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

Grief and the AI split

blog.lmorchard.com

Post reply on HN
Print view View original

161–170 of 404 posts

Re: Grief and the AI split

#161

Post by sifar »

CharlieDigital wrote: post #5

The divide is a matter of perspective. I'm a 23+ year dev; among the highest level ICs in my org. It's still craft, its just that the craft is different. I don't write *.ts, *.cs files anymore; I write *.md files that other devs are using, that we're using as guardrails, that ensures that we minimize the slop while increasing speed and basically lift every developers level up by several notches. I went from building…

You are building a system that has a shaky mental model and which may or may not adhere to the *.md files.

Re: Grief and the AI split

#162

Post by dang »

kalalakaka wrote: post #6

[dead]

Could you please not create an account for every few comments you post? This is in the site guidelines: https://news.ycombinator.com/newsguidelines.html.

You needn't use your real name, of course, but for HN to be a community, users need some identity for other users to relate to. Otherwise we may as well have no usernames and no community, and that would be a different kind of forum. https://hn.algolia.com/?sort=byDate&dateRange=all&type=comme...

Re: Grief and the AI split

#163

Post by dang »

bonkabonka wrote: post #18

Yow, submitter sure isn't shy with their bias. Maybe defang the title?

Submitted title was "The AI coding divide: craft lovers vs. result chasers" - which does seem to be a fair statement of what the article is about, and in that sense not so biased.

We've reverted the title to be that of the article now, though, in keeping with the site guidelines, since it was neither misleading nor linkbaity.

https://news.ycombinator.com/newsguidelines.html

Re: Grief and the AI split

#165

Post by dang »

lmorchard wrote: post #122
furyofantares wrote: post #40

Author doesn't care about their blog writing as craft, either (it's been fed through an LLM.)

Sure, I ran the post past an LLM for some ideas on clarity and tightening it up - but I wrote, edited, and published it myself.

It's increasingly clear that the LLMs leave more of a mark than authors realize when they run their writing through for a touching-up. This has been coming up a lot lately: https://news.ycombinator.com/item?id=47346449.

That's why readers end up reacting to the LLM imprints rather than the content.

I don't mean to be critical because it's a good article! But I bet if you shared the version before it was "tightened up", most of us would prefer it.

(I suppose I'd better add that this isn't a criticism of LLMs either - it's about figuring out how to use them well: https://news.ycombinator.com/item?id=47342045)

Re: Grief and the AI split

#166

Post by dang »

School-Cotton wrote: post #67

People who say directing an AI is just "moving up another level of abstraction" are missing the point that it's a completely different kind of work. Everything from machine code to Haskell is a predictable deductive logical system, whereas AIs are not.

It's different, but it isn't completely different. That's one reason why it's hard to make sense of this change.

Re: Grief and the AI split

#167

Post by ares623 »

sarchertech wrote: post #69

I’ve heard this thesis a lot, but it’s almost always from the result chasers. It doesn’t resonate with me because I am a result chaser. I like woodworking because I like building something that never existed before. I don’t mind using a CNC router or a 3 printer to help me out. I don’t care about the process, I care about the result. But I care deeply about the quality of the result. I don’t care about the beauty of…

> I like woodworking because I like building something that never existed before. I don’t mind using a CNC router or a 3 printer to help me out. I don’t care about the process, I care about the result. But I care deeply about the quality of the result.

Why not outsource it to someone else? That way you do none of the work.

Re: Grief and the AI split

#168

Post by bluefirebrand »

PaulHoule wrote: post #23

You can use gen AI entirely in the spirit of craft. For instance if you need to consume, implement or extend some open source software you can load it up in an agent IDE and ask “How do I?” questions or “how is it that?” questions that put you on a firm footing.

You don't need AI for this, we've had search engines and good online resources for decades

Re: Grief and the AI split

#169

Post by ofrzeta »

hungryhobbit wrote: post #53
simonw wrote: post #2

This sounds right to me: > Before AI, both camps were doing the same thing every day. Writing code by hand. Using the same editors, the same languages, the same pull request workflows. The craft-lovers and the make-it-go people sat next to each other, shipped the same products, looked indistinguishable. The motivation behind the work was invisible because the process was identical. Helps explain why some people are d…

I strongly disagree. There's always been two camps ... on everything! Emacs vs. vi. Command-line editor vs. IDE. IntelliJ vs. VS Code. I could do like twenty more of these: dev teams have always split on technology choices. But, all of those were rational separations. Emacs and vi, IntelliJ and VS Code ... they're all viable options, so they boil down to subjective preference. By definition, anything subjective will…

For the sake of argument let's assume we have a common goal: produce a software product that does its job and is maintainable (emphasis on the latter).

Now given that LLMs are known to not produce 100% correct code you should review every single line. Now the production rate of LLMs is so high that it becomes very hard to really read and understand every line of the output. While at the same time you are gradually losing the ability to understand everything because you stopped actively coding. And at the same time there are others in your team who aren't that diligent adding more to the crufty code base.

What is this if not a recipe for disaster?

Re: Grief and the AI split

#170

Post by g-b-r »

sockgrant wrote: post #152
g-b-r wrote: post #130

Earlier quoted context omitted.

> it can help you massively improve your code cleanliness. All of the little nice-to-have features, the cleanups, the high unit test coverage, nagging bug fixes, etc., they’re all trivial to do now. It can help if you write poor code without it, probably High unit test coverage only means something if you carefully check those tests, and if everything was tested

The only way Claude can help improve your code cleanliness is if you write poor code? Code coverage means nothing if you didn't carefully check every test? "and if everything was tested" do you know what code coverage is? not gonna engage the trolling

> The only way Claude can help improve your code cleanliness is if you write poor code?

No? You assert that it writes better code than the average software developer?

> Code coverage means nothing if you didn't carefully check every test? "and if everything was tested" do you know what code coverage is?

Do you know?

Code coverage only tells what amount of the code gets *touched* by the tests.

To achieve code coverage it's enough to CALL the code, it doesn't tell you anything about the correctness of the tests: they could all end with a return true, and a code coverage tool would be perfectly happy.

So, yes, if you don't carefully check the test suite that the agent writes, it might well be worthless (or simply much less useful than you assume it to be, more realistically).

With "if everything was tested" I meant that you also need to check if the agent wrote all the tests that are needed, besides verifying that the ones it wrote are correct.

Post reply on HN