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

51–60 of 168 posts

Re: My LLM codegen workflow

#51

Post by daxfohl »

danphilibin wrote: post #24
jrexilius wrote: post #12

The first part of this, where you told it to ask YOU questions, rather than laboriously building prompts and context yourself was the magic ticket for me. And I doubt I would have stumbled on that sorta inverse logic on my own. Really great write up!

This is the key to a lot of my workflows as well. I'll usually tack some form of "ask me up to 5 questions to improve your understanding of what I'm trying to do here" onto the end of my initial messages. Over time I've noticed patterns in information I tend to leave out which has helped me improve my initial prompts, plus it often gets me thinking about aspects I hadn't considered yet.

Frankly getting used to doing this may help our communication with other engineers as well.

Re: My LLM codegen workflow

#52

Post by brokencode »

rotcev wrote: post #13

This is the first article I’ve come across that truly utilizes LLMs in a workflow the right way. I appreciate the time and effort the author put into breaking this down. I believe most people who struggle to be productive with language models simply haven’t put in the necessary practice to communicate effectively with AI. The issue isn’t with the intelligence of the models—it’s that humans are still learning how to u…

> “I appreciate the time and effort the author put into breaking this down.”

Let’s be honest. The author was probably playing cookie clicker while this article was being written.

Re: My LLM codegen workflow

#53

Post by hy4000days »

balls187 wrote: post #34
sampton wrote: post #32

Earlier quoted context omitted.

The end of artisan frameworks - probably for the better.

It's likely the end of a lot of abstractions that made programming easier. At some point, specialized code-gen transformer models should get really good at just spitting out the lowest level code required to perform the job.

This.

Future programming language designers are then answering questions like:

"How low-level can this language be while considering generally available models and hardware available can only generate so many tokens per second?",

"Do we have the language models generate binary code directly, or is it still more efficient time-wise to generate higher level code and use a compiler?"

"Do we ship this language with both a compiler and language model?"

"Do we forsake code readability to improve model efficiency?"

Re: My LLM codegen workflow

#54

Post by codeisawesome »

Would be great if there were more details on the costs of doing this work - especially when loading lots of tokens of context via repo mix and then generating code with context (context-loaded inference API calls are more expensive, correct?). A dedicated post discussing this and related considerations would be even better. Are there cost estimations in the tools like aider (vs just refreshing the LLM platform’s billing dashboard?)

Re: My LLM codegen workflow

#55

Post by theturtle32 »

jrexilius wrote: post #12

The first part of this, where you told it to ask YOU questions, rather than laboriously building prompts and context yourself was the magic ticket for me. And I doubt I would have stumbled on that sorta inverse logic on my own. Really great write up!

Can confirm, this is an excellent tactic when working with LLMs!

Re: My LLM codegen workflow

#56

Post by randomcatuser »

> I really want someone to solve this problem in a way that makes coding with an LLM a multiplayer game. Not a solo hacker experience. There is so much opportunity to fix this and make it amazing.

This i think is the grand vision -- what could it look like?

in my mind programming should look like a map -- you can go anywhere, and there'll be things happening. and multiple people.

If anyone wants to work on this (or have comments, hit me up!)

Re: My LLM codegen workflow

#58

Post by manmal »

mike_hearn wrote: post #44
rd wrote: post #15

Has anyone who evolved from a baseline of just using Cursor chat and freestyling to a proper workflow like this got any anecdata to share on noticeable improvements? Does the time invested into the planning benefit you? Have you noticed less hallucinations? Have you saved time overall? I’d be curious to hear because my current workflow is basically 1. Have idea 2. create-next-app + ShadCN + TailwindUI boilerplate 3.…

Aider + AI generated maps and user guides for internal modules has worked well for me. Just today I did my own version of a script that uses Gemini 2 Flash (1M context window) to generate maps of each module in my codebase, i.e. a short one or two sentence description of what's in every file. Aider's repo maps don't work well for me, so I disable them, and I think this will work better. I also have a scratchpad file…

LLMs forcing us to improve our documentation habits. Seriously though, many languages allow API doc generation out of comments. Maybe these docs can just be flattened into a file.

Re: My LLM codegen workflow

#59

Post by fragmede »

daxfohl wrote: post #51
danphilibin wrote: post #24

Earlier quoted context omitted.

This is the key to a lot of my workflows as well. I'll usually tack some form of "ask me up to 5 questions to improve your understanding of what I'm trying to do here" onto the end of my initial messages. Over time I've noticed patterns in information I tend to leave out which has helped me improve my initial prompts, plus it often gets me thinking about aspects I hadn't considered yet.

Frankly getting used to doing this may help our communication with other engineers as well.

promo from L5->L7 confirmed.

Re: My LLM codegen workflow

#60

Post by fallinditch »

Great post and discussion.

Also, don't forget that your favorite AI tools can be of great help with the factors that cause us to make software: research, subject expertise, marketing, business planning, etc.

Post reply on HN