Humans definitely don’t make mistakes. Especially not with their jank home servers. All of it done without shortcuts and auditable in code, with a standard process.

You’ve set some imaginary high bar that is rarely actually met outside of nerds shit talking on the internet and a small percentage of users.

I bet you I do less work and have a more efficient and locked down network, file permissions, fully rootless, updated on the hour, 100% in code, and observable setup than 98% of you just running sudo apt upgrade and praying. But yeah, my little agent working in an nemoclaw sandbox is going to go rogue and destroy my server somehow and I definitely believe the AI hype bros that are definitely “accidentally “ are hacking orgs and not going to end the human race🙄

Man, the ignorance and prejudice over how llm work is insane.

Hermes + maybe $5-10 worth of tokens if I need more compute than ollama can provide (on a busy month). Running everything in a nice podlet setup and have reduced maintenance down to trivial levels. Config gets occasionally shipped to GitHub

In theory I might lose the ui if it bricked itself but in reality that doesn’t happen.

So made up fears over settled law. Makes perfect sense.

🤣

Drop your compose files in an AI and it’ll take 20 seconds to convert. There really isn’t a huge migration costs.

I don’t understand why you people over complicate your lives by over engineering shit at home.

This isn’t the burn you think it is. Should we start listing actual high use hand coded abandoned foss projects?

You can use a free account for limited usage.

You should just install open claw + claude to manage and setup your services if you just want it to work and see a working example on your device. Its a simple task for AI and you can review and learn from configuration that applies to only your system.

What value does rote memorization of a command, that varies by the system you are on, bring?

Parsing logs and pointing out anomalies isn’t solving anything. Second, your ass was just going to Google it anyway and end up the the same documentation. You’d just take longer with more effort to get there 🤷‍♂️

Everyone will screech but you should just run openclaw or similar and have it go through your logs. It’ll tell you the exact name of your igpu device and help you figure out why it’s not working. It’ll also help manage your queues, quality indexes, space, etc.

It’s reduced my server maintenance by at least 2/3rds.

I love how confident y’all are that AI isn’t going to affect your coding and you really think you’ll survive in the industry without adjusting how you work.

Even today, it’s already better than most coders at small specialized scoped tasks.

Use the tools when appropriate. This is such a stupid fucking thing to get your undies in a twist over.

But yeah, I’m sure y’all will lead the fork and put in your own time to own it.

The UI didn’t support remotes on console and use tiles. Really amateur shit. No need to set up a reverse proxy. I have a lifetime, zero need to switch.

If someone could focus on making BT controllers not be unusable trash on Linux, that would probably be a more useful start.

I like AI and use it. This post was just sad. What a crazy way to announce you don’t have an AI product while saying your product is dead.