For what it's worth, I've used Claude to write a lot of smaller utility tools that I wouldn't normally have the time to sit down and implement, but which also solve straightforward problems.
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'.
That is in fact the difficult part. You have to explain it all coherently while adjusting to the reader's frame. No one does that for no good reason. It is hellish work.
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:
I mean, given that the English you wrote above didn't make it clear that was the only part you were complaining about, it's worth it to consider that maybe precision is hard in natural language regardless of how it's written
I'm reverse engineering a cherished video game from my childhood. I got to the audio engine part and things got pretty difficult. Managed to map out the locations of the audio data but figuring out which song was which was going to take a long time.
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.
i definitely used to write bash functions for this sort of thing tho. no GUI, but it was useful to do stuff like obscure my working hours (make it look like i did personal stuff after-hours. make it seem like stuff took all day instead of an hour..like adding sawdust to meat).
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.
“Editing” commits is not niche, and editing metadata like dates seems to come up a few times for a fair few number of people.
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.
For what it's worth, I've used Claude to write a lot of smaller utility tools that I wouldn't normally have the time to sit down and implement, but which also solve straightforward problems.
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'.
but if you were sharing those utilities - even in a github gist! - why not write the English parts for human consumption yourself?
That is in fact the difficult part. You have to explain it all coherently while adjusting to the reader's frame. No one does that for no good reason. It is hellish work.
git has a notoriously overcomplicated interface, so this is a scenario that I can honestly understand why someone wouldn't want to do it by hand
but what about the writing English to describe it part? does English also have a notoriously overcomplicated interface lol
Well, yeah, it does.
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
I mean, given that the English you wrote above didn't make it clear that was the only part you were complaining about, it's worth it to consider that maybe precision is hard in natural language regardless of how it's written
it is pretty clear in context given what i was responding to
Maybe I'm misunderstanding, too, but it seems to me that most people responding to you misunderstood your point.
I certainly didn't read it the way they intended!
They can, just in today's world, they just are not deemed impressive enough by the voting public to make it to the front page.
that's troubling..
People are lazy.
A tool like this never sees the light of day without an LLM. Git is complicated and use case for this is rather niche.
I'm reverse engineering a cherished video game from my childhood. I got to the audio engine part and things got pretty difficult. Managed to map out the locations of the audio data but figuring out which song was which was going to take a long time.
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.
> Without LLMs, none of this would ever have happened.
That would have been better for the world.
i definitely used to write bash functions for this sort of thing tho. no GUI, but it was useful to do stuff like obscure my working hours (make it look like i did personal stuff after-hours. make it seem like stuff took all day instead of an hour..like adding sawdust to meat).
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.
Yep, tell Claude to spit out a shell script. Use Python if bash is not enough.
It wasn't hard to just..figure it out though. One sitting tops.
Claude is learned (taught? lol) helplessness, at scale. I'm pretty sure it's their real moat.
If you dont use that regularly, why keep the app?
“Editing” commits is not niche, and editing metadata like dates seems to come up a few times for a fair few number of people.
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.
Because I have better things to do with my time.
I have better things to do than read LLM prose copy-pasted verbatim too.
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.