Making
160
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
72% Positive
Analyzed from 5550 words in the discussion.
Trending Topics
#don#something#code#made#making#things#more#llm#doing#still
Discussion Sentiment
Analyzed from 5550 words in the discussion.
Trending Topics
Discussion (62 Comments)Read Original on HackerNews
Instead, what I've been doing for my personal projects has been about designing algorithms with TLA+. I write that by hand, model check and sometimes even prove the properties I think are interesting or useful, and then tell Claude to implement it based on the spec. Usually I still need to correct the generated code but it's a lot less.
Certainly in these cases, I take pride in what I did, because ultimately the "Invisible Hand" always means I'm outsourcing some of the work of a project no matter how involved I want to be. If I build a deck outside, I'm not forging the nails myself, I'm not growing and chopping down the trees for lumber, I'm not designing my own power tools, etc. There's always a level of outsourcing of the work that I don't find interesting or that I don't know how to do, or don't have the resources to do myself.
With software, the parts that I end up feeling proudest of, and this predates widespread use of LLMs, are the algorithms and tricks I come up with to build something. When I figure out a way to avoid a lock, or figure out a way to use less memory, or figure out a way to increase throughput, I'm less concerned with the actual "code", and much more concerned about the "how".
So like when I went to a restaurant last week and "made" a cheeseburger with no lettuce and extra onions, because it wouldn't exist if I hadn't created it.
To me, making something can mean you did the physical work of its creation even if there's no particular creative expression, like "I made a peanut butter and jelly sandwich."
It can also apply to tasks where you've offloaded a bunch of work that once would've been done by hand, like "I made this bench using a circular saw."
Where things get hairy even with physical objects is processes like CNC or 3D printers. If you download "Articulated dragon.stl" from a website and press the print button, did you make that? Personally, no. But if you designed your own flexy dragon and printed it, then yes. If you set up a relief carving on a CNC machine or do a perfectly fit inlay, are you making that? Operating these still takes quite a bit of knowledge and skill, but different knowledge and skill from hand woodworking. What if the tools improve and become very easy to operate?
I don't think there's a hard line you can draw. But if there is, it's somewhere between "did everything by hand with no assistance from recently invented tools because those are cheating" and "ordered a sandwich and waited for the finished result to show up."
Both of the examples the parent gave include some kind of planning and ideating to get to a final product, regardless of the fact that they employed tools to do a bulk of the coding work.
In your analogy, what I’m talking about is more like talking to a chef with the idea of a novel recipe and describing the ingredients and how you would like it to taste (of course also accepting suggestions).
I would take more pride in that meal than in a standard burger I completely cooked myself - maybe because I know I am able to prepare a great tasting burger and already did so many times. OTOH if this would be the first burger I made in my life I would be immensely proud of it.
If anything, I would say your conclusion should be flipped: you didn't really do the "making," but you can still be proud of what you _did_ do: provide direction and a vision for a solution to a problem.
I ask 10 actors for 10 scenes and I combine them into a movie I wanted.
I ask 10 agents for 10 functions and I combine them into a program I wanted.
What's the difference and why is the guy who used agents not credited the same way as a director? Maybe all that's missing is a long list of credits for everyone involved -- so transparency in who did what?
This became more relevant to me when I began meeting producers as a software engineer in game development.
You didn't make it
You can be proud of having commissioned a thing… be it landscaping or software… just not for making anything you didn’t.
And of course there are shades of grey in between, depending on how critical you were to the doing.
I can hire a maid to make my bed for me and tell her how exactly to fluff my pillows and duvet but I would take no pride in that.
Aw, now I feel sad for you. It's definitely possible, and I do it every weekend.
Given that a compiler doesn't include a statistical model likely to create one's written Rust code, the compiled bytecode is quite clearly an expression of said writing.
That's different from telling a maid to generally clean your home. If you gave a maid specific instructions on how to clean and how to move things around in a way that made a noticeable impact on how clean your house ended up being, you could be proud of the managerial work you're doing. But no one does that, because people pay money to not have to work.
Likewise, if you just told an LLM to let it rip on a general task then you're not doing much work, but if you were managing the LLM to do specific things then you are doing significant work.
Article does take a stance on the term "making" vs "having a hand in creation" fwiw. I guess the latter doesn't have a great term yet which is why an argument over the term making is sincere
Maybe the sense of alienation people are experiencing right now is because code is the one concrete thing they drive which is "independent" from this social matrix. Most of the real value I've ever delivered doing this SWE thing wasn't through code, it was through understanding the system, recognizing issues, and working with leadership on addressing them
The joy of hackernews was seeing applied human ingenuity, most of these weren’t successful products anyway. Just like I don’t watch computer chess games, we should have an easy way to distinguish AI generated software, art etc and then I can happily avoid them.
Where i've felt lacking for the last ~5 years though is output. Specifically blocked by having the energy to create all these damn ideas.
I find LLMs neat, albeit their own type of exhausting, as they open up a lot of possibilities for things i want. Ie software i've wanted but have never cared to find the time for or didn't have the time for.
LLMs feel like a software equivalent to a 3D Printer. I don't have to carve it out of wood now. But also like a 3D printer there are some tasks that LLMs are just horrible for. So it's a niche, a skill even, to find software you want that also are a good for for unsupervised development. It's also of course massively more risky than a 3D printed doohickey depending on its internet access/etc.
With that said i still don't really take pride in something vibe coded. I just take enjoyment out of using a thing that i've wanted but never had time for.
For me the difference is in the extent that I can reason about how changes in the input affect the observable behavior of the output. When the executable the compiler outputs doesn’t behave in the way I intended, then in 99.99% of cases this is completely on me, and, importantly, I could have predicted it from the source code. Conversely, I can analyze any such misbehavior by reasoning on the source code. This doesn’t hold to any remotely comparable extent for the relation between vibecoded programs and the prompts used to create them.
I think for tasks that are about decisions, having the LLM make decisions is what makes it feel like the LLM did something for me.
Consider mowing the lawn. Imagine I had a lawnmower robot that does the mowing all on its own. Despite perfect accuracy, I didn't mow the lawn; it did. If I sit on that lawnmower the whole time and start driving it instead of letting it go on its own, then I mowed the lawn. Even if I stand there and control it with a joystick, I still mowed the lawn. Ownership comes from the decisions about where to mow.
This is analogous to the compiler example: It generally doesn’t matter which exact variation of machine instructions the compiler chooses to generate from the source code. It doesn’t significantly impact the ability to predict the resulting program’s behavior in detail based on the source code.
This predictability relation is what allows the creator to reason about the creation, to reason about which exact change to apply to the input to effect a precise modification in the output.
In that sense, the robot lawnmower is like a compiler, if it yields the state of lawn that I specified. I largely don’t care if it first moved left or right, the same as I largely don’t care if a compiler translates a multiplication by a power of two with a shift instruction or a multiplication instruction.
However, we use LLMs precisely for their heuristics, for their property to actually make material choices. Therefore LLMs inherently conflict with the ability to reason about which exact input will yield which desired output.
In making something, you develop a tangible understanding of and opinions for how and why your creation is how it is.
I have a lot of vibecoded projects. I feel "ownership" in varying degrees proportional to the amount of care and depth I put into them.
Some are ok with deciding if and when the process should be started and whether the outcome is good and bad. But often they lack the judgment to truly decide what is good and what is bad. They trust the makers to provide equally good options in terms of lower concerns (that matters to the makers) and only make the judgment according to some other concerns.
The main difference when using a compiler is that the compiler will (99.999...%) produce correct binary code for my programs and will fail loudly if it cannot. But the compiler is not concerned about correctness of the algorithm written in the programming language. Responsibilities are clearly outlined and the compiler does the job perfectly, while I try to do mine as well. So when I do a good job, I don't have to worry about the compiler part and I can assume the result will be good as well.
LLM usage has no such clear line. Assuming the user can judge whether the outcome is good or bad according to the prompt, the LLM tool is not reliable enough to produce a good result for everything that was not specified in the prompt. Which is different when collaborating with humans. If you say to a professional artist "I want a batman drawing", you needn't check for missing toes and the numbers of arms.
I usually do instantly lose respect when I hear some project is vibe coded... I get that's how it is now but yeah. To me when you say "I made this" but it's actually claude code that shat out the code well... ultimately though it's about money and freedom. You can do whatever you want to do, I need to get my own freedom then do what I enjoy.
Currently trying to figure out the right kind of caffeine intake, seems hot chocolate might be my jam vs. coffee. I'm lucky we have a gym at work so I work out first 30 minutes of the day helps and do walks.
I have to grind on the side though to get out as I have $100K in debt. That six fig day job still means I'm check to check.
Conversely, there are 100k+ LoC codebases from years ago that I can still generally walk through in my mind's eye
Sometimes I'm not interested in the inner workings of a technology, I just want a one-off tool. Ex: No interest in web tech. But, vibe-coded a tool to scrape and cross-reference a couple of online reports. Now I have the info I need for other projects.
Sometimes I know exactly what I want and it's quicker to hand-hold the AI through making it for me. Ex: Put together yet another SIMD math lib recently. SIMD intrisics are an obnoxious API. But, a non-SIMD implementation is easy to verify and many SIMD implementations are easy to validate vs. the non-SIMD reference. It's just a huge amount of obtuse code.
Sometimes I don't know exactly what I want and it's great to have a always-online partner to bounce questions off of, do rapid-prototyping for me, do code reviews for me. AIs aren't perfect. But, being instant, patient and often right makes them a huge improvement over online forums.
It was never about writing every line by hand, it was about solving a problem and making my life better. LLMs let me do that at a speed never seen before.
I was and am and avid Home Assistant fan but the number of automations/scripts I now have is higher by a magnitude than ever before. Few things would reach the level where it made sense to spend my time writing and debugging a workflow but now I can speak my automations into existence.
Yesterday I got a candle warmer, I wanted to set it up so when I turned it on it started a timer to turn off and I wanted a push notification to see if I wanted to extend the timer when it was close to finishing. All things I knew were possible but HA YAML is miserable (all YAML is) and the UI is not much better (it's a hard problem, I get it). I prompted Claude and had a working implementation in <10min. Additionally it asked if I wanted to auto-turn off if I left the house (yes!) and if it should auto-start the timer if ever detected the candle warmer was on without a timer set (power loss, HA restart, manual interaction with warmer).
My HA automations have never been more bulletproof and if they do something wrong it's as simple as telling Claude Code and having it fix the problem. For example, my motion activated lights (motion sensor -> HA -> smart switch) were working great but I realize that while in the shower my main bathroom lights would sometimes turn off. 1 prompt later and Claude grouped up my motion sensor in the shower to the one in the bathroom so if motion on either was detected the lights would stay on but the shower light would only turn on if its motion detector detected motion.
HA is only one small part of my LLM usage but it's representative of my overall point.
I made this argument yesterday that this is the real breakthrough for coding. Languages, syntax, frameworks, etc. no longer matters. ASM, Fortran, even punch cards are back on the menu if you're bold enough to prompt for it.
This is basically me. I still love having Claude build things for me, a lot of it is just things only I will ever use, but it fulfills my needs, and that's worth it for me.
I use it two ways I guess: to get unstuck while coding something myself, and to automate building side-projects I have no time for but that linger in my head for years.
The only thing being "redefined" is corporate agendas to push the bar of "good enough" lower to the point where it lies below cheap, and equals wasteful.
As a swe i've always enjoyed the process of designing solutions to problems: design a great architecture, find the right abstractions that make everything fit naturally, write good clean code, etc ... that's what i enjoy doing.
Now there's the part where i've had these ideas for years that i've always though that i'd be cool to work on. But basically it would have required a 10 person team for months, out of reach. Now i have Claude, Codex and Grok and i've already built many projects.
The code isn't pretty, i didn't enjoy it as much as i would have if it were done manually, but i did something i never could have done otherwise.
There's some fun in the process though. I feel like a team manager and i occasionally step in to push for some architectural changes or code rewrites because things become too brittle because of not good enough architecture.
> TLDR: I gain a lot of fulfillment by making things. I don't consider things built by others at my request to be made by me, and are therefore much less fulfilling. And then I feel sad. This article starts strong and then heads off into the weeds.
Secondly, maybe this conversations boils into: what level of abstraction are we comfortable working at?
I mean that to the tune of "To bake an apple pie, you must first create the universe".
Few people will create the universe (please introduce yourself, if you are one); some will buy the apples and the crust and put them together; some will make the crust from scratch; some will grow the apples from seed; some will follow a recipe; some will buy a frozen pie; some will simply buy the pie.
I think we can all agree that buying the pie is not baking it. But what about the others? To me, there's an argument that all of them are "baking the pie", just taking place at different levels of abstraction. And I think you can take pride in any of them, and hopefully more pride in whether the pie is delicious and well-shared.
Because I absolutely feel I made entire SaaS products, cool ones, by hand and they sat on a multitude of packages and infra I but glued together.
For frontend, I tailored templates, and instead put energy and time into making modern frontend toolchains and Django backends work together. This was satisfying to understand and build.
Being at ease with the minute details of Django or latest flags of esbuild felt like knowing the various modes of my Dewalt or Dewalt-colored power tools.
Building with AI is not a passive activity, and doing so well and efficiently, there is a ton to master and it evolved a great deal in the past six months.
So leveraging the tools using custom skills, custom CLIs, etc this is very important and very valuable thing to do. I would classify it as a serious contemporary computer science skill that should be taught in addition to the fundamentals.
Presume now, you're making and leveraging all of the modern bells and whistles of Claude Code and Codex. That is, you're reading the release notes and you have personal tooling so you can switch between them easily.
You can build incredible things with sustainable release workflows and reasonable security and possibly more than what a solo dev's "production quality" of yore.
I know this because I had Fable look at an entirely "hand crafted" SaaS I built over two years and it found about a page of bullets just in p0-p1 that I had not caught in my artisanal best effort. They were real issues, maybe unlikely but still things that I would have fixed if I had known.
But what can not be replaced is *taste*.
You can build all day and night and if it ain't good people won't use it. If you can't describe it in a way that makes sense to people they won't care.
If you build something people don't want you've not really made anything more than we did before we had AI as a tool.
I do think it can still achieve the same level of satisfaction if it is built well. Because it actually does take a lot of skill and knowledge to make something well using agentic programming. This is regardless of whether people want it.
Maybe a hot take, but I do think, that even from seasoned developers, the idea they've been doing the 'logical' part so long they'd have it done anyway without AI and it'd only take more time is delusional, when, from personal experience, even when I code something I 'know' and I've 'done', I have to remember stuff, google what isn't ingrained in my brain, and so on.
I don't know if the author would consider this a part of making, but a single thing you build is, obviously, a mix of things you've built. I no longer sense this minor feeling of 'making' when I'm doing something. To make a logic that's part of a bigger system and see it running, thinking how it's gonna be once it's all done... I no longer feel that.
I think there's a lot of parallel with experienced programmers using LLMs and that idea about steroids that it just gets you there faster. I'm pretty sure I could eventually program most of the things I've used AI to write, and what it produces at the top end I/you can't really prove that I wouldn't have thought of it. But is that really true?
Is his required knowledge of metals, assembly complexity, tolerances, just waved away because he doesn't turn the dials or change the tools any more?
To some degree, some folks esp. for "lights out" machining are just pushing buttons and loading/unloading pallets of stock/parts, but usually the job description for that is "machine operator".
A machinist is expected to understand feeds and speeds and how they interact with toolpaths and materials and tooling.
The big question of course will be how things fall out with the on-coming generation of 5-axis machines which are intended to be AI-driven:
https://toolguyd.com/new-ai-powered-desktop-cnc-machines-202...
Instead of saying "create instructions for CNC to make me a _thing_, then instruct the CNC machine to actually create the _thing_" they went and created the instructions themselves.
Yes. The CNC doesn't act on its own.
If I ask the CNC "make me a widget", am I a machinist?
It's the loss of understanding. When you make something, you gain a deeper appreciation for the nuance of all that is required to breath life into it. When you outsource understanding to another (agent, contractor, w/e), you're losing the nuanced understanding of the creation.
>After all, you create the prompts, don't you? You said you were proud of doing things. Isn't that doing a thing?
This feels like the difference between putting together an ikea futon and building a hand-hewn table from logs. The fidelity of your understanding is different depending on how deeply you're engaging. But not felling and drying your own timber doesn't mean you can never make something from dimensional lumber.
I'd take the author's word "making" to mean something more like "having enough understanding of the implementation of the task, that you could recreate the output without recourse to the same set of tools".
Tested against their examples:
>I had a new front deck put in [by a contractor]
As a consequence of this addition, did you learn enough about decks so that you could you reproduce this feat if no contractor were available? If no, you didn't make the deck. If yes, you were probably watching/helping the whole time, and you can claim (at least partial) makesmanship.
> any more than using a hammer to drive nails does.
If you didn't have access to the hammer, could you still accomplish the task of attaching two boards together with a nail? Likely yes, use a rock. It's harder, but the understanding of driving the nail is transferable to other implements.
> What if I had an AI-powered hammer and asked it to hit a nail for me? What's the difference? But at that point, I can't say that I hammered it.
This one contradicted his compiler example. He says that he did write the Fibonacci program, even if the AI-powered compiler translated it to assembly. So by similar reasoning, you can claim you hammered a nail with an AI hammer, so long as you understood the aspects of hammering which the AI took care for you to such a degree that you could reproduce the effects even in the absence of the AI hammer.
The crux of the tension is around "what did you learn from the implementation of this task". If you learned enough to reproduce the objective without the assistance of AI (perhaps much slower), then you can claim the high fidelity understanding that came from making. If you didn't internalize anything, and the AI/contractor managed complexity on your behalf, then the output was commissioned, not made.
I think where people get worked up about this, is that it's not easy to tell what understanding other folks are taking away from their AI usage. It does seem like a bifurcating event where some people are going to net gain understanding of their world due to these new tools, while others will net lose understanding.
In the code scenario, I most likely won't go over the final result: for various reasons, I often lack the interest and drive to understand the nuts and bolts of it. So I'll just try to assess whether it's sufficiently good for my goals, and then move on.
But in the circuit design scenario, I only use it as a "technical expert" to bounce ideas back and forth with, and to explore concepts I don't fully grasp. I use it as a sort of ELI5 machine, and never ever ask it to do something for me - just to explain.
The fundamental difference in outcome is that I remember next to nothing about the code, and have no feeling of "ownership" over it, nor do I feel proud or care about it at all.
Conversely, I am incredibly proud of the PCBs and circuits I design, even if technically some parts of it came straight out of AI recommendations. I really feel like I did the job, and AI was just a helper tool to get the tough concepts untangled quicker in my head.
Ultimately I think if you delegate 100% of the work to AI, and don't care enough to use its output to at least learn something, it's only natural that you'll never feel any connection to it, let alone any sense of ownership over its output. Being the prompt author is simply not enough. That's why I think you hit the nail on the head there: deeply understanding the output is the key, I just couldn't put my finger on it before, and now I can. Thanks for that.
Alongside understanding, you also loose taste and perception. You can still say whether some things is good or bad, especially if you interact with it, but you can no longer articulate why. And with perception loss, you can no longer preempt a bad situation as you lose your awareness of things.
So for you a car may be a vehicle that you drive around. But for a mechanics it's a much complex system. When something doesn't work, you will lack the vocabulary to express what's wrong. And even when everything works, you may not be able to explain how.
The thing is, LLM are very buggy translators. Agents in software development help because they provide a way for LLMs to verify their output. But correctness is very hard to express. OK for a simpler task, but not really for a complex systems. Just like fluency in a foreign language is not about knowing the rules of grammar and a lots of words, but also knowing the idioms and other figure of speech.