Uh oh, looks like you didn’t read far enough:

On Monday, two days after the incident occurred, Mr Crane confirmed that the data had been recovered. The Independent has reached out to Anthropic and Cursor for comment.

So again… Well, do I need to paste it again?

So again, because we make backups before letting AI touch anything:

“Hey slop machine, you fucked up. Restore the last backup and document the mistake you made in AGENTS.md so we avoid making that mistake again. Im going to go make a coffee, brb”

Oops, slop machine broke something.

“Hey slop machine, you fucked up. Restore the last backup and document the mistake you made in AGENTS.md so we avoid making that mistake again. Im going to go make a coffee, brb”

Hardware I’m running:

• 8/16 AMD CPU
• 32GB system RAM
• 12GB GPU VRAM (AMD)

I’m mainly using these MoE models:

Qwen-3.6-35B-A3B

• Q4_K_M quant quality
• 128k context (conversation length before it compacts)
• Gives me about 260 prefill and 19 token gen speeds

Gemma4-26B-A4B

• Q8 quant quality
• 128k context length
• Gives me about 190 prefill and 14 token gen speeds

I created git repos on my main workstation for each homelab server/service I maintain that keeps:

• documentation
• notes
• lessons learned
• scripts, configs
• runbooks
• backup details
• security audit details
• log items that need attention
• infrastructure

I just point a local LLM (offline model that runs on my workststion) into those repos and ask it to perform certain things on those servers. It can do things like update packages, install packages, make config changes, set/check permissions, read logs (and fix errors in real time), and check the health of the overall system.

I have it run pre backups before making changes, then post backups once its done.

Once changes are in place and everything is running okay, I ask it to update documentation in the repo and tag the release.

I use opencode that connects to a llama.cpp service. opencode lets me gate the AI so that any elevated commands that it needs to run (e.g. sudo or ssh), I have to approve it. It cant just go around making changes without permission.

This question is how new apps are born

Those devices should most certainly be on two separate networks. Internet facing devices should be on a DMZ and not be allowed to talk to your internal network. You can then allow your internal network reach your DMZ devices, but only allow return traffic from the DMZ.

Which cloud service is going to last 1000 years?

One thing you could deploy throughout all your internal networks are honeypots that send alerts upon ANY network activity. Nobody should be hitting those at all.

Healthy storage pool? Any disk errors?

HDDs or SSDs locally?

You should be able to find an Android Auto / Apple CarPlay device that will give you what you’re asking for. Then just set your phone to Do Not Disturb or a specific Driving mode so that it doesn’t let you control the phone itself until you reach the destination or are at a complete stop.

Newpipe should let you download and convert as MP3 or whatever format and then you just play in your music player of choice.

According to TechCrunch, that dataset is built off of Public Domain works.

https://techcrunch.com/2025/06/06/eleutherai-releases-massive-ai-training-dataset-of-licensed-and-open-domain-text/

The Common Pile v0.1, which can be downloaded from Hugging Face’s AI dev platform and GitHub, was created in consultation with legal experts, and it draws on sources, including 300,000 public domain books digitized by the Library of Congress and the Internet Archive. EleutherAI also used Whisper, OpenAI’s open source speech-to-text model, to transcribe audio content.

Yeah but which one? Can you name one?

Which datasets are not complying? Call them out by name. Gotta keep them accountable.

The big update is coming soon. They’ve been working on it for a long time now. Its in the final stretch and should hopefully be in TestFlight soon.

Swiftfin is an official tvOS jellyfin app:

https://apps.apple.com/us/app/swiftfin/id1604098728

This is per:

https://jellyfin.org/downloads

Yes, I do. You’re not the only crazy person. If I don’t wipe it, it looks blurred, smudged, or get that weird effect where it looks like I have astigmatism.

Sorry, wish I was able to share more. I honestly JUST started diving into this stuff after your post. Learning a lot from the various other comments though. Hopefully some of the other commenters can help you get the answers you’re looking for.

Ollama is in the Arch Linux package repository, whereas llama.cpp is in the AUR. Both options are available.

https://wiki.archlinux.org/title/Llama.cpp

Also, looks like Ollama is mostly written in Go and C, versus C and C++.

VC backed or not, both packages are under the MIT license.