Using "AI" has been beneficial for example to generate image descriptions automatically, which were then used as alternative text on a website. This increased accessibility AND users were able to use full text search on these descriptions to find images faster. Same goes for stuff like classification of images, video and audio. I know of some applications in agriculture where object detection and classification etc. is used to optimize the usage of fertilizer and pesticides reducing costs and reducing environmental impact they cause. There are ofcourse many more examples like these but the point should be clear.

Danke vielmals!

Link zu dem Artikel, irgendwer? Bittte bitte.

While this will get you a selfhosted LLM it is not possible to feed data to them like this. As far as I know there are a 2 possibilities:

1. Take an existing model and use the literature data to fine tune the model. The success of this will depend on how much "a lot" means when it comes to the literature

2. Create a model yourself using only your literature data

Both approaches will require some yrogramming knowledge and understanding of how a llm works. Additionally it will require a preparation of the unstructured literature data to a kind of structured data that can be used to train or fine tune the model.

Im just a CS student so not an expert in this regard ;)

Is there a difference between tab stacking and something like tree style tabs?

I specifically said anecdotlly. Your experience and my experience a not representative of anything. Also that is only a small portion of my comment and was meant more a a sidenote.

We were also not talking about windowed mode at all here. It was specifically about what happens when you press the green window control button, which as far as I know puts the app in fullscreen on macos and the equivalent on any other OS known to me is to maximize the window.

Just FYI Drew DeVault also started a fork recently https://codeberg.org/redict/redict/

Somehow I only had issues with CrowdSec. I used it with Traefik but it would ban me and my family every time they used my selhosted matrix instance. I could not figure out why and it even did that when I tried it on OPNSense without the Traefik bouncer...

Naja also das design ist jetzt farblich nicht großartig gleich. Die Anordnungen der Elemente sowie die Nutzerführung beim ersten Benutzen der App und der Einstellungsumfang sind aber schon ziemlich ähnlich. Es hatte mich lediglich interessiert ob das eine evtl. eine Gabel des anderen ist oder ähnliches.

Edit: ich meinte natürlich Gabel und nicht fork!