Hang on now...

...is it, just maybe, possible that the industry with the largest fractional job losses¹ to LLMs to far could be troll farms?²

I mean, I'm not sure how we would tell. Even if a few countries have some employment data that covers the case, there's no way the big players are putting it out there. But it seems like a really good use case: take a small model that produces good output in the few to few-dozen words range, post train it for your ideological bent and let it loose. If you need to, you can use something a little smarter as the agentic driver. The task is requesting web pages, parsing out threads, and posting or replying (more HTML events). This is stuff there are skills for all over the places.

It's not like it's good news even if it's true: it makes a bad problem and the people in charge aren't the ones getting hurt.

---

¹ Real job losses: not dog-and-pony-show we "cut" jobs we wanted to get rid for stock-price manipulation purposes, say it's AI, than hire as many roles back again as soon as we vest or get the bonuses. As a side note: if you've offered one of those "oops, AI isn't ready just yet" positions you should drive a very hard, very expensive bargain.

² You know, the people that rouge states, criminal organizations, or political parties that you don't like and so on pay to spam opinionated, wrong, and non-constructive comments on social media.

If you use social media...

...follow real people.

Right now my social media feeds are full of superficial AI generated or supported slop. Much of it obvious chosen in hopes that it will appeal to me and almost all of it presented it multiple variations on a theme. The last couple of weeks it's been all "Gen-X people are great" all the time for me. Jeeze, people! Subtle much? Somebody is A/B testing like crazy.¹

To be sure, superficially appealing slop was a staple of social media before generative AI burst forth from the lab, but this feels different to me. Previously we had artisanal slop—²each title hand-crafted (albeit often poorly) by people with idiosyncratic views and genuine pockets of expertise and ignorance. Even the ones that were just a voice track overlayed on some photos or animations had character. Now we're getting smooth, undifferentiated pap with really good production values but no soul.

And really, there are two things you can do in response if this bother you. The first is just don't do social media at all. That's probably best. But if you must, be mindful about the the content you tell the algorithm you want. For me that means content generated by a single person or a small team, with human sensibilities in the driver's seat.³ And if I don't feel confident about it I assume it's too much AI and nope out early.

---

¹ Do you remember when congress called the tech bros to testify. The biggest travesty of the whole dog-n-pony show was that no one asked them how many tuneable dials "the algorithm" had and how often they tweaked them. It doesn't matter what company we're talking about, the answers are "a lot" and "we have whole teams of salaried professions who work on that continuously". The algorithm is not a thing apart for company policy (which was the crafted message of the testimony), rather it is an expression of the policy.

² Do you see what I did there?

³ And of course, keeping up your intake of content that engages deeply with difficult topics (which means long-form and wrestling with uncertainty, ambiguity, and doubt), is the cognitive equivalent of making sure you get enough vitamins, minerals, and fiber in your diet.

Really? Why?

I was at a local warehouse store this evening. Picking up a couple of staples we're out of of, but also browsing for intermittently available treats and otherwise engaging in the behaviors that result in spending more than you intended in those places. In the end I brought home a new choice in canned soft-drinks. There are six cans each of three flavors packed into a 3x6 grid. The box opens on the short end, so that you see three cans. It would have been very convenient for me if each row of six was a different flavor so I could put the box on my pantry shelf, open the end and have immediate access to all the available flavors. Of course that isn't what they did: two full rows of one flavor, then two rows of the next, and the final flavor all the way at the "back".

Sigh.

If I was in a charitable mood I might wonder about the difficulty of building a packing line to do the right thing as compared to what they did. But I'm not; I'm just unreasonably torqued off by this tiny inconvenience and feeling really unlikely to buy this product again.

Missing feature

Me

Hey CVA,¹ navigate to my Super Secret Lair.²

CVA

Okay. ::brings up a map::

Me, going bug-eyed

Dang CVA, why that way?

At this point CVA says nothing and you either follow it or not, which is not how you would interact with a human navigator. What we need is support for closing the loop on that question:

CVA

There are heavy delays on your usual routes.³

---

¹ Creepy Voice Assistant

² For the traffic-aware routing. I know where the SSL is.

³ Knowing my "usual routes" would be just another creepy thing about the voice assistant but, oh, so useful. I'm gestating another post on the tension there.

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 whose 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...

Side Quest: Infrastructure Build-Out

My hobby programming project stalled out. Again. Because I still didn't want to npm install.

This time the issue was a test harness.

The project is a wannabe game engine. Or at least a wannabe animation engine for now: user interaction is still in the works. I had gotten far enough to be bothered by the ways the physics isn't working right.¹ But the code is growing in size, and fixing the physics code will be fiddly. That is, after all, why it doesn't work right as things stand. Unit tests are part of my process for handing that kind of fiddly.

And when you search for pure JavaScript unit testing frameworks, they all request the forbidden incantation as step one. For the same perfectly valid reasons tall the language server did, I'm sure.

Now, I've written testing frameworks of various kinds in the past. A set of tests in Fortran for my dissertation analysis after the second attempt collapsed under it's own weight; a really kludgy mess of c-preprocessor and GNU-make just because I thought I was clever,² and a command-line end-to-end driver at work. None of them are professional or polished but they all work in some sense, and that teaches a lesson: it doesn't have to be fancy to work.

With that sort of thing in mind I conceived a vague notion of a minimal test harness that would write its output into a webpage.³ Obviously I'm not the first person to have that idea, and a little searching got me an example to use as inspiration. Thanks, Alex!

Only I couldn't leave well enough alone. I made it part of my "learn to program with AI" effort, worked with Gemma4 to give it a fluent interface despite my misgivings about that whole idea and thus was TestOf born. Maybe it'll be useful for someone else.

---

¹ Embarrassing for a physicist, I can assure you.

² Please use something better than that!

³ We are talking JavaScript, after all.

Paging Generative Freud. Dr Freud, you are needed in the psych ward

I had a brainstorm today about a possible prompt to test the edges of LLM conpetence. It's longer prompt than most of the ones I use and demands a longer answer, so context lengths have to be expanded and it runs slowly on available hardware. As a result I've only begun investigating it.

But it triggered an idea for another "off the wall humor" type question which is quite succinct. The thing is that when I started asking models about that one I got a surprise, and thinking it might be perculiar to a particular model family I tried some others; and the surprise persisted. What. The. Absolute. Heck?

There is an old saw that a boat is a hole in the water that you throw money into, which is not the core of my prompt but has a similar flavor. What I'm actually asking the models to react to is a pair of definitions of two classes of boats in terms of how they make you broke. If you've spent anytime in boat-owning circles you've probably heard it. The joke is funny because (a) it acknowleges that boats are conspicuously expecnsive to own, and (b) it distinguishes between motor boats and sail bots, and you can order the definitions so your audience feels good about not being in one category until you hit them with the definition for the class of boat they own. Then it's rueful smiles all 'round.

Only ... model after model has wanted to interpret it as some kind of financial metephor. The difference between spending big for lots of velocity and binding your time doing things right in the hopes of achieving a better outcome. Or something like that.

Where are they getting that? Does their training data inclue lots of articles from the popular business press? Or something?

Weird.

Oddly it seems to come outstronger when models are allowed to reason.