How many featured guests does it take to change the "band" of an album?

Let's say, you're writing a music app. Something like Apple Music, Amazon Music, Spotify, or whatever. You will, of course, want to offer your users multiple ways to find music. A flexible search interface, a list of songs, a list of albums and so on. The fun comes if you decide to offer a list of artists. When should an album show up under a particular artist? How do you handle ensembles that aren't publishing as a named entity (i.e. it's by a bunch of people and not "by a band")? Worse still, how do you deal with tracks that include a featured guest artists on an album that is otherwise by a single person or band?

As a programmer who cares about users, my vote would be to accept some duplicate presentations due to fuzzy matching rather than risk disappointing a user who disagrees with my way of answering those questions. But that doesn't seem to be what Apple picked. Indeed, I simply can't deduce the logic (if any?) underlying how Apple Music handles these questions. In the album list one album can show up more than once, partitioned according to the performance credit for each song. An album by a band that has one song with a featured guest performer isn't enough to make that band show up in the list of artists.¹ WTF, Apple? What are you thinking? Just ... WHY?!?

---

¹ I've ripped the True Love Never Dies from CD, but Otherwise doesn't show up in my artists list, because I only have that one album at it has one track featuring Ash Costello. Grrr...

Yes. Yes, she is.

When Geddy Lee and Alex Lifeson announced, last year, that they had chosen a drummer to join them for a few more Rush shows, I was at once squealingly excited and deeply fearful. I mean, I knew intellectually that there is no way the guys would agree to go out with a less than fantastic drummer, but the emotions do not play by the same rules as reason. Well, I found a few videos and a few expert opinions, and that allayed much of my worry. And then a few months ago we go the video from the Juno awards and that was very promising. But there were a few lingering, irrational concerns. Was she good enough?

Well, I'm back from the opening show.¹

There is a lot that could be said about things like song selection (we go La Villa Strangiato and YYZ!), and the tributes to Neil (sniffling back tears), and how incredible Time Stand Still sounds with Aimee Mann harmonizing on stage, and on and on but I'll let others cover that.

The answer is unambiguous.

All the delicacy and subtlety on display in the videos I've seen of her earlier work was there, but when Neil's drum parts demand The Beast she's got that too.² The crowd's reaction to the first big fill in Tom Sawyer was emphatic, and Geddy's reaction to that was something to witness.

---

¹ Thanks to Mrs. NoSwampCoolers for deciding that this was going to happen while tickets were still available.

² And while she looks completely different from Neil, in the hard parts her face carried the same grim determination. But when the drum chart was merely fast and demanding joy and satisfaction would break through.

Maybe another example of my favorite weakness of LLMs?

We've flown out to stay with my in-laws for the best part of a week. Because reasons.

I brought my work computer in case I need to respond to some crises or just find some time to do useful work rather than burning PTO (which is always in short supply). Unfortunately, my work computer is currently an eight-pound, desktop-replacement beast. For which I really want to bring a spare display (and I have fifteen-inch, USB HD panel for that purpose). With all the weight and volume devoted to work computing I opted for the barest minimum of person hardware: my Raspberry Pi 400, its mouse and, associated cabling to talk to that same panel.

Now, the 400 is a surprisingly good computer for what I paid for it, but it's also quite limited. In particular it has only 4GB of RAM, and while the CPU supports NEON SIMD there is no dedicated graphics processor. It's completely unsuited to running LLMs without add-on hardware. But I got bored, so I decided to try anyway.

I was looking for relatively modern models that will fit in RAM and found Llama3.2:1b (7 months old) and codegemma:2B (9 months old). One conversation and one code support. Nice.

I've been speculating about down-quantizing some slightly bigger models, but in the mean time I started playing around with the baby llama. I didn't want to challenge it with my usual questions for probing the weakness of larger and more powerful models, so I started by just asking it to tell me about the band Rush.

As models do, it then produced a bunch of plausible sounding text. Some of it was incomplete and some was simply wrong. For some reason it thinks Rush won more major award than they did. It seems to have selected exclusively praising text to reproduce (which is fine by me: I like the band and don't find most complaints directed at them to be at all convincing), but there is a non-trivial amount of criticism and none of it is represented or even acknowledged by the answer.

Now, let's be frank: there is a limit to how much factual detail you can expect to be encoded in what is, after all, a somewhat niche cultural subject when you have only two billion parameters available to try to represent a full cross section of English language knowledge. No general purpose model of this size is going to get everything right on a query of that kind. So, I'm not saying that the fact of errors is surprising or even interesting. But I am wondering what we can learn from the nature of the errors.

So let's look more closely at some of the errors. In its "Discography" section the model lists

• Start with School Days (1974)
• Caress of Steel (1975)
• Fly by Night (1975)
• 2112 (1976)
• Two-Side Streets (1978)
• Permanent Waves (1980)
• Moving Pictures (1981)
• Hold Your Fire (1987)
• Presto (1997)
• Test for Echo (2004)
• Snakes & Arrows (2007)
• Clockwork Angels (2012)

which has both omissions and errors.

I haven't the faintest clue what to make of the title mistake for the first album (which was 1974 but was self-titled). It's not the title of any Rush song or album that I'm aware of and a casual search of the web doesn't turn up any song or album by that name at all. The search does turn up a reasonable number of hits on Stanley Clarke's 1976 album School Days and a number of suggestions that people just beginning to explore Mr. Clarke's music should "Start with" that very same album. Interesting, but not terribly enlightening.

Nor do I have any theories concerning which albums are omitted. It doesn't look to me like the list is either the commercial hits or the fan favorites, and beyond that I don't know what patterns to look for.

But I do want to talk about the 1978 entry in the model's list. The proper album title for that year is Hemispheres.The thing that strikes me here is proper title and the substitute text share a conceptual relationship to the number two (two halves; two ways). My (admittedly wild) guess is that we're seeing a side affect of the model's attention system identifying "two" as an important concept to use when trying to infer tokens.

If true that would be interesting, because the attention system is one of the significant ways in which LLMs differ from Markov Chain generators. But it may also be responsible for the models difficulty in know what is a quotation and what is commentary which I've already discussed in the context of scientific papers.

Yeah, why doesn't she?

One of my habits¹ is singing along to whatver music is playing in the car. Today I was belting out The Warning's² When I'm Alone while driving my daughter to gymnastics. She's usually heads-down over her tablet in the car, so I have to make my own entertainment.

As the song wrapped up she asked me what the singer meant by the "hole in [her] soul".

These are the kinds of moments that make parenting a minefield, but also so worth it.

The song is about maintaining outward calm in the face of inner turmoil in a inescapable situation,³ but I don't think⁴ my seven year old really has a reference for that. So I tried to explain that in this case "soul" means how you're really feeling inside and told her somthing like "The whole song is about making the people around you think you're OK, while you're really, really sad on the inside". That seemed to satisfy her at first.

Then, after a few moments of quiet, she asked me "Why doesn't she just tell them?"

Stonkered for the second time in as many minutes. Alas, I suppose that she will understand some day.

---

¹ Good? Bad? Fine when I'm alone but annoying otherwise?

² I'll try to keep the pathetic fan-boying to a minimum here, but if have any interest in rock and don't know this band it's worth a little of your time to check them out. In addition to the song noted above consider Choke, Evolve, Disciple, or Hell you call a Dream as introducers.

³ Written by a homesick fifteen year-old and a better expression of that state of being than I've managed in more than fifty years of being at least a little messed up. Go figure.

⁴ Hard to know with absolute certainty: once you send them to school you don't know everything about what's going on in their life unless someone tells you. I feel pretty confident that either the child or a teacher would have clued us in but there is still room, however small, for doubt.