Live data from Hacker News

Version Control for AI Coding

branching.app

11–20 of 27 posts

Re: Version Control for AI Coding

#14
post #4

Take a look at my thoughts on version control and vibecoding https://github.com/TZubiri/keyboard-transpositions-checker My idea is that we should not commit LLM written code, but rather we should commit the prompts. The LLM prompts are source code, the LLM code is target code. If you use typescript and scss, you would commit that, not the generated js and css. That LLMs are typically non-deterministic introduces some…

You can't as far as I'm aware unless you control the entire batch during inference, or don't use batching which would require you to run your own inference.

Re: Version Control for AI Coding

#15
post #4

Take a look at my thoughts on version control and vibecoding https://github.com/TZubiri/keyboard-transpositions-checker My idea is that we should not commit LLM written code, but rather we should commit the prompts. The LLM prompts are source code, the LLM code is target code. If you use typescript and scss, you would commit that, not the generated js and css. That LLMs are typically non-deterministic introduces some…

I have been thinking similarly but you need to store the prompt AND the source code. We are far away from deterministic LLMs. I don't even know if this makes sense at all.

Re: Version Control for AI Coding

#16
post #6

Baffling. Not at all clear from the site or video what this does, what problem it is solving, and what about LLM coding is different such that it needs new ideas in version control. Is it just that there are more commits and more conflicts because people are pushing more garbage without regard for consistency and stability? I would suggest solving that by pushing less garbage, or at least having fewer people pushing…

I don't know about this product but I think we need to version control the prompts together with the code.

Re: Version Control for AI Coding

#17
post #4

Take a look at my thoughts on version control and vibecoding https://github.com/TZubiri/keyboard-transpositions-checker My idea is that we should not commit LLM written code, but rather we should commit the prompts. The LLM prompts are source code, the LLM code is target code. If you use typescript and scss, you would commit that, not the generated js and css. That LLMs are typically non-deterministic introduces some…

"Surely"? Have you tried it?

And don't call me Shirley.

Re: Version Control for AI Coding

#18
post #4

Take a look at my thoughts on version control and vibecoding https://github.com/TZubiri/keyboard-transpositions-checker My idea is that we should not commit LLM written code, but rather we should commit the prompts. The LLM prompts are source code, the LLM code is target code. If you use typescript and scss, you would commit that, not the generated js and css. That LLMs are typically non-deterministic introduces some…

It's an interesting idea

Re: Version Control for AI Coding

#19
post #6

Baffling. Not at all clear from the site or video what this does, what problem it is solving, and what about LLM coding is different such that it needs new ideas in version control. Is it just that there are more commits and more conflicts because people are pushing more garbage without regard for consistency and stability? I would suggest solving that by pushing less garbage, or at least having fewer people pushing…

I don't know about this product but I think we need to version control the prompts together with the code.

That won't help much unless the LLM model version remains constant, is added, and/or can be invoked again. Not impossible for locally hosted models, but nigh impossible for the ever-changing online ones.

Re: Version Control for AI Coding

#20
post #6

Baffling. Not at all clear from the site or video what this does, what problem it is solving, and what about LLM coding is different such that it needs new ideas in version control. Is it just that there are more commits and more conflicts because people are pushing more garbage without regard for consistency and stability? I would suggest solving that by pushing less garbage, or at least having fewer people pushing…

I don't know about this product but I think we need to version control the prompts together with the code.

You do! I personally organize them into Markdown playbooks, organized in a way that makes sense for the project, and which live in the repo’s .claude folder (or .ai, or whatever).
Post reply on HN