I do selfhost my own, and even tried my hand at building something like this myself. It runs pretty well, I’m able to have it integrate with HomeAssistant and kubectl. It can be done with consumer GPUs, I have a 4000 and it runs fine. You don’t get as much context, but it’s about minimizing what the LLM needs to know while calling agents. You have one LLM context that’s running a todo list, you start a new one that is charge of step 1, which spins off more contexts for each subtask, etc. It’s not that each agent needs it’s own GPU, it’s that each agent needs it’s own context.

I am and do, I have no qualms with AI if I host it myself. I let it have read access to some things, I have one that is hooked up to my HomeAssistant that can do things like enable lighting or turn on devices. It’s all gated, I control what items I expose and what I don’t. I personally don’t want it reading my emails, but since I host it it’s really not a big deal at all. I have one that gets the status of my servers, reads the metrics, and reports to me in the morning if there were any anomalies.

I’m really sick of the “AI is just bad because AI is bad”. It can be incredibly useful - IF you know it’s limitations and understand what is wrong with it. I don’t like corporate AI at scale for moral reasons, but running it at home has been incredibly helpful. I don’t trust it to do whatever it wants, that would be insane. I do however let it have read permissions (and I know you keep harping on it, but MCP servers and APIs also have permission structures, even if it did attempt to write something, my other services would block it and it’d be reported) on services to help me sort through piles of information that I cannot manage by myself. When I do allow write access it’s when I’m working directly with it, and I hit a button each time it attempts to write. Think spinning up or down containers on my cluster while I am testing, or collecting info from the internet.

AI, LLMs, Agentic AI is a tool. It is not the hype every AI bro thinks it is, but it is another tool in the toolbelt. To completely ignore it is on par with ignoring Photoshop when it came out, or Wysiwyg editors when they came designing UIs.

Everyone keeps forgetting “if you allow it”. They show you what commands it’s going to run. So yes I’m okay with it, I review everything it will do.

Yes, that’s pretty much all an mcp server is, that’s what I’m trying to explain. The ai just chooses what commands out of a list. Each command can be disabled or enabled. Everyone freaking out here like it has sudo access or something when you opt into everything it does

If you allow it to run bash commands, it requires approval before running them:

https://docs.openclaw.ai/tools/exec-approvals

It’s not arbitrary code in this case, it’s well defined functions, like list emails, read email, delete email. The agentic portion only decides if it should have those functions invoked.

Now if they should is up for debate. Personally I would be afraid it would delete an important email that it incorrectly marks as spam, but others may see value.

Yup, interacting with and posting with content on these platforms is the best way, people trickle in to see what it’s like. I doubt we’ll ever have a big migration, the goal is long term sustained trickles

Like I said, I was agreeing with your title. Thought we were going to have an interesting conversation on AI generated rage bait. Here we are instead.

Technically, I didn’t read the post, but agreed with your title. Then all of your comments after I’ve accused of baiting, but yeah maybe the post was just to bait too.

Stop trying to bait us.

No. No it was not. None of them have been.

Let’s take your first question.

Honest question, are you good just passively watching all this MAGA shit spread?

There was nothing honest about this. I said I didn’t want to read the Facebook post. An honest question would have been:

I know there are many reasons why not you but why don’t you want to go on Facebook?

That’s an honest question.

You had a very obvious agenda. You are obviously trying to bait me into some argument, which I am not getting into with you. Your question was completely dishonest, because it both did not ask me about anything relevant to what I said, and there was also no way for me to answer you without you having a fully planned response.

We aren’t taking the rage bait. That’s for Facebook. Stop trying to bait us.

Why do you turn everything into an inflammatory question?

Me watching it isn’t going to help anything.

Not going to look at the link, but I see it’s Facebook, and from my last experience over a year ago it was well over 90% AI generated rage bait

Yeah I tried tabby too and they had like a mandatory "we share your code " line and I hoped out. Like if you’re going to do that I might as well just use claude

From OPs anger I think we can assume he may live 1000km further north

It means extremes for sure. It’s why the hurr durr it’s cold out people are morons, our climates are changing. Warming causes global changes.

Some areas get drier like California. Some places get colder. Midwest of the US gets more intense and frequent tornadoes and extreme storms. My area is getting more rain.

Take what you already get in terms of extreme weather, dial it up to 11.

Exactly, they join d the main networks and instances, who hate the Al right trolling, anger, and hatred, and have defederated all of them. They’re still out there, isolated and alone, b cause we all chose we didn’t want to sit here and listen to their drivel.

Thanks for letting us know, in fact it may be worth a today I learned style post because I don’t think people know this

Yeah, last time I went there was over a year ago and had a similar experience to op, now I go to my local shop. Same price now as mcds, but I get almost 2x the food and it’s better quality.