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

Nobody has built a software factory

medium.com

Post reply on HN
Print view View original

51–60 of 81 posts

Re: Nobody has built a software factory

#51

Post by grim_io »

deadbabe wrote: post #25

I propose a software farm . Imagine a large multi dimensional grid. Each axis of the grid represents a spectrum of how a specific feature could be implemented. You thus have one axis per feature. Now you plot a cloud of random points all over the grid and at each point have an agent build a solution where the features are expressed according to the corresponding intensity values at the point. Now you go through and r…

Like The Matrix, but it's us who harvest the dreaming machines.

Not a future I envisioned, but a preferable one.

Re: Nobody has built a software factory

#52

Post by simonw »

sarreph wrote: post #3

I really like the premise of this article because I am intensely interested in learning about software factories. As much as "software factory" is a buzzword, it's still SOTA and it's absolutely going to happen / keep happening in the tech industry over the next few years. However, I can't read this, not because I refuse to -- I want to -- but because my the cogs in my mind just stop whirring at all of the LLM-isms,…

Ugh, this one was so sloppy. "No engineer can hold that in their head, and that’s the point: the machine holds it." Shudder.

Re: Nobody has built a software factory

#53

Post by zrail »

nzoschke wrote: post #43
zrail wrote: post #31

Earlier quoted context omitted.

1. Make your tests as fast as practicable 2. Split out "syntactically correct" fast checks like linters into a standalone script and call it along with the slower checks in a full-check script 3. Set the fast-check script as a pre-commit hook and the full-check script as a pre-push hook. 4. Give the model instructions that it needs to run the fast-check script after every change and the full-check script when it thin…

pre-commit and pre-push hooks sound smart. I like that those will work the same for any human or any harness vs harness hooks. Then push straight to main? Or do we need GitHub to help manage the queue https://docs.github.com/en/repositories/configuring-branches...

I think that's orthogonal to testing/ci/hooks and depends on what you're building and what stage you're at. Personally I would not run anything with real users without PRs and branch protection.

Re: Nobody has built a software factory

#54

Post by simonw »

steveklabnik wrote: post #35
daveguy wrote: post #17

Earlier quoted context omitted.

Wait. It's going to happen and it's SOTA, but you can't read the article because genAI produces such garbage? Seems like a disconnect there.

writing prose and writing code are two different things I can get good code out of LLMs. I can rarely get good writing out of them. Maybe it's a skill issue, but it's not inherently a contradiction that they're better at some things than others. It's much easier to RL coding than writing.

Being dull and predictable and repeating existing patterns are characteristics of good code, and simultaneously characteristics of bad writing.

Re: Nobody has built a software factory

#55

Post by Seattle3503 »

measurablefunc wrote: post #4

This is obviously written by AI so I stopped reading at the first headline.

I ran Pangram after seeing the "Everyone Bought the Motor. Ford Rebuilt the Floor" headline. 97% AI.

I have all the AI subscriptions myself, I don't need a meet proxy. ai;dr

Re: Nobody has built a software factory

#56

Post by ianjbutler »

deadbabe wrote: post #25

I propose a software farm . Imagine a large multi dimensional grid. Each axis of the grid represents a spectrum of how a specific feature could be implemented. You thus have one axis per feature. Now you plot a cloud of random points all over the grid and at each point have an agent build a solution where the features are expressed according to the corresponding intensity values at the point. Now you go through and r…

This is the old idea of giving two teams the same project and letting a third team judge/merge a solution incorporating good parts of each. Just like the old idea, of course you would do this with infinite resources.

You can already sort of do this in way that isn't insanely wasteful if your project has strong measures of correctness. But even then things like compilers have a very real axis for friction in "user/developer/agent experience".. doing it at scale involves some kind of LLM-as-Judge pointed at something which is not an objective value. So .. not only piling on additional false work, but work which is very likely to be incorrect/noisy.

Re: Nobody has built a software factory

#57

Post by Isamu »

OccamsMirror wrote: post #38
sarreph wrote: post #3

I really like the premise of this article because I am intensely interested in learning about software factories. As much as "software factory" is a buzzword, it's still SOTA and it's absolutely going to happen / keep happening in the tech industry over the next few years. However, I can't read this, not because I refuse to -- I want to -- but because my the cogs in my mind just stop whirring at all of the LLM-isms,…

As soon as I read this: "Everyone Bought the Motor. Ford Rebuilt the Floor." my brain recoiled and I did not want to continue reading it.

This is rapidly becoming the damning accusation of quasi-journalism: this sounds like AI.

There should be journalism classes on how to not sound like a bot.

Re: Nobody has built a software factory

#58

Post by ardit33 »

nater5000 wrote: post #27

I definitely agree with the sentiment of this article, give or take. I've seen it at the place a previously worked at and now the place I currently work at: everybody wants AI to make coding faster and more efficient, but nobody is willing to take the risk of changing course and bending the firm's processes around what would actually make the agents more useful. Maybe this is more general than the qualms against "sof…

Was this written by AI?

My experience, with the latest models, they do write code that looks correct/polished, but often do not fully solve the problem, or solve the wrong thing, or introduce un-needed complexity. By often, I mean at least 10%-15%, which is still a high enough error rate, that you don't want to let loose in even a trivial service, let alone a service that is on the critical side.

For now humans are absolutely needed in the loop.

Re: Nobody has built a software factory

#59

Post by Spartan-S63 »

mccoyb wrote: post #21

I don’t think it’s possible to build a software factory unless you truly do not care about what you’re putting out. Agent swarms, self learning, Ralph loops, execution DAGs, spending hours trying to convey my preferences into skills, yada yada — the reality is that no matter how long I spend trying to close the amortization gap between my expertise and (insert autonomous agent loop) … I always come back to see shit t…

The fascination with "software factories" is strange. We don't have "bridge factories" or "skyscraper factories." We engineer those for the specific requirements from each individual project.

I think it's rooted in the idea that AI is going to "solve" software engineering when it's really only another tool that magnifies leverage. Same thing with traditional engineering and their computer-assisted tools. It doesn't "solve" engineering, but it does automate some of the repetitive things that aren't the biggest value-add.

Software isn't a manufactured product and that's where the disconnect is. You can't build software factories unless you don't care about the quality. For some companies, that might be fine, but I imagine that's a much smaller subset of the market than folks think.

Re: Nobody has built a software factory

#60

Post by Isamu »

simonw wrote: post #52
sarreph wrote: post #3

I really like the premise of this article because I am intensely interested in learning about software factories. As much as "software factory" is a buzzword, it's still SOTA and it's absolutely going to happen / keep happening in the tech industry over the next few years. However, I can't read this, not because I refuse to -- I want to -- but because my the cogs in my mind just stop whirring at all of the LLM-isms,…

Ugh, this one was so sloppy. "No engineer can hold that in their head, and that’s the point: the machine holds it." Shudder.

A machine supremacist wrote this. Beware the machine uprising!
Post reply on HN