@jerry@infosec.exchange @faultcraft@infosec.exchange @GossiTheDog@cyberplace.social I think "a bit toxic" is an understatement tbh. Most of my exposure to mastodon is people being extremely angry and frustrated, and I often avoid engaging with anyone because the immediate feeling is that they'll jump at me if I even put a single comma in the wrong place (judging from the other comments when I read them). Most of the time I don't really feel like even opening the app because I'll just end up feeling even worse for no real gain
Daniele
mastodon 4.7.3@gabrielesvelto@mas.to I don't think the comparison is entirely fair tho. Both sed and syntax tree based editing are really powerful (and I use both when it makes sense), but if you need to do a one off migration you might be spending hours trying to figure out how to make it work right, while an llm will do a good enough job where you need to review the changes and fix a few mistakes, usually at the first try, without you having to actively spend time on it.
@gabrielesvelto@mas.to answering in order:
>what about the time spent setting up the LLM, sandboxing it and then reviewing all the changes?
This for what I'm working on is usually between 30 and 40 minutes, start to end (minus the time that the LLM takes to do its own work in its own git subtree, while I do other stuff). For context, claude doesn't commit, I review the changes locally (git is blacklisted). In my case this is been pretty stable on 100-150 tasks where I did the same kind of migration
@grumpygamer@mastodon.gamedev.place are you also gonna stop using any software that uses ffmpeg/curl, and throw away your apple computer?
This is just a provocation of course, people might have their reasons to stay on X, drivers might have their own reasons to drive a Tesla, I personally don't think it's constructive to just bash at them without trying to understand their point of view.
@grumpygamer@mastodon.gamedev.place https://diaowinner.itch.io/galmuri-extended is nice and very complete but I don't know if it works well at higher resolutions (8x8 font)
@gabrielesvelto@mas.to and ok, but what is the *actual* scenario you're imagining? because my coding tasks go as such when I use LLMs:
1. I have 10-15 classes that need to change the way we do X from Y to Z
2. I prompt the LLM, telling it "change A,B,C so that they use Z instead of Y"
3. I review the code, fixing mistakes as I see them
1/x because post length limits