wagesj45

What country is that?

This is important. I dunno about scale, but backups. I started out hosting a chat room on a raspberry pi. It was a fun side project. But then, that became where my friends all hung out. That was the place, so it became important to me. And then the SD card got corrupted. I then moved on to a consumer laptop. It was way more stable, much faster. But if I messed up anything about the installation, I was hosed.

I very highly suggest using Proxmox, like you say, and setting up automatic backups. And occasionally transfer them to a hard drive. It doesn’t matter what kind of virtual CPUs or services you install, gedaliyah@lemmy.world, as long as you have a plan for when something you host becomes important to you and you lose it.

Proxmox on physical servers hosting a variety of vanilla Debian installations. I have a physical router running pfsense as well as two HP miniservers running OpenMediaVault.

C# is good. I use Visual Studio on Windows, so I’m not familiar with the tooling in VS Code in Linux, but I’ve heard good things. .NET is a nice environment to work in, the runtime works on all the OSs, and you can even package it into a self-contained binary with a little finagling.

The problems I’ve had with my RPis have all revolved around the fragility of their SD storage. I got burned one too many times trying to host something important in my house with these things, just for them to get corrupted and lose everything. Backing up these systems was its own nightmare, which failed as much as it succeeded.

I think a lot of people in this thread are just upset/projecting because this is the first real hint that they’re not as much of a special-boy-programmer as they think. OP’s use case is fairly limited in scope, using the LLM for something it is actually pretty good for, and never implied he doesn’t check the output. They’ll never admit it, and will deflect, but they’re just worried.

Of course he knows why he made the changes. He made them. But computers are much faster as typing and with a sophisticated enough LLM you can offload some gruntwork. I’d argue if you’re not utilizing all the tools at your disposal, you’re not performing like you should.

I think we just have to accept that marketing has to dumb down and generalize for the mass market.

So they’re using our data and also getting paid for it

Yeah? Isn’t that the point of paying for a music service? I pay, they give me access to music and curate it in a way that would be enjoyable to me. How could they do that without some information about me? This is a prime example of what a company should use your data for.

This logic is really sending me, man.

If it’s a neural network doing it, then that’s fine.

From all the war stories you see online, they don’t have that much to lose.

I thought the point was a mental BDSM exercise where you come to others for help and are instead punished for your ignorance.

Posters aren’t saying that its impossible to put search results through an LLM and ask it to cite the source it reads. They’re saying that the neural networks, as used today in LLMs, do not store token attribution in the vocabulary or per node. You can implement a system for the neural network to work in that provides it the proper input (search results) and prodding (a prompt that encourages the network to biasing toward citation), not that the single LLM can conceptualize of that on its own.

Neither do I.

Consider switching now. Your continued usage is contributing to the user numbers they see reported that gives them the confidence to pull this shit in the first place.

oh look, the fun police are here

I was just reiterating your point and agreeing with you, bud.

Use the tool for the job. It is simple advice, but it will make your life so much easier.