Spelling nit:
“Over my skis” ~ in over my head.
“Over my skies” ~ very far overhead. In orbit maybe?
My LLM codegen workflow
41–50 of 168 posts
Re: My LLM codegen workflow
#42I don’t mind LLMs, but what irks me is the customer noncompete, you have these systems that can do almost anything and the legal terms explicitly say you’re not allowed to use the thing for anything that competes with the thing. But if the things can do almost anything then you really can’t use it for anything. Making a game with Grok? No, that competes with the xAI game studio. Making an agents framework with ChatGPT? No, that competes with Swarm. Making legal AI with Claude? No, that competes with Claude. Seems like the only American companies making AI we can actually use for work are HuggingFace and Meta.
Re: My LLM codegen workflow
#43I don’t mind LLMs, but what irks me is the customer noncompete, you have these systems that can do almost anything and the legal terms explicitly say you’re not allowed to use the thing for anything that competes with the thing. But if the things can do almost anything then you really can’t use it for anything. Making a game with Grok? No, that competes with the xAI game studio. Making an agents framework with ChatGP…
Ignore the noncompetes. Never get sued. If you do, everyone else is on your side.
Re: My LLM codegen workflow
#44Has 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 that I tell the model it can update to reflect anything new it learns, so that gives it a crude form of memory as it works on the codebase. This does help it use internal utility APIs.
Re: My LLM codegen workflow
#45This is pretty much my flow that I landed on as well. Dump existing relevant files into context, explain what we are trying to achieve, and ask it to analyze various approaches, considerations, and ask clarifying questions. Once we both align on direction, I ask for a plan of all files to be created/modified in dependency order with descriptions of the required changes. Once we align on the plan I say lets proceed one file at a time, that way I can ensure each file builds on the previous one and I can adjust as needed.
Re: My LLM codegen workflow
#46I don’t mind LLMs, but what irks me is the customer noncompete, you have these systems that can do almost anything and the legal terms explicitly say you’re not allowed to use the thing for anything that competes with the thing. But if the things can do almost anything then you really can’t use it for anything. Making a game with Grok? No, that competes with the xAI game studio. Making an agents framework with ChatGP…
Form a Nonprofit X and a Corp Y:
Noprofit X publishes outputs from competing AI, which is not copyrightable.
Corp Y injests content published by Nonprofit X.
Re: My LLM codegen workflow
#47Looks similar to my experience, except this part:
> if it doesn’t work, Q&A with aider to fix
I fix errors myself, because LLMs are capable of producing large chunks of really stupid/wrong code, which needs to be reverted, and thats why it makes sense to see the code at least once.
Also I used to find myself in a situation when I tried to use LLM for the sake of using LLM to write code (waste of time)
Re: My LLM codegen workflow
#48I don’t mind LLMs, but what irks me is the customer noncompete, you have these systems that can do almost anything and the legal terms explicitly say you’re not allowed to use the thing for anything that competes with the thing. But if the things can do almost anything then you really can’t use it for anything. Making a game with Grok? No, that competes with the xAI game studio. Making an agents framework with ChatGP…
Ignore the noncompetes. Never get sued. If you do, everyone else is on your side.
Meh, why pay to teach someone else’s bot? I’m sticking with open source
Re: My LLM codegen workflow
#49I think LLM codegen still requires a mental model of the problem domain. I wonder how many upcoming devs will simply never develop one. Calculators are tools for engineers /and/ way too many people can't even do basic receipt math.
Calculations are for calculators. I was good at math in school but now I struggle / take so much time doing receipt math and for what? What's the purpose of the time you spend doing it, when do you need to have your brain trained for this specific task?
For me, being able to notice when you mess up your own calculations. It doesn't help that we teach arithmetic operations ass-backwards (smallest to largest instead of largest to smallest).
Re: My LLM codegen workflow
#50Has 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.…
If you steer it and build a stdlib, you get better outcomes. See https://ghuntley.com/stdlib