Hacker News new | past | comments | ask | show | jobs | submit
piker | on: Ask HN: How is AI-assisted coding going for you professionally?
I am working on a sub 100KLOC Rust application and can't productively use the agentic workflows to improve that application.

On the other hand, I have tried them a number of times in greenfield situations with Python and the web stack and experienced the simultaneous joy and existential dread of others. They can really stand new projects up quick.

As a founder, this leaves me with what I describe as the "generation ship" problem. Is it possible that the architecture we have chosen for my project is so far out of the training data that it would be faster to ditch the project and reimplement it from scratch in a Claude-yolo style? So far, I'm convinced not because the code I've seen in somewhat novel circumstances is fairly mid, but it's hard to shake the thought.

I do find chatting with the models incredibly helpful in all contexts. They are also excellent at configuring services.

koyote | parent | next
If what you are doing is novel then I don't think yolo'ing it will help either. Agents don't do novel. I've even noticed this in meeting summaries produced by AI: A prioritisation meeting? AI's summary is concise, accurate, useful. A software algorithm design meeting, trying to solve a domain-specific issue? AI did not understand a word of what we discussed and the summary is completely garbled rubbish.

If all you're doing is something that already exists but you decided to architecture it in a novel way (for no tangible benefit), then I'd say starting from scratch and make it look more like existing stuff is going to help AI be more productive for you. Otherwise you're on your own unless you can give AI a really good description of what you are doing, how things are tied together etc. And even then it will probably end up going down the wrong path more often than not.

loading story #47398402
cyanydeez | parent
I'm surprised there's no more attempts to stablize around a base model, like in stable diffusion, then augment those models with LoRas for various frameworks, and other routine patterns. There's so much going into trying to build these omnimodels, when the technology is there to mold the models into more useful paradigms around frameworks and coding patterns.

Especially, now that we do have models that can search through code bases.