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

241–250 of 269 posts

Re: Eight Myths on Software Engineering and GenAI

#241

Post by swat535 »

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…

> you can feed more and more and more

I have a meta thought..

Hypothetically what happens once there is no more data to be fed to the system? Are we expecting AI to invent its own data and reach full cognition?

Currently we are feeding it the data that humans created but if we stop (i.e "why bother?") thinking that AI will do it all?

Re: Eight Myths on Software Engineering and GenAI

#242

Post by geraneum »

dagss wrote: post #188
geraneum wrote: post #171

Earlier quoted context omitted.

> 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,…

> observe that the agent day after day do handle user input safely

How do you observe the issues that aren’t apparent via a GUI? Do you notice the circular logic in your reasoning?

Re: Eight Myths on Software Engineering and GenAI

#243

Post by mekael »

champagnepapi wrote: post #200
t-writescode wrote: post #177

Earlier quoted context omitted.

Goodness, how is that being tolerated? I guess it can’t be stopped without a lot of political capital; but 16k lines of code is HUGE, and I cannot imagine that it’s actually 16k lines of value - I’ve written whole new subsystems of a product in fewer lines. Are these all written in an exceptionally verbose language like Go or Java? Are they VERY well documented? Are they doing things they shouldn’t be doing???

Brother at my startup one person shipped 75k lines in two weeks. We’re living in the golden age of slop

I mean, I've done that for a couple of things, but probably 90+ percent was vendored libraries and javascript which could be ignored. Sadly, this is not one of those cases, and Im guessing yours isn't either?

Re: Eight Myths on Software Engineering and GenAI

#244

Post by derdi »

lz400 wrote: post #44

Like many others in the comments, I feel there are a lot of assumptions in this piece. Before, coding is only 14% therefore, small slice. I think that's a very superficial assumption. That was because coding was expensive and we needed to be sure we didn't code the wrong thing. If code is as cheap as it is now, we will optimize differently, we will structure around it. Instead of so many meetings we will code 5 diffe…

> Before, coding is only 14% therefore, small slice.

But also, no, because they write:

> “coding” (not including bug fixing, testing, etc.)

What if bug fixing includes "coding", or "writing code", or however one would want to define that? Especially in the enterprise setting they evoke, a lot of work will not be "coding" in the sense of churning out new features, but "coding" in the sense of fixing bugs. I know a lot of my "coding" is in this category. But we're not given a number for it. I suspect the slice would be bigger if they included this type of "coding".

Re: Eight Myths on Software Engineering and GenAI

#245

Post by archagon »

champagnepapi wrote: post #200
t-writescode wrote: post #177

Earlier quoted context omitted.

Goodness, how is that being tolerated? I guess it can’t be stopped without a lot of political capital; but 16k lines of code is HUGE, and I cannot imagine that it’s actually 16k lines of value - I’ve written whole new subsystems of a product in fewer lines. Are these all written in an exceptionally verbose language like Go or Java? Are they VERY well documented? Are they doing things they shouldn’t be doing???

Brother at my startup one person shipped 75k lines in two weeks. We’re living in the golden age of slop

software """engineering"""

Re: Eight Myths on Software Engineering and GenAI

#246

Post by satvikpendem »

dofm wrote: post #205
satvikpendem wrote: post #190

Earlier quoted context omitted.

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

Is this really true? At least one very headline AI researcher is pretty much an Anthropic spokesperson.

That they believe in the PR is itself PR, they're paid to be spokespeople as well as researchers.

Re: Eight Myths on Software Engineering and GenAI

#247

Post by paul7986 »

cjcenizal wrote: post #147
paul7986 wrote: post #36

Earlier quoted context omitted.

By trade I'm a UX Researcher/Designer who designs in code (HTML/CSS) and have done so since 2009. Recently I vibe coded an entire python app with a database and each time I didnt know what to do I would just feed screenshots to Gemini or Codex for guidance (i think i could share my screen with Codex and it can guide me via a voice conversation). I know I could follow up and build a companion iPhone and Android app us…

I also work in UX and SWE, and heavily use GenAI in my work. I don’t have a positive outlook for people who limit their career to one of those fields, but I do have a positive outlook for generalist, multi-disciplinary careers. When you have the experience and skill to steer product development from end-to-end, you can produce high-quality products super-quickly. The experience and skills are the differentiator — if…

So one person now doing the job a handful use to do. That's what I hear you saying and Ive been thinking since my lay off in Feb. prompting me to be back in school.

Re: Eight Myths on Software Engineering and GenAI

#248

Post by dxdm »

al_be_back wrote: post #236

> Myth 3: Lines of Code Written by AI... how come lines of code (or expressions) by an engineer aren't a good way to measure progress (Gates point etc) but GenAI tokens must count and be paid for?

That's a good point. They're not selling progress, they are claiming to enable progress by selling you (tokens in -> tokens out), making it your responsibility to connect the two. Filling that gap is part of your expertise that you can get paid for.

Re: Eight Myths on Software Engineering and GenAI

#249

Post by germandiago »

Yopolo wrote: post #222
germandiago wrote: post #220

Earlier quoted context omitted.

> I'm pretty sure we will solve this issue. Either already through World Models or another architecture. Please elaborate. How? With which technique? Currently the only path forward is to feed more data and tweak for specific situations (fitting, basically). How does that help in the general case or in new situations with current tecchnology (LLMs, concretely). Noatter how far you get, this is not a general or reliab…

> Please elaborate. How? With which technique? Reinforcement learning can just solve things even if they are new. It doesn't understand how a tool works? Give it a vm with the tool, a thousand agents and let it discover it automatically. Use the thumbs up/down emoji + chat analysis when a customer is unhappy, feed that to a RL Loop. The AI Researchers though work on World Models, grounding the AI and letting it simul…

> eah now i just ask the LLM to describe to me the bug. Works very well.

I think you are confusing giving theories about what a bug might be with certainty. It does help bc it csn accelerste things, but many times I had AIs with challenging bugs throwing a lot of misleading theories to me. For the easier bugs, I was just as capable most of the time. Not every time, so there is some potential time saving there. But also time waste.

As for research and fast prototyping you are right: I find it a good tool to explore bc yiu do not need the quality of a final product and researxh is in big part throwaway work.

But I was talking about software that needs features, maintenance, etc. This is just not the same thing.

Re: Eight Myths on Software Engineering and GenAI

#250

Post by dagss »

geraneum wrote: post #242
dagss wrote: post #188

Earlier quoted context omitted.

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,…

> observe that the agent day after day do handle user input safely How do you observe the issues that aren’t apparent via a GUI? Do you notice the circular logic in your reasoning?

What do you mean GUI? Of course the observation of the agents behaviour happens by reading the code it emits.
Post reply on HN