LLaMA can't. Chameleon and similar ones can:

• https://arxiv.org/abs/2405.09818

For Tolkien's work, there is the twelve volume "The Complete History of Middle Earth" which is about as inside baseball as you can get for Tolkien.

I'd replace HoME with Parma Eldalamberon, Vinyar Tengwar and other journals publishing his early materials here.

Recommending Italo Calvino's Six Memos for the Next Millennium, the lectures he has been preparing shortly before his death.

Not an assembly guide for a work of literature, but it'll help your own process if it's already ongoing and you want to improve.

The lectures also have some comments on what Calvino himself was doing here and there and why.

For me specifically, if spoilers hurt a book, it probably wasn't worth reading in the first place. I love when authors demonstrate mastery of language and narration, and no amount of spoilers can overshadow the direct experience of witnessing it enacted.

If you were an author here, how would you approach writing alt texts for this article?

• https://arxiv.org/abs/2303.10798

Maybe alt texts aren't the way to accessibility.

One upside of visual LLMs is that the user can prompt them, effectively interrogating the picture (but good luck debugging occasional nvidia/amd driver issues breaking the inference engine without using your sight).

I wonder how screen readers handle complex TikZ/PGF diagrams (converted to HTML or not, they aren't very accessible). Multimodal LLMs?

Both work very well for the entire journey there and back. I use the first I get my hands on (typically scale armour) and upgrade it to +8. But if it's plate armour, you might have to start using it before gaining the necessary strength, so be ready to spend more time and food on a few levels in the prison area.

The Phoebus cartel strikes again!

I expected that recording would be the hard part.

I think some of the open-source ones should work if your phone is rooted?

I've heard that Google's phone app can record calls (though it says it aloud when starting the recording). Of course, it wouldn't work if Google thinks it shouldn't in your region.

By the way, Bluetooth headphones can have both speakers and a microphone. And Android can't tell a peripheral device what it should or shouldn't do with audio streams. Sounds like a fun DIY project if you're into it, or maybe somebody sells these already.

Haven't heard of all-in-one solutions, but once you have a recording, whisper.cpp can do the transcription:

• https://github.com/ggerganov/whisper.cpp

The underlying Whisper models are MIT.

Then you can use any LLM inference engine, e.g. llama.cpp, and ask the model of your choice to summarise the transcript:

• https://github.com/ggerganov/llama.cpp

You can also write a small bash/python script to make the process a bit more automatic.

I enjoy xenharmonic music and modern academic music the most, but I'm not familiar with everything there, so any recommendations are welcome if you, reader, have something in your mind.

Because we have tons of ground-level sensors, but not a lot in the upper layers of the atmosphere, I think?

Why is this important? Weather processes are usually modelled as a set of differential equations, and you want to know the border conditions in order to solve them and obtain the state of the entire atmosphere. The atmosphere has two boundaries: the lower, which is the planet's surface, and the upper, which is where the atmosphere ends. And since we don't seem to have a lot of data from the upper layers, it reduces the quality of all predictions.