Replying to @⁨sun@shitposter.world⁩

@sun@shitposter.world @lain@lain.com The problem is that output from LLMs currently has a legally ambiguous status. You can not risk integrating it into any existing free software right now, so that's why a lot of projects, with some exceptions, choose not to allow it or heavily limit its usage only to specific tasks.

And on a personal note I think obvious LLM output is extremely tasteless. Seeing someone not even use some effort to at least even write their own README file makes me cringe. I always compare it to the same type of feeling you get when you see a corporate logo which uses Comic Sans.

Replying to @⁨besserwisser@shitposter.world⁩

@besserwisser @Phobos @lain @SuperDicq @sun i like to program and i wanna learn because it's nice, so what I do is use the LLM as a tool for learning how to program/solve an issue when programming. When I have an issue I ask it how to fix it by giving it examples of what I've done, and when I know I wanna implement smth but don't know how, I ask it to teach me the best practices or how it is usually done in that program.

Replying to @⁨lain@lain.com⁩

@lain @Phobos @SuperDicq @sun @mischievoustomato That's kind of a trap I fear to fall into. Letting the LLM do stuff instead of doing it myself and learn in the process. Also, I don't want to pay for whatever subscription I need to get something decent for a little hobby project and local models are probably gonna be really slow and clunky.

Replying to @⁨besserwisser@shitposter.world⁩

@besserwisser @Phobos @lain @SuperDicq @sun speed. You can learn much faster with LLMs than not. Having to google whatever issue exists pre-LLM era was painful. Oftentimes stuff seemingly didn't have a fix or required obscure """fixing""". Docs aren't usually good or practical. Also for making stuff like test suites or helping you debug stuff when things aren't visibly clear.