I’m not a programmer by any stretch but what LLM’s have been great for is getting my homelab set up. I’ve even done some custom UI stuff for work that talks to open source backend things we run. I think I’ve actually learned a fair bit from the experience and if I had to start over I’d be able to do way way more on my own than I was able to when I first started. It’s not perfect and as others have mentioned I have broken things and had to start projects completely from scratch but the second time through I knew where pitfalls were and I’m getting better at knowing what to ask for and telling it what to avoid.
I’m not a programmer but I’m not trying to ship anything either. In general I’m a pretty anti-AI guy but for the non-initiated that want to get started with a homelab I’d say its damn near instrumental in a quick turnaround and a fairly decent educational tool.
This is the correct way to do it, use it, see if it works for you and try to understand what happened.
It’s not that different from using examples or stack overflow. With time you get better, but you need to have that last critical thinking step. Otherwise you will never learn and will just copy paste hoping it works
As a programmer I’ve found it infinitely times more useful for troubleshooting and setting up things than for programming. When my Arch Linux nukes itself again I know I’ll use an LLM, when I find a random old device or game at the thrift store and want to get it to work I’ll use an LLM, etc. For programming I only use the IntelliJ line completion models since they’re smart enough to see patterns for the dumb busywork, but don’t try to outsmart me most of the time which would only cost more time.
I’m not a programmer by any stretch but what LLM’s have been great for is getting my homelab set up. I’ve even done some custom UI stuff for work that talks to open source backend things we run. I think I’ve actually learned a fair bit from the experience and if I had to start over I’d be able to do way way more on my own than I was able to when I first started. It’s not perfect and as others have mentioned I have broken things and had to start projects completely from scratch but the second time through I knew where pitfalls were and I’m getting better at knowing what to ask for and telling it what to avoid.
I’m not a programmer but I’m not trying to ship anything either. In general I’m a pretty anti-AI guy but for the non-initiated that want to get started with a homelab I’d say its damn near instrumental in a quick turnaround and a fairly decent educational tool.
This is the correct way to do it, use it, see if it works for you and try to understand what happened. It’s not that different from using examples or stack overflow. With time you get better, but you need to have that last critical thinking step. Otherwise you will never learn and will just copy paste hoping it works
As a programmer I’ve found it infinitely times more useful for troubleshooting and setting up things than for programming. When my Arch Linux nukes itself again I know I’ll use an LLM, when I find a random old device or game at the thrift store and want to get it to work I’ll use an LLM, etc. For programming I only use the IntelliJ line completion models since they’re smart enough to see patterns for the dumb busywork, but don’t try to outsmart me most of the time which would only cost more time.
lol it did save me from my first
rm -rf /