool, now polish some more and come back when it's below 100 lines change, excluding tests and docs. I don't dare touch it before.
They serve as guardrails for agents to not do stupid things.
If your goal is for AI to write code that works, is maintainable and extensible, you have to include as many deterministic guardrails as possible.
That sounds like the advice of someone who doesn't actually write high-quality code. Perhaps a better title would be "how to get something better than pure slop when letting a chatbot code for you" - and then it's not bad advice I suppose. I would still avoid such code if I can help it at all.
Man, you are really missing out of the biggest revolution of my life.
This is the opinion of someone who has not tried to use Claude Code, in a brand new project with full permissions enabled, and with a model from the last 3 months.
Claude code is great at figuring out legacy code! I dont get the «for new systems only» idea, myself.
This is a fading but common sentiment on hacker news.
There’s a lot of engineers who will refuse to wake up to the revolution happening in front of them.
I get it. The denialism is a deeply human response.
Its only revolutionary if you think engineers were slow before or software was not being delivered fast enough. Its revolutionary for some people sure, but everyone is in a different situation, so one man's trash can be other man's treasure. Most people are treading both paths as automation threatens their livelihood and work they loved, also still not able to understand why would people pay to companies that are actively trying to convince your employer that your job is worthless.
Even If I like this tech, I still dont want to support the companies who make it. Yet to pay a cent to these companies, still using the credits given to me by my employer.
Of course software hasn’t been delivered fast enough. There is so so so much of the world that still needs high quality software.
It's insane! We are so far beyond gpt-3.5 and gpt-4. If you're not approaching Claude Code and other agentic coding agents with an open mind with the goal of deriving as much value from them as possible, you are missing out on super powers.
On the flip side, anyone who believes you can create quality products with these tools without actually working hard is also deluded. My productivity is insane, what I can create in a long coding session is incredible, but I am working hard the whole time, reviewing outputs, devising GOOD integration/e2e tests to actually test the system, manually testing the whole time, keeping my eyes open for stereotypically bad model behaviors like creating fallbacks, deleting code to fulfill some objective.
It's actually downright a pain in the ass and a very unpleasant experience working in this way. I remember the sheer flow state I used to get into when doing deep programming where you are so immersed in managing the states and modeling the system. The current way of programming for me doesn't seem to provide that with the models. So there are aspects of how I have programmed my whole life that I dearly miss. Hours used to fly past me without me being the wiser due to flow. Now that's no longer the case most of the times.
> in a brand new project
Must be nice. Claude and Codex are still a waste of my time in complex legacy codebases.
Brand new projects have a way of turning into legacy codebases
What are you talking about? Exploring and explaining the legacy codebases is where they shine, in my experience.
This take is pretty uncharitable. I write high quality code, but also there's a bunch of code that could be useful, but that I don't write because it's not worth the effort. AI unlocks a lot of value in that way. And if there's one thing my 25 years as a software engineer has taught me is that while code quality and especially system architecture matter a lot, being super precious about every line of code really does not.
Don't get me wrong, I do think AI coding is pretty dangerous for those without the right expertise to harness it with the right guardrails, and I'm really worried about what it will mean for open source and SWE hiring, but I do think refusing to use AI at this point is a bit like the assembly programmer saying they'll never learn C.
Can you be specific? You didn't provide any constructive feedback, whatsoever.
The article did not provide a constructive suggestion on how to write quality code, either. Nor even empirical proof in the form of quality code written by LLMs/agents via the application of those principles.
Yes it did, it provided 12 things that the author asserts helps produce quality code. Feel free to address the content with something productive.
Look up luddites on Wikipedia, might be too deep to see the similarities though.