• 0 Posts
  • 54 Comments
Joined 3 years ago
cake
Cake day: June 12th, 2023

help-circle







  • The customer receives a list of feat and fix commit titles as info with a release.

    The problem is that the language customers want and the language developers want are different things. Abusing commit messages to try to create documentation is just a bad idea. Spend a few mins to summarize for your users what has changed. You should be able to pull the tickets that went into a release for that pretty easily. Hell have AI do it if you’re that lazy. But as a developer I want to know what your commit did. Just explain your change in a way that will help me later on.


  • Fine - then add 3-5 actually random letters to the start of all your commits from now on.

    No? I don’t understand what you’re so upset about…

    Because it’s NOISE that I’m sifting through as a tech lead. And they’re often lies anyway. “feats” can have refactors and bug fixes. fix can add new features. Devs are horribly bad at separating out these types of changes neatly when making commits. “chore” is just too cute by half. I know “Version bump: 1.2.3” is just a version bump - I don’t need you to whine about it being a chore.


  • You don’t. Users are different audience than the development team. Messages intended for one group are different from those for the other. This is my biggest gripe about this “semantic” BS. Commit comments are for the dev team. You should summarize it in a way that makes sense to users.

    Every time I see a “changelog” from a team for something I use that is full of “fix: loop pointer in Foo.java” I just roll my eyes. Like that tells me anything useful. If I cam technically savvy enough and care I can go look at the git history. But as a user that’s meaningless.





  • This is false. There is a pile of research demonstrating that copies of training data can be extracted from trained models, going back at least 5 years. If the model can reproduce a copy of the original, then it must be stored in the neural network in some form.

    They also generate novel output. Lots of it. Is that novel output in the model too because it can be reproduced from the model?

    “Can be extracted from” is not the same as “exists in the model”. I can write a random letter generator that will eventually spit out real words. But those words don’t “exist” in my code.


  • The issue here is that the output must contain human expression to be protected. If you ask it to just solve a problem for you then you haven’t put expression in because that’s just functional use. And if it doesn’t respond in kind by preserving your expression then likewise there’s nothing protected.

    Wasn’t that the issue with photography as well? “I just push a button” and the machine takes the photograph. Did I create that photo or did the camera? The expression was deemed to be that of the photographer in this case. But it’s the machine doing the actual work.

    On the other hand, if your start with clearly copyright protected works of your own like books or poem collections, then if you ask it to expand on it or edit then you’ll have much more of your actual expression in the output. Or, if you simply only use the LLM output as a template and then edit yourself to make it yours.

    Right. And what if you guide the LLM through writing the code? e.g. “No not like that - do this instead” - or if you go beyond telling it what you want and tell it how to go about doing it? What if you have style guidelines that you want it to follow? How much of the code has your “expression” in it as a result? Frankly that can be a lot more work than “push a button and the machine does the work”. But whether that work is considered to be the “expression” of the developer or not… I dunno.

    I feel like there’s a lot of gray area here. Everything from “just fully vibe-coded” to “coded along-side an LLM”.


  • Randomness or no, a copy-paste machine is still a copy-paste machine. It doesn’t do anything else. LLMs are language search algorithms with fancy optimization routines bolted on, nothing more.

    This sort of extreme reductionism is not helpful. They are significantly different from a “copy-paste” machine. The original training data does not exist in the model itself. It’s very much a “transformative” process.

    Reaching a different conclusion about the “transformative nature” (or whatever) of LLM output requires understanding less about how they actually work.

    This sounds like you’re saying “wilful ignorance is better than knowledge” - surely that’s not what you meant though?