It's a humorous reference to a (in-)famous serious post by Stallman, see https://www.gnu.org/gnu/incorrect-quotation.en.html

1. It says it is $8/month, which is not mentioned on the github page, so I had been thinking it was free in addition to being AGPL-3.0; it links to https://snapify.it/ which is where I see the fee.

2. It says "for everyone" but looks like it might be Linux-specific, and it doesn't say anything about which OSes are supported.

IIUC, the fee is just to use their instance, and hosting your own instance is actually free. Also, it looks like the client side of it runs in a browser, so it will support pretty much any OS.

This appears to be mercifully shorter and less intimidating than the must-have bible, "Curtis Roads. The Computer Music Tutorial. MIT Press, Cambs, MA, 1996".

It says it was originally published by Wiley in 2009, and the rights reverted to the author in 2025, whereupon the author released it on the net for free.

If someone wanted to start making computer music I'm not sure I'd recommend this or Curtis Roads' book as a starting point.

These aren't resources for getting started. They're more like encyclopedias for learning about DSP and tech once you've established the fundamentals of music and sequencing.

If a beginner wants practical knowledge for making records with electronic instruments I'd give them a DAW, teach them to record and sequence, teach them basic music theory, and then point them to something like Ableton's synthesis tutorials that will teach them about oscillators, envelopes, filters, LFOs, and basic sample manipulation.

That's 80% of the necessary skills right there.

I think he should fix that, but meanwhile see: https://almightylisp.com/book/essentials

It's not uncommon to have a regression test for compilers that are written in their own language (e.g. some C compilers): compile each new version with itself, then use that to compile itself again, then use the result on unit tests or whatever, which should yield the same results as before.

The point being that determinism of a particular form is expected and required in the instances where they do that.

(I'm not arguing for or against that, I'm simply saying I've seen it in real life projects over the years.)

GCC's build process does this. GCC is built 3 separate times, starting with the host compiler, then with the compiler from the previous step. If the output of stage 2 and 3 do not match the build fails.

That's an excellent question, but the answer would depend on goals and the evaluation system used.

It seems to me that CEOs have a different opinion than anyone who cares instead about actual people.

SO is the website Stack Overflow.

Life mimics art.

Yep; this has frustrated me for two decades.

For the languages that we westerners regard as having very exotic grammars -- not like Chinese, which is comparatively straightforward, but like the aboriginal languages of Australia -- AFAIK there's no experience on such subjects yet.

For the world's most common/famous languages (English, Mandarin, Portuguese, etc) there's every reason to think that it's just a question of how much training data is available for training up an LLM.

In particular note that the Chinese experiments with their Deepseek LLM technology does well with both Mandarin and English, which all by itself is fairly illustrative.

If "exotic" grammars turned out to pose a major problem for LLMs, that would possibly challenge some of the most mainstream theories about linguistics, so I regard that as unlikely.