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

Professional software developers don't vibe, they control

arxiv.org

Post reply on HN
Print view View original

201–210 of 259 posts

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

#201

Post by epolanski »

_cenw wrote: post #31
runtimepanic wrote: post #4

The title is doing a lot of work here. What resonated with me is the shift from “writing code” to “steering systems” rather than the hype framing. Senior devs already spend more time constraining, reviewing, and shaping outcomes than typing syntax. AI just makes that explicit. The real skill gap isn’t prompt cleverness, it’s knowing when the agent is confidently wrong and how to fence it in with tests, architecture,…

Is anyone else getting more mentally exhausted by this? I get more done, but I also miss the relaxing code typing in the middle of the process.

Yes it's taxing and mentally draining, reading code and connecting dots is always harder than writing it.

And if you let the AI too loose, as when you try to vibe code an entirely new program, I end up in the situation where in 1 day I have a good prototype and then I can spend easily 5 times as much sorting the many issues and refactoring in order to have it scale to the next features.

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

#203

Post by qweiopqweiop »

simonw wrote: post #125
William_BB wrote: post #111

Earlier quoted context omitted.

Ok I will bite. Every single example you gave is in a hobby project territory. Relatively self-contained, maintainable by 3-4 devs max, within 1k-10k lines of code. I've been successfully using coding agents to create such projects for the past year and it's great, I love it. However, lots of us here work on codebases that are 100x, 1000x the size of these projects you and Karpathy are talking about. Years of domain…

Most of the stuff I'm talking about here came out in November. There hasn't been much time for professional teams to build new things with it yet, especially given the holidays!

For what it's worth, I'm working with it on a huge professional monorepo, and the difference was also stark.

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

#204

Post by littlestymaar »

sarchertech wrote: post #143
jaggederest wrote: post #10

Earlier quoted context omitted.

Hi it's me, the guy who wants to be a full-time code reviewer.

If you really did that full time and never wrote code, you’d be a terrible reviewer.

This is fine for us who've been building code by hand for many years before the advent of LLMs but it's definitely going to be a problem going forward.

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

#205

Post by wiseowise »

throw-12-16 wrote: post #190
websiteapi wrote: post #15

we've never seen a profession drive themselves so aggressively to irrelevance. software engineering will always exist, but it's amazing the pace to which pressure against the profession is rising. 2026 will be a very happy new year indeed for those paying the salaries. :)

Software Engineers will still exist. Software Devs not so much. There is a huge difference between the two and they are not interchangeable.

Good luck convincing new overlords.

Your take is this meme https://knowyourmeme.com/memes/dig-the-fucking-hole.

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

#206

Post by danielbln »

ActionHank wrote: post #181
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…

For what it’s worth I know this is likely intended to read as the new generation of models will somehow better than any paper will be able to gauge, that hasn’t been my experience. Results are getting worse and less accurate, hell, I even had Claude drop some Chinese into a response out of the blue one day.

I can absolutely not corroborate this, Opus 4.5 has been nothing but stellar.

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

#207

Post by mannycalavera42 »

ActionHank wrote: post #181
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…

For what it’s worth I know this is likely intended to read as the new generation of models will somehow better than any paper will be able to gauge, that hasn’t been my experience. Results are getting worse and less accurate, hell, I even had Claude drop some Chinese into a response out of the blue one day.

same here. While getting a commandline for ffmpeg instead of giving me the option "soft-knee" it used "soft-膝" (where 膝 is the chinese for knee) was easy to spot and figure out but still... pretty rubbishy ¯ \ _ (ツ) _ / ¯

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

#208

Post by mannycalavera42 »

littlestymaar wrote: post #204
sarchertech wrote: post #143

Earlier quoted context omitted.

If you really did that full time and never wrote code, you’d be a terrible reviewer.

This is fine for us who've been building code by hand for many years before the advent of LLMs but it's definitely going to be a problem going forward.

strong +1 here :-)

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

#209

Post by generic92034 »

epolanski wrote: post #200
simonw wrote: post #102

Earlier quoted context omitted.

Coding agents and much better models. Claude Code or Codex CLI plus Claude Opus 4.5 or GPT 5.2 Codex. The latest models and harnesses can crunch on difficult problems for hours at a time and get to working solutions. Nothing could do that back in ~March. I shared some examples in this comment: https://news.ycombinator.com/item?id=46436885

Cool, but most developers do mundane stuff like glueing APIs and implementing business logic, which require oversight and review. Those crunching hard problems will still review what's produced in search of issues.

What is (in general) mundane about business logic? This can be highly complex, with deep process integration all over your modules.

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

#210

Post by soulofmischief »

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…

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 models, and 5.2 codex, are leagues better than GPT-4 when it comes to solving problems procedurally, using tools, and deep discussion of scientific, mathematic, philosophical and engineering problems.

Models have increasingly longer context, especially some Google models. OpenAI has released very good image models, and great editing-focused image models in general have been released. Predictably better multimodal inference over the short term is unlocking many cool near-term possibilities.

Additionally, we have seen some incredible open source and open weight models released this year. Some fully commercially viable without restriction. And more and more smaller TTS/STT projects are in active development, with a few notable releases this year.

Honestly, the landscape at the end of the year is impressive. There has been great work all over the place, almost too much to keep up with. I'm very interested in the Genie models and a few others.

For an idea:

At the beginning of the year, I was mildly successful getting at coding models to make changes in some of my codebases, but the more esoteric problems were out of reach. Progress in general was deliberate and required a lot of manual intervention.

By comparison, in the last week I've prototyped six applications at levels that would take me days to weeks individually, often developing multiple at the same time, monitoring agentic workflows and intervening only when necessary, relying on long preproduction phases with architectural discussions and development of documentation, requirements, SDDs... and detailed code review and refactoring processes to ensure adherence to constraints. I'm morphing from a very busy solo developer into a very busy product manager.

Post reply on HN