I've known people advocating for proportional fonts for source code for a long time (many of them also in the literate programming camp). It would be funny if LLM slop was the final aesthetic push over the last few hurdles there to making it more common.
The other difference was that Bootstrap met WCAG standards and had a very strong baseline of accessibility. These LLM slop outputs meet no such standards and seem to laugh in the face of accessibility.
Yeah, that's very true. I've gotten a lot of mileage out of Claude's `design` skill, which does an accessibility pass that I've found pretty decent as someone with only minor experience in the area — contrast, tab/focus ordering, things of that nature. The catch is that you have to actually have to want to check these things, just like you have to want to not ship slop.
The vast majority of LLM slop seems to be Tailwind to me, so sort of the opposite of a library, just a bunch of common patterns in Tailwind so common as to be everywhere but not common enough anyone bothered to put them into a reusable library.
Exactly. The benefit to the Bootstrap boom was it elevated a lot of cookie cutter designs like a raft on a series of sensible defaults that were are close to sensible/good taste as some very talented designers could make industrial cookie cutter standards. Bootstrap enshrined smart, intelligent defaults like good color contrast and a baseline of accessibility for developers just copy and pasting and modifying what Bootstrap gave them. For a brief moment the "I just need to get this done" web had a good accessible baseline.
LLMs aren't starting from sensible defaults and don't have to meet WCAG scores unless you tell them to (and even then might hallucinate checks they didn't actually make).
All caps text is a roadblock for reading speed/comprehension. Accessibility experts were finally convincing major company design standards to stop doing it when LLMs made it a default again [0] for headers and incidental text.
Not to mention that all caps text is also generally associated with shouting and just feels rude to some readers.
[0] Or more accurately trained on all the bad examples before experts started catching them and has stuck to the mistake.
It's partly a "Don't think of a Pink Elephant" problem. I've worked on several projects where I had to keep telling prompt writers to stop writing negative examples because the more you include the more its "attention" to them is all it has. Like telling a toddler not to do something and being surprised that is now all they can think about and they want to keep doing it. These prompt writers kept getting surprised that I'd delete all their negative examples and harshly worded "Don't do X" and "Never Y" and "NO: Z" sections they spend so much time on and got better results with smaller more focused positive example only prompts.
Hah! I also thought about it this way and ended up added a "purple elephant rule" to my pi prompt to discourage the behaviour, since I figured LLMs lean on metaphors so much.
Of course, I quickly reverted this change as purple elephants started cropping up in comments and other prose :)
I've seen a couple companies already change their design standards to "best in class Tailwind designs from Claude, use this prompt file/Agent file/skill file combo for all UX work".
Looking at automated emails I get from Microsoft and GitHub it certainly feels like they are one weird layoff from doing it company-wide.
The worst part is these glassification Tailwind heavy slop almost universally fail WCAG guidelines (and personally, seem hard to read to me because of taking the whispy sans serif thing to its foregone conclusion by almost exclusively using what to me are unreadably thin weights of the already too thin Inter font). The slop is going so quickly backwards for companies that invested in accessibility and these companies need to be taken to task for forgetting design isn't just aesthetics but readability and accessibility.
"Confidence scores" have always implied an anthopocentric meaning that doesn't exist. An algorithm doesn't have "confidence" in the way that a person has confidence, but as soon you put something with that name in front of a business person they assume the number is always a meaningful "letter grade curve" or "universal percentage". I still believe so much that the old quote to "there's lies, damned lies, and then statistics" remains a key to understanding so much why ML is leading to dumb outcomes versus hype. People don't understand statistics, so machines that produce nothing but statistics especially confuse people. (I feel this applies to LLMs as well.)
LVT is about assessing improvements, conservation can be understood as an improvement and valued as such. For the same reasons that urban parks should have a different tax assessment than low value surface parking lots.
> Using a functional language for data transforms sounds like a sane idea, haven't played around with it yet but it's definitely on my list now.
It's been one of the plays that the F# community has also been trying to make (somewhat with a modicum of help from Microsoft's marketing arm, but not enough help from what I've seen) pitching F# as a language close enough to Python to feel familiar and useful to data science but with the performance help of rich ML types and the modern .NET performance ecosystem.
(To my experience: getting "fast" compared to Python seems easy for most functional languages. Getting data science out of Python seems hard for a lot of sociology reasons more than technical ones.)
reply