Not same results as DeepL but… You can use any popular online LLM for excellent translation. There are also “small” language models that you can run on your phone (if you havet a reasonable modern/powerful phone that is): https://github.com/mlc-ai/mlc-llm

Because the political and economical situation is extreme.

I’ve heard it said that every successful Swedish war campaign begins with the loss of their entire fleet.

Hmm… I can see the thread in mastodon, except for that specific comment. Everything is visible if I visit social.kernel.org in Firefox though.

Everyone knows the Comanches were nothing but peace loving kindness and happy joy.

It might also be interesting to plot complexity/branching over time. Since you mention emergent complexity. Also, one might want to do some intelligent filtering or compression when it comes to branching so that it doesn’t account for too irrelevant moves.

I recall that the client display some complexity number for every game you play. Unfortunately, I don’t have computer access ATM so I’m not able to run the Java app (it’s probably doable on Android, but meh…). I believe most of the worlds abstract strategy games are in the database/library, so you can just check them out.

I also found this: https://boardgamegeek.com/geeklist/284017/estimating-abstract-game-complexity-using-ludii

Any shitty old laptop can self host any git service as long you only have a single or handful of users.

You might find this project interesting: https://ludii.games/

There are some papers related to complexity. https://ludii.games/references.php

And I believe the game engine contains some mechanism to quantify complexity of different game systems.

I’m in tech. LinkedIn has only done damage when it comes to finding a job. It brings a lot of noise into the process. Will never use it again.

deleted by creator

It’s the language of GNU. And a scheme. That’s also why you would choose Haunt. It’s probably not for you.

https://www.gnu.org/software/guile/

If you’re into GNU/Guile Scheme, there is also Haunt: https://dthompson.us/projects/haunt.html

My only advice is that you stick to one model and give it some time. You need to “learn” your model. I will probably never go back. I had huge issues with getting good results from Google and my subjective experience is that this is far better. However, I do still use conventional search engines as a complement. It’s not all or nothing.

This is the one I use: https://docs.mistral.ai/capabilities/agents/

Just tell the modell to do web searches in the system prompt.

All providers should have something similar. With a user friendly UI.

If you code your own agent and utilize an API or run a model locally, you can of course do even more. There are many tools if you want to do RAG on your own local data.

Because it’s useful. Have you tried? But the LLM has to be able to use conventional search engines as well. I tell my LLM agent to prioritize certain kinds of websites and present a compressed answer with references. Usually works way better than a standard Google search (which only produce AI generated junk results anyway).

You can get very good answers or search results by utilizing RAG.

Super expensive Apple, Adobe and Canon equipment? Because they don’t know better and symbols of social status are important?

Too bad IPEX-LLM is dragging their feet.

My guess is that most of the world, including Swedes, has become more positive towards “Made in China” since January 19.

Yes. That was it. Don’t know why the setting changed.