ES version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
70% Positive
Analyzed from 5803 words in the discussion.
Trending Topics
#code#more#lines#loc#don#should#same#engineers#company#engineering
Discussion (122 Comments)Read Original on HackerNews
There is no description of what the thing is, no indication of what value it provides its users. The closest it gets is "the product has been used by hundreds of users internally, including daily internal power users".
But the fact that the thing has a million lines of code is repeated twice in the first few hundred words.
[1] https://openai.com/index/harness-engineering/
[2] https://news.ycombinator.com/item?id=48416264
My guess is it’s an email filter.
> million lines of code
> written 100% by agents
Yeah, probably an email filter. Or maybe a JS menu for a departmental wiki that basically recreates jquery using MS JScript and transpiles it into JS 5.
It may also be an email generator.
The email filter team is trying to match the pace of innovation of the email generation team. At stakes is the ability for the employees to process the billions of mission-critical generated emails each of them receives each day.
https://openhub.net/p/chrome/analyses/latest/languages_summa...
I do think that over the past few months, it feels like the hype around producing unmaintainable amounts of LoC has started dying down. More pragmatic and realistic takes are seemingly shared more openly, and are maybe even getting through to top leadership at some tech companies. Maybe not all is lost yet.
I wonder if a small part of this is more and more business and product people actually trying to incorporate AI into their daily workflows. I have seen this in both small companies I work for. People were very excited about getting Claude Cowork a couple of months ago, and while they use it daily, I would say they are rather underwhelmed compared to the magic they were expecting. Complaints include the output being mediocre and verbose, it getting the most basic things wrong, hitting token limits all the time, and people going back to doing things themselves because it is faster.
Sure, there is some degree of holding it wrong in the beginning, but people are realizing that maybe, just maybe, there is still somewhat of a gap between what AI CEOs, LinkedIn grifters, and YouTube AI supplement peddlers claim and reality.
Seemingly engineers get this wrong too. I'm reminded of when Cursor bragged about how many lines of code a group of agents could produce, with the underwhelming results of a barely working browser, when the same could be built with much less code.
But they highlighted the amount of code as they were proud over how much slop their constellation of agents had shit out, and these were supposedly engineers, really strange to see.
And anyway, I’m pretty sure what people really mean by this “less is better” mantra is: the lowest amount of code that still accomplishes the goal and is still readable is preferred. Linux apparently has 40M lines of code, and I bet most of it is better than mine. Some things just take lots of code.
Which seems to leave room for these agent salesmen to pitch SLoC as a plus. We just have to believe those lines are all good ones. I that case, it would be impressive. I don’t believe it, but they are probably pitching to people who do.
I think it is (or should be) a goal & business-oriented concern as well, not just an engineer's who enjoys their craft.
More complex systems are worse than simpler systems (that accomplish the same), in cost, maintenance, fragility, ease of understanding, etc. Fewer moving parts usually result in higher reliability, fewer things that can break down or fail to interact properly, etc. That's a business concern too, not just engineering craftmanship or whatever. Business people should care about this too.
I don't think this is the same as bikeshedding over irrelevant details, something we software engineers are often prone to. Monstrous complexity does impact the business!
“Technical debt” never hooked management in the same way and we have found it hard to convince them that it needs to be addressed. Debt in general is something that can be a problem, but doesn’t need to be avoided or addressed until it is a problem so the can is kicked down the road.
AI slop is an easier concept to quantify. It's basically the code for which insufficient people in the organisation have a meaningful understanding of how it works or what it does.
Its connotation also includes being vastly larger than needed for the purpose it serves, _if_ there is even any purpose.
Did those engineers not actually read the complete tweet? Because it wasn't about "engineers should write 1M LOC per month of product code" it was "we want to scale automated porting of code to safe languages so that 1 engineer managing 1M LOC of automated conversion can work". Which doesn't seem like satire at all..? It just means "develop mostly reliable AI-driven refactoring tools with good guard rails". Which seems quite sensible, actually?
Porting to a new language is easy, but does nothing useful. What we need is to fix the mistakes of the past so we can get to the future. We need to make acceptable performance.
Making a grand claim of a goal and not really having an explanation on how to achieve it isn't really much better. I could say "we want to scale food production so that one farmer could manage a million acres of corn a month", but that wouldn't really be sensible. A line of code is less work than an acre of corn of course, but I don't think it's at all apparent what upper bound for how much code is actually plausible for a single engineer to generate in a month and have any degree of confidence in. Given the absurd levels of hype around AI from non-engineering management in the past couple of years, it's not clear why the benefit of the doubt is earned here when there legitimate are managers and executives claiming pretty much exactly what you're claiming this guy wasn't.
Otherwise it really sounds like a recipe for unnecessary huge risk with dubious expected positive outcome.
Not saying don’t have fun, but on the other side maybe not with the core product of you cash cow already?
Because many programmers don't believe that'd work. See the reaction to Bun's porting to rust. (I bet Bun will work and prove those programmers wrong, but that's another story.)
> Because it wasn't about "engineers should write 1M LOC per month of product code" it was "we want to scale automated porting of code to safe languages so that 1 engineer managing 1M LOC of automated conversion can work"
These are one and the same. Whether it's ported code or not doesn't change that. The framing device also doesn't matter, because it's the exact "Oh it's our goal" shtick that executives use in the former's case.
"It's just a measure" doesn't cut it in a world where every single AI measure immediately gets turned into a target by executives greedy for efficiencies that don't exist.
EDIT:
Right, I forgot. This is HN where everyone is a galaxybrain and "Port a million lines of code per month" is a totally reasonable goal for a single individual.
In contrast, converting 1M LOC of code per month is a much more solid measure, as long as you measure LOC of the source, not the new code. Sure, in the short term you can pick the easy/verbose things to port, but it's hard to do sustainably. A 5M LOC code base would still be expected to be ported in 5 engineer months.
Granted, you can still rush the work, not test properly, neglect good planning and engineering. Ported lines of code should not be the only measure (just like with any other measure). But it's a much less problematic measure than coding 1M LOC
The marketing ploys of OpenAI/Anthropic where agents build something that nobody uses might be hard to track given that there are zero users. But what about everyone using agents for real software? It's trivial to prove that agents make progress.
Why? If you can deliver the same thing in fewer correct lines of code wouldn't that be preferable? At a bare minimum if you're still insisting on using AI to slop out your project, having it do things in fewer lines of code means you can fit more into your LLM's context window.
it really depends on what you're doing. If your goal is "become interoperable with the N different and incompatible network protocols that people have devised for doing task X" I'd really like to know a solution that doesn't have at least some part of the amount of code that scales with N.
Example: consider https://bitfocus.io/connections which connects to 700 different things. Right now it's written with Node.JS, with one repo per connection (example: https://github.com/bitfocus/companion-module-meyersound-gala...). Let's say you want to make a similar product but that runs on ESP32 where performance is paramount so you need C++ or Rust. How do you do that without at least as many lines of code as the existing JS implementations for every system supported by Companion?
Moreover, writing too terse code harms readability and maintainability. There is such a thing as irreducible complexity.
Because they're bullshitting and using AI as an excuse to correct from their covid era over-hiring while simultaneously making themselves look good to investors by showing they're embracing the hip new technologies to become a more streamlined and cost-efficient operation than ever.
The reasons we rejected LoC and other measurements have not changed (broadly: code output isn't important, quality output is). AI has all the same problems people do. But for whatever reason we are throwing what we've learnt away. It's kind of embarrassing.
I wonder if we'll ever get back to that? If it's still relevant?
They are implicitly saying that as a company, they don't want to be more productive. They want the same productivity by paying fewer more productive people.
Why is there an imbalance between what an employer gets paid for a unit of production and what an employee gets paid for a unit of production?
I believe you mean same output but fewer people? But by definition that would be higher company productivity, as the definition of productivity at the company and/or national level is the ratio of outputs to inputs. If you have fewer people but are getting the same output, then the productivity of the company (or nation) has improved.
If you had fewer people but the same productivity then there would be no benefit to the company as the outputs would correspondingly be reduced (and it may actually be worse for the company if the company has any fixed costs).
https://www.mckinsey.com/featured-insights/mckinsey-explaine...
Because labor gets exploited to make the owners richer. That's the basic fact, even though the owners (as a class) have financed a lot of propaganda to justify and obscure it.
Only a person who never tried to organize labor into a company could ever have such a couch-sitter opinion
It is weird that the author seems to understand that the pro-AI claims made by AI companies about the product’s necessity are not falsifiable, but then backtracks with “woah woah woah but don’t think I’m anti-AI.”
How is the assertion above any more rigorous than the productivity claims the author is criticizing throughout the rest of the article? That you won’t “survive” if you don’t adopt AI within a few months?
It is not true when the AI CEO says it, and it is not true when the person calling BS on the AI CEO… for some reason also says it…
It's not the first article I've read recently that is an ad for AI after a short context pretending to criticize it, with nothing connecting them.
So yes, use AI. Don't nitpick the costs and benefits. The world is headed this way; if you want to develop software for a living and afford to eat, you need to be too.
Need more devs? Why? If a company was being profitable just fine prio AI era, they will still be profitable if they decide not to use AI. Shipping crap faster is not a formula for success. Shipping quality faster? I prefer shipping quality at a good pace
growth is much more important than profitability
> If you got a free headcount increase essentially overnight, why wouldn’t you use it to deliver more value to your customers, faster?
That shows that it's really just short-sighted profit-taking. Boss just wants another lambo in the garage, and doesn't really plan to be around, when it's time to pay the piper.
Non-Functional requirements is a vestigial term from ‘function point analysis’ which is from the late 70s, and which also ended up being a proxy for LoC.
The entire industry is so focused on measuring now, and incentives are so skewed to short term that lagging indicators like maintainability are a non starter in many organizations that it will be challenging to fix this time.
https://www.goodreads.com/quotes/536587-measuring-programmin...
A) a newly-receptive audience - engineers who have discovered that they very much enjoy and appreciate the tradeoff of proximity to the code for amplified velocity and impact, now that it's possible to achieve without being a manager of messy human teams.
B) an ecosystem in which it's grown nearly impossible to connect a functional description of something to how much bespoke construction and effort was involved, partially because of marketing and partially because of how much software already exists to be built on top of. It's impossible to tell from a few paragraphs of functional description whether something was built in a weekend or took a team 4 years to ship, so volume of code is the natural fallback for describing complexity.
Ugh. Just imagine the following on a normal curve:
Pre-AI: The goal is to make more money.
With-AI: The goal is to ship more code.
Post-AI: The goal is to make more money.
Can't wait to see how we get there...
I don't think so. Take a good company A (with a good product and a good pace of good features) of today. Take the extreme case they decide not to use AI at all. Well, they will still be shipping good features at their current pace.
No amount of AI will make a bad company ship a better product than A's. If any, bad/mediocre companies will be pushing crap faster than they did before, but that's it.
AI can make good companies better, but cannot make bad companies good. Why does company A need to worry about shitty companies using AI? Sure, other good competitors could be using AI, but all in all, shipping "faster" is not the "mark" of good quality
Skeptic and sceptic are pronounced identically, because they are just different spelling of the same word.
Maybe you've confused it with septic?
Since this is an area where failure can lead not to Instagram accounts getting hacked, but planes falling out of the sky and nuclear reactors spewing radioactive elements, it’s worth a close look. Some of the most visible companies in this sector include: QNX, Wind River, SYSGO, Lynx, Green Hills, Siemens Embedded, etc. None of them seem to have much if any adoption of LLMs for source code generation based on public statements.
Research in this area agrees with this view:
“In this paper, I have conducted a comparative analysis of the C++ code generated by popular LLMs including: OpenAI ChatGPT, Google Gemini, DeepSeek, Meta AI, and Microsoft Copilot for compliance with MISRA C++. The study revealed that none of the evaluated LLMs generated MISRA-compliant code despite clear prompts, with DeepSeek showing the fewest violations and Meta AI the most.”
https://arxiv.org/abs/2506.23535
> When a company says “AI made everyone more productive, so we need fewer people”, I want to see the evidence - and I don’t believe it exists today. Show me that x% of your workforce is genuinely idle (or even just underutilised) because the work can now be done by fewer people. Even then: I’ve never seen a product/SaaS company that didn’t have an endless roadmap. If you got a free headcount increase essentially overnight, why wouldn’t you use it to deliver more value to your customers, faster? That should show up as MAU, conversion, revenue.
I see some people calling for calm instead of AI panic by invoking Jevons Paradox. But at least within these companies there's no good evidence of Jevons in action, is there? The roadmap is endless, but when employees are perceived to be idle they get fired instead of being assigned more (or more ambitious) tasks.
To be fair, one could claim Jevons applies to "the market" at large, but at least we can say the evidence from tech companies is not encouraging. So maybe it is, indeed, time to panic a bit?
> Choosing the layoff instead tells me the productivity claim is doing PR work for a decision that was already made for other reasons (over-hiring, investor pressure, take your pick).
Yup, I think we all suspect this. Though it's probably a mix of the two factors.
Anyone relying on a steady paycheck from an employer should panic a bit all the time, because nothing can save them from bad management. The reference to Jevons Paradox doesn't say anything about individual managers responding correctly. If 30% of managers screw up, that's a lot of collateral damage.
Now to respond to your actual point, I don't think software developers should panic. Even if pure software engineering gets hit hard, I'm having trouble imagining a scenario where years of software development skills plus knowledge in a specific domain isn't a good thing for current software developers. This is unlike what happened with international trade, where you had 60-year old textile workers losing their jobs, no alternative jobs, and no policy being offered to compensate them for the effects of trade.
This may be true, but they followed in May with this [0]:
> Importantly, survey results are not necessarily grounded in reality. There are reasons to be skeptical of people’s responses to counterfactual questions such as about AI’s effect on productivity — for instance, our study in early 2025 found that people overestimated AI’s effect on their time spent on tasks by 40 percentage points on average.
[0] https://metr.org/blog/2026-05-11-ai-usage-survey/#productivi...
Deciding what to build. Reviewing Code. And testing code. Are the new bottleneck.
So of course we don't see massive productivity gains. Because these parts of the SCLC were always bottlenecked but their capacity matched the throughout. We fired all the dedicated QAs years ago. Sr+ engineers that do all the code review are limited.
Teams have not re-organized to match the new code-input velocity.
Engineers don't want to do QA because it's "beneath them".. and most engineers don't like performing or are not Sr enough to do extensive or high quality code review.
People. Already. Know. This.
It hasn't been the bottleneck for decades for the majority of products.
I’m fine with doing QA. But the fact is that it’s not how management measure my productivity. Spending hours doing QA looks like wasting time to them because it’s not an activity they track. They track my tickets so any hours not spent on them is literally harmful.
Also there’s the fact that you can’t QA your own output. It’s easy to overlook mistakes and defects.
> and most engineers don't like performing or are not Sr enough to do extensive or high quality code review.
Just like QA, code review takes time. It’s easy to justify that time when the submitter has put in the effort to ensure that the contribution is worthwhile. Or can explain the design clearly. Not so much when it’s slop thrown over the wall.
> Deciding what to build. Reviewing Code. And testing code. Are the new bottleneck.
None of those are truly bottleneck. Deciding what to build is obvious: Something that solve a user problem. Reviewing code is easy when the intent of the code is clear (with additional prose if needs be). Testing code is equally easy and should already be automated.
The one slow activity has always been about designing the solution. And it has no relation to code. It’s mostly deep thinking and research. I do it on the sofa or in front of a whiteboard. If I’m typing, I already have a solution in mind.
I'm currently working in an internal team, so I value cost savings estimation, but even before prioritising was also a bottleneck (although a small one compared to architecture and design)
I mean, if you give 219 people a free text box and ask them to explain anything, you're extremely unlikely to get the exact same answer twice...
Why?
> Be curious, try the new tools, test the latest models. To not do so is silly. > [...] > you could delay adopting “the cloud” for a couple of years and survive. With AI you might get a few months. The way we work has already changed, and it’s not changing back as far as I can tell.
I really dislike these claims that act like they know the future of engineering, that they’ve been let in on some enlightenment that we haven’t been. What’s going to happen in a few months? Is Sam Altman going to nuke my house from orbit? Or is it because my CTO is going to fire me for not using AI? If it’s the latter, that’s not a curiosity problem, that’s a “there’s a gun to my head” problem.
If you want a more in depth explanation, go look for interviews with devs who were already super-productive before LLMs and now came around to using them everyday.
I still write code manually to keep my trad-coding skills from withering away, but using AI without a doubt has allowed me to better test my existing apps. Create playwright automations I would've never had the time for. Allowed me to search through docs many times faster. And it just making programming more fun when I do use it for more challenging problems, and I actually get something working at the end of the day.
A few of my workflows now are: Use an LLM to generate code that generates code.
"Second Order AI Software Engineering(TM)"
That is why I have created one (Open Honest Slop Audit).
Funny how AI is continuing the same story of non/semi technical busy bodies with their dumb bullshit.
https://imgur.com/a/UW15xVE
I spend a lot of my time taking over codebases other people left behind, and the AI-heavy ones have a recognizable shape: lots of plausible-looking code, thin tests, and nobody who can tell you why a given abstraction exists. Writing was never the hard part. Deciding what not to build, and being able to delete it confidently later, is the part that does not get faster with a model.
What did get faster for me is reading and reverse-engineering unfamiliar code - which is a little ironic, since the same tools are now producing more of the unfamiliar code that needs reverse-engineering in the first place.
Every line of code an LLM instantly spits out is a line a human engineer will eventually have to read, understand, debug, and migrate when the underlying business logic changes. The "better publicist" might be successfully selling these generation metrics to executives, but it's the actual engineering teams who are going to be paying the maintenance tax on all this auto-generated sprawl for the next decade.