Hey fellow programmers, I wanted to share a little experiment I’ve been
conducting lately that has significantly improved my workflow. I’ve started
using AI to generate my Git commit messages, and it’s been a game-changer! By
feeding all the changes I’ve made into a language model with a large context
window (LLM), the AI not only generates a concise commit title but also provides
bullet points describing each of the changes in precise detail. The level of
detail and informativeness it brings to my commit messages is incredible. I used
to spend a considerable amount of time crafting commit messages that accurately
captured the essence of the changes I made. Now, with the help of AI, I find
myself copy-pasting its generated messages most of the time. It’s not just a
time-saver; it also ensures that my commits are well-documented and easy to
understand for my team members. If you haven’t explored using AI for your Git
commits, I highly recommend giving it a try. It can significantly boost your
productivity and help you maintain clean and informative version control
history. Plus, it’s a fascinating intersection of AI and software development!
Have you experimented with similar AI-powered tools for your programming tasks?
I’d love to hear your experiences and any recommendations you might have. Let’s
discuss the future of AI in programming in the comments!
It writes more informative commits than I could ever make so I’m just reading what it says and mostly copy/pasting completely most of the time, I write all of the changes I’ve made into an LLM with a large context window and it write a very detailed commit not just with a title but with bullet points describing each of the changes precisely
If a glorified autocomplete algorithm can write more informative and concise commit messages than you, the actual author behind the code, I think you need to sit down and think long and hard what that actually implies.
That an AI might be better at writing documentation than the average dev, who is largely inept at writing good documentation?
Understandably, as technical writing isn’t exactly a focus point or career growing thing for most devs. If it was, we would be writing much better code as well.
I’ve seen my peers work, they could use something like this. I’d welcome it.
I disagree. I am capable of writing a good commit message, I just don’t really want to. Depending on the change, formulating a concise text that includes all relevant information can be quite time consuming.
I can travel to Italy on foot. Will I do that? Of course not. What does it imply? That I’m incapable of moving my body? Of course not! It just means I’m too lazy to do it and that there are faster ways to get to the same goal.
I disagree. I am capable of writing a good commit message, I just don’t really want to. Depending on the change, formulating a concise text that includes all relevant information can be quite time consuming.
formulating a concise text that includes all relevant information
how do you write Pull-Requests? Just half-assing it? Writing good commit messages help you write a good PR as well (as it can be just a summary of the things you commited) But yeah, you do you.
There is a saying, which I don’t generally agree with. Those who can, do. Those who can’t, teach. That said, writing good code and describing code effectively are two different skills, and there is no guarantee any given individual will have both.
If a glorified autocomplete algorithm can write more informative and concise commit messages than you, the actual author behind the code, I think you need to sit down and think long and hard what that actually implies.
I don’t need to think long and hard to realize how lazy I am. Only a stupid person would need to think long and hard to realize something so simple.
And you are probably referring to the LLM generated post anyway, because I never said that it can write “more informative and concise commit messages than me”. You are the one saying that.
If a glorified autocomplete algorithm can write more informative and concise commit messages than you, the actual author behind the code, I think you need to sit down and think long and hard what that actually implies.
And what does it imply?
That an AI might be better at writing documentation than the average dev, who is largely inept at writing good documentation?
Understandably, as technical writing isn’t exactly a focus point or career growing thing for most devs. If it was, we would be writing much better code as well.
I’ve seen my peers work, they could use something like this. I’d welcome it.
it implies that the author of the code has no idea what they were doing.
I disagree. I am capable of writing a good commit message, I just don’t really want to. Depending on the change, formulating a concise text that includes all relevant information can be quite time consuming.
I can travel to Italy on foot. Will I do that? Of course not. What does it imply? That I’m incapable of moving my body? Of course not! It just means I’m too lazy to do it and that there are faster ways to get to the same goal.
how do you write Pull-Requests? Just half-assing it? Writing good commit messages help you write a good PR as well (as it can be just a summary of the things you commited) But yeah, you do you.
There is a saying, which I don’t generally agree with. Those who can, do. Those who can’t, teach. That said, writing good code and describing code effectively are two different skills, and there is no guarantee any given individual will have both.
I don’t need to think long and hard to realize how lazy I am. Only a stupid person would need to think long and hard to realize something so simple.
And you are probably referring to the LLM generated post anyway, because I never said that it can write “more informative and concise commit messages than me”. You are the one saying that.
Don’t ever call me a glorified autocomolete algorithm again