The worst part about GPT-3 is people using it to automate things where the entire value comes from what the human annotates rather than automates. This is an idea, which like many others involving GPT-3, which I believe will destroy more value than it creates.
Gptcommit: Never write a commit message again (with the help of GPT-3)
21–30 of 106 posts
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#22This is horrible. Commit messages should contain the reason why this change has been made and not imprecise prose summaries of what the diff looks like.
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#23There are tools that I wish didn’t exist and this is one of them.
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#24I don't really ever want to read answers from GPT to questions that I didn't knowingly myself ask GPT. If GPT can write a commit message from you, don't write it at all and let me ask it that if that's what I want. It may be a positive to you to spend a few seconds less on commit messages but it's a net negative for the world for it to become polluted with vast amounts of flatly incorrect text with no knowledge as to…
Except for startups when commit messages are more like "asdf", "aoeu", "quick fix", or "demo" because some investor barged in and demanded a demo before they would wire funds. If ChatGPT could change that to something like "disable current limits" or "disable safety checks" or whatever that might be marginally better.
this is just normal every day commit messages in most startups I've seen
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#25I don't really ever want to read answers from GPT to questions that I didn't knowingly myself ask GPT. If GPT can write a commit message from you, don't write it at all and let me ask it that if that's what I want. It may be a positive to you to spend a few seconds less on commit messages but it's a net negative for the world for it to become polluted with vast amounts of flatly incorrect text with no knowledge as to…
Except for startups when commit messages are more like "asdf", "aoeu", "quick fix", or "demo" because some investor barged in and demanded a demo before they would wire funds. If ChatGPT could change that to something like "disable current limits" or "disable safety checks" or whatever that might be marginally better.
This indicates commit quality. Why lose this info? If you have only time to put "aoeu" into commit message would you have time to correct ChatGPT output? ;)
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#26this is awful.
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#27Comments here are acting like you can't add/edit the commit. It offers a starting point. Yes it's just-above-diff level, but it is at-least-above-diff level.
But my main though is that IDK about using this for anything closed source. Feed openai's API your codebase, one commit at a time. Even if they promise not to train on your prompt history today, ToS could change. Seems fine if you run it locally though.
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#28I don’t get the hate. Don’t use it all the time, but this could be useful as part of a danger report.
A readable summary for the ones who may not understand code - your developer will never write that.
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#29I don't really ever want to read answers from GPT to questions that I didn't knowingly myself ask GPT. If GPT can write a commit message from you, don't write it at all and let me ask it that if that's what I want. It may be a positive to you to spend a few seconds less on commit messages but it's a net negative for the world for it to become polluted with vast amounts of flatly incorrect text with no knowledge as to…
Except for startups when commit messages are more like "asdf", "aoeu", "quick fix", or "demo" because some investor barged in and demanded a demo before they would wire funds. If ChatGPT could change that to something like "disable current limits" or "disable safety checks" or whatever that might be marginally better.
asdf is still better than having lies sprinkled in randomly.
Maybe prefixing them all with gpt: would help
Re: Gptcommit: Never write a commit message again (with the help of GPT-3)
#30Earlier quoted context omitted.
Except for startups when commit messages are more like "asdf", "aoeu", "quick fix", or "demo" because some investor barged in and demanded a demo before they would wire funds. If ChatGPT could change that to something like "disable current limits" or "disable safety checks" or whatever that might be marginally better.
asdf is still better than having lies sprinkled in randomly. Maybe prefixing them all with gpt: would help
> asdf is still better than having lies sprinkled in randomly.
I think this is the core of my argument, yeah. If a _reader_ needs better than they can run GPT themselves. But the _writer_ using it is worse than useless, it's actively harmful.