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

Ask HN: How is AI-assisted coding going for you professionally?

news.ycombinator.com

Post reply on HN
Print view View original

621–630 of 657 posts

Re: Ask HN: How is AI-assisted coding going for you professionally?

#621

Post by er453r »

reachableceo wrote: post #351
er453r wrote: post #288

For my specific niche (medical imaging) all current models still suck. The amount of expert knowledge required to understand the data and display it in the right way - probably never was in the training set. We have this one performance-critical 3D reconstruction engine part, that just just has to go FAST through billions of voxels. From time to time we try to improve it, by just a bit. I have probably wasted at leas…

Did you feed back the results of the tests / benchmark to the model? I’m presuming you have a very robust test framework / benchmark setup etc? I’m presuming you fed the model the baseline results of that setup as a starting point ?

Everything is contained in unit tests, so it is really easy to check a small change and get the results for the same dataset.

I have had put the agents in a small feedback loop - but limited to ~5 iterations, since I do not want to burn through my credits. Honestly, I think putting it in a loop for a case like this does not show the "intelligence" part of AI, it makes it more of a more-sophisticated random walk.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#622

Post by P-MATRIX »

The multi-agent divergence issue keeps coming up. When each agent restarts cold, there's no agreed-upon view of what's been decided versus what's still in flux — so they end up working from different assumptions about the same codebase. External state files help but don't fix the root thing, which is that agents need a shared starting point: what constraints are currently in force, what the risk posture is, what's already been resolved. Without that baseline, divergence isn't a bug, it's structural.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#624

Post by dendrite9 »

jermaustin1 wrote: post #616
windex wrote: post #554

Earlier quoted context omitted.

>so you can make fries and ketchup from the same plant! We should be friends. I like your ideas.

I'm always looking for people to share my weird ideas that have absolutely nothing to do with software or computers. Unfortunately my only friends are all software people who have no interest outside of computers. Something I've found to have very little interest in anymore.

Did you see this last year about the origins of potatoes?

I'd like to get into grafting fruit trees, my uncle was a major fruit eater and filled the yard with many varieties of apples and pears. The apple tree where I live was a mess and I've jsut started the pruning to get it under control.

https://www.npr.org/2025/08/13/nx-s1-5494517/strange-but-tru...

Re: Ask HN: How is AI-assisted coding going for you professionally?

#625

Post by tmaly »

viccis wrote: post #268

Haven't seen this mentioned yet, but the worst part for me is that a lot of management LOVES to use Claude to generate 50 page design documents, PRDs, etc., and send them to us to "please review as soon as you can". Nobody reads it, not even the people making it. I'm watching some employees just generate endless slide decks of nonsense and then waffle when asked any specific questions. If any of that is read, it is b…

If Claude Code can parse these design documents, I would recommend making a skill to do an adversarial review of the document. Then just generate that review, do some minor edits to make it look like a human wrote it and send it back to them.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#626

Post by andrei_says_ »

tmaly wrote: post #625
viccis wrote: post #268

Haven't seen this mentioned yet, but the worst part for me is that a lot of management LOVES to use Claude to generate 50 page design documents, PRDs, etc., and send them to us to "please review as soon as you can". Nobody reads it, not even the people making it. I'm watching some employees just generate endless slide decks of nonsense and then waffle when asked any specific questions. If any of that is read, it is b…

If Claude Code can parse these design documents, I would recommend making a skill to do an adversarial review of the document. Then just generate that review, do some minor edits to make it look like a human wrote it and send it back to them.

Which is fine if we are fine with pretending to do our jobs.

But deep down I know that slop is noise and words no longer represent understanding.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#627

Post by andrei_says_ »

ZoomZoomZoom wrote: post #528
alper wrote: post #515

Earlier quoted context omitted.

One group of people pretends to have written something and another group of people pretends to have read something. Much productivity is gained. Zizek had a great point about this.

At least both get paid in not-pretend money.

For the time being. Their manager is under constant pressure to lay them off and replace them with “ai”.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#628

Post by enceladus06 »

tim-tday wrote: post #234
onlyrealcuzzo wrote: post #10

I work at a FAANG. Professionally, I have had almost no luck with it, outside of summarizing design docs or literally just finding something in the code that a simple search might not find: such is this team's code that does X? I am yet to successfully prompt it and get a working commit. Further, I will add that I also don't know any ICs personally who have successfully used it. Though, there's endless posts of peopl…

This is wild. I’m on the other end. I’ve probably prompted 10,000 lines of working code in the last two months. I started with terraform which I know backwards and forwards. Works perfectly 95% of the time and I know where it will go wrong so I watch for that. (Working both green field, in other existing repos and with other collaborators) Moved on to a big data processing project, works great, needed a senior engine…

What I've found Claude really helpful for is filling in the gaps. When you know vaguely how do to something like interpret data, but what other packages exist in xyz random technical domain? That is how I found for expample https://cran.r-project.org/web/packages/gggenes/vignettes/in... and Orthofinder when trying to teaching myself computational biology.

But sometimes even Claude gets stuck e.g. when I was trying to set up micropython via platformio running inside wsl2 on a windows 11 it got stuck setting up my ESP32 board.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#629

Post by iExploder »

After 12+ years of hardcore c/c++ in embedded, I'm having a blast with Claude...

my productivity definitely improved.. especially with tasks that I would consider boring or tedious to hand code due to repetition (I have coded this at company X and now Im doing N-th variant of it again at company Y from scratch...) claude will mostly one-shot these things with proper prompt and constraints.

I think software engineering has changed, the new paradigm is creating proper fixtures for agents to run in (like environment, code execution and bench/unit test access) and defining specs, inputs, outputs and constraints of the problem, then let Claude iterate on it and sip on coffee.

I find that some "taste" in software and understanding complex systems is needed for "agentic coding" to be useful. I like to constrain the system (code and problem wise) to decrease the potential search space, otherwise the things tend to fall apart after a few prompts.

One negative I'm seeing is people generate huge PRs with endless PR descriptions, just cos its easy... I believe less is more with these tools and effort should be made to keep the changes minimal and filter out of the excessive noise from code and docs... however I understand the incentive of LLM providers is to maximize amount of changes and complexity of the codebases (more tokens more $$ to extract :) so this will most likely be a never-ending battle

Re: Ask HN: How is AI-assisted coding going for you professionally?

#630

Post by iExploder »

karmasimida wrote: post #424
lazy_afternoons wrote: post #408

Surprised to see HN being bearish on this. I have 10 years of experience. I am a reasonable engineer. I can tell you that about half of the hype on twitter is real. It is a real blessing for small teams. We have 100k DAU for a consumer crud app. We built and maintain everything in-house with 3 engineers. This would have taken atleast 10 engineers 3-4 years back. We don't have a bug list. We are not "vibe coding" , 2…

HN is in denial, which is understandable AI is already better at understanding code than 99.99% of human, the more I use it the more I believe this is true. It can draw connections between dots far quicker and accurate than a human could ever be. At very least, AI is going to be a must even as a co-supervisor to your project What in doubt right now, is whether AI can manage a codebase fully autonomously without bring…

> AI is already better at understanding code than 99.99% of human

not to nitpick here, but AI does not understand code. AI (LLMs) are token predictors pr at best sophisticated pattern matching in huge search space...

Post reply on HN