In the dice example[0] and in this one, the expected output is a distribution e.g. "1: 16.7%, 2: 16.7%...", not a random generation. I agree that in implementation, the architecture is not designed to accurately calculate or incorporate any known uncertainties like these, but the task itself is completely reasonable and arguably trivial.

IMO the lesson here is: even in trivial cases, Jev's outputs are just ~reasonableness scores which do not correspond to actual probabilities. They should not be treated as actual probabilities without careful calibration and plenty of meta-uncertainty about how well that calibration extrapolates.

The problem is, most of the value proposition of Jev is that it gives you the probabilities without doing that, which it doesn't.

[0] https://kantahayashiai.github.io/posts/jev-does-not-play-dic...

I think you hit on my core criticism of this and similar analyses: LLMs are a tool, and using them to draw from a distribution is misuse of the tool. It's not what it's designed/tuned for. Asking follow ups like "is Jev calibrated when I mis-use it?" is asking the wrong question. The right question would be, "is Jev calibrated for expected use cases?". And based on some initial exploration, I do think Jev is calibrated for common natural language questions

I don't think so. The author is expecting Jev to output the equivalent of "H: 50%, T:50%", not the equivalent of "TTHTTHTHH..."

> drawing more affluent people pushing up LVT driving out residents

Land value taxes only go up if the land value (and thus the demand) is overall going up. The taxes lower desirability, but are also proportional to desirability. So, it's more like a frictional force: inherently counter-cyclical, able to slow down a property value increase but not to reverse it.

So the theory says "nobody goes to the ballpark, it's too crowded" shouldn't happen. And even imagining weird time-delays, mismodeling, etc that could cause it, everything in your scenario is directionally the same with normal property taxes. If it happened, we'd see it today.

IMO a single "Main Thing // Detail" is fun and fine and is where the trope came from. I see a ton of "Home // Our Work // Donate // About Us" which has beome cringy.

I think lots of AI tells these days are leaks from the ai/writer connection into text for the reader. It partly feels like the inevitable result of RLHF with the wrong human's feedback ("I did it! Pick me!") and partly feels like thinking tokens leaking into the main text.

"Here's the argument, in plain terms", "It's not just X, it's Y", "It's worth stating precisely", "The sharper distinction here"... They're things that gesture toward the relationship between the text and the prompt, making it clear where it matched the author's expectations and where it deviated.

Not that humans are immune from coding/writing for their boss instead of their user/reader!

Humanity has built every capable institution, every scientific discovery, every technological innovation, without mind-reading. Quite the opposite: By putting thoughts from our latent spaces into words, we better separated the good arguments from the bad ones, placed trust where it was more deserved, and learned to stand on giant's shoulders so well we thought thoughts the giants never would have.

Anyway, I'm much more optimistic about the worlds with AIs that make the effort to properly explain themselves.

I imagine OP is more describing e.g. the backed up 1-lane highway exit, where the second lane is clearly for through traffic. Uber drivers in that situation will often drive straight to the end, signal, completely stop, and just wait for someone to let them in.

Why not every line of knights moves too? Because the cells aren't adjacent I'd say. (Both immediately make the problem unsolvable since all corners must match).

Seems "unfair" that hexagons have multiple line lengths to consider. I think this article's modification is a good one in that framing: Shifting every number up or down doesn't make the magic squares any easier, but it certainly helps with hexagons.

Cool problem. I always doing it a bit unsatisfying that magic hexagons so trivially disallowed solutions that aren't order 3. Starting at a different index is a nice modification, especially since for magic squares it's an equally hard problem.

He says "every order" is solvable this way but I don't think any solution could work for an order 2 hexagon, even without his simplifying constraints (since fixing any side cell to x requires 2 cells to be set to sum-x).

> if it actually wrapped around on itself with a half-twist, wouldn’t the letters wind up backwards too? Then 6-Down wouldn’t be MESSENGER but rather MESSENGER, and so on.

This premise is assuming the Mobius strip is transparent, which the header image clearly isn't. No letter-reversals or any symmetry is needed. On normal, opaque paper, you can just make a crossword as a normal long loop. (proof: Write GGGGGGG on one side of a paper, and write it upside-down on the other side. With a twist, you'll get one long GGGGGGGGGGGGGG... looping as if it were one boring single-sided loop).

A true Mobius strip doesn't have "sides" like the paper model of one does. You can see that in the quote from Martin Gardner where he talks about a creature completing a loop becoming a mirror image with respect to it's friends. I assume the author wanted the paper model to mimic that property.

Incidentally, the author's choice makes for a much more interesting puzzle than the one you would have them use (IMO)--yours would be indistinguishable from a puzzle written on a cylinder.

I agree it's an interesting puzzle! Just thought he made the jump to transparent paper without introduction in a way that confused me. It seemed instead like a non-transparent Mobius strip would join itself upside-down after a full loop, which wasn't obviously untrue.