Professional software developers don't vibe, they control • Hacker News Board

Re: Professional software developers don't vibe, they control

#221

Post by game_the0ry » Wed, Dec 31, 2025, 2:00 PM UTC

flurie wrote: post #91

game_the0ry wrote: post #2

> Through field observations (N=13) and qualitative surveys (N=99)... Not a statistically significant sample size.

This is a qualitative methods paper, so statistical significance is not relevant. The rough qualitative equivalent would instead be "data saturation" (responses generally look like ones you've received already) and "thematic saturation" (you've likely found all the themes you will find through this method of data collection). There's an intuitive quality to determining the number of responses needed based on the topi…

So, I upvoted your comment bc I genuinely believe there is something in your comments worth learning from, but...

> This is a qualitative methods paper, so statistical significance is not relevant.

I have never heard of a "qualitative methods paper" and it sounds like something a researcher would do to push a narrative with "qualitative data" rather than data that could be measured.

Tell me why I am wrong.

Re: Professional software developers don't vibe, they control

#222

Post by aspenmartin » Wed, Dec 31, 2025, 2:01 PM UTC

mhitza wrote: post #195

aspenmartin wrote: post #26

Earlier quoted context omitted.

I think the issue is folks talk past each other. People who find coding agents useful or enjoyable are labeled “on the hype train” and folks for which coding agents don’t work for them or their workflow are considered luddites. There are an incredible number of contradicting claims and predictions out there as well, and I believe what we see is folks projecting their reaction to some amalgamation of them onto others.…

Hard to have a conversation when often the critics of LLM output receive replies like "What, you used last week's model?! No, no, no, this one is a generational leap" Too many people are invested into AI's success to have a balanced conversation. Things will return to normal after a market shakedown of a few larger AI companies.

On HN I think you overestimate the number of optimists that are optimists because they have some vested interest. Everyone everywhere arguably has a vested interest. I would also argue all of the folks on HN that are hostile and dismissive of coding agents also have a vested interest (just for the sake of contrasting your argument). If coding agents were really crappy I wouldn’t be using them just like I didn’t use them until end of 2025.

What conversation is hard to have? If you mean trying to convince people coding agents can or cannot do a specific thing then that may never go away. If you take an overall theme or capability, in some cases it will “just work” and in other cases it needs some serious steering or scaffolding, and in other cases it will just waste as much time as you will let it. It’s an imperfect tool and it may always be, and two people insisting it can do something and it cannot do that same thing may both be right.

What is troubling to me is the attitude of folks that are heavily hostile towards these models and the people that use them. People routinely conflate market promises and actual delivered tools and capabilities and lump people who enjoy and get lots of mileage out of these tools into what appears to be a big strawman camp of fawning fans who don’t understand or appreciate Real Software Engineering; people who would write bad code anyway and not know. It’s quite insulting but also wrong. Not saying you are part of this camp! But as one lonely optimist in a sea of negativity that’s certainly the perspective I’ve developed from the “conversations” I’ve seen on HN

Re: Professional software developers don't vibe, they control

#223

Post by danielbln » Wed, Dec 31, 2025, 2:03 PM UTC

perfmode wrote: post #77

tikimcfee wrote: post #42

Earlier quoted context omitted.

Ya know, I have to admit feeling something like this. Normally, the amount of stuff I put together in a work day offers a sense of completion or even a bit of a dopamine bump because of a "job well done". With this recent work I've been doing, it's instead felt like I've been spending a multiplier more energy communicating intent instead of doing the work myself; that communication seems to be making me more tired th…

You’re possibly not entering into the flow state anymore. Flow is effortless. and it is rejuvenating. I believe: While communication can be satisfying, it’s not as rejuvenating as resting in our own Being and simply allowing the action to unfold without mental contraction. Flow states. When the right level of challenge and capability align and you become intimate with the problem. The boundaries of me and the problem…

Flow state can happen at various levels of abstraction, not just when hand writing code in a gen 3 language.

Re: Professional software developers don't vibe, they control

#224

Post by danielbln » Wed, Dec 31, 2025, 2:04 PM UTC

whstl wrote: post #149

MikeTheGreat wrote: post #121

Earlier quoted context omitted.

I forget where I saw this (a Medium post, somewhere) but someone summed this up as "I didn't sign up for this just to be a tech priest for the machine god".

Someone commented yesterday that managers and other higher-ups are "already ok with non-deterministic outputs", because that's what engineers give them. As a manager/tech-lead, I've kind of been a tech priest for some time.

Which is why it's so funny to hear seasoned engineers lament the probabilistic nature of AI systems, and how you have to be hand setting code to really think about the problem domain.

They seem to all be ICs that forget that there are abstraction layers above them where all of that happens (and more).

Re: Professional software developers don't vibe, they control

#225

Post by danielbln » Wed, Dec 31, 2025, 2:10 PM UTC

lifetimerubyist wrote: post #54

banbangtuth wrote: post #9

You know what. After seeing all these articles about AI/LLM for these past 4 years, about how they are going to replace me as software developers and about how I am not productive enough without using 5 agents and being a project manager. I. Don't. Care. I don't even care about those debates outside. Debates about do LLM work and replace programmers? Say they do, ok so what? I simply have too much fun programming. I…

Hear hear. I didn't spend half my life getting an education, competing in the corporate crab bucket, retraining and upskilling just to turn into a robot babysitter.

Then continue to write code as a hobby, noone is going to take that away from you. But if you want someone to pay you for hand setting code the way you always have then .. well you might find that harder and harder as time goes on.

Re: Professional software developers don't vibe, they control

#226

Post by danielbln » Wed, Dec 31, 2025, 2:15 PM UTC

lexandstuff wrote: post #71

zwnow wrote: post #17

Idk, I still mostly avoid using it and if I do, I just copy and paste shit into the Claude web version. I wont ever manage agents as that sounds just as complicated as coding shit myself.

It's not complicated at all. You don't "manage agents". You just type your prompt into an terminal application that can update files, read your docs and run your tests. As with every new tech there's a hell of a lot of noise (plugins, skills, hooks, MCP, LSP - to quote Kaparthy) but most of it can just be disregarded. No one is "behind" - it's all very easy to use.

Easy to use, hard to master. Or: low skill floor, high skill ceiling. My output wouldn't be nearly as good without subagents and skills, and MCPs are somewhat required if you deploy tool using agents at scale.

It's like saying all you need is notepad to develop. It's not wrong, but.. you know.

Re: Professional software developers don't vibe, they control

#227

Post by danielbln » Wed, Dec 31, 2025, 2:19 PM UTC

danavar wrote: post #186

So much of my professional SWE jobs isn't even programming - I feel like this is a detail missed by so many. Generally people just stereotype SWE as a programmer, but being an engineer (in any discipline) is so much more than that. You solve problems. AI will speed up the programming work-streams, but there is so much more to our jobs than that.

There is also so much more you can automate and use AI agents for than "programming". It's the world's best rubber duck, for one. It also can dig through code bases and compile information on data flows, data models and so on. Hell, it can automate effectively any task you do on the terminal.

Re: Professional software developers don't vibe, they control

#228

Post by danielbln » Wed, Dec 31, 2025, 2:20 PM UTC

throw-12-16 wrote: post #193

Getting big "I'll keep making saddles in the era of automobiles" vibes from these comments.

Yeah, it feels many SWEs have painted themselves into a corner. They love the nose-to-code-grindstone process and chain themselves to the abstraction layer of today. I don't think it's gonna end well for them, let's see.

Re: Professional software developers don't vibe, they control

#229

Post by simonw » Wed, Dec 31, 2025, 2:32 PM UTC

foldr wrote: post #213

soulofmischief wrote: post #210

Earlier quoted context omitted.

2025 has been a wild year for agentic coding models. Cutting-edge models in January 2025 don't hold a candle to cutting edge models in December 2025. Just the jump from Sonnet 3.5 to 3.7 to 4.5, and Opus 4.5 has been pretty massive in terms of holistic reasoning, deep knowledge as well as better procedural and architectural adherence. GPT-5 Pro convinced me to pay $200/mo for an OpenAI subscription. Regular 5.2 model…

>By comparison, in the last week I've prototyped six applications at levels that would take me days to weeks individually [...] I don't doubt that the models have got better, but you can go back two or three years and find people saying the exact same stuff about the latest models back then.

I don't think that's true of three years ago - that's taking us back into GPT-3 territory.

And two years ago we were mostly still stuck with GPT-4 which had an 8,000 input context limit, very challenging to get real coding work done with that.

Easy enough to prove though, find some examples of people saying that 2-3 years ago and I shall concede the point!

Re: Professional software developers don't vibe, they control

#230

Post by simonw » Wed, Dec 31, 2025, 2:35 PM UTC

utopiah wrote: post #197

simonw wrote: post #33

This is pretty recent - the survey they ran (99 respondents) was August 18 to September 23 2025 and the field observations (watching developers for 45 minute then a 30 minute interview, 13 participants) were August 1 to October 3. The models were mostly GPT-5 and Claude Sonnet 4. The study was too early to catch the 5.x Codex or Claude 4.5 models (bar one mention of Sonnet 4.5.) This is notable because a lot of acade…

> academic papers take 6-12 months to come out, by which time the LLM space has often moved on by an entire model generation. This is a recurring argument which I don't understand. Doesn't it simply mean that whatever conclusion they did was valid then? The research process is about approximating a better description of a phenomenon to understand it. It's not about providing a definitive answer. Being "an entire mode…

The problem is with how people interpret these results.

A paper comes out that says "we did a study of developers and found that AI-assistance had no impact on their productivity (using the state of the art models available in September 2024) and a lot of people will point to that as incontestable evidence that "AI doesn't work".