Riker catches an alien “virus” (from a plant) and lays down naked under a shiny blanket for the rest of the episode. Pulaski forces Riker to dream of the most boring and worst segments from season 1 and 2.

Most shows have flashback episodes that feature highlights. TNG had a clip show that showcased the worst segments. It was the most lackluster finale episode of any Star Trek season. And this was even well after Riker “grew the beard”.

Merlin wasn’t available here when I checked at some point in time (last year?)

whoBIRD does use BirtNET, from Cornell, so it’s basically the same backend (although it may be an older version).

I recently tried out Merlin (which is now available here) and it’s amazing. It’s definitely more featureful than whoBIRD, although both have the core “recognize bird directly using your phone” features.

For anyone OK with non-FOSS apps, Merlin is great. For anyone who wants a FOSS app for bird detection, whoBIRD is still pretty good.

Either way, identifying apps using ones phone is nice. 👍 Big things to Cornell for making the ML for both of these apps.

Oh, nice! Then there are two great FOSS keyboard under maintenance again! Thanks for mentioning that.

whoBIRD

An app that recognizes birds singing near you, all on device, and has an option to show a photo of the bird too. It’s exclusive to F-Droid (not on Google Play), and the only bird recognizing app I know of that does it all immediately on your device (without sending it to a server). https://f-droid.org/en/packages/org.woheller69.whobird/

Organic Maps

Highly detailed OpenStreetMap maps local on your device. Wonderful for walking directions, as it has on-device routing and maps out walking pathways (which is something that even Google Maps does not do well) https://f-droid.org/en/packages/app.organicmaps/

AntennaPod

The best podcast client also happens to be Free Software and on F-Droid. https://f-droid.org/en/packages/de.danoeh.antennapod/

HeliBoard

This is the best FOSS keyboard that’s under active maintenance. It even supports swiping, but that requires a non-free binary library from Google. (Maintained fork of OpenBoard.) https://f-droid.org/en/packages/helium314.keyboard/

Breezy Weather

Good weather app that has so many details (including pollen too) and fetches from multiple sources. It looks great as well. https://f-droid.org/en/packages/org.breezyweather/

Agreed.

Additionally, the graphic oversimplifies things as well. The resulting genetically modified crop is often not even all that close close to the same as the non-GMO, as seen by studies such as this one:

https://enveurope.springeropen.com/articles/10.1186/s12302-023-00715-6

Basically; GMO soybeans contain proteins which differ and also include additional proteins. This can cause allergic reactions to modified soy where non-modified soy might not cause an issue.

Monsanto supposedly even knew about these proteins and higher risk of allergic reaction and chose to not disclose it. (I saw some research that mentioned this years ago… It’d be hard to find the exact source I read back then.) This specific paper, which talks about additional proteins and side-effects brought in by the new transgenic splicing, also explicitly states that Monsanto did studies themselves and failed to report relevant findings:

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5236067/

Obviously, other methods can also change proteins too, but these papers show it isn’t as clear cut as the graphic in the original post claims.

Along these lines, here’s a study that finds differences not just in soybeans grown organically versus ones treated by glyphosate (Monsanto Round-Up pesticide) but also between GMO and non-GMO crops, both treated by the pesticide.

https://www.sciencedirect.com/science/article/pii/S0308814613019201

But, yeah this is just a long way of agreeing with the parent post and saying that the end goal is to make the plants resistant to poison, not to make them better for humans, all to make more money. (In this case, Monsanto is even double-dipping by selling both the pesticide and the crops tailor-made for the pesticide.)

Other GMO crops might be closer to the original crop and might also actually be beneficial for humans without drawbacks. However, Monsanto’s soybeans are problematic, and other crops might be as well, especially if they’re made by companies who have money as their primary goal.

GNOME 46 (currently in release candidate mode and fully releasing later this month on March 20) is adding support for remote graphical logins via rdp:

https://9to5linux.com/gnome-46-to-introduce-headless-remote-logins-via-gnome-display-manager

So you’ll be able to do this pretty soon, after upgrading.

It’ll be in Fedora 40, scheduled for release around April 16.

https://fedorapeople.org/groups/schedule/f-40/f-40-all-tasks.html

Yeah, that’s a big, weird if though. Most modern apps can rely on the runtimes for their dependencies and not have to ship their own custom dependencies.

It’s different from something like AppImage, where everything is bundled (or Snap, where a lot more needs to be bundled than a typical Flatpak, but not as much as with an AppImage).

Additionally, there’s always some level of sandboxing in Flatpaks (and Snap packages) and none at all for RPMs, Debs, or AppImages.

Also, Flatpak dedupicates common files shared across flatpak apps and runtimes, so there isn’t “bloat” like what you’re talking about.

https://blogs.gnome.org/wjjt/2021/11/24/on-flatpak-disk-usage-and-deduplication/

That’s not how Flatpak works.

Flatpak has runtimes, which is where most shared libraries are. There’s a common base one called Freedesktop, a GNOME runtime, a KDE runtime , an Elementary runtime, and more. (The GNOME and KDE ones are built on top and inherit from the Freedesktop base runtime.)

https://docs.flatpak.org/en/latest/available-runtimes.html

Additionally, at least for Flathub, they have shared modules for commonly used libraries that aren’t in runtimes. (Many are related to games or legacy support like GTK2.)

https://github.com/flathub/shared-modules

Lastly, some distributions are building their own runtimes and apps on top, so the packages they build are available as flatpaks as well. This is the case for Fedora, Elementary, Endless, and others.

https://fedoraproject.org/wiki/Flatpak

Yeah, some of the smaller models are even reasonable on my old laptop in CPU mode.

General rule of thumb: The larger the model, the better it is. But not necessarily. 😉 I’ve found zephyr and mistral are both quite good for a tradeoff and work on CPU. Of the ones that really need more RAM and/or a GPU with a lot of vRAM, mixtral seems like the best.

Additional fun is to use a Modalfile (which is like a Containerfile, but is a recipe for models instead of containers) to customize a local model on top of one of the existing ones.

For a simple one to demonstrate, I have a system instruction to output everything in the form of the poem “This Is Just To Say”, but customized per topic.

It really works best with mixtral (I’ve tried other ones, especially smaller ones):

FROM mixtral
PARAMETER temperature 1
SYSTEM """
You will respond to everything in a modified poem in the form of "This Is Just To Say" by William Carlos Williams, except change all the specifics to be what the subject is. Do not say any other text. Try to make the syllables the same as the original and use the same formatting.

You can expand in length in responses when there is too much to talk about, but keep the format and style of the poem.

Do not respond in any other way.

For reference, the full poem is:

I have eaten
the plums
that were in
the icebox

and which
you were probably
saving
for breakfast

Forgive me
they were delicious
so sweet
and so cold
"""

Yes, you just instruct the system with natural text like that and it (usually) abides. I tried it without the poem being referenced inline, and it mostly worked fine… but it works even better being mentioned in the file.

I have that saved in ~/Projects/ollama/ as Modelfile.fun-plums

I run the server almost as above, but now also pass in my ollama project directory as a mounted volume with z (for SELinux mapping)… don’t forget to have run sudo setsebool container_use_devices=true first, else it won’t work:

podman run --detach --replace --device /dev/kfd --device /dev/dri --group-add video -v ollama:/root/.ollama -p 11434:11434 -v ~/Projects/ollama:/models:z --name ollama ollama/ollama:0.1.24-rocm

(You can run this command if you already have the server running. It will replace it with the new one. This is for AMD. You’d want to use the NVidia or CPU container if you don’t have an AMD card. The CPU container is the fasted to download. The version here is newer than the one for AMD that I listed above, so it might be a multi-gigabyte download if you don’t have this new one yet. The important and new part is ~/Projects/ollama:/models:z)

Then, create the model. This will be almost instant if you already have the base model downloaded (in this case, mixtral), otherwise it will auto-download the base model:

podman exec -it ollama ollama create fun-plums -f /models/Modelfile.fun-plums

(The path to the model in this command is the internal path from the point of view within the container.)

Then, you run it like any other model.

Here’s me running it, and bringing up the topic of leftover pizza.

$ podman exec -it ollama ollama run fun-plums
>>> pizza
 I have consumed
the pizza
that was on
the counter

and which
you were likely
saving
for lunch

Forgive me
it was satisfying
so tasty
and so warm

You can also paste the text from the reader mode of an article and it’ll summarize it with a poem based on that one. 🤣

For example, copying and pasting the text from https://www.theverge.com/2024/2/10/24068931/star-wars-phantom-menace-theater-showings-25th-anniversary-may resulted in:

 I have watched
the Phantom Menace
that was on
the silver screen

and which
you may have
missed or
disliked once

Forgive me
it has charm
a new sheen
and Darth Maul

FOSS apps (all on Flathub)

Some of the AI related apps I’ve been using that are both Free Software and offline (where it runs on your computer without using network services in the cloud) are:

• OCR: “Frog” can take screenshots, select images, accept drag and drop, and you can paste an image from the clipboard. It’ll read the text on the images and immediately have a text area with the result. https://flathub.org/apps/com.github.tenderowl.frog — it’s powered by Tesseract. Note: The completely optional text-to-speech that Frog has does use an online service. But the rest is offline.

• Speech to text: “Speech Note” does text to speech, speech to text, and translations… all locally on your computer, and it supports GPU acceleration (which isn’t needed, but it makes it a little faster). https://flathub.org/apps/net.mkiol.SpeechNote — This is basically the all-in-one “Swiss army knife” of ML text processing. Thanks to being a Flatpak, you don’t have to do anything special for the dependencies. It’s all taken care of for you. It also has tons of different models (for different voices, different backends) all available from within the UI, which just needs a click for downloading.

• Upscaling images: There are two that do something similar, using some of the same backends. A nice and simple one is “Upscaler”. https://flathub.org/apps/io.gitlab.theevilskeleton.Upscaler Another one that’s cross platform is “Upscayl” https://flathub.org/apps/org.upscayl.Upscayl — these both use ESRGAN and Waifu2x in the background.

• Closed captioning: “Live Captions” uses an ML model to transcribe text realtime. It’s wonderful for when a video doesn’t have subtitles, or when you’re participating in a video call (which might also not have CC). There’s also a toggle mode that will transcribe based on microphone input. The default is to use system audio. https://flathub.org/apps/net.sapples.LiveCaptions

• Web page translations: Firefox, for the past few releases, has the ability to translate web pages completely local in-browser. It does need to download a small model file (a quantized one around 20 megabytes per language pair), but this happens automatically on first use. All you need to do is click the translate icon (when it’s auto-detected) or go to the menu and select “Translate page…”. Firefox is located in your distribution already (and is usually installed by default in most Linux distributions) and is available as an official package from Mozilla on Flathub as well. Newer versions keep improving on this, improving speed (it’s pretty quick already), improving accuracy, improving reliability (sometimes you have to try to translate a couple of times on some pages), and adding languages. But what’s there in the release of Firefox is already great.

Chat and image generation (more advanced)

While all the above are graphical apps and on Flathub (some may have distro packages too), there are some additional AI/ML things you can run on Linux as well:

• Chat ML: “Ollama” (https://ollama.ai/) is a friendlier wrapper around llama.cpp and lets you run a variety of models (some FOSS, some just source-available-and-gratis, some not at all).

You can run Ollama in a container to make it even easier. Even a Podman container on your user account works. (You don’t need to set it up as a system container.) The instructions for Docker work on Podman (just swap the docker command for podman instead).

While the official instructions only list CPU (which is fine for some of the smaller models) and NVidia, it’s also possible to use an AMD GPU too:

# Enable device as user (run once per boot)
sudo setsebool container_use_devices=true

# Set up the ollama server for AMD acceleration (run once per session)
podman run --pull=always --replace --detach --device /dev/kfd --device /dev/dri --group-add video -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:0.1.22-rocm

# Command-line interaction (run any time you want to use it — the last part is which model you want to use)
podman exec -it ollama ollama run llama2

llama2 is the default ML; there are so many others available. Mixtral is a good one if you have enough vram on your GPU. Whatever you specify, it will auto-download and set it up for you. You only need to wait the first time. (The ROCm version of takes a while to download. Each model varies. The good thing is, it’s all cached for subsequent uses.)

If you want a web UI like ChatGPT, then you could also run this instead of the command line interaction command:

podman run -d --replace -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui ghcr.io/ollama-webui/ollama-webui:main

…and visit http://localhost:3000/

When done, run podman stop ollama and podman stop ollama-webui to free up resources from your GPU.

There are also integrations for text editors and IDEs, similar to GitHub’s CoPilot. Neovim has a few already. VS Code (or VS Codium) has some too (like twinny and privy).

• Image generation: “Stable Diffusion” is the go-to here. There are a bunch of forks. Some of the better ones are:
  • “Fooocus” https://github.com/lllyasviel/Fooocus/ — an easy to use streamlined app (with some advanced settings) where you don’t need to prompt as much or tweak settings to get a good result by default.
  • “SD.next” https://github.com/vladmandic/automatic — A fork of the Automatic111 fork of the default Stable Diffusion web app that uses the Gradio UI.
  • “ComfyUI” https://github.com/comfyanonymous/ComfyUI — A node-based UI for Stable Diffusion. …and there are a ton others. Forks of forks of forks.

Krita, GIMP, and Blender all have plugins that can interface with some of these too (usually using a SD Automatic111 API).

For Stable Diffusion on AMD, you need to have ROCm installed and might need to set or use an environment variable to make it work with your card. Something like: HSA_OVERRIDE_GFX_VERSION=11.0.0 or HSA_OVERRIDE_GFX_VERSION=10.3.0 (depending on your GPU). Prefixing means just putting that at the beginning of the the command with a space and then the rest of the command. Setting it as a variable depends on your shell. You might need to export it for some (like for bash). Prefixing it is fine though, especially when you use ctrl+r to do a substrang search in your shell history (so you don’t need to retype it or remember silly-long commands).

As using these image generating apps pulls down a lot of Python libraries, I’d suggest considering setting up a separate user account instead of using your own, so the app doesn’t have access to your local files (like stuff in ~/.ssh/, ~/.local/, your documents, etc.). Setting up containers for these is not so easy (yet), sadly. Some people have done it. And they do run in a toolbox or distrobox podman container… but toolbox and distrobox containers don’t really contain so much, so you’re better off using podman (with a “docker” container) directly or running it as a separate account for some type of isolation from your user account files.

Everything else above is at least contained (via containers or Flatpak) to some degree… but stuff locally via pip installs can do anything. And it’s not just hypothetical either, for example: PyTorch nightly was compromised for a few days on Christmas of 2022.

There are some graphical apps on Flathub for connecting to Stable Diffusion and a ChatGPT AI (which ollama now has)… but in the course of setting them up, you basically have a web and/or text-based UI to interact with.

I basically gave up on podcasts on the desktop and only use AntennaPod on my phone. When I’m at my desktop, I have my phone paired with my computer via Bluetooth and play that way. I can pause it on my computer via KDE Connect (GSConnect on GNOME).

Bluetooth audio from phone to desktop works on Fedora Linux quite well. It probably works on other Linux distros too. I’m guessing it might also work on other OSes like Windows and macOS.

KDE Connect is available on Android, iOS, KDE (and can run on other desktops too), GNOME (via the GSConnect extension), Windows, and macOS.

This solves the syncing problem by sidestepping the need for it. My podcast state is always correct and I always have my podcasts with me, even when out and about.

Docker on Windows and Mac also runs containers through a VM though. (It’s more obvious on Windows, where you need WSL (powered by a VM) and Hyper-V (a way to run VMs on Windows). But on a Mac, VMs to run Linux are also used to run Docker containers inside the VM.)

Podman Desktop helps to abstract VMs away on Windows and macOS: https://podman-desktop.io/

For the command line, there’s “podman machine” to abstract away the VM. https://podman.io/docs/installation (installing on macOS is mentioned on that page and Windows has a link to more docs which also uses the podman machine command.)

As for Docker compose, you can use it directly with Podman too: https://www.redhat.com/sysadmin/podman-docker-compose (there’s also podman-compose as well). The only thing Docker compose doesn’t support with Podman is swarm functionality.

Docker compose can even work with rootless Podman containers on a user account. It requires an environment variable. https://major.io/p/rootless-container-management-with-docker-compose-and-podman/ (it’s basically enabling the socket for podman and using the environment variable to point at the user podman socket)

You can set up mount points on Linux, at least in GNOME, very easily. (It’s even fully automatic for external disks.) I’d be surprised if it isn’t as easy in KDE and other desktops too.

The problem here (at least from what it sounds like) isn’t setting up mount points. The problem is fixing an incorrect fstab on the disk that’s causing the system to hang on boot.

(This isn’t a typical situation, which is why I also asked about how the partition was added to the system.)

Good point! GNOME Disks can do this, actually. I didn’t think about that.

(Edit: However, I think it’ll just edit the /etc/fstab of the running system. In other words, the one of the live session, not the one on the installation.)

My first attempt to try to fix something like this would be to:

1. Download Fedora Workstation live media. (Within Windows or some other computer that boots.)
2. Flash it to a USB stick.
3. Reboot to the live desktop from the USB stick. (It might require pressing F12 or some other key combo during boot.)
4. “Try out” Fedora. (That is: do not install.)
5. Open GNOME Disks. (I think it’s included. Otherwise, you can sudo dnf install gnome-disks to install it temporarily on the live session.)
6. Try to mount the main filesystem that contains /etc/fstab (it should ask you for the LUKS password.
7. Comment out the Windows mount point. Or if you want to keep it (if the partition still exists and is just “dirty” and still needs a check from Windows) add “,nofail” after “auto” to the options in the line for the mount, so your system should still boot without that mount point.
8. Save the /etc/fstab file.
9. Shut down the computer.
10. Unplug USB stick.
11. Boot computer. Linux should successfully boot… hopefully. 😉

I’m also wondering: How did you add the Windows partition to Fedora? Was it from within Fedora’s installer (aka: “Anaconda”)? Or did you add it in a different way?

(BTW: I use Silverblue and have a long history with Fedora. 😁)