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

Ask HN: How are you LLM-coding in an established code base?

news.ycombinator.com

Post reply on HN
Print view View original

61–69 of 69 posts

Re: Ask HN: How are you LLM-coding in an established code base?

#61

Post by wrs »

mattmanser wrote: post #48
lukevp wrote: post #26

Earlier quoted context omitted.

One thing I think people confuse with context is they see an LLM has say 400k context and think their codebase is way bigger than that, how can it possibly work. Well, do you hold a 10 million line codebase in your head at once? Of course not. You have an intuitive grasp of how the system is built and laid out, and some general names of things, and before you make a change, you might search through the codebase for s…

Yes, I do have a map of the code in my head of any code base I work on. I know where most of the files are of the main code paths and if you describe the symptoms of a bug I can often tell you the method or even the line that's probably causing it if it's a 'hot' path. Isn't that what we mean by 'learning' a codebase? I know my ability is supercharged compared to most devs, but most colleagues have it to some extent…

There’s a company called driver.ai whose idea is to parse your codebase and provide the “map” (navigation of code structure and connectivity) to LLMs. (I haven’t tried it.)

Re: Ask HN: How are you LLM-coding in an established code base?

#62

Post by adzicg »

__mharrison__ wrote: post #58
adzicg wrote: post #22

We use claude code, running it inside a docker container (the project was already set up so that all the dev tools and server setup is in docker, making this easy); the interface between claude code and a developer is effectively the file system. The docker container doesn't have git credentials, so claude code can see git history etc and do local git ops (e.g. git mv) but not actually push anything without a review.…

This is very similar to what I teach clients. However, my process involves more TDD. I use tests as guardrails to keep the AI from doing something silly and to prevent regressions.

tdd is very present in our process, it's mandated by CONTIRIBUTING.md with very specific instructions on how to structure tests.

Re: Ask HN: How are you LLM-coding in an established code base?

#65

Post by orian »

I use it when I know what and where need to be done, because the complexity of the system and that making mistakes can fail the whole app. I do research in codebase using Claude ultrathink.

Our system is pretty well tested, so this helps a lot.

I know most people at my company use it, and with pretty good results(?)

Personally, I stoped voluntarily reviewing code and caring about quality of code that I’m not responsible for. The AI slop is real and reviewing it is counter-career, instead of pushing product forward and getting praised you spend it fighting with AI. I just accepted that this is how the products looks these days.

Re: Ask HN: How are you LLM-coding in an established code base?

#67

Post by PaulDavisThe1st »

jstummbillig wrote: post #66
PaulDavisThe1st wrote: post #21

Earlier quoted context omitted.

We don't review it, we just say it.

So it's not something you thought about.

We were open to it, but the actual results of LLM code generation are so uniformly poor that until there's substantive evidence of a change on that front, we're not willing to review on a case by case basis.

Re: Ask HN: How are you LLM-coding in an established code base?

#68

Post by jstummbillig »

PaulDavisThe1st wrote: post #67
jstummbillig wrote: post #66

Earlier quoted context omitted.

So it's not something you thought about.

We were open to it, but the actual results of LLM code generation are so uniformly poor that until there's substantive evidence of a change on that front, we're not willing to review on a case by case basis.

Ah, I meant review the policy, not the cases.

Re: Ask HN: How are you LLM-coding in an established code base?

#69

Post by PaulDavisThe1st »

jstummbillig wrote: post #68
PaulDavisThe1st wrote: post #67

Earlier quoted context omitted.

We were open to it, but the actual results of LLM code generation are so uniformly poor that until there's substantive evidence of a change on that front, we're not willing to review on a case by case basis.

Ah, I meant review the policy, not the cases.

We will review the policy when one of the core developers interacts with an LLM regarding a real coding problem in our application and gets back something that isn't drivel.
Post reply on HN