Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I am happier writing code by hand

abhinavomprakash.com

Post reply on HN
Print view View original

291–300 of 334 posts

Re: I am happier writing code by hand

#291

Post by coldtea »

Ygg2 wrote: post #287
coldtea wrote: post #207

> Yes, coding is not software engineering It absolutely is. > Even if I generate a 1,000 line PR in 30 minutes I still need to understand and review it. Since I am responsible for the code I ship, this makes me the bottleneck. You don't ship it, the AI does. You're just the middleman, a middleman they can eventually remove altogether. > Now, I would be lying if I said I didn’t use LLMs to generate code. I still use C…

> It absolutely is. It isn't. Coding is to software engineering, what calculation is to math. A necessary but insufficient condition. > And then soon the boss demands more output, like the guys who left it all to Claude and even run 5x in parallel give. You can get 100x output for 1/100x the price, if you replace the monthly Claude subscription with a Markov chain. Think of the efficiency gains. Sure, it will be garb…

>It isn't. Coding is to software engineering, what calculation is to math. A necessary but insufficient condition.

It is that, but to Computer Science, its lofty academic cousin.

To Software Engineering coding is an essential part.

Re: I am happier writing code by hand

#292

Post by hintymad »

woeirua wrote: post #5

This is no different then carpentry. Yes, all furniture can now be built by machines. Some people still choose to build it by hand. Does that make them less productive? Yes. Will they ever carve furniture by hand for a business? Probably not. Can they still enjoy the act of working with the wood? Yes. If you want to code by hand, then do it! No one's stopping you. But we shouldn't pretend that you will be able to do…

Maybe a better question is: Is natural language to code what high-level programming is to hand-written assembly? Brooks claims the "essential complexity" lies in the specification: if a spec is precise enough to be executable, it’s just code by another name. But is the gap actually that large today? When I ask for a "centered 3x3 Tailwind grid", the patterns are so standardized that the ambiguity nearly vanishes. It’s like asking for a Java 8 main method. The implementation is so predictable that the intent and the code are one and the same. Or using jargons, most of the coding has a strong prior that leads to predictable posterior.

The key question now is: how far can AI go? It started with simple auto-completion, but as AI absorbs more procedural know-how, it becomes capable of generating increasingly larger chunks of maintainable code. Perhaps we are reaching a point where established patterns are so well-understood that AI can bridge the gap between a vague intent and a working system, effectively automating away what Brooks once considered essential complexity.

In the long run, this probably makes experts more valuable, but it’ll gut the demand for standard engineers. So much of our market value is currently tied to how hard it is to transfer expertise among humans. AI renders that bottleneck moot. Once the know-how is commoditized, the only thing left is the what and why.

Re: I am happier writing code by hand

#293

Post by wiredpancake »

krupan wrote: post #99
neversupervised wrote: post #27

Dev happiness is not the determining factor of how software will be written at scale

If you think unhappy devs are going to produce anything good then please let me know the stock ticker of your company so I can short it

[dead]

Re: I am happier writing code by hand

#295

Post by agentultra »

zemvpferreira wrote: post #288
agentultra wrote: post #285

Earlier quoted context omitted.

I haven’t worked in a furniture factory but I have assembled car seats in a factory for Toyota. The difference matters because the people who worked together to smash the looms created the myth of Ned Ludd to protect their identities from persecution. They used organized violence because they had no leverage otherwise to demand fair wages, safety guarantees, and other labour protections. What they were fighting for w…

We agree, which makes me question your original point with the power tool somehow being different even more. Every automation gives more leverage to capital over labour. That's the history of technology. Downstream it makes this great life with indoor plumbing etc possible but automation in any form will always erode skilled labourers as a class. It's all essentially the same in that regard.

The introduction of looms wasn’t what displaced workers.

It was capitalists seeking profits by reducing the power of labour to negotiate.

We didn’t mass layoff carpenters once we had power tools and automation.

We had more carpenters.

Just like we had more programmers once we invented compilers and higher level languages.

LLMs just aren’t like power tools. Most programming tools aren’t like power tools.

Programming languages might be close to being “power tools,” as they fit in the “centaur” category. I could write the assembly by hand or write the bash scripts that deploy my VMs in the cloud. But instead I can write a program, give it to a compiler, and it will generate the code for me.

LLM generated code fits in the reverse-centaur category. I’m giving it instructions and context but I’m not doing the work. It is. My labour is to feed the machine and deliver its output. If there was a way to remove me from that loop, you bet I’d be out of a job in a heartbeat.

Re: I am happier writing code by hand

#296

Post by vdfs »

chasd00 wrote: post #91
acedTrex wrote: post #6

I will do what i know gives me the best possible and fastest outcome over the long term, 5-10 year period. And that remains largely neovim and by hand. The process of typing code gives me a deeper understanding of the project that lets me deliver future features FASTER. I'm fundamentally convinced that my investment into deep long term grokking of a project will allow me to surpass primarily LLM projects over the lon…

This is the way. I think we’re in for some rough years at first but then what you described will settle in to the “best practice” (I hate that term). I look forward to the really bizarre bugs and incidents that make the news in the next 2-3 years. …Well as long as they’re not from my teams hah :)

> really bizarre bugs and incidents that make the news in the next 2-3 years

I take it that you are not using Windows 11

Re: I am happier writing code by hand

#297

Post by krackers »

nijave wrote: post #266
freeopinion wrote: post #59

I think it is pretty indisputable that there is a valuable place for AI. I recently had to interact with a very horrible db schema. The best approach I came up with to solve my challenge involved modelling a table with 300 columns. Converting some sql ddl to a Rust struct was simple but tedious work. A prompt with less than 15 words guided an AI to produce the 900+ loc for me. It took a couple seconds to scan it to s…

It's still possible to script out codegen. Frequently use Python to generate code like that. Really I'd rather have AI generate a codegen script that deterministically does the struct from schema generation I've had enough instances where it's slid in a subtle change like adding "ing" to a field name to not fully trust it

Yup, it feels weird to use LLMs to perform large scale refactors, but LLMs to meta-codegen which you then use to do the refactor works really well. The quality of the generated tool itself doesn't matter so long as it's deterministic and you can reasonably see what it's doing. It the same vein it works nicely for random one-off parsers (either DSL parsing or abstractly as screen scraping): nothing you'd be robustly confident in, but good for throwaway parsing.

Re: I am happier writing code by hand

#298

Post by krackers »

throw7272855 wrote: post #209

Coding with AI falls in one of three categories: 1. The thing to be written is available online. AI is a search engine to find it, maybe also translate it to the language of choice. 2. The thing (system or component or function) is genuinely new. The spec has to be very precise and the AI is just doing the typing. This is, at best working around syntax issues, such as some hard-to-remember particular SQL syntax or so…

There's another category (possibly a subset of 1), the implementation is novel but set of requirements is known and has a set of conformance tests so tight that the LLM can basically brute force its way to a solution. See e.g. the Claude Compiler thing. In this case it's less "search engine + translator" and more of "brute force search".

Re: I am happier writing code by hand

#299

Post by krackers »

pdimitar wrote: post #205
askonomm wrote: post #193

Seems like the author has a case of all or nothing. The real power in agentic programming, to me, is not in extremes, but in that you are still actively present. You don't give it world-size things to do, but byte-sized, and you constantly steer it. It's to be detailed enough to produce quality, and to be aware of everything it produces, but not so detailed that it makes sense to just write the code yourself. It's a…

I am with you and fully agree with your "it does not have to be an all or nothing" stance. A remark on one part of your comment: > What are you adding to the mix here? Your prompting skills? The answer to that is an unironic and dead-serious "yes!". My colleagues use Claude Opus and it does an okay job but misses important things occasionally. I've had one 18-hour session with it and fixed 3 serious but subtle and di…

> unless the LLM companies manage to make another big leap.

Why is it a big leap? If the behavior you want can already be elicited by models just with the right level prompting, it's something that can be trained toward. As a simple mental model you could for instance imagine training a verifier-type model of Claude that given a problem spits out a prompt detailing "its success criteria, never to delete tests, never to relax requirements X & Y & Z, always to use this exact feedback loop when testing after it iterated on a fix, and a bunch of others." Also things like specific feedback loop or agentic harnesses will also end up being trained in, similar to how Claude is specifically trained for use with Claude Code.

Thinking of "prompt engineering" as a skill is a fools game, these are language models after all. Do you really think you will hold an advantage over them in your ability to phrase things?

Re: I am happier writing code by hand

#300

Post by kcexn »

agentultra wrote: post #81
woeirua wrote: post #5

This is no different then carpentry. Yes, all furniture can now be built by machines. Some people still choose to build it by hand. Does that make them less productive? Yes. Will they ever carve furniture by hand for a business? Probably not. Can they still enjoy the act of working with the wood? Yes. If you want to code by hand, then do it! No one's stopping you. But we shouldn't pretend that you will be able to do…

I’ve heard this metaphor before and I don’t think it works well. For one, a power tool like a bandsaw is a centaur technology. I, the human, am the top half of the centaur. The tool drives around doing what I tell it to do and helping me to do the task faster (or at all in some cases). A GenAI tool is a reverse-centaur technology. The algorithm does almost all of the work. I’m the bottom half of the centaur helping t…

Maybe. I'm not sure its that different though? If one person can do the work of two because of power tools, then why keep both? Same with AI. How people feel about it doesn't seem relevant.

Maybe the right example is the role of tractors in agriculture. Prior to tractors you had lots of people do the work, or maybe animals. But tractors and engines eliminate a whole class of labor. You could still till a field by hand or with a horse if you want, but it's probably not commercially viable.

Post reply on HN