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

I'm going back to writing code by hand

blog.k10s.dev

Post reply on HN
Print view View original

401–410 of 656 posts

Re: I'm going back to writing code by hand

#401

Post by hatefulmoron »

linuxftw wrote: post #388
hatefulmoron wrote: post #381

Earlier quoted context omitted.

Plan mode improves results, but it doesn't solve the underlying problems. Pretty often Claude Opus 4.7 on xhigh will formulate a reasonable enough plan, churn for a while, then come back with a summary that it didn't stick to the plan because it wasn't accurate. Worse, the disclaimer is buried under a bunch of "did X, did Y on line Z of file a/b/c", as if it's just a minor inconvenience. To the extent the plan was in…

You have to review the plan and fill in any missing gaps or correct anything that's wrong. Plan mode often isn't one shot, it might take a few iterations, but once the plan is nailed down, the results are usually very good.

You're right. I think having it spawn lots of subagents, read everything, formulate a big and detailed plan, only for it to be subtly wrong while requiring me to carefully review the result and the intermediate plans that produced it is quite tiring. I suppose things slip through.

Re: I'm going back to writing code by hand

#402

Post by sevenzero »

hansmayer wrote: post #382
sevenzero wrote: post #351

Earlier quoted context omitted.

> I wonder why? Because I like to save time?

...which means you depend on the LLMs? Of course strictly "to save time". It's not like you are slowly forgetting how to start a project in the first palce or implement that db integration, right?

LOL why would I ever forget how to start a project or how to connect to a DB or make migrations and whatnot, brother generating a web form for creating and updating models is not that big of a deal. A LLM can do this while providing a11y attributes and proper styling in like 10 minutes. This includes creating a migration which I take a look at and correct if needed, creating the model, creating required policies, creating the controller endpoints which i correct in case its needed, creating a template file for the crud operations with search and pagination and whatnot while making it somewhat look good.

I can do all of this myself, but why would I waste 1-2 hours (per model) on doing all that myself if I can just instruct some stupid LLM to do it for me? It's repetitive boilerplate.

Re: I'm going back to writing code by hand

#403

Post by pron »

linuxftw wrote: post #340
pron wrote: post #192

Yep. The only people I've heard saying that generated code is fine are those who don't read it. The problem is that the mitigations offered in the article also don't work for long. When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it’s small, like the selection of a data structure. You can tell the agent what the…

Try plan mode. The problems you're speaking about are already solved.

They are nowhere near solved. Agents make serious mistakes in judgment and do it frequently enough to threaten the viability of the codebase unless you slow down and monitor them very, very closely. If you do that, it's all good. If you're not, your codebase is rotting at a superhuman speed underneath you and you have no idea until it collapses.

Re: I'm going back to writing code by hand

#404

Post by famouswaffles »

imtringued wrote: post #160
brabel wrote: post #103

Earlier quoted context omitted.

I was trying to follow similar rules, until one day I had to solve a hard mathematical problem. Claude is a phd level mathematician, I am not. I, however, know exactly the properties of the desired solution and how to test it’s correct. So I decided to keep Claude’s solution over my basic, naive one. I mentioned that in the pull request and everyone agreed that was the right call. Would you open exceptions like that…

You do realize you can ask Claude about the things you don't understand? "PhD level" just means you finished a bachelor and masters degree and are now doing a bit of original research as an employed research assistant. Claude isn't "PhD level" anything. This shows a complete lack of understanding here. Claude has read every single text book in existence, so it can surface knowledge locked away in book chapters that p…

Man people really overestimate training. Claude did not 'read' any of that either. I wish frontier models behaved like people that had read and remembered everything they've trained on, but they're not.

Re: I'm going back to writing code by hand

#405

Post by zephen »

black_knight wrote: post #288
sirwhinesalot wrote: post #277

Earlier quoted context omitted.

This is actually what I do. I'm extremely picky about the code and force the LLM to rewrite it 1000x times until it is basically exactly what I want. You might be wondering what is the point when it would be faster for me to just write the code myself? I have ADHD and for whatever reason telling the LLM what to do instead of doing it myself bypasses the task avoidance patterns and/or focus problems I tend to suffer f…

I have used LLMs a couple of times to get started on something. I don’t have ADHD, so this is not a regular occurrence for me. But when I have tried this, I have always found the LLM solution so horrible that it instantly inspired me to do it myself. So, in that sense it worked, I got unstuck, but no LLM garbage makes it into the project.

Even pre-AI, when working with slop generated by other humans, starting with something was often better than staring at a blank screen.

Re: I'm going back to writing code by hand

#406

Post by contagiousflow »

jstummbillig wrote: post #303
raincole wrote: post #290

Earlier quoted context omitted.

The "people" in your hypothetical story have been wrong the whole time. The correct attitude is: When AI can complete lines, you still have to read and understand the code. When AI can complete whole functions, you still have to read and understand the code. When AI can complete features and tickets, you still have to read and understand the code.

Not at all. Code is not important, intent is. The leader of a product/company does not have to read code. It doesn't matter if it is generated by humans or non-humans. It simply needs to be correct enough to be usable and then steerable towards better outcomes. Understanding of code never existed from the business perspective.

Can you think of a good way to encode intent into a system?

Re: I'm going back to writing code by hand

#407

Post by wiseowise »

djeastm wrote: post #275

When it was Copilot tab-completing lines, people would say, "yea, but you still have to make sure you're the one writing the whole functions". Then when it was completing functions, people would say, "yeah, but you still have to make sure you're the one writing the logic around the functions" Then when it was completing the logic around the functions, people would say, "yeah, but you still have to make sure you're th…

> but it is interesting watching the expectations moving over time.

While the salary stays stagnant or even reduced if you adjust for inflation.

Re: I'm going back to writing code by hand

#408

Post by zephen »

pron wrote: post #192

Yep. The only people I've heard saying that generated code is fine are those who don't read it. The problem is that the mitigations offered in the article also don't work for long. When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it’s small, like the selection of a data structure. You can tell the agent what the…

> What I've seen is that if you define the architectural constraints, the agent writes complex, unmaintainable code...

To be fair, there are many people like this as well. One of my personal favorite examples was way back in the 80s when I inherited the code for a protocol converter that let ASCII terminals communicate with IBM mainframes via the 3270 protocol.

One of the pieces of code in there, for managing indicator lights, was simply wrong. It was ca. 150 lines of Z80 assembly language that was trying to faithfully follow the copious IBM documentation of how things worked, but it had subtle issues and didn't always work.

My approach was to accept the documentation as accurate (the IBM documentation was always verbose and almost never wrong), but to reason that the original 3270 had these functions implemented in TTL logic gates, and there was no way in heck that they were wasting enough gates on indicator lights to require the logical equivalent of 150 instructions.

So in my mind, it had to be a really simple circuit that had emergent properties that required the reams of documentation. With that mindset, I was able to craft correct code for this in 12 instructions.

Many systems are likewise fractal in nature. You want to figure out the generating equations, rather than all the rules that derive from those. And, in many cases, writing down the generating equations is at least as easy to do in code as it would be to do in English for someone or something else to implement.

Re: I'm going back to writing code by hand

#409

Post by esafak »

gylterud wrote: post #283
forgotaccount3 wrote: post #269

Earlier quoted context omitted.

> you need to micro-manage it. It is significantly easier to micro-manage an AI than a suite of junior developers. The AI doesn't replace a principal engineer, it's replacing junior and weaker senior developers who need stories broken down extremely concisely to be able to get anything done. The time it takes to break down a story such that a junior through weak senior developers can pick it up and execute it well wo…

Juniors learn. Some juniors are potential good seniors. Over time they will internalise good architecture and be able to make good judgments on their own. Micromanaging LLMs is like having Dory from Finding Nemo as your colleague. You find ways to communicate, but there is no learning going on.

Juniors don't always learn.

Re: I'm going back to writing code by hand

#410

Post by IanCal »

yakshaving_jgt wrote: post #169
meetingthrower wrote: post #162

Earlier quoted context omitted.

So right. All these guys have never been managers. Do you think humans don't write things that break? Or that teams sometimes take a wrong path and burn a week of work? Or months? Well now you can experience all of that in 30 minutes of vibecoding. As a former tech product manager, it feels EXACTLY the same.

Except it isn't the same because the cost is different, which allows discovery that we couldn't afford previously.

Yes, lots of the process and problems and solutions to them are the same but we’ve just massively cut the cost of a part of development. That has huge ramifications about when it makes sense to tackle different things and how tradeoffs work out.

Was it strongdm talking about the dark factories? They were working on some integration software so needed to use google drive and slack and lots of other things. They fully reimplemented those to the level they needed for their tests - outside of the biggest firms this would probably have been an enormous time and money sink. Now it’s reasonable.

On a personal project, with my wife we wanted a tracker for holiday planning. Five minutes given a barely through through request and we had a working prototype, fixed bugs in seconds and then talked through with a model what we needed and how it did or didn’t fit (and we needed that first version to figure that out). It helped drive out actual requirements from us, prioritise them, choose a stack add tickets and then went ahead and implemented it pretty far. Have a mostly working v2 which has highlighted some details about what we really wanted. Total invested cost was one day of a $20 subscription and maybe half an hour of talking to a bot and checking results.

Post reply on HN