The future of software development is software developers • Hacker News Board

Re: The future of software development is software developers

#261

Post by bdcravens » Tue, Dec 30, 2025, 1:04 PM UTC

snickerer wrote: post #198

After working with agent-LLMs for some years now, I can confirm that they are completely useless for real programming. They never helped me solve complex problems with low-level libraries. They can not find nontrivial bugs. They don't get the logic of interwoven layers of abstractions. LLMs pretend to do this with big confidence and fail miserably. For every problem I need to turn my brain to ON MODE and wake up, the…

"real programming"

Perhaps you're doing some amazing low-level work, but it feels like you're way overestimating how much of our industry does that. A massive amount of developers show up to work every day and just stitch together frameworks and libraries.

In many ways, it feels similar to EVs. Just because EVs aren't yet, and may never be, effective to moving massive amounts of cargo in a day with minimal refueling, doesn't mean that they aren't an effective solution for the bulk of drivers who have an average commute of 40 miles a day.

Re: The future of software development is software developers

#262

Post by embedding-shape » Tue, Dec 30, 2025, 1:04 PM UTC

underdeserver wrote: post #245

snickerer wrote: post #198

After working with agent-LLMs for some years now, I can confirm that they are completely useless for real programming. They never helped me solve complex problems with low-level libraries. They can not find nontrivial bugs. They don't get the logic of interwoven layers of abstractions. LLMs pretend to do this with big confidence and fail miserably. For every problem I need to turn my brain to ON MODE and wake up, the…

People are saying Codex 5.2 fullsolved crypto challenges in 39C3 CTF last weekend. Three months ago I would have agreed with you, but anecdotal evidence says Codex 5.2 and Opus 4.5 are finally there.

You'll get a vastly different experience the more you use these tools and learn their limitations and how you can structure things effectively to let them do their job better. But lots of people, understandably, don't take the time to actually sit down and learn it. They spend 30 seconds on some prompt not even a human would understand, and expect the tooling to automatically spend 5 hours trying its hardest at implementing it, then they look at the results and conclude "How could anyone ever be productive with this?!".

People say a lot of things, and there is a lot of context behind what they're saying that is missing, so then we end up with conversations that basically boil down to one person arguing "I don't understand how anyone cannot see the value in this" with another person thinking "I don't understand how anyone can get any sort of value out of this", both missing the other's perspective.

Re: The future of software development is software developers

#263

Post by kvemkon » Tue, Dec 30, 2025, 1:06 PM UTC

constantcrying wrote: post #237

shafyy wrote: post #236

Earlier quoted context omitted.

> The promise of LLMs is not that they solve the single most difficult tasks for you instantly, but that they do the easy stuff well enough that they replace offshore teams. But that's exactly the *promise* of LLMs by the hypepeople behind it.

>But that's exactly the promise of LLMs by the hypepeople behind it. I do not know and do not care what the "hypepeople" say. I can tell you that, by pure logic alone, LLMs will be superior at simple and routine tasks sooner, which means they will compete with outsourced labor first. LLMs need to be measured against their competition and their competition right now is outsourced labor. If an LLM can outperform an off…

> If an LLM can outperform an offshore team at a fraction of the cost,..

And "a few moments later" happens the same as with those "cost effective" clouds.

[1] https://www.heise.de/en/news/IDC-Many-companies-want-partly-...

[2] https://www.idc.com/resource-center/blog/storm-clouds-ahead-... (original)

Re: The future of software development is software developers

#264

Post by embedding-shape » Tue, Dec 30, 2025, 1:08 PM UTC

conartist6 wrote: post #257

conartist6 wrote: post #246

Earlier quoted context omitted.

More than any other effect they have LLMs breed something called "learned helplessness". You just listed a few things it may stay better than you at, and a few things that it is not better than you at and never will be . Planning long running projects and deciding are things only you can do well!! Humans manage costs. We look out for our future. We worry. We have excitement, and pride. It wants you to think none of t…

Plus I think I've almost never see so little competition for what I think are the real prizes! Everyone's off making copies of copies of copies of the same crappy infrastructure we already have. They're busy building small inconsequential side projects so they can say they built something using an LLM.

> They're busy building small inconsequential side projects

Unironically, sending a program to build those for me have send me almost endless amount of time. I'm a pretty distracted individual, and pretty anal about my workflow/environment, so lots of times I've spent hours going into rabbit-holes to make something better, when I could have just sucked it up and do it the manual way instead, even if it takes mental energy.

Now, I can still do those things, but not spend hours, just a couple of minutes, and come back after 20-30 minutes to something that lets me avoid that stuff wholesale. Once you start stacking these things, it tends to save a lot of time and more importantly, mental energy.

So the programs by themselves are basically "small inconsequential side projects" because they're not "production worthy and web scale SaaS ready to earn money", but they help me and others who are building those things in a big way.

Re: The future of software development is software developers

#265

Post by embedding-shape » Tue, Dec 30, 2025, 1:10 PM UTC

monsieurbanana wrote: post #225

jvanderbot wrote: post #215

Earlier quoted context omitted.

I think any further discussion about quality just needs to have the following metadata: - Language - Total LOC - Subject matter expertise required - Total dependency chain - Subjective score (audited randomly) And we can start doing some analysis. Otherwise we're pissing into ten kinds of winds. My own subjective experience is earth shattering at webapps in html and css (because I'm terrible and slow at it), and anno…

I agree in that these discussions (this whole hn thread tbh) are seriously lacking in concrete examples to be more than holy wars 3.0. Besides one point: junior developers can learn from their egregious mistakes, llms can't no matter how strongly worded you are in their system prompt. In a functional work environment, you will build trust with your coworkers little by little. The pale equivalent in LLMs is improving…

> Besides one point: junior developers can learn from their egregious mistakes, llms can't no matter how strongly worded you are in their system prompt.

I think if you set off an LLM to do something, and it does a "egregious mistake" in the implementation, and then you adjust the system prompt to explicitly guard against that or go towards a different implementation and you restart from scratch again yet it does the exact same "egregious mistake", then you need to try a different model/tool than the one you've tried that with.

It's common with smaller models, or bigger models that are heavily quanitized that they aren't great at following system/developer prompts, but that really shouldn't happen with the available SOTA models, I haven't had something ignored like that in years by now.

Re: The future of software development is software developers

#266

Post by skydhash » Tue, Dec 30, 2025, 1:14 PM UTC

mattmanser wrote: post #173

jmogly wrote: post #69

Earlier quoted context omitted.

I would say it varies from 0x to a modest 2x. It can help you write good code quickly, but, I only spent about 20-30% of my time writing code anyway before AI. It definitely makes debugging and research tasks much easier as well. I would confidently say my job as a senior dev has gotten a lot easier and less stressful as a result of these tools. One other thing I have seen however is the 0x case, where you have given…

Ok, if you're a senior dev, have you 'caught' it yet? Ask it a question about something you know well, and it'll give you garbage code that it's obviously copied from an answer on SO from 10 years ago. When you ask it for research, it's still giving you garbage out of date information it copied from SO 10 years ago, you just don't know it's garbage.

I use web search (DDG) and I don’t think I have ever try more than one queries in the vast majority of cases. Why because I know where the answer is, I’m using the search engine as an index to where I can find it. Like “csv python” to find that page in the doc.

Re: The future of software development is software developers

#267

Post by sokoloff » Tue, Dec 30, 2025, 1:16 PM UTC

techblueberry wrote: post #249

sokoloff wrote: post #230

Earlier quoted context omitted.

It is certainly possible that AI is the one great disruptor that we can’t adapt to. History over millenia has me taking the other side of that bet, seeing the disruptions and adaptations from factory farming, internal combustion engines, moving assembly lines, electrification, the transistor, ICs, wired then wireless telecommunications, the internet, personal computing, and countless other major disruptions.

Have we though? 1. Fundamentals do change, Yuval Noah Harari made this point in the book Sapiens, but basically there are core beliefs (in fact the idea that things do change for the better is relatively new, “the only constant is change”. Wasn’t really true before the 19th century. What does “the great disrupter we can’t adapt to” mean exactly? If humans annihilate themselves from climate change, the earth will adap…

Isn’t this “healthy, large middle class” a reality that is less than 100 years old in the best of cases? (After a smaller initial emergence perhaps 100 years prior to that.) In 250K years since modern humans emerged, that’s a comparative blink of an eye.

There might be slight local dips along the timeline, but I think most Westerners (and maybe most people, but my lived experience is Western) would not willingly trade places with their same-percentile positioned selves from 100, 200, 500, 1000, 2000, 10K, 50K, or 250K years ago. The fact that few would choose to switch has to be viewed with some positive coefficient in a reasonable success metric.

Re: The future of software development is software developers

#268

Post by meindnoch » Tue, Dec 30, 2025, 1:20 PM UTC

threethirtytwo wrote: post #115

hansmayer wrote: post #42

Earlier quoted context omitted.

> I’ve done things with Claude I never thought possible for myself to do, That's the point champ. They seem great to people when they apply them to some domain they are not competent it, that's because they cannot evaluate the issues. So you've never programmed but can now scaffold a React application and basic backend in a couple of hours? Good for you, but for the love of god have someone more experienced check it…

What you wrote here was relevant about 9 months ago. It’s now outdated. The pace and velocity of improvement of Ai can only be described as violent. It is so fast that there are many people like you who don’t get it.

Sure. Just hurry up bro, because Kurzweil is not getting any younger.

Re: The future of software development is software developers

#269

Post by sod22 » Tue, Dec 30, 2025, 1:22 PM UTC

fragmede wrote: post #250

snickerer wrote: post #198

After working with agent-LLMs for some years now, I can confirm that they are completely useless for real programming. They never helped me solve complex problems with low-level libraries. They can not find nontrivial bugs. They don't get the logic of interwoven layers of abstractions. LLMs pretend to do this with big confidence and fail miserably. For every problem I need to turn my brain to ON MODE and wake up, the…

> After working with agent-LLMs for some years now, I can confirm that they are completely useless for real programming. "completely useless" and "real programming" are load bearing here. Without a definition to agree on for those terms, it's really hard not to read that as you're trying to troll us by making a controversial unprovable claim that you know will get people that disagree with you riled up. What's especi…

Who cares about semantics.

Ultimately it all boils down to the money - show me the money. OAI have to show money and so do its customers from using this tool.

But nope, the only thing out there where it matters is hype. Nobody is on an earnings call clearly showing how they had a numerical jump in operating efficiency.

Until I see that, this technology has a dated shelf life and only those who already generate immense cash flows will fund its continued existence given the unfavourable economics of continued reinvestment where competition is never-ending.

Re: The future of software development is software developers

#270

Post by meindnoch » Tue, Dec 30, 2025, 1:27 PM UTC

techblueberry wrote: post #243

qweiopqweiop wrote: post #178

Earlier quoted context omitted.

Have you tried Opus 4.5 (or similar recent models)? With Claude code 2, it's actually harder to mess things up IMO

I remember when about a year ago people were asking the same thing about gpt-4.5, the answer is always “yes, I’ve tried them all”

Ok, but have you tried claude-sonnet-GPT-codex-4.5-thinking-fast? That's the game changer. Anyone saying bad things about vibe coding without trying claude-sonnet-GPT-codex-4.5-thinking-fast is like a dinosaur to me, doomed to extinction. Seriously, give claude-sonnet-GPT-codex-4.5-thinking-fast a try, you'll thank me ;)