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

181–190 of 269 posts

Re: Eight Myths on Software Engineering and GenAI

#181

Post by jurgenburgen »

mikeyouse wrote: post #50
decimalenough wrote: post #24

Earlier quoted context omitted.

> That meeting that you spent an hour in to understand the requirements? You don't need that meeting if you're not writing the code. How are you going to prompt the LLM or validate its output if you don't understand the requirements?

In some number of cases, the business partner who would have passed you the requirements will just generate the code themselves.. I’m shocked shin some engineers don’t see a massive disruption coming..

> In some number of cases, the business partner who would have passed you the requirements will just generate the code themselves.. I’m shocked shin some engineers don’t see a massive disruption coming..

It’s because you are engaging in first-order thinking. You imagine the immediate result which is that software engineers are replaced.

If you engaged in second-order thinking you would realize that if software engineers can be replaced, _any_ work can eventually be automated. So why stress about it, we’ll figure out a replacement for capitalism. It seems like the world is starting the slow swing to the left so eventually the problem will be solved.

Of course might be those engineers you mention are engaged in no thinking.

Re: Eight Myths on Software Engineering and GenAI

#182

Post by fhd2 »

mfru wrote: post #175

I've found that using LLMs for significant amounts of code generation completely drain the result from any dopamine I would get doing it myself. Have others noticed this as well? This is going so far as to me losing interest in side projects because I have "lost touch" with the code base.

With GenAI, we can now produce something without caring about it - or while caring about it very little.

And the parts we don't care about aren't necessarily worse, they are just... arbitrary. Could be good, could be bad, no one knows, because no one really cares.

I find that if I care about something a lot, it's a pretty similar time investment than pre LLMs. And it makes me feel invested and proud in the result, motivated to show it and improve it.

If I care about something very little, in the past I just wouldn't have done it at all. Now I might, but I feel that same disconnect you mentioned.

I think being strategic in what we do and do not care about is likely the key skill we'll have to build to actually make the best of the tech.

Re: Eight Myths on Software Engineering and GenAI

#183

Post by Patient0 »

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…

Sorry where in the article does it make this point? I cannot find the text "On my visits to the Bay Area" anywhere in the original article.

Re: Eight Myths on Software Engineering and GenAI

#185

Post by delis-thumbs-7e »

mfru wrote: post #175

I've found that using LLMs for significant amounts of code generation completely drain the result from any dopamine I would get doing it myself. Have others noticed this as well? This is going so far as to me losing interest in side projects because I have "lost touch" with the code base.

Yep. ADHD very strong in this one, so LLM code generation takes pretty much all joy out of coding. It’s like watching a computers play chess. Yeah, no thanks.

Re: Eight Myths on Software Engineering and GenAI

#186

Post by ubercore »

Yopolo wrote: post #152
germandiago wrote: post #127

Earlier quoted context omitted.

> This is such a weird point to make I think it is a great point to make, because if everyone really believed that AIs will do everything without human intervention in a handful of years, as the marketing repeats again and again (AGI, singularity, etc.) and have been saying for years... why then get bothered? Because we DO know LLMs have their hallucinations, limitations, perform tasks not previously seen way worse t…

No we don't know your 'points' The Hallucinations are becoming less, significantly by now. It also might be already were it is cheaper for one of the big few companies to spend millions and billions to teach the LLM / creating the training data necessary for an LLM to do something which it is not yet good enough due to the fact, that they sell this capability then to everyone who wants to use this capabilitiy. We hav…

Hallucinations were low hanging fruit in some ways. As someone working on a large-ish complex-ish distributed system that has to be maintained and support customers, it's still very high value to have Claude in the mix, but the core problem of needing to monitor, advise, course correct, and make sure you don't end up with more code and complexity than you need is, at least in my experience, still roughly the same. The sharp edges are being filed off very rapidly, but the core experience of "make and maintain a large system" isn't advancing nearly as fast, IMO.

Re: Eight Myths on Software Engineering and GenAI

#187

Post by jbstack »

dmurray wrote: post #176
germandiago wrote: post #127

Earlier quoted context omitted.

> This is such a weird point to make I think it is a great point to make, because if everyone really believed that AIs will do everything without human intervention in a handful of years, as the marketing repeats again and again (AGI, singularity, etc.) and have been saying for years... why then get bothered? Because we DO know LLMs have their hallucinations, limitations, perform tasks not previously seen way worse t…

It's a very silly point to make to AI researchers specifically. If they don't work on those projects, the AI won't advance and won't magically be able to replicate the work in "one to three years".

Relevant xkcd: https://xkcd.com/989/

Re: Eight Myths on Software Engineering and GenAI

#188

Post by dagss »

geraneum wrote: post #171
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…

> 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. Good example of what not to review if you're working on your hobbies. Also exploratory can sometimes be done this way. However, this ultimately boils down to how you approach programming as an engineering discipline, including your responsibility for the outc…

But if you observe that the agent day after day do handle user input safely; and also routinely run an agent that scans for security vulnerabilities and observe it finding cases where input is not handled safely in existing code, you may conclude that the chance of an issue is at the same level at, or probably lower than, if a human wrote it and a human reviewed it.

("Escaping" user input is not good practice though, use parameters, assuming you are talking about SQL.)

Re: Eight Myths on Software Engineering and GenAI

#190

Post by satvikpendem »

germandiago wrote: post #127
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…

> This is such a weird point to make I think it is a great point to make, because if everyone really believed that AIs will do everything without human intervention in a handful of years, as the marketing repeats again and again (AGI, singularity, etc.) and have been saying for years... why then get bothered? Because we DO know LLMs have their hallucinations, limitations, perform tasks not previously seen way worse t…

The AI researchers are not the ones making the marketing, much less believing in it.
Post reply on HN