Unfortunately they patched the mscz downloads and now they’re charging for merely viewing more than one page of certain scores. Musescore4 is great but I hope musescore.com burns.

There is a button to change the color scheme to B&W

Getting worse every year too

You should get your lemmy checked for dementia

This thing makes it so you can’t hear yourself, though. So it has that added difficulty.

Better than nothing still, don’t let perfect be the enemy of good and all that

Snafus

That website is pure gold lmao, they absolutely knew

That’s the point

You can’t just write “degrees kelvin” in a science community and expect a pedant not to come up, you know?

I don’t disagree but this meme is ass lmao

Until a court rules in favour of this no one will budge as this is just an opinion. I do hope it comes to that as since Spain ruled that charging for not planting cookies was a okay browsing news sites has been miserable.

If I’m being completely honest, now that I’ve woken up with a fresh mind, I have no idea where I was going with that last part. Giving LLMs access to tools like running code so that they can fact check or whatever is a really good idea (that is already being tried) but I don’t think it has anything to do with the problem at hand.

The real key issue (I think) is getting AI to keep learning and iterating over itself past the training stage. Which is actually what many people call AGI/the “singularity”.

It is true that newer models that have ingested more training data are better at this kind of thing, but it is not because they are using logic, but because they are copying and following examples they already learnt, if that makes sense. I got the question from a test passed to kids ages 12-13, so arguably it wasn’t really that challenging. If you want to you can try out the more advanced problems from the same place I got it from, although it’s in Spanish, so pass it through Google Translate first.

If you turn to programmers they’ll tell you that AI usually makes mistakes no human would normally make such as inventing variables that don’t exist and that kind of thing. It is because in the examples it learnt from they have mostly existed.

What I mean to say is, if you give an AI a problem that is not in its training data and can only be solved using logic (so, you can’t apply what is used in other problems) it will be incapable of solving it. The Internet is so vast that almost everything has been written about so AIs will seem to know how to solve any problem, but it is no more than an illusion.

HOWEVER, if we manage to integrate AIs and normal, mathematical computation really closely so that they function as one, that problem might be solved. It will probably also have its caveats, though.

Logic. As an example, non textbook math questions. I asked ChatGPT 3.5 this:

Four friends (A, B, C and D) are standing in line. How many combinations are possible given that A and C cannot be next to eachother?

It answered 20, the correct answer is 12.

(- also Catholicism)

How will small artists get to make themselves known, though? Not everyone has the option to play live.

Counterpoint: C function pointers (or just C in general)

There have been some theories on this phenomenon, with the most prevalent being the tendency for Wikipedia pages to move up a “classification chain”. According to this theory, the Wikipedia Manual of Style guidelines on how to write the lead section of an article recommend that articles begin by defining the topic of the article. A consequence of this style is that the first sentence of an article is almost always a definitional statement, a direct answer to the question “what is [the subject]?”

As much as I want them to give HDMI the middle finger I don’t think they have enough leverage in the GPU market to pull such a bold move off.