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.

Eh? Seyfried is good, but paired with maga tits Sweeney idk. Sweeney is trying too hard to be serious after rightfully being called out for being… Well…

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.

Man good thing they’re coming out with so many new games. I’d be worried about the long term health of these big companies if it weren’t for the solid pipes of great new titles rolling out

And they’re punishing dispatch devs for their shit choice. They’re not returning the consoles or refusing to buy Nintendo, they’re returning the game that Nintendo censored.

Next they’ll just have copilot play the games for us! Of course there will be a mandatory price increase

This one got me lol, you got a real audible chuckle out of me, congrats

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

Was I the only one who thought Deadpool and wolverine was meh at best? I don’t remember any of the story, I remember a few cameos, but meh.

Lemmy is not a chat platform, and the fediverse is the wrong technology for that. There are plenty of decentralized chat apps already that have that capability

Why not just go to any of those apps?

I honestly don’t know how they’re so disconnected from reality. To in the same statement within 2 paragraphs say they both want to be more focused on the gamer, and immediately then say “More GenAI, more recurring payments, more Games as a Service”. I just, I don’t know man. I don’t want layoffs but man they really just don’t get it do they?

Yeah so, we know gamers have hated our stuff because of these horrible shitty practices - but, and hear me out, what if we did that stuff even more, don’t even mention things like great stories and fun worlds or anything gamers have been asking for, and also laid off most of our staff and forced return to office too?

Ubisoft founder and CEO, Yves Guillemot, said the company must pursue a “radically new” value-creation model and become a more “gamer-centric” organization to find its footing in an increasingly competitive and selective triple-A market.

Good! Realizing it needs to be about the gamer again not just shareholder value.

“The new operating model will further empower the execution of the Group’s strategy, centered on Open World Adventures and GaaS-native experiences, supported by targeted investments, deeper specialization, and cutting-edge technology, including accelerated investments behind player-facing Generative AI,” reads the document.

Oh god damnit nevermind, the boycott continues

Lovers in a dangerous spacetime was a ton of fun! Very adorable, simple mechanics, plays on one screen, and not too hard. Also came out over 5 years ago so win win

Asus has always just chased after the short term goals. This reminds me when they suddenly made android tablets, and mini pcs, and every stupid tech fad. They’re always after the latest fad, they release a subpar product, and then it fizzles.

Kai Leng - ME3