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

What we lost the last time code got cheap

poppastring.com

Post reply on HN
Print view View original

51–60 of 126 posts

Re: What we lost the last time code got cheap

#51

Post by rectang »

chris_st wrote: post #31
esafak wrote: post #19

Earlier quoted context omitted.

It lets you understand the code base at reduced granularity when you want. Or zoom in beyond the written lines to explain _why_ some code is the way it is.

I asked Claude to tell me why something was implemented the way it was, and got an excellent response. One data point, would love to hear more examples.

I agree, Claude has been pretty great at explaining code. It even does well at explaining to me old code that I wrote by hand — including both non-intuitive quirks and flaws.

Claude in its default configuration has untapped potential for explaining and documenting code because it defaults to writing no comments. I added this to my global CLAUDE.md and so far so good:

    # Comments

    Keep existing comments unless they're wrong
    or stale. Err slightly toward adding short
    explanatory comments for non-obvious code.

Re: What we lost the last time code got cheap

#52

Post by dilyevsky »

andybak wrote: post #2

Personally I've found one of the biggest gains with coding agents is in helping me read code. Actually - that's a lie. I don't read the code. Mostly (unless my spidey-sense goes off) I ask the LLM to read the code and tell me what it does. And then I make a decision based on that. I guess I'm wondering if the article is missing half the picture. Yes - AI is wrong some of the time (and that % varies based on a host of…

The "It’s harder to read code than to write it" was always silly. The example spolsky gives to support it is basically "devs like to rewrite other devs code, therefore reading is hard" which is obviously bunch of nonsense. That's like saying reading poetry is harder than writing poetry because poets keep writing new poems despite the fact that Shakespeare already wrote it. Now that you can recruit LLM to explain any complicated codebase to you it's even less true.

Re: What we lost the last time code got cheap

#53

Post by wiremine »

> The code they [LLMs] produce is often fine. It works. It passes tests. It might ship as-is.

I don't disagree, but I've been thinking about this a bit: a lot of _human_ written code was/is less-than-fine. And a lot of human devs didn't understand the context when they wrote it.

I'm not advocating that we fire devs, or evangelizing that LLms are awesome. But I do wish there was a slightly more honest take on the pre-LLM world: it's not just about cost reduction, it's about solving some long-term structural deficiencies of industry.

Re: What we lost the last time code got cheap

#54

Post by crooked-v »

pmmucsd wrote: post #36

Related (maybe the same thing): Whenever an agent is planning there are often architecture and product choices that it asks humans to make. None of this intent is captured in the code or comments. We started a decisions.md file and updated CLAUDE.md and AGENTS.md to create an entry in the decisions.md file everytime it has to ask a human about what to do. It captures the intent so at least we have doc that describes…

The structure https://acai.sh/ uses feels to me like a decent starting point for this kind of thing that avoids the "single giant file" issue.

Re: What we lost the last time code got cheap

#55

Post by xienze »

croemer wrote: post #21

Reads at least partially like LLM writing, for example: > When code production gets cheap, the cost doesn't disappear. It migrates. > It was true then. It is unavoidably true now.

Like clockwork, every single thread about something AI-related has someone expressing their disgust at passages of LLM-written text. In many cases by the same people who are enthusiastically embracing LLM-generated software. Why don't we show the same level of contempt for LLM-authored software as we do for even the slightest hint of LLM-authored text in a blog post?

Re: What we lost the last time code got cheap

#56

Post by olsondv »

When I generate code with AI, I will read through each change as it makes them (babysitting). If I don’t understand it, then I ask for explanation right away. At least by the end I have a grasp on what each change does and the reasoning. Then, I can make a PR and highlight the same info for my reviewer and for longevity. Our codebase style is not to litter comments everywhere. We go back to the code review for details and discussion. Obviously, this only works if the changes are small.

Re: What we lost the last time code got cheap

#57

Post by nostrademons »

pmmucsd wrote: post #36

Related (maybe the same thing): Whenever an agent is planning there are often architecture and product choices that it asks humans to make. None of this intent is captured in the code or comments. We started a decisions.md file and updated CLAUDE.md and AGENTS.md to create an entry in the decisions.md file everytime it has to ask a human about what to do. It captures the intent so at least we have doc that describes…

Human coders have the same problem too - oftentimes the most important question that future maintainers have of the code is "Why was this decision made?", but that's not captured anywhere in the code itself.

The right place for this is usually in the design doc or commit message, and robust engineering organizations will ensure that commits are cross-referenced back to design and requirements docs so you can trace decisions from git blame back to the actual rationale.

The same process also works pretty well with LLMs. Google, for example, is internally championing a process where the engineer has a dialog with the LLM to generate a design doc, oftentimes with an adversarial LLM to poke holes in the design. Once the design is fully specified, the last step is to ask the LLM to turn the design doc into code. This creates a human-readable artifact that traces the decisions that the human and AI collaboratively made, which then can be traced back from the code.

Re: What we lost the last time code got cheap

#58

Post by CharlesW »

pmmucsd wrote: post #36

Related (maybe the same thing): Whenever an agent is planning there are often architecture and product choices that it asks humans to make. None of this intent is captured in the code or comments. We started a decisions.md file and updated CLAUDE.md and AGENTS.md to create an entry in the decisions.md file everytime it has to ask a human about what to do. It captures the intent so at least we have doc that describes…

> Whenever an agent is planning there are often architecture and product choices that it asks humans to make. None of this intent is captured in the code or comments.

It must be in order to have an effective AI-assisted software engineering workflow, but it's not something that's magically done for you (usually). Knowledge management of project context is everything. Even the little music app I'm building has >100 ADRs (https://en.wikipedia.org/wiki/Architectural_decision), and that's just one form of project memory.

Re: What we lost the last time code got cheap

#59

Post by Aurornis »

andybak wrote: post #2

Personally I've found one of the biggest gains with coding agents is in helping me read code. Actually - that's a lie. I don't read the code. Mostly (unless my spidey-sense goes off) I ask the LLM to read the code and tell me what it does. And then I make a decision based on that. I guess I'm wondering if the article is missing half the picture. Yes - AI is wrong some of the time (and that % varies based on a host of…

There are times when reading the code is necessary, but oh boy are LLMs so much faster at finding the part of the codebase I want to read.

Several projects I work on call into or interact with gigantic codebases. A couple years ago I would have to allocate 30 minutes some times to either trace through the code base or setup and attach a debugger to step through the code until I found the part I needed to know about.

Now I send an LLM to go find it and it comes back with a list of files and line numbers in minutes.

It’s still not perfect. I had a codebase walk this morning where even GPT-5.5 extra high failed to find something I knew was in there on the first pass. It got it with some more directed prompting. If you delegate trust 100% to an LLM you will get bit eventually.

Re: What we lost the last time code got cheap

#60

Post by amarant »

lamename wrote: post #48
superfrank wrote: post #43

Earlier quoted context omitted.

Maybe it's just because I grew up spending way too much time on the internet, but I write like that and have since well before LLMs. As much as people like to attribute that style to AI, I don't think it's the dead giveaway that people act like it is.

Exactly. HN darling Paul Graham writes this way. I find the constant critique of punchy style a bit tiring. It would be more productive for the grandparent to think about the content and state an opinion.

I swear the worst part about llms are their critics.
Post reply on HN