Comment by thinkingtoilet
1 day ago
The main benefit I've gotten from AI that I see no one talking about is it dramatically lessens the mental energy required to work on a side project after a long day of work. I code during the day, it's hard to find motivation to code at night. It's a lot easier to say "do this", have the AI generate shitty code, then say, "you duplicated X function, you over complicated Y, you have a bug at Z" then have it fix it. On a good day I get stuff done quicker, on an average day I don't think I do. However, I am getting more done because the it takes a huge chunk out of the mental load for me and requires significantly less motivation to get something done on my side project. I think that is worth it to me. That said, I am just about to ban my junior engineers from using it at work because I think it is detrimental to their growth.
I agree with the side-project thing, where the code is only incidental to working on the real project. I recently wanted to organize thousands of photos my family had taken over decades and sprawled on a network drive, and in 5 minutes vibe-coded a script to recursively scan, de-dupe, rename with datetime and hash, and organize by camera from the EXIF data.
I could have written it myself in a few hours, with the Python standard docs open on one monitor and coding and debugging on the other etc, but my project was "organize my photos" not "write a photo organizing app". However, often I do side projects to improve my skills, and using an AI is antithetical to that goal.
I've found a lot of utility in this. Small throw away utility apps where I just want to automate some dumb thing once or twice and the task is just unusual enough that I can't just grab something off the shelf.
I reached for claude code to just vibe a basic android ux to drive some rest apis for an art project as the existing web UI would be a PITA to use under the conditions I had. Worked well enough and I could spend my time finishing other parts of the project. It would not have been worth the time to write the app myself and I would have just suffered with the mobile web UI instead. Would I have distributed that Android app? God no, but it did certainly solve the problem I had in that moment.
Very much the same for me. I use some LLMs to do small tasks at work where I know they can be useful, it's about 5-10% of my coding work which itself is about 20% of my time.
Outside of work though it's been great to have LLMs to dive into stuff I don't work with, which would take me months of learning to start from scratch. Mostly programming microcontrollers for toy projects, or helping some artists I know to bring their vision to life.
It's absurdly fun to get kickstarted into a new domain without having to learn the nitty-gritty first but I eventually need to learn it, it just lowers the timeframe to when the project becomes fun to work with (aka: it barely works but does something that can be expanded upon).