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

At Amazon, some coders say their jobs have begun to resemble warehouse work

nytimes.com

Post reply on HN
Print view View original

821–830 of 897 posts

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#821

Post by harper »

agarren wrote: post #351

> [Harper Reed] cautioned against being overly precious about the value of deeply understanding one’s code, which is no longer necessary to ensure that it works. That just strikes me as an odd thing to say. I’m convinced that this is the dividing line between today’s software engineers and tomorrow’s AI engineers (in whatever form that takes - prompt, vibe, etc.) Reed’s statement feels very much like a justification…

It was not a strong metaphor! Can't win them all.

You are correct tho. I do think that we are approaching the point of "If it compiles, ship it"

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#822

Post by jrochkind1 »

guappa wrote: post #672
throwaway2037 wrote: post #554

Earlier quoted context omitted.

Before I started using advanced IDEs that could navigate project structures very quickly, it was normal to have a relatively poor visibility -- call it "fog of war/code". In a 500,000 line C++ project (I have seen a few in my career), as a junior dev, I might only understand a few thousand lines from a few files I have studied. And, I had very little idea of the overall architecture. I see LLMs here as a big opportun…

That's what documentation is for. If you don't have that, AI won't figure it out either.

I'm not sure that's true?

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#823

Post by Izkata »

skydhash wrote: post #773
sanderjd wrote: post #739

Earlier quoted context omitted.

I've been telling friends and family - and kids interested in going entering this field - this for years (decades actually, at this point), that I don't spend much of my time typing out code. I've found that it's very hard for people to conceptualize what else it would be that we're spending our time doing.

I think that's a good part of the issue. You have the computer that is doing stuff. And you have the software engineer that was hired to make it do the stuff. And the connection between them is the code. That's pretty much the simplistic picture that everyone has. But the truth is that the way the computer works is alien and anything useful becomes very complex. So we've come up with all those abstractions, embed the…

> It's an imaginary world which is very hard to depict to other people. It's not purely abstract like mathematics, nor it's fully physical like mechanics.

This is one of the reasons I like the movie Hackers - the visualizations are terrible if you take it at face value, but if you think of it as a representation of what's going on inside their minds it works a whole lot better, especially compared to the lines-of-code-scrolling-past version usually shown in other movies/tv.

For anyone who doesn't know what I'm talking about, just the hacking scenes: https://youtu.be/IESEcsjDcmM?t=135

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#824

Post by 33hsiidhkl »

skeeter2020 wrote: post #702
33hsiidhkl wrote: post #683

Earlier quoted context omitted.

For any given seed value, the output of an LLM will be identical- it is deterministic. You can try this at home with Llama.cpp by specifying a seed value when you load a LLM, and then seeing that for a given input the output will always be the same. Of course there may be some exceptions (cosmic ray bit flips). Also, if you are only using online models, you can't set the seed value, plus there are multiple models, so…

I feel this is technically correct but intentionally cheating. no one - including the model creators - expects that to be the interface; it undermines they entire value proposition of using an LLM in the first place if I need to engineer the inputs to ensure reproducability. I'd love to hear some real world scenarios that do this where it wouldn't be simpler to NOT use AI.

When should a model's output be deterministic? When should a model's output be non-deterministic?

When many humans interact with the same model, then maybe the model should try different seed values, and make measurements. When model interaction is limited to a single human, then maybe the model should try different seed values, and make measurements.

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#825

Post by guappa »

jrochkind1 wrote: post #822
guappa wrote: post #672

Earlier quoted context omitted.

That's what documentation is for. If you don't have that, AI won't figure it out either.

I'm not sure that's true?

Such a project is way too large for AI to process as a whole. So yes it's true.

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#826

Post by Revisional_Sin »

close04 wrote: post #602
alpaca128 wrote: post #434

Earlier quoted context omitted.

They took their time precisely specifying the robot movements so they're always repeatable. Almost like...some sort of carefully crafted code.

You misconstrue the analogy. The robot isn’t equivalent to the code in this analogy. It’s the thing that generates the code. The robot operates deterministically, it has a fixed input and a fixed output. This is what makes it reliable. Your “AI coder” is nothing like that. It’s non deterministic on its best day, and it gets everything thrown at it so even more of a coin toss. This seriously undermines any expectation…

That was exactly their point.

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#827

Post by strogonoff »

solaire_oa wrote: post #808
strogonoff wrote: post #741

Earlier quoted context omitted.

> The submitter should also have thoroughly reviewed their own MR/PR What does it mean to have to review your own code as a separate activity? Do many people contribute code that they wrote but… never read? > Submitting LLM barf Oh right…

Writing/reading code and reviewing code are distinct and separate activities. It's completely common to contribute code which is not production ready. If you need an example, it's easy to add a debugging/logging statement like `console.log`, but if the coder committed and submitted the log statement, then they clearly didn't review the code at all, and there are probably much bigger code issues at stake. This is a pr…

Just call it “committing bad code”. LLM autocomplete aside, I don’t see how reviewing own code can happen without either a split personality, or putting enough time that you completely forgot what exactly you were doing and have fresh eyes and mind.

If person A committed code that looks bad to person B, it just means person A commits bad code by the standard of person B, not that person A “does not review own code”.

Maybe it’s a subjective difference, same as you could call someone “rude” or you could say the same person “didn’t think before saying”.

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#828

Post by strogonoff »

blub wrote: post #778
strogonoff wrote: post #741

Earlier quoted context omitted.

> The submitter should also have thoroughly reviewed their own MR/PR What does it mean to have to review your own code as a separate activity? Do many people contribute code that they wrote but… never read? > Submitting LLM barf Oh right…

I always review the local diff before pushing. Can sometimes catch typos, or unclear comments or naming issues. The concept and design were by that point iterated on, so it doesn’t happen that I need to rewrite a significant amount of code.

My preferred workflow requires me to go through every changed chunk and stage them one by one. It’s very easy with vim-fugitive. To keep commits focused, it requires reading every chunk, which I guess is an implicit review of sorts.

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#829

Post by throwaway2037 »

guappa wrote: post #825
jrochkind1 wrote: post #822

Earlier quoted context omitted.

I'm not sure that's true?

Such a project is way too large for AI to process as a whole. So yes it's true.

I have a question: Many people have spoken about their experience of using LLMs to summarise long, complex PDFs. I am so ignorant on this matter. What is so different about reading a long PDF vs reading a large source base? Or can a modern LLM handle, say, 100 pages, but 10,000 pages is way too much? What happens to an LLM that tries to read 10,000 pages and summarise it? Is the summary rubbish?

Re: At Amazon, some coders say their jobs have begun to resemble warehouse work

#830

Post by guappa »

throwaway2037 wrote: post #829
guappa wrote: post #825

Earlier quoted context omitted.

Such a project is way too large for AI to process as a whole. So yes it's true.

I have a question: Many people have spoken about their experience of using LLMs to summarise long, complex PDFs. I am so ignorant on this matter. What is so different about reading a long PDF vs reading a large source base? Or can a modern LLM handle, say, 100 pages, but 10,000 pages is way too much? What happens to an LLM that tries to read 10,000 pages and summarise it? Is the summary rubbish?

It can't handle large contexts, so the way they often do it is file by file, which loses the overall context.
Post reply on HN