xcjs

It's not built in, but I generally recommend Solid Explorer for that functionality: https://play.google.com/store/apps/details?id=pl.solidexplorer2&hl=en_US&gl=US

The Nuzu repository is already wiped.

At some point, you lose productivity and reduced work weeks have shown increases in productivity can happen.

Now the question is - are they open sourcing the original Winamp, or the awful replacement?

I love this feature and use it all the time! Are there any apps I can replace this with?

Rust specializes in making parallel processing secure and approachable, so it's going get used in problems where parallel processing and efficiency matter.

Rust is also now allowed to be used in the Linux kernel for the same reasons, which is exciting!

Honestly, taking the time learn Docker and then learn more about the specific containers that you want to use is probably going to be the easiest way forward in your position. If you have any specific questions about Docker or the containers you're looking at, I can try to help.

When it comes to network mounts, I've found it a lot easier to use rclone for that purpose, and that's currently what I use for the backend of my Plex server.

With UI decisions like the shortcut bar, they really don't. I switched to another SMS app because I couldn't stand it.

Not with this announcement, but it was.

Google was working on a feature that would do just that, but I can't recall the name of it.

They backed down for now due to public outcry, but I expect they're just biding their time.

I'd say not because of those things but due to overall socioeconomic well-being.

I use significant hardware component or model:

• Z390
• AERO15

...or sometimes intended purpose:

• USERV - Ubuntu SERVer
• PlexBox - Plex Server
• NAS - NAS
• Runner - GitLab Runner
• MDEV - Mobile DEVelopment
• MDEV2 - Mobile DEVelopment, Version 2

I also have a Kubernetes cluster that ranges from K8S_0 to K8S_5.

Let's maybe leave the racism at the front door? Or, you know, entirely?

This is a bit outdated with .NET Core. You can just compile it for a Linux target or install the .NET runtime from Microsoft.

I'm not sure Mono supports all the newer language features.

With his experience (and I agree if this is the case), he's probably expecting issues with unsupported configurations of Windows 11.

I guarantee that at some point after Windows 10 support drops that Microsoft will start pushing features that require TPM functionality. Maybe it will be minor at first, like you can't use PIN logins without it. Eventually it might move on to HTTPS requests failing without root certificates protected by a secure element store. Maybe OS updates will fail to install making these customized Windows 11 installs just as useless as Windows 10.

I've been a software developer for over a decade, and while I will never say always, usually unsupported configurations like this TPM workaround eventually fail. I wouldn't place my trust in it lasting.

Same story here, and Connect seems to be the furthest along.

I'll probably switch to Sync for Lemmy when it makes it's debut, but Connect is almost a good enough replacement.

I'm using a combination of:

• The Boox Palma reader, though they have larger tablets if you prefer. I'm not sure about the others, but the Palma runs Android with the Play Store.
• Kavita to host my ebooks online.
• FolderSync with SFTP to sync all of my books ahead of time to my SD card.
• Moon Reader to add my Kavita server's OPDS feed as an online catalog if I need to grab something manually.
• Calibre to manage and embed metadata.

Systemd was created to allow parallel initialization, which other init systems lacked. If you want proof that one processor core is slower than one + n, you don't need to compare init systems to do that.

No offense intended, but are you sure it's using your GPU? Twenty minutes is about how long my CPU-locked instance takes to run some 70B parameter models.

On my RTX 3060, I generally get responses in seconds.

Correction: migrated to GitLab, but I don't expect they'll want to keep it there.

I'm not familiar with creating fonts specifically, but you'll want to commit any resources necessary to recreate the font file, including any build scripts to help ease the process and instructions specifying compatible versions of tooling (FontForge in this case). Don't include FontForge in the repository, of course.

The compiled font files should be under releases in GitHub for the repository.

Git isn't generally meant for binary resources but as long as they're not too large, they'll be fine. You just may not have meaningful ways to compare changes easily.

Show me a music store I can purchase music from on my phone through an app, and I'll purchase it.

I...do not miss XP, but I understand the nostalgia attached to it.

I learned a lot of technical skills on XP, but that's what made me appreciate the architectural decisions behind UNIX-likes all the more.

I mean, sysvinit was just a bunch of root-executed bash scripts. I'm not sure if systemd is really much worse.

I was reflecting on this myself the other day. For all my criticisms of Zuckerberg/Meta (which are very valid), they really didn't have to release anything concerning LLaMA. They're practically the only reason we have viable open source weights/models and an engine.

It doesn't quite say that, but I think the meaning is essentially the same: "Don't choose a name after a project unique to that machine." - RFC 1178

For my homelab, I think that's fine to do. I'm unlikely to have multiple Plex servers locally, for example, and if so, numerically naming them is fine - I provision with Ansible, and if I'm at the point where I'm having sequentially numbered hosts, they'll be configured as cattle anyway. Also, having the names reflect the services a host provides makes it easier to match in my playbooks.

I think it's a better scheme than turning to mythology, fiction, or animal species, which oddly enough RFC 1178 does encourage you to do.

Or maybe just let me focus on who I choose to follow? I'm not there for content discovery, though I know that's why most people are.

PNG support lossless compression through deflation, but there are encoders that can apply a lossy filter to the image to make the compression more effective.

PNG doesn't support lossy compression natively, to be clear.

I've done something similar, but I'm using compose files orchestrated by Ansible instead.

I was going to recommend Ansible as well - documentation as code can never be out of date if you continue using it.

It's a W3C managed standard, but there are tons of behavior not spelled out in the specification that platforms can choose to impose.

The standard doesn't impose a 500 character limit, but there's nothing that says there can't be a limit.

Just so you're aware why people are disagreeing with you - an installed browser does not change the behavior of HTTP calls made in other applications.

Sounds like a job for Ansible. ;-)

I bought a used 2018 model over a new current model because of the lack of physical function keys.

Also, Dell, bring back Fn + Left for Home and Fn + Right for End!

Who looked at a great keyboard layout and decided, "I know! I'll make this Developer Edition hardware more difficult to develop on!"

I think this is part of a larger trend of Microsoft refusing to patch any bug they simply don't want to.

I've had an issue with the Remote Desktop app on Android for three years where the cursor drifts further and further away from where it's drawn over the course of a session and when the Android keyboard pops up. Several users have reported the issue (including myself), and Microsoft still hasn't fixed it.

Once again, this has been a major usability bug for over three years. The only way around it is to disconnect from the session and reconnect every time you use the keyboard or once the drifting becomes too much.

What is obscene is subjective.

If it does include a VPN provider, then you're correct - it would work for other applications.

I don't think it's common knowledge for people who don't have the app, so you may want to include information about that in your original post.

I think discoverability is still a problem.

I use Discord for real-time communication, but leaving a platform that's closing up access for a platform with already closed access makes no sense to me. It doesn't solve the original problem.

That depends on what you mean by container. I use it to orchestrate Docker containers for my infrastructure and then some.

Of course! Here's the documentation for the docker-compose module: https://docs.ansible.com/ansible/latest/collections/community/docker/docker_compose_module.html

It does rely on the recently-made-legacy docker-compose client, so for now it's still required to install that. If you need some advice or pointers, let me know.