We write code by hand

We write code by hand handcraftedcode.org

We use Natural Intelligence to build software libraries and applications in production today. Some of them you may be using right now.

42 points•batmang•9 days ago•71 comments•

#code #hand #write #write code #libraries #intelligence #software #natural

71 comments

gravypod9 days ago

I feel like I have gone from 100% hand written code -> 0% hand written -> 50% and climbing.

I think there are things LLMs are really good at coding up and experimenting with but I think there's still a need to understand the btoader context of your software so you need to dive in at some point.

dimonomid9 days ago

It's very important to understand what's happening, sure. Blindly shipping AI-produced code without understanding is just irresponsible. But how does writing code helps with that? Reading helps a lot, but writing just slows things down in my experience so far.

tripledry9 days ago

I compare it to math, you can't learn it by reading it you need exercises. Same thing, reading is not sufficient. Just my experience.

bluefirebrand9 days ago

You can't learn what good code is by reading it, you have to write code to learn what good code looks like

gravypod9 days ago

LLMs will make tradeoffs without consulting you. This is sometimes a feature and often a bug. Many times a decision made up front can have non obvious implications down the line. This is one of the biggest values I bring to be table as a more experienced swe.

I think if I fully understand everything the agent is going to do and trivially verify the output quality, LLMs are a win. For one off prototypes, the same is true. For software which is unique, complex, and performing a task which has not been fully specified I find myself needing to drop into my editor more and more.

Recently I've been moved to a research focused team and I really need to have proof that something is happening. I've had Claude Opus 5 gaslight me by telling me it did something and when I read the code it obviously did not. This happens more and more with my tasks that are kind of complex.

I've found a lot of the claims by AI people have been 6mo - 2 years "ahead" of my experience. I think we are now in an era where harness engineering is highly valuable (making a test, looping an agent, manually annealing with new ideas) but the claims that no one writes code manually seems like it may not be fully there for all code.

arcrae9 days ago

I had a similar experience but I'm closer to 95-99% hand written again now. I still use AI for reviewing and prototyping, but it feels like writing the code myself is the best way to actually know what's going on.

ghthor9 days ago

I like to write the edges between modules, because that’s easier than prompting. Think interfaces, or public func signatures.

velcrovan9 days ago

The language here means that signers are affirming that they continue to write at least some code by hand, not that they never use AI tools for coding. I'm not sure that's enough virtue to deserve its own signal.

edit to add: the irony of the grammatical error in this presumably hand-written sentence inside the "Who's behind this?" link:

> Jared’s web studio Whitefusion is currently partnering with quality businesses & organizations which believe in staying away from costly hype cycles and the value of the human touch.

abnercoimbre9 days ago

Self-plug but Handmade Cities [0] is grassroots organizing that prefers not to spend its time with stuff like this.

Join a local meetup!

[0] https://handmadecities.com

gottagocode9 days ago

I began programming as means to express myself artistically, but over time, it became more of a way to value myself instead. AI is helping me get back to the former, and with that I have peace.

__alias9 days ago

I like this sentiment. It's the same I share as well.

dimonomid9 days ago

To me, literally writing code by hand instead of letting AI do it feels like digging a foundation pit with a shovel instead of letting an excavator do it. Sure it can be done but much slower and the benefits are questionable. But curious if you have reasons to believe otherwise?

bluGill9 days ago

Every excavator crew I've seen has a shovel on the truck. They sometimes pull it out of the truck and use it. Most of the time though you can get the excavator there and get the job done faster than any hand work.

The most common use for a shovel seems to be "this is as close as I dare get to the wire we know is around here - scrape the dirt away until you find it and then I'll dig the rest out."

dimonomid9 days ago

Yeah a small amount of manually-written code still makes sense, when it's faster to write it than to tell LLM to write it.

In particular comments. I'm not a fan of the comment style LLM tends to write, so I often just write them manually.

And also coming up with the right architecture is also often manual job. Design how to implement things, and let LLM implement it.

alerighi9 days ago

It's not the same example, the excavator is driven by a human being, it's a tool (in coding world the same as using an high level programming language instead of writing bits into the computer memory).

The LLM *may* be used as a mere tool, that is something you ask question time to time, but shouldn't be the thing that makes the work that you should do. Because if we arrive at this point (hopefully never) at that point the CEO of the tech companies may as well say, why we still need developers? Let's fire all of them.

Fortunately they did not, because there is STILL VALUE in writing code by hand, understanding what it happens, what the code will do, etc. I hope this will not be a lost skill, or well, if it does good for me, because the same as nowadays things being able to repair electronic devices makes a ton of money (I've considered opening a repair shop) because there is no one still doing it, will do programmers that well, know how to program.

dimonomid9 days ago

Yes, LLM is a tool. And CEOs of the tech companies are retaining developers not because there is value in writing code by hand, it's because developers can use that tool effectively and responsibly: they can tell bad code from good code, they design the solution, let AI do the hard boring work of coding it out, then these developers check its output, test it, also they can be creative and e.g. ask LLM to review LLM's output, etc etc.

But the need to manually type stuff out arises very infrequently in my experience. It happens but it's an exception, not the rule.

swatcoder9 days ago

If your work is analogous to digging a foundation pit or something like framing up homes in a development, that makes a lot of sense. But that's not the only kind of work many of us do, and analogies to things like finish carpentry, functional sculpture, or fine furniture are more applicable. Hand craft doesn't always make a difference, but there's plenty of places where it does.

Plus, for a lot of people with fluency and experience, it's simply more fun/natural and not meaningfully less productive.

greggoB9 days ago

Genuine question: do you feel this disparity despite being diligent and checking the LLM's output, or is that not factored in?

It's also been my experience that generating an entire app/portion of code can be much easier by typing out a relatively concise prompt, but this only applies if it's the kind of code I'm

1) free from having to verify afterwards,

2) not having to fight with the LLM to get right, or

3) is coming from someone else in the form of a PR that may/may not have been checked by them first.

Having to deal with these cases has sometimes been the equivalent of using a spoon to dig a foundation, at least in my experience.

dimonomid9 days ago

Of course checking the LLM's output and testing it and iterating on it is factored in. And yeah that verification and testing and iteration where most of the time goes, and still it ends up being significantly faster than typing everything manually, and the end result quality is often higher I believe.

To avoid fighting with the LLM to get right, it's useful to first come up with the architecture manually, run it by the LLM first (without writing any code - just talking to it, asking it to find flaws in your architecture), and once both you and LLM are happy with the plan, fire it to execute. This step removes a lot of friction (but not all of it - later iterations are still almost always necessary)

pydry9 days ago

This is a pretty good metaphor to explain why there is so much unmaintainable slop around these days.

foolfoolz9 days ago

if you write a prompt, and see the code and edit it by writing another prompt, you the human wrote that code. you may not have typed the keyboard for each character in the code. but the llm did not write it all for you. this is the same as a pair programmer, 2 authors

jiwidi9 days ago

big agree here.

People dont seem to realize prompt to code is just another interface. Is the human review part that we should care about, did this code get reviewed and reiterated on? Is it fully AI generated and reviewed?

Those are the important tasks.

Whoever feels like a better programmer because they write all the terraform files by hand and not use an llm, dislike.

zabriel_goss9 days ago

The difference between Vibe coding and AI-assisted coding. There is a gradation!

Read the full thread on Hacker News →

71 comments

Related stories