Well, if a meaningful commit message can be created only with a model as big as 1B parameters, I’m better off doing them meself.

Commit messages are for sure short and easy to come up with, already. The problem’s typing some common stuff every single time.

Thanks for letting us know. Yeah sure. It’s not worth it. I personally take about 10s to write the commit message. So such a thing will just make it worse.

I see. didn’t think of this one. Note that there is a commit message, one line, and there is an extended description. The extended description, most of the time, is like you said and an LLM cannot do it. But I was wondering if that one line could be auto-generated. If not for every commit, at least for some common changes. But I will take your word that a Language model won’t be good.

Of course it is. We use computers to automate things. This is one of them. What is the problem with that?

Thanks. noted.

they are not notes to meself when there are others in the project. And the commit message is not always one line. Sometimes it’s more. And even if it is one line, it is still annoying to manually type for everything and every change.

I want meaningful commit messages pal :)

8GB means around 8B parameters. It’s no where near small. I meant the classic language models before LLMs existed. Something which I can easily execute on CPU to generate the commit messages.

And here, I’m not asking for “what model” rather “what utility” which uses such these models. Finding or training a model is much easier than maintaining such a software and keeping it useful.

Thanks. It’s a good short post.

Also, there is nothing wrong with wanting attention. Attention is a natural need of any human. I want me voice to be heard, me post to be read. They are all okay.

Thank you!

oh yeah! that’s it! But I wanted it for Lua. So the keyword is “documentation generator”?

Yup. But in a web UI. So we can find other relevant entities.

LOL :D

Everyone thinks LLMs boost productivity. But from psychological point of view, the developer being both the subject and the object is no where near scientific and reliable.

In other words, the developer who is using the LLM also reports they are productive. But humans can rarely be good judge over themselves. That’s why we’ve got therapists. So we have to wait for some serious and well done research if LLMs boost productivity.

Another concern I have which prevents me from using LLMs, is the unknown long term effect on the codebase. You know, writing something is much easier than maintaining it for years after years. And every decision you make, you must be mindful of this. So I’m gonna wait and see what’ll happen after 1-3 years to the softwares with heavy LLM assists. Will their codebase still be easy to maintain?