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

I’m spending months coding the old way

miguelconner.substack.com

Post reply on HN
Print view View original

201–210 of 387 posts

Re: I’m spending months coding the old way

#201

Post by spockz »

apricot wrote: post #86

I am this very term teaching 18-year-old students 6502 assembly programming using an emulated Apple II Plus. They've had intro to Python, data structures, and OO programming courses using a modern programming environment. Now, they are programming a chip from the seventies using an editor/assembler that was written in 1983 and has a line editor, not a full-screen one. We had a total of 10 hours of class + lab where I…

One of my favourite experiences coming up as an engineer was working with a very senior engineer right in the beginning. Whenever he had a task or problem, he would start out thinking, maybe doodling a bit on paper, go for a walk, and only then sit down at his computer and start typing. He would type in one go only compiling in the end, and it would work. (Even typos were rare.)

All this to say that it is extremely useful to have the program and the problem space in your head and to be able to reason about it before hand. It makes it clearer what you expect and easier to catch when something unexpected happens.

Re: I’m spending months coding the old way

#202

Post by sixtyj »

apricot wrote: post #86

I am this very term teaching 18-year-old students 6502 assembly programming using an emulated Apple II Plus. They've had intro to Python, data structures, and OO programming courses using a modern programming environment. Now, they are programming a chip from the seventies using an editor/assembler that was written in 1983 and has a line editor, not a full-screen one. We had a total of 10 hours of class + lab where I…

I thought it was common practice to think things through first and only then start doing something, but it seems that these days a lot of people have taken inspiration from Zuckerberg’s motto, “move fast and break things”… I’ll never forget that.

Re: I’m spending months coding the old way

#203

Post by BodyCulture »

usernametaken29 wrote: post #73
LeCompteSftware wrote: post #21

This is ominous and very depressing given what we've recently learned / reconfirmed about LLMs sapping our ability to persist through difficult problems: > There were 2 or 3 bugs that stumped me, and after 20 min or so of debugging I asked Claude for some advice. But most of the debugging was by hand! Twenty whole minutes. Us old-timers (I am 39) are chortling. I am not trying to knock the author specifically. But he…

I’ve worked in financial modelling before where you need to make sure results are correct, not approximate. One time there was a nasty bug in pandas multiindexes (admittedly we banned pandas for all new code because it just can’t do semver). Spent 9 days to debug three lines of code. Endurance and patience are learned skills and sometimes they’re the only way you can get a correct verifiable solution.

What are you using instead of pandas? Thanks!

Re: I’m spending months coding the old way

#204

Post by deaux »

brianush1 wrote: post #158
phaser wrote: post #36

Here’s how i do it: I create a lot of stuff using AI to the max, but I also spend the necessary of time on reviewing that the AI is producing code that passes my cognitive load standards. this involves some tokens spent on grooming code and documenting well. Most of this is effortless thanks to an AGENTS.md based on this: https://github.com/zakirullin/cognitive-load/blob/main/READM... but i have a good sense of catch…

> Don’t abuse DRY, a little duplication is better than unnecessary dependencies. That's an interesting thing to include. I agree with this point in principle, but I've found that Claude, at least, duplicates logic FAR too often and needs nudging in the other direction.

> but I've found that Claude, at least

You hit on a very important point here. The linked AGENTS.md is a bad idea for general purpose use because the things it's meant to tackle, including an inherent bias towards or against DRY, is one of the big differences between model families. GPT 5.4 Codex has a very different "coding personality" from Claude Opus.

It's a product of whatever model it was tested on.

Re: I’m spending months coding the old way

#205

Post by otabdeveloper4 »

heyalexhsu wrote: post #144
AstroBen wrote: post #45

I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).

I can see the logic behind "manual coding" but it feels like driving across country vs taking the airplane. Once I've taken the airplane once, its so hard to go back...

Real life measurements show a 25 percent improvement in coding speed when using AI at best. And this is before you take technical debt into account!

Yes, AI unlocks coding for people who fail FizzBuzz. This isn't really relevant to making software though.

Re: I’m spending months coding the old way

#206

Post by oneeyedpigeon »

heyalexhsu wrote: post #144
AstroBen wrote: post #45

I wish more was being invested in AI autocomplete workflows. That was a nice middle-ground. But yeah my hunch is "the old way" - although not sure we can even call it that - is likely still on par with an "agentic" workflow if you view it through a wider lens. You retain much better knowledge of the codebase. You improve your understanding over coding concepts (active recall is far stronger than passive recognition).

I can see the logic behind "manual coding" but it feels like driving across country vs taking the airplane. Once I've taken the airplane once, its so hard to go back...

Airplanes are good for certain types of journey, but they're vastly inefficient for almost all of them.

Re: I’m spending months coding the old way

#207

Post by lionkor »

bdangubic wrote: post #150
fouronnes3 wrote: post #148

Earlier quoted context omitted.

I've had a lot of enjoyment flipping the agentic workflow around: code manually and ask the agent for code review. Keeps my coding skills and knowledge of the codebase sharp, and catches bugs before I commit them!

if it catches a lot of bugs maybe you’d be better of letting it write it in the first place :)

It also writes lots of bugs which it'll catch some of, in an independent review chat.

This is bogus. If you think LLMs write less buggy software, you haven't worked with seriously capable engineers. And now, of course, everyone can become such an engineer if they put in the effort to learn.

But why not just use the AI? Because you can still use the AI once you're seriously good.

Re: I’m spending months coding the old way

#208

Post by jb1991 »

bdangubic wrote: post #150
fouronnes3 wrote: post #148

Earlier quoted context omitted.

I've had a lot of enjoyment flipping the agentic workflow around: code manually and ask the agent for code review. Keeps my coding skills and knowledge of the codebase sharp, and catches bugs before I commit them!

if it catches a lot of bugs maybe you’d be better of letting it write it in the first place :)

This is definitely not correct in my opinion. You’re essentially saying, instead of a person actually getting better at the craft, just give up and let someone else do it.

Re: I’m spending months coding the old way

#210

Post by neonstatic »

stringfood wrote: post #192
neonstatic wrote: post #189

Earlier quoted context omitted.

> It sounds weird but it’s a form of teamwork. I can't do it. If I let an LLM write code for me, that code is untouchable. I see it as a black box, that I will categorically refuse to open. If it works, I use it, but don't trust it. If it breaks, I get frustrated. The only way that works for me is me behind the driving wheel at all times and an LLM as an assistant that answers my questions. We either brainstorm somet…

but demanding to be behind the wheel and understand all the code will affect velocity compared to other teams that are utilizing AI to the max

What good is "velocity" if no-one understands the direction we are going and how we are going? Sounds like a recipe for disaster.
Post reply on HN