Glad the LLM noted this - I was worried this would reimplement git
In what world are AI generated comments actually value adds?
This indeed pollutes the code with a bunch of nonsense. One of the things I have it maintain instead is a "findings" document with lessons learned and such.
In my experience the comments behave as a form of prompt injection. The llm makes a conceptual mistake, writes it in a comment, and now subsequent agents make the same mistake!
I imagine this style of commenting is partially responsible for model improvement in SWE work, a trained trait through feedback, since it makes the comments actually useful. Not to you or me, but to an LLM.
Some of these errors are obvious to a human, that's why we find the comments unnecessary. But if everyone's using LLMs and said model tends to make this error, then they are very useful. It's like a comment you would leave for another human to help them avoid a footgun. It's just a LLM footgun, not a human one.
One way to clear some of the low-hanging slop is to just have a separate agent code reviewing and pruning any comments that don't stand on their own purely in the context of the diff, but it still doesn't catch it all.
One small example is an extension for the `gh` cli where I give it a PR number and multiple branches and it cherry-picks that PR to those branches, or lets me know if some of the branches don't work. For managing multiple release branches it's very handy, but not so handy that I would have spent a lot of time and energy doing a good job of it.
This seems like a similar sort of thing - a user friendly way to do something that most people don't need, and most people who need it probably don't need it very badly.
I haven't used claude to replace my actual skills - researching, solving problems, etc. - but I do use it to replace all the stuff which is essentially 'spend a few hours reading API docs and writing boilerplate code'.
Effective and clear communication is really important and often really hard for engineers. It is said that one goal of stackoverflow was to help programmers learn how to write through practice, as it’s both very hard and very critical to their effectiveness:
https://blog.codinghorror.com/how-to-write-without-writing/
But programmers are also lazy*, so why put in the effort to improve when you can just get llms to do the work for you?
* not necessarily in a bad way
like you said, niche and probably unnecessary. and if i were to have published them (even in a gist!) i would have written the docs myself instead of forcing people to read LLM-speak. That's just lazy.
Claude is learned (taught? lol) helplessness, at scale. I'm pretty sure it's their real moat.
Claude somehow wrote a bespoke one-off Python script to play back the songs straight out of the ROM. I give it the ROM and a hexadecimal address and it just plays it. Converts the data from the ROM into PCM audio samples and pipes them over SSH into termux on my phone where they are played back via SoX play.
Yes, Claude wrote a literal sound synthesizer so I could do this. Claude painstakingly tuned the goddamn synthesizer too, he tweaked it over and over again until the output sounded right based on annoyingly human feedback like "these notes are supposed to be in the background but they are too loud".
This tool turned a painstaking reverse engineering task into a nostalgic listening experience that brought literal tears to my eyes. I mapped out every single song in the game this way.
Without LLMs, none of this would ever have happened.
That would have been better for the world.
You can already expose the commit object as the headers (metadata) and the commit message. That’s like a spreadsheet: change these columns and we will make a new commit. That changed format can then be persisted as a commit object. So.
> A tool like this never sees the light of day without an LLM.
Are LLMs memory holing all the numerous tools built around Git (with git(1) or without)? There was already a query-Git-like-SQL tool before The Age of LLMs. I never tried that, but was that simpler to implement than this tool? Edit: Okay, maybe it wasn’t “niche” so that’s the differentiator.
And yet here we are. I have to read LLM design docs that turn into LLM PRs with LLM PR descriptions and comments and docs.