Sir. Haxalot

That is probably part of the problem. My guess is that for some reason programming.dev is trying to send a backlog of events since the time your instance was shut down. This doesn’t seem like something that should happen though, as I’d expect Lemmy to mark an instance as Gone and stop trying to send events after a while.

I’m like 90% sure that this post is AI Slop, and I just love the irony.

First of all, the writing style reads a lot like AI… but that is not the biggest problem. None of the mitigations mentioned has anything to do with the Huntarr problem. Sure, they have their uses, but the problem with Huntarr was that it was a vibe coded piece of shit. Using immutable references, image signing or checking the Dockerfile would do fuck-all about the problem that the code itself was missing authentication on some important sensitive API Endpoints.

Also, Huntarr does not appear to be a Verified Publisher at all. Did their status get revoked, or was that a hallucination to begin with?

To be fair though the last paragraph does have a point, but for a homelab I don’t think it’s feasible to fully review the source code of everything you install. It would rather come down to being careful with things that are new and doesn’t have an established reputation, which is especially a problem in the era of AI coding. Like the rest of the *arr stack is probably much safer because it’s open source projects that have been around for a long time and had had a lot of eyes on it.

The free version is mainly just a number of user and device limit. Although the relaying service might be limited as well, but that should only matter if both of your clients have strict NAT, otherwise the Wireguard tunnels gets directly connected and no traffic goes through Netbirds managed servers.

You can also self-host the control plane with pretty much no limitations, and I believe you no longer need SSO (which increased the complexity a lot for homelab setups).

That seems to be the terms for the personal edition of Microsoft 365 though? I’m pretty sure the enterprise edition that has the features like DLP and tagging content as confidential would have a separate agreement where they are not passing on the data.

That is like the main selling point of paying extra for enterprise AI services over the free publicly available ones.

Unless this boundary has actually been crossed in which case, yes. It’s very serious.

That is kind of assuming the worst case scenario though. You wouldn’t assume that QA can read every email you send through their mail servers ”just because ”

This article sounds a bit like engagement bait based on the idea that any use of LLMs is inherently a privacy violation. I don’t see how pushing the text through a specific class of software is worse than storing confidential data in the mailbox though.

That is assuming that they don’t leak data for training but the article doesn’t mention that.

They’re probably not going to use it…

… but if they do it’s going to be a hell of a good starting point in motivating people to leave Facebook

Honestly you pretty much don’t. Llama are insanely expensive to run as most of the model improvements will come from simply growing the model. It’s not realistic to run LLMs locally and compete with the hosted ones, it pretty much requires the economics of scale. Even if you invest in a 5090 you’re going to be behind the purpose made GPUs with 80GB VRAM.

Maybe it could work for some use cases but I rather just don’t use AI.

Maybe i misunderstand what you mean but yes, you kind of can. The problem in this case is that the user sends two requests in the same input, and the LLM isn’t able to deal with conflicting commands in the system prompt and the input.

The post you replied to kind of seems to imply that the LLM can leak info to other users, but that is not really a thing. As I understand when you call the LLM it’s given your input and a lot of context that can be a hidden system prompt, perhaps your chat history, and other data that might be relevant for the service. If everything is properly implemented any information you give it will only stay in your context. Assuming that someone doesn’t do anything stupid like sharing context data between users.

What you need to watch out for though, especially with free online AI services is that they may use anything you input to train and evolve the process. This is a separate process but if you give personal to an AI assistant it might end up in the training dataset and parts of it end up in the next version of the model. This shouldn’t be an issue if you have a paid subscription or an Enterprise contract that would likely state that no input data can be used for training.

I can’t really tell if you’re joking or not but no, I’m saying that it’s a bug, and at no point anything is sent off your computer

I like that the article excerpt clearly says that it’s simply about files not being removed when the trash bin is emptied, and it’s a problem specific to the Canonical snap system… Yet every single other comment in here rants about Microsoft spyware. Not many people read beyond the headline, lol.