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

My LLM codegen workflow

harper.blog

Post reply on HN
Print view View original

101–110 of 168 posts

Re: My LLM codegen workflow

#101

Post by dimitri-vs »

cipehr wrote: post #94

Am I the only one that doesn’t see the hype with Claude? I recently tried it, hit the usage limit, read around found tons of blogs and posts from devs saying Claude is the best code assistant LLM… so I purchased Claude pro… and I hate it. I have been asking it surface level questions about Apache spark (configuring the number of tasks retries, errors, error handling, etc.) and it hallucinated so much, so frequently.…

Claude is exceptionally good at taking "here is two paragraphs of me rambling off about a feature I want in broken voice to text" and actually understanding what you want. It has really good prompt adherence but at the same time knows when to read between the lines.

Re: My LLM codegen workflow

#103

Post by sejje »

briga wrote: post #73

Absolutely LLMs are great for greenfield projects. They can get you to a prototype for a new idea faster than any tool yet invented. Where they start to break down, I find, is when you ask it to make changes/refactors to existing code and mature projects. They usually lack context, so they doesn't hesitate to introduce lots of extra complexity, add frameworks you don't need, and in general just make the situation wor…

You can use LLMs and actually understand your code.

Re: My LLM codegen workflow

#105

Post by fastball »

rollinDyno wrote: post #25

Something I quickly learned while retooling this past week is that it’s preferable not to add opinionated frameworks to the project as they increase the size of the context the model should be aware of. This context will also not likely be available in the training data. For example, rather than using Plasmo for its browser extension boilerplate and packaging utilities, I’ve chosen to ask the LLM to setup all of that…

It's not just frameworks – I noticed this recently when starting a new project and utilizing EdgeDB. They have their own Typescript query builder, and [insert LLM] cannot write correct constructions with that query builder to save its life.

Re: My LLM codegen workflow

#106

Post by y1n0 »

sejje wrote: post #103
briga wrote: post #73

Absolutely LLMs are great for greenfield projects. They can get you to a prototype for a new idea faster than any tool yet invented. Where they start to break down, I find, is when you ask it to make changes/refactors to existing code and mature projects. They usually lack context, so they doesn't hesitate to introduce lots of extra complexity, add frameworks you don't need, and in general just make the situation wor…

You can use LLMs and actually understand your code.

I agree, but where I run into problems is my existing projects are large. In the last couple weeks I’ve had two cases where I really wanted AI help but I couldn’t fit my stuff in the 128k context window.

These are big legacy projects where I didn’t write the code to begin with, so having an AI partner would have been really nice.

Re: My LLM codegen workflow

#108

Post by bambax »

sambo546 wrote: post #98
bambax wrote: post #20

This is all fine for a solo dev, but how does this work with a team / squad, working on the same code base? Having 7 different instances of an LLM analyzing the same code base and making suggestions would not just be economically wasteful, it would also be unpractical or even dangerous? Outside of RAG, which is a different thing, are there products that somehow "centralize" the context for a team, where all questions…

I've started substituting "human" for "LLM" when I read posts like these. Is having 7 different humans analyzing the same code base any less wasteful?

They are not analyzing the same code base, they are all contributing to the same code base, each in their own domain. It would seem relevant that any advice an LLM gives to one of them is kept consistent -- in real time -- with any other advice to any other dev, instead of having to wait for each commit or push.

Re: My LLM codegen workflow

#110

Post by abrookewood »

blah2244 wrote: post #107

This is a great article -- I really appreciate the author giving specific examples. I have never heard of mise ( https://mise.jdx.dev/ ) before either, and the integration with the saved prompts is a nifty idea -- excited to try it out!

Mise is great - it's an alternative to ASDF and remains call compatible from memory, but is much faster.
Post reply on HN