← Back to context

Comment by Thanemate

4 hours ago

Not trying to rain on someone's parade but, the only reason why would care about style guides nowadays is to feed them to our model of choice and let it do what it's supposed to be doing.

So it's not like I am willing to read through this and think to myself "I cannot wait to pick up some new ways of doing things". I'm the general to my agentic army now.

I guess you would code manually every now and then for your own enjoyment but at that point do you care about style guides written for scale?

I'm not sure I really agree with your main point (I think it's probably still important for LLM-generated code to be generally human-understandable, at least if you care about long-term maintainability), but setting that aside to answer this question:

> I guess you would code manually every now and then for your own enjoyment but at that point do you care about style guides written for scale?

I think they're still quite valuable in that case, for a couple reasons:

- When learning a new language (which happens much more frequently when writing code "for pleasure," as it were), "written for scale" guidelines still translate pretty well to "written for oneself" IME. At the very least, they tell you what to expect in code you read, and give you a reasonable starting point as you develop your own taste and stylistic preferences.

- I've noticed some open source projects beginning to institute anti-AI contribution guidelines, and such projects still benefit from codified style guides. Google obviously doesn't fall under this category themselves, but in other language ecosystems, their style guides tend to find use in OSS projects.

> I'm the general to my agentic army now.

What have you produced with your agentic army? Would you like to share with the class?

  • Why would they when the class is full of dropouts who, generously, have a 0 percent chance of going "hey, y'know what, that's actually kinda cool! I'm going to change my mind about LLMs being useless" and a 100% chance of going "ur project is total shit and you should feel bad".

    • The people you call "dropouts" have written 100% of the software that people actually use and actually keeps the real world running, so maybe you shouldn't write them off.

      3 replies →

First paragraph: “includes guidance on API and implementation design”

It seems to me that if the intent is not just to produce code but also to operate it, having the different pieces behave in a similar, predictable way is kind of nice. Whether the software is written by AI or humans.

This is what we do in my company, give the guidelines to the model. Unfortunately, the model isn't always following them and it's impossible to enforce them manually. There's too much code to review, the code is generally low quality, and is more often than not auto-approved by AI.

Unless you're working on your own project on which you have full control, or you have a strong authority figure in your company who cares about that, it's a lost battle.

It's sad for anyone who love their craft, but tbh I'm not even sure it matters anymore for most projects.

  • Either you can put it in a linter and automate/force it, or people/agents will take liberties. I feel like there's usually exceptions where a well-meaning guideline doesn't properly fit a specific scenario.

The point of style guides is to optimize for readability despite a cognitively diverse workforce coding in the same repos.

I would think they're probably even more meaningful in an agentic world.

Shitty generals can't review meaningfully review the work of their troops.

On top of that all, I just enjoy programming itself. It's less and less of the meat of a software job over time, but I was coding before I got paid for it, and I'll probably keep coding well after I can get paid for it.

  • > Shitty generals can't review meaningfully review the work of their troops.

    Except that reviewing has become just asking your agent what that piece of code does in english. Reading code has a bit of cognitive load, that we will probably drop it in coming years

Not trying to rain on someone's parade, but the only reason I would care about HN comments nowadays is to feed them to my model of choice and let it generate the contrarian hot takes it's supposed to be generating. So it's not like I am willing to read through this thread and think to myself "I cannot wait to pick up some new ways of complaining about documentation." I'm the Editor-in-Chief to my synthetic pundit army now.

I guess you would type out a comment manually every now and then for your own enjoyment, but at that point do you really care about comments at scale?

---

EDIT (above is a joke) It's very important that every time you find something that is of no use to you, you write a comment explaining that this link is of no interest to you, discouraging people from things you have no interest in. Monoculture for all!

Are you saying that you don't ever look at the code once it's been generated?

  • AI bros think you can never look at code and make good software. They're wrong, of course, but they refuse to listen and will probably never listen until the shoddy quality of their work becomes too great to paper over.

    • If you set up a really good AI code review pipeline then you can get pretty close. I've heard a couple of tech companies are targeting 80% of changes not needing human review and they'll probably scale up from there.