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

When AI writes the software, who verifies it?

leodemoura.github.io

Post reply on HN
Print view View original

71–80 of 309 posts

Re: When AI writes the software, who verifies it?

#71

Post by skydhash »

yoaviram wrote: post #30

I just finished writing a post about exactly this. Software development, as the act of manually producing code, is dying. A new discipline is being born. It is much closer to proper engineering. Like an engineer overseeing the construction of a bridge, the job is not to lay bricks. It is to ensure the structure does not collapse. The marginal cost of code is collapsing. That single fact changes everything. https://no…

> I just finished writing a post about exactly this. Software development, as the act of manually producing code, is dying.

It was never that. Take any textbook on software engineering and the focus was never the code, but on systems design and correctness. I'm looking at the table of contents of one (Software Engineering by David C. Kung) and these are a few sample chapters:

  ...
  4. Software Requirement Elicitation
  5. Domain Modelling
  6. Architectural Design
  ...  
  8. Actor-System Interaction Modeling
  9. Object Interaction Modeling
  ...
  15. Modeling and Design of Rule-Based Systems
  ...
  19. Software Quality Assurance
  ...
  24. Software Security
What you're talking about was coding, which has never been the bottleneck other than for beginners in some programming languages.

Re: When AI writes the software, who verifies it?

#72

Post by shinycode »

yoaviram wrote: post #30

I just finished writing a post about exactly this. Software development, as the act of manually producing code, is dying. A new discipline is being born. It is much closer to proper engineering. Like an engineer overseeing the construction of a bridge, the job is not to lay bricks. It is to ensure the structure does not collapse. The marginal cost of code is collapsing. That single fact changes everything. https://no…

Our CEO, an expert in marketing has discovered Claude Code and is the one having the most open PR of all developers and is pushing for us to « quickly review ». He does not understand why review are so slow because it’s « the easiest part ». We live in a new world.

Re: When AI writes the software, who verifies it?

#75

Post by nemo44x »

I believe the old ways, which agile destroyed, will come back because the implementation isn’t the hardest part now. Agile recognized correctly that implementation was the hard part to predict and that specification through requirements docs, UML, waterfall, etc. were out of date by the time the code was cooked.

I don’t think we’ll get those exact things back but we will see more specification and design than we do today.

Re: When AI writes the software, who verifies it?

#76

Post by cesarb »

throwaw12 wrote: post #54
radlad wrote: post #51

Earlier quoted context omitted.

I don't quite follow - are you describing an issue with the way your team has structured PRs? IMO, a PR should contain just enough code to clearly and completely solve "a thing" without solving too much at once. But what this means in practice depends on the team, product, velocity, etc. It sounds like your PRs might be broken up into too small of chunks if you can't understand why the code is being added.

I am saying PRs I get are around 60-70 lines of change, which is small enough to be considered as single unit (add to this unit tests which must pass with new change, so we are talking about 30 line change + 30 line unit test) But when looking at the PR changes, you don't always see whole picture because review subjects (code lines) are scattered across files and methods, and GitHub also shows methods and files parti…

> Its difficult problem, because even if GitHub shows whole body of the updated method or a file, you still don't see grand picture.

> For example: A (calls) -> B -> C -> D

> And you made changes in D, how do you know the side effect on B, what if it broke A?

That's poor encapsulation. If the changes in D respect its contract, and C respects D's contract, your changes in D shouldn't affect C, much less B or A.

Re: When AI writes the software, who verifies it?

#77

Post by jpollock »

charlieflowers wrote: post #53
madrox wrote: post #42

I encourage everyone to RTFA and not just respond to the headline. This really is a glimpse into where the future is going. I've been saying "the last job to be automated will be QA" and it feels more true every day. It's one thing to be a product engineer in this era. It's another to be working at the level the author is, where code needs to be verifiable. However, once people stop vibing apps and start vibing kerne…

> "any sufficiently advanced agent is indistinguishable from a DSL." I don't quite follow but I'd love to hear more about that.

If the llm is able to code it, there is enough training data that youight be better off in a different language that removes the boilerplate.

Re: When AI writes the software, who verifies it?

#78

Post by fmbb »

madrox wrote: post #42

I encourage everyone to RTFA and not just respond to the headline. This really is a glimpse into where the future is going. I've been saying "the last job to be automated will be QA" and it feels more true every day. It's one thing to be a product engineer in this era. It's another to be working at the level the author is, where code needs to be verifiable. However, once people stop vibing apps and start vibing kerne…

There are still no successful useful vibe codes apps. Kernels are pretty far away I think.

Re: When AI writes the software, who verifies it?

#79

Post by bwestergard »

nemo44x wrote: post #75

I believe the old ways, which agile destroyed, will come back because the implementation isn’t the hardest part now. Agile recognized correctly that implementation was the hard part to predict and that specification through requirements docs, UML, waterfall, etc. were out of date by the time the code was cooked. I don’t think we’ll get those exact things back but we will see more specification and design than we do t…

Agile was a response to the coordination problems in certain types of firms. Waterfall persisted in organizations that have and require a more traditional bureaucratic structure. Waterfall makes sense if you are building a space probe or an unemployment insurance system, agile makes sense if you are trying to find product market fit for a smartphone app.

Re: When AI writes the software, who verifies it?

#80

Post by FartyMcFarter »

throwaw12 wrote: post #54
radlad wrote: post #51

Earlier quoted context omitted.

I don't quite follow - are you describing an issue with the way your team has structured PRs? IMO, a PR should contain just enough code to clearly and completely solve "a thing" without solving too much at once. But what this means in practice depends on the team, product, velocity, etc. It sounds like your PRs might be broken up into too small of chunks if you can't understand why the code is being added.

I am saying PRs I get are around 60-70 lines of change, which is small enough to be considered as single unit (add to this unit tests which must pass with new change, so we are talking about 30 line change + 30 line unit test) But when looking at the PR changes, you don't always see whole picture because review subjects (code lines) are scattered across files and methods, and GitHub also shows methods and files parti…

If the code is well architected, the contract between C and D should make it clear whether changes in D affect C or not. And if C is not affected, then B and A won't be either.
Post reply on HN