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

31–40 of 126 posts

Re: What we lost the last time code got cheap

#31

Post by chris_st »

esafak wrote: post #19
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…

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.

Re: What we lost the last time code got cheap

#32

Post by lamename »

gojomo wrote: post #25

The context of when that previous experience - Heartland outsourcing to India – happened would be helpful. The 90s? The 00s? The 10s?

The link in the article that is right near the words you're talking about links to a wikipedia page that says the book is from 2005. So I conclude it was 2005 or soon after

Re: What we lost the last time code got cheap

#33

Post by ai_fry_ur_brain »

esafak wrote: post #19
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…

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.

Why not just read the code.. Ya'll are literally letting your brain atrophy by using llms this way.

Re: What we lost the last time code got cheap

#34

Post by somewhatgoated »

kadhirvelm wrote: post #13

Curious what other teams are doing to keep encouraging people to think critically about their code? I’ve been finding it harder to keep people motivated, keep them engaged with all the changes coming in. And I can’t blame them, it’s been overwhelming. Is everyone else just using more AI..?

More AI is always the answer.

Re: What we lost the last time code got cheap

#35

Post by recursive »

lamename wrote: post #30
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.

Do you disagree with the point made?

Forming a human opinion about slop is like asymmetrical warfare. Or maybe a closer analogy is a Gish Gallop. It can be generated with way less effort than it takes to comprehend it, much less form a coherent opinion on it.

Re: What we lost the last time code got cheap

#36

Post by pmmucsd »

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 why certain choices were made.

Re: What we lost the last time code got cheap

#37

Post by rogerrogerr »

lamename wrote: post #30
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.

Do you disagree with the point made?

LLMs are running a gish gallop at Internet scale. It is not necessary or possible to disprove every sequence of tokens that emerges from one.

https://en.wikipedia.org/wiki/Gish_gallop

Re: What we lost the last time code got cheap

#38

Post by kuboble »

copperx wrote: post #27
foobarian wrote: post #16

Earlier quoted context omitted.

It's been pretty great for ramping up into codebases too. "Give me a summary of project in current checkout in markdown form."

do you enjoy reading markdown? I don't, even with the editor in preview mode.

I'm actually asking claude to make me eli5 htmls with svg diagrams of the code I want to understand.

Once I even asked him to create for me a manim video about it.

Re: What we lost the last time code got cheap

#40

Post by Forgeties79 »

lamename wrote: post #30
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.

Do you disagree with the point made?

If I want a boring, rote LLM answer I will prompt it myself. I don’t read blogs to have a middleman between me and a prompt.
Post reply on HN