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

Eight Myths on Software Engineering and GenAI

queue.acm.org

Post reply on HN
Print view View original

111–120 of 269 posts

Re: Eight Myths on Software Engineering and GenAI

#111

Post by t-writescode »

simonw wrote: post #105
geraneum wrote: post #90

Earlier quoted context omitted.

Does the code get reviewed? How do you deal with increased amount of code that may need to be looked at?

I review the code that matters - anything security adjacent or that's an API that will be used by other code in the future. I don't review code that either works or doesn't - most HTML and CSS layout code for example. There I test it on desktop and mobile and commit it if it works. Ditto for stuff that's simple. A JSON endpoint that runs a SQL query and returns some JSON? If it works and a glance at the tests looks O…

> Ditto for stuff that's simple. A JSON endpoint that runs a SQL query and returns some JSON? If it works and a glance at the tests looks OK then I trust my agents wrote it properly.

That is *exactly* the sort of area I *wouldn’t* blindly trust AI, there’s a huge security boundary there. What if the AI is doing string concatenation with user-provided data???

Re: Eight Myths on Software Engineering and GenAI

#112

Post by seizethecheese »

decimalenough wrote: post #23
a_bonobo wrote: post #16

>On my visits to the Bay Area, I would ask AI researchers or interns why they are doing their current research or projects, when in a year or three agentic LLMs could probably do them; This is such a weird point to make that doesn't become correct just because everyone makes it, all the time. Why clean the ocean if some magic future tech will clean them? Why save the world now if some benevolent AI is 'just around th…

I think you meant to post this in response to https://news.ycombinator.com/item?id=49174900 ?

Yes I double checked the quote is not in the article. HN is probably the best place on the internet for people actually reading the article, but this being the top comment here suggests that the majority of voters still do not read the article

Re: Eight Myths on Software Engineering and GenAI

#113

Post by ReactiveJelly »

bwhiting2356 wrote: post #110
a_bonobo wrote: post #16

>On my visits to the Bay Area, I would ask AI researchers or interns why they are doing their current research or projects, when in a year or three agentic LLMs could probably do them; This is such a weird point to make that doesn't become correct just because everyone makes it, all the time. Why clean the ocean if some magic future tech will clean them? Why save the world now if some benevolent AI is 'just around th…

A fully automated utopia isn't just going to happen. Even with frontier models, the integrations, the evals, the UX, need a lot of work and someone needs to do it. After I've automated this thing I'll move on to the next task, this is what it means to be a software engineer.

An actual utopia would require never-before-seen democratic mandate from people who are currently on the brink of hot civil war

Re: Eight Myths on Software Engineering and GenAI

#114

Post by simonw »

unknownfuture wrote: post #104
simonw wrote: post #40

Earlier quoted context omitted.

How's this? https://simonwillison.net/2026/Jul/13/datasette-code-frequen... I have similar charts across my three main open source projects: https://github.com/simonw/datasette/graphs/code-frequency https://github.com/simonw/llm/graphs/code-frequency https://github.com/simonw/sqlite-utils/graphs/code-frequency

The article mentions that coding is only a fraction of dev time and thus accelerating that part of the job can only create incremental gains, and oh PS, lines of code and similar metrics are a bad way if measuring dev productivity, anyway, and we've known that for decades. The OP claims AI accelerates non-coding parts of the job, too, and so the article is misguided. I ask for evidence. In response you give me... cod…

I don't have anything else to hand that I can think of. I don't keep a time tracking diary.

Re: Eight Myths on Software Engineering and GenAI

#115

Post by sevenzero »

a_bonobo wrote: post #16

>On my visits to the Bay Area, I would ask AI researchers or interns why they are doing their current research or projects, when in a year or three agentic LLMs could probably do them; This is such a weird point to make that doesn't become correct just because everyone makes it, all the time. Why clean the ocean if some magic future tech will clean them? Why save the world now if some benevolent AI is 'just around th…

Also people tend to forget that LLMs still just work on compressed data... Where are the MAJOR breakthroughs? Where is all the "crazy" AI output going? Software seemed to degrade in quality a lot in the recent years. All "improvements" LLMs go through are simply improvements on how to burn more tokens out of my pockets given that Claude now want an actual browser extension to "visually" confirm small changes every time I use it for UI. They are still just data parrots.

Re: Eight Myths on Software Engineering and GenAI

#116

Post by hombre_fatal »

t-writescode wrote: post #111
simonw wrote: post #105

Earlier quoted context omitted.

I review the code that matters - anything security adjacent or that's an API that will be used by other code in the future. I don't review code that either works or doesn't - most HTML and CSS layout code for example. There I test it on desktop and mobile and commit it if it works. Ditto for stuff that's simple. A JSON endpoint that runs a SQL query and returns some JSON? If it works and a glance at the tests looks O…

> Ditto for stuff that's simple. A JSON endpoint that runs a SQL query and returns some JSON? If it works and a glance at the tests looks OK then I trust my agents wrote it properly. That is *exactly* the sort of area I *wouldn’t* blindly trust AI, there’s a huge security boundary there. What if the AI is doing string concatenation with user-provided data???

We're pretty far past this if you're using anything close to the sota models.

But you could be defensive with a security checklist in agents.md and have adversarial review, if you wanted.

Re: Eight Myths on Software Engineering and GenAI

#117

Post by blackqueeriroh »

AdieuToLogic wrote: post #82
mkozlows wrote: post #48

Earlier quoted context omitted.

Your PM can write the ticket, and your QA can test the output.

>> How are you going to prompt the LLM or validate its output if you don't understand the requirements? > Your PM can write the ticket, and your QA can test the output. If your PM can write the ticket and your QA can test the output, why not cut out the middleman by having the PM write the coding agent prompt(s)? And if your PM can write the coding agent prompt(s), why not cut out the QA group by having the PM write…

Because customers have better things to do.

Re: Eight Myths on Software Engineering and GenAI

#118

Post by gmueckl »

lz400 wrote: post #97
AdieuToLogic wrote: post #85

Earlier quoted context omitted.

> That was because coding was expensive and we needed to be sure we didn't code the wrong thing. Coding has never been expensive as it is nothing more than a reification of a solution to a problem as it is understood at that time. It is the underlying understanding of the problem which has always been expensive and remains so.

Coding was expensive in the sense that once you decided what to do, it took a few engineers months / years to do moderately complex projects. That's not true anymore. Therefore the risk of "coding the wrong thing" is less.

Is it? The temptation to start without a thorough design is now much stronger because the implementation osnperceived to be cheap and easy to replace. But if you start building the wrong thing fast, you still get the right thing later than when you had checked properly at the start.

Re: Eight Myths on Software Engineering and GenAI

#119

Post by sevenzero »

tkzed49 wrote: post #109
1saadcodes wrote: post #108

I think the paper would have been stronger if it acknowledged how quickly the underlying evidence is becoming outdated. AI-assisted development in 2026 isn't just better models. The way many devs including myself work has changed and matured quite a bit as compared to last year

how so?

Many devs now work in YOLO mode letting LLMs automate their tasks.

Re: Eight Myths on Software Engineering and GenAI

#120

Post by cyptus »

tkzed49 wrote: post #109
1saadcodes wrote: post #108

I think the paper would have been stronger if it acknowledged how quickly the underlying evidence is becoming outdated. AI-assisted development in 2026 isn't just better models. The way many devs including myself work has changed and matured quite a bit as compared to last year

how so?

I think the tooling around the models themself has improved _a lot_ - they are really good at giving the models the correct context, even in big code bases
Post reply on HN