HTTP/1.1 200 OK Date: Thu, 15 Jan 2026 23:25:16 GMT Server: Apache/2.4.41 (Ubuntu) Last-Modified: Sun, 21 Sep 2025 15:04:26 GMT ETag: "1d951-63f5104dbe49f-gzip" Accept-Ranges: bytes Vary: Accept-Encoding Content-Encoding: gzip Content-Length: 35674 Content-Type: application/rss+xml https://blog.plover.com The Universe of Discourse (Mark Dominus Blog) en https://blog.plover.com/2025/09/21#what-changed-twice <p>As I have <a href="https://blog.plover.com/prog/git-habits.html">explained in the past</a>, my typical workflow is to go along commiting stuff that might or might not make sense, then clean it all up at the end, doing multiple passes with <code>git-add</code> and <code>git-rebase</code> to get related changes into the same commit, and then to order the commits in a sensible way. Yesterday I built a new utility that I found helpful. I couldn't think of a name for it, so I called it <code>what-changed-twice</code>, which is not great but my I am bad at naming things and my first attempt was <code>analyze-commits</code>. I welcome suggestions. In this article I will call it Fred. </p> <p>What is Fred for? I have a couple of uses for it so far.</p> <p>Often as I work I'll produce a chain of commits that looks like this:</p> <pre><code>470947ff minor corrections d630bf32 continue work on `jq` series c24b8b24 wip f4695e97 fix link a8aa1a5c sp 5f1d7a61 WIP a337696f Where is the quincunx on the quincunx? 39fe1810 new article: The fivefold symmetry of the quince 0a5a8e2e update broken link 196e7491 sp bdc781f6 new article: fpuzhpx 40c52f47 merge old and new seasons articles and publish b59441cd finish updating with Star Wars Droids 537a3545 droids and BJ and the Bear d142598c Add nicely formatted season tables to this old article 19340470 mention numberphile video </code></pre> <p>It often happens that I will modify a file on Monday, modify it some more on Tuesday, correct a spelling error on Wednesday. I might have made 7 sets of changes to the main file, of which 4 are related, 2 others are related to each other but not to the other 4, and the last one is unrelated to any of the rest. When a file has changed more than once, I need to see what changed and then group the changes into related sets.</p> <p>The <code>sp</code> commits are spelling corrections; if the error was made in the same unmerged topic branch I will want to squash the correction into the original commit so that the error never appears at all.</p> <p>Some files changed only once, and I don't need to think about those at this stage. Later I can go back and split up those commits if it seems to make the history clearer.</p> <p>Fred takes the output of <code>git-log</code> for the commits you are interested in:</p> <pre><code>&#036; git log --stat -20 main...topic | /tmp/what-changed-twice </code></pre> <p>It finds which files were modified in which commits, and it prints a report about any file that was modified in more than one commit:</p> <pre><code> calendar/seasons.blog 196 40 d1 math/centrifuge.blog 193 33 misc/straight-men.blog 53 b5 bd prog/jq-2.blog 33 5f d6 193 1934047 196 196e749 33 33a2304 40 40c52f4 53 537a354 5f 5f1d7a6 b5 b59441c bd bdc781f d1 d142598 d6 d630bf3 </code></pre> <p>The report is in two parts. At the top, the path of each file that changed more than once in the log, and the (highly-abbreviated) commit IDs of the commits in which it changed. For example, <code>calendar/seasons.blog</code> changed in commits <code>196</code>, <code>40</code>, and <code>d1</code>. The second part of the report explains that <code>196</code> is actually an abbreviation for commit <code>196e749</code>.</p> <p>Now I can look to see what else changed in those three commits:</p> <pre><code>&#036; git show --stat 196e749 40c52f4 d142598 </code></pre> <p>then look at the changes to <code>calendar/seasons.blog</code> in those three commits</p> <pre><code>&#036; git show 196e74 40c52f4 d142598 -- calendar/seasons.blog </code></pre> <p>and then decide if there are any changes I might like to squash together.</p> <p>Many other files changed on the branch, but I only have to concern myself with four.</p> <p>There's bonus information too. If a commit is <em>not</em> mentioned in the report, then it only changed files that didn't change in any other commit. That means that in a rebase, I can move that commit literally anywhere else in the sequence without creating a conflict. Only the commits in the report can cause conflicts if they are reordered.</p> <p>I write most things in Python these days, but this one seemed to cry out for Perl. <a href="https://github.com/mjdominus/git-util/blob/master/bin/what-changed-twice">Here's the code</a>.</p> <p>Hmm, maybe I'll call it <code>squash-what</code>.</p> https://blog.plover.com/2025/05/25#quincunx <p>A <em>quincunx</em> is the X-shaped pattern of pips on the #5 face of a die.</p> <p><a href="https://pic.blog.plover.com/history/quincunx/x.png"><img class="center" border=0 src="https://pic.blog.plover.com/history/quincunx/x-th.png" alt="A square with five dots arranged in an X" /></a></p> <p>It's so-called because the Romans had a common copper coin called an <em>as</em>, and it was divided (monetarily, not physically) into twelve <em>uncia</em>. There was a bronze coin worth five uncia called a <em>quīncunx</em>, which is a contraction of <em>quīnque</em> (“five”) + <em>uncia</em>, and the coin had that pattern of dots on it to indicate its value.</p> <p><em>Uncia</em> generally meant a twelfth of something. It was not just a twelfth of an <em>as</em>, but also a twelfth of a pound , which is where we get the word “ounce”, and a twelfth of a foot, which is where we get the word “inch”.</p> <p>The story I always heard about the connection between the coin and the X-shaped pattern of dots was the one that is told by Wikipedia:</p> <blockquote> <p>Its value was sometimes represented by a pattern of five dots arranged at the corners and the center of a square, like the pips of a die. So, this pattern also came to be called quincunx.</p> </blockquote> <p>Or the Big Dictionary:</p> <blockquote> <p>… [from a] coin of this value (occasionally marked with a pattern resembling the five spots on a dice cube),…</p> </blockquote> <p>But today I did Google image search for qunicunxes. And while most had five dots, I found not even one that had the dots arranged in an X pattern.</p> <p><a href="https://pic.blog.plover.com/history/quincunx/coin1.png"><img class="center" border=0 src="https://pic.blog.plover.com/history/quincunx/coin1-th.png" alt="Pictures of the two sides of an ancient, corroded, worn, weathered coin. Each one has a four-armed cross who arms have crossbars at the ends, and the one on the right also has five dots. The dots are in a cluster in the space between the cross's lower and left arms, and are arranged in a row of three and, closer to the center, a row of two." /></a></p> <p><a href="https://pic.blog.plover.com/history/quincunx/coin2.png"><img class="center" border=0 src="https://pic.blog.plover.com/history/quincunx/coin2-th.png" alt="Another cruddy coin. The obverse shows the head of a person, probably Minerva, wearing a plumed helmet. Above the head is a row of five dots." /></a></p> <p><a href="https://pic.blog.plover.com/history/quincunx/coin3.png"><img class="center" border=0 src="https://pic.blog.plover.com/history/quincunx/coin3-th.png" alt="This coin is covered with green oxide. The obverse is another helmeted Minerva, surmounted by a horizontal row of five dots. The reverse has a picture of an owl, and, on the right, a column of five dots." /></a></p> <p>(I believe the heads here are Minerva, goddess of wisdom. The owl is also associated with Minerva.)</p> <p>Where's the quincunx that actually has a quincuncial arrangement of dots? Nowhere to be found, it seems. But everyone says it, so it must be true. <!-- come on now, they wouldn't let it on the Internet if it wasn't true! --></p> <h2>Addenda</h2> <ul> <li><p>The first common use of “quincunx” as an <em>English</em> word was to refer to trees that were planted in a quincuncial pattern, although not necessarily in groups of exactly five, in which each square of four trees had a fifth at its center.</p></li> <li><p>Similarly, the <a href="https://en.wikipedia.org/wiki/File:Quincunx_(Galton_Box)_-_Galton_1889_diagram.png">Galton Box</a>, has a quincuncial arrangement of little pegs. Galton himself called it a “quincunx”.</p></li> <li><p>The OED also offers this fascinating aside:</p> <blockquote> <p><strong>Latin</strong> <em>quincunx</em> occurs earlier in an English context. Compare the following use apparently with reference to a v-shaped figure: </p> <p><strong>1545</strong> <em>Decusis</em>, tenne hole partes or ten Asses...It is also a fourme in any thynge representyng the letter, <em>X</em>, whiche parted in the middel, maketh an other figure called <em>Quincunx</em>, <em>V</em>. </p> </blockquote> <p>which shows that for someone, a quincuncial shape was a V and not an X, presumably because V is the Roman numeral for five.</p> <p>A <em>decussis</em> was a coin worth not ten <em>uncia</em> but ten <em>asses</em>, and it did indeed have an X on the front. A five-<em>as</em> coin was a <em>quincussis</em> and it had a V. I wonder if the author was confused?</p> <p>The source is <a href="https://archive.org/details/bim_early-english-books-1475-1640_bibliotheca-eliot-_elyot-sir-thomas_1545"><em>Bibliotheca Eliotæ</em></a>. The OED does not provide a page number.</p></li> <li><p>It wasn't until <em>after</em> I published this that I realized that today's date was the extremely quincuncial 2025-05-25. I thank the gods of chance and fortune for this little gift.</p></li> </ul> https://blog.plover.com/2025/05/23#quince <p>The quince is so-named because, like other fruits in the apple family, it has a natural fivefold symmetry:</p> <p><a href="https://pic.blog.plover.com/bio/quince/quince.png"><img class="center" border=0 src="https://pic.blog.plover.com/bio/quince/quince-th.png" alt="several greenish-yellow quinces. They are like shiny pears, but less elongated. In the foreground, one is cut in half, to reveal five wedge-shaped hollows arranged symmetrically to form a circle, each filled with shiny brown seeds." /></a></p> <p>This is because their fruits develop from five-petaled flowers, and the symmetry persists through development. These are pear blossoms:</p> <p><a href="https://pic.blog.plover.com/bio/quince/pear-blossoms.png"><img class="center" border=0 src="https://pic.blog.plover.com/bio/quince/pear-blossoms-th.png" alt="A small branch from a pear tree, with green leaves and white pear blossoms. The bossoms have five petals each, against which a cluster of dark-tipped stamens contrasts." /></a></p> <p>You can see this in most apples if you cut them into equatorial slices:</p> <p><a href="https://pic.blog.plover.com/bio/quince/cut-apples.png"><img class="center" border=0 src="https://pic.blog.plover.com/bio/quince/cut-apples-th.png" alt="Apple slices on a cutting board, each with a hole in the middle from the seed capsule in the center of the core, in the shape of a five-pointed star." /></a></p> <p>The fivefold symmetry isn't usually apparent from the outside once the structure leaves the flowering stage. But perfect Red Delicious specimens do have five little feet:</p> <p><a href="https://pic.blog.plover.com/bio/quince/rs-apples.png"><img class="center" border=0 src="https://pic.blog.plover.com/bio/quince/rs-apples-th.png" alt="A dozen Red Delicious apples, bottoms up to show that each does have five little bumps arranged around the blossom end." /></a></p> <p>P.S.: I was just kidding about the name of the quince, which actually has nothing to do with any of this. It is a coincidence.</p> https://blog.plover.com/2025/05/08#seasons <p>[ I started thinking about this about twenty years ago, and then writing it down in 2019, but it seems to be obsolete. I am publishing it anyway. ]</p> <p><link href="https://pic.blog.plover.com/calendar/seasons/style2.css" rel="stylesheet" /></p> <p>The canonical division of the year into seasons in the northern temperate zone goes something like this:</p> <blockquote> <ul> <li>Spring: March 21 – June 21</li> <li>Summer: June 21 – September 21</li> <li>Autumn: September 21 – December 21</li> <li>Winter: December 21 – March 21</li> </ul> </blockquote> <p>Living in the mid-Atlantic region of the northeast U.S., I have never been happy with this. It is just not a good description of the climate.</p> <p>I begin by observing that the year is not equally partitioned between the four seasons. The summer and winter are longer, and spring and autumn are brief and happy interludes in between.</p> <p>I have no problem with spring beginning in the middle of March. I think that is just right. March famously comes in like a lion and goes out like a lamb. The beginning of March is crappy, like February, and frequently has snowstorms and freezes. By the end of March, spring is usually skipping along, with singing birds and not just the early flowers (snowdrops, crocuses, daffodil) but many of the later ones also.</p> <p>By the middle of May the spring flowers are over and the weather is getting warm, often uncomfortably so. Summer continues through the beginning of September, which is still good for swimming and lightweight clothes. In late September it finally gives way to autumn.</p> <p>Autumn is jacket weather but not overcoat weather. Its last gasp is in the middle of November. By this time all the leaves have changed, and the ones that are going to fall off the trees have done so. The cool autumn mist has become a chilly winter mist. The cold winter rains begin at the end of November.</p> <p>So my first cut would look something like this:</p> <div class="seasonal-calendar" style="grid-template-columns: 1fr 2fr; width: 60%;"> <!-- Headers --> <div class="header months-header">Months</div> <div class="header seasons-header">Seasons</div> <!-- Months --> <div class="month jan">January</div> <div class="month feb">February</div> <div class="month mar">March</div> <div class="month apr">April</div> <div class="month may">May</div> <div class="month jun">June</div> <div class="month jul">July</div> <div class="month aug">August</div> <div class="month sep">September</div> <div class="month oct">October</div> <div class="month nov">November</div> <div class="month dec">December</div> <!-- Main Seasons --> <div class="season winter1">Winter</div> <div class="season spring">Spring</div> <div class="season summer">Summer</div> <div class="season autumn">Autumn</div> <div class="season winter2">Winter</div> </div> <p>Note that this puts Thanksgiving where it belongs at the boundary between autumn (harvest season) and winter (did we harvest enough to survive?). Also, it puts the winter solstice (December 21) about one quarter of the way through the winter. This is correct. By the solstice the days have gotten short, and after that the cold starts to kick in. (“As the days begin to lengthen, the cold begins to strengthen”.) The conventional division takes the solstice as the <em>beginning</em> of winter, which I just find perplexing. December 1 is not the very coldest part of winter, but it certainly isn't autumn.</p> <p>There is <em>something</em> to be said for it though. I think I can distinguish several subseasons — ten in fact:</p> <h2>Dominus Seasonal Calendar</h2> <div class="seasonal-calendar"> <!-- Headers --> <div class="header months-header">Months</div> <div class="header seasons-header">Seasons</div> <div class="header subseasons-header">Sub-seasons</div> <!-- Months --> <div class="month jan">January</div> <div class="month feb">February</div> <div class="month mar">March</div> <div class="month apr">April</div> <div class="month may">May</div> <div class="month jun">June</div> <div class="month jul">July</div> <div class="month aug">August</div> <div class="month sep">September</div> <div class="month oct">October</div> <div class="month nov">November</div> <div class="month dec">December</div> <!-- Main Seasons --> <div class="season winter1">Winter</div> <div class="season spring">Spring</div> <div class="season summer">Summer</div> <div class="season autumn">Autumn</div> <div class="season winter2">Winter</div> <!-- Sub-seasons --> <div class="sub-season midwinter1">Midwinter</div> <div class="sub-season late-winter">Late Winter</div> <!-- Placeholders for the rest of the sub-seasons --> <div class="sub-season early-spring">Early spring</div> <div class="sub-season late-spring">Late spring</div> <div class="sub-season early-summer">Early Summer</div> <div class="sub-season midsummer">Midsummer</div> <div class="sub-season late-summer">Late Summer</div> <div class="sub-season early-autumn">Early autumn</div> <div class="sub-season late-autumn">Late autumn</div> <div class="sub-season early-winter">Early winter</div> <div class="sub-season midwinter2">Midwinter</div> </div> <p>Midwinter, beginning around the solstice, is when the really crappy weather arrives, day after day of bitter cold. In contrast, early and late winter are typically much milder. By late February the snow is usually starting to melt. (March, of course, is always unpredictable, and usually has one nasty practical joke hiding up its sleeve. Often, March is pleasant and springy in the second week, and then mocks you by turning back into January for the third week. This takes people by surprise almost <em>every year</em> and I wonder why they never seem to catch on.)</p> <p>Similarly, the really hot weather is mostly confined to midsummer. Early and late summer may be warm but you do not get blazing sun and you have to fry your eggs indoors, not on the pavement.</p> <p>Why the seasons seem to turn in the middle of each month, and not at the beginning, I can't say. Someone messed up, but who? Probably the Romans. I hear that the Persians and the Baha’i start their year on the vernal equinox. Smart!</p> <p>Weather in other places is very different, even in the temperate zones. For example, in southern California they don't have any of the traditional seasons. They have a period of cooler damp weather in the winter months, and then instead of summer they have a period of gloomy haze from June through August.</p> <h3>However</h3> <p>I may have waited too long to publish this article, as climate change seems to have rendered it obsolete. In recent years, we have barely had midwinter, and instead of the usual two to three annual snows we have zero. Midsummer has grown from two to four months, and summer now lasts into October.</p> https://blog.plover.com/2025/05/02#claude-xar <h2>Then I had two problems…</h2> <!-- alternate title: Fucking `xargs`, how does it work? --> <p>A few days ago I got angry at <code>xargs</code> for the hundredth time, because for me <code>xargs</code> is one of those "then he had two problems" technologies. It never does what I want by default and I can never remember how to use it. This time what I wanted wasn't complicated: I had a bunch of PDF documents in <code>/tmp</code> and I wanted to use GPG to encrypt some of them, something like this:</p> <pre><code> gpg -ac &#036;(ls *.pdf | menupick) </code></pre> <p><a href="https://github.com/mjdominus/util/blob/master/bin/menupick"><code>menupick</code></a> is a lovely little utility that reads lines from standard input, presents a menu, prompts on the terminal for a selection from the items, and then prints the selection to standard output. Anyway, this didn't work because some of the filenames I wanted had spaces in them, and <a href="https://blog.plover.com/Unix/whitespace.html">the shell sucks</a>. Also because <code>gpg</code> probably only does one file at a time.</p> <p>I could have done it this way:</p> <pre><code> ls *.pdf | menupick | while read f; do gpg -ac "&#036;f"; done </code></pre> <p>but that's a lot to type. I thought “aha, I'll use <code>xargs</code>.” Then I had two problems.</p> <pre><code> ls *.pdf | menupick | xargs gpg -ac </code></pre> <p>This doesn't work because <code>xargs</code> wants to batch up the inputs to run as few instances of <code>gpg</code> as possible, and <code>gpg</code> only does one file at a time. I glanced at the <code>xargs</code> manual looking for the "one at a time please" option (which should have been the default) but I didn't see it amongst the forest of other options. </p> <p>I think now that I needed <code>-n 1</code> but I didn't find it immediately, and I was tired of looking it up every time when it was what I wanted every time. After many years of not remembering how to get <code>xargs</code> to do what I wanted, I decided the time had come to write a stripped-down replacement that just did what I wanted and nothing else.</p> <p>(In hindsight I should perhaps have looked to see if <code>gpg</code>'s <code>--multifile</code> option did what I wanted, but it's okay that I didn't, this solution is more general and I will use it over and over in coming years.)</p> <h2><code>xar</code> is a worse version of <code>xargs</code>, but worse is better (for me)</h2> <p>First I wrote a comment that specified the scope of the project:</p> <pre><code> # Version of xargs that will be easier to use # # 1. Replace each % with the filename, if there are any # 2. Otherwise put the filename at the end of the line # 3. Run one command per argument unless there is (some flag) # 4. On error, continue anyway # 5. Need -0 flag to allow NUL-termination </code></pre> <p>There! It will do <em>one</em> thing well, as Brian and Rob commanded us in the Beginning Times.</p> <p>I wrote a draft implementation that did not even do all those things, just items 2 and 4, then I fleshed it out with item 1. I decided that I would postpone 3 and 5 until I needed them. (5 at least isn't a YAGNI, because I know I have needed it in the past.)</p> <p>The result was this:</p> <pre><code> import subprocess import sys def command_has_percent(command): for word in command: if "%" in word: return True return False def substitute_percents(target, replacement): return [ s.replace("%", replacement) for s in target ] def run_command_with_filename(command_template, filename): command = command_template.copy() if not command_has_percent(command): command.append("%") res = subprocess.run(substitute_percents(command, filename), check=False) return res.returncode == 0 if __name__ == '__main__': template = sys.argv[1:] ok = True for line in sys.stdin: if line.endswith("\n"): line = line[:-1] if not run_command_with_filename(template, line): ok = False exit(0 if ok else 1) </code></pre> <p>Short, clean, simple, easy to use. I called it <a href="https://github.com/mjdominus/util/blob/master/bin/xar"><code>xar</code></a>, ran</p> <pre><code> ls *.pdf | menupick | xar gpg -ac </code></pre> <p>and was content.</p> <h2>Now again, with Claude</h2> <p>The following day I thought this would be the perfect opportunity to try getting some LLM help with programming. I already had a baseline version of <code>xar</code> working, and had thought through the problem specification. Now I could do it over with the LLM and compare the two results. The program I wanted was small and self-contained. If the LLM sabotaged me somehow, I would probably notice, and if I didn't, it wouldn't matter, because I had a working version already.</p> <p>So I asked Claude about it. I knew Claude was not the right choice, because Claude is not really designed for this task, and has no integration with the coding editor, but Claude is what I am familiar with so I thought I'd give it a shot.</p> <p>On the whole it went extremely well. <a href="https://claude.ai/share/5749f96b-aaa1-401d-b9e1-fac8f4d7a9bb">The complete transcript is here</a>. I imagine this was pretty much a maximally good experience, that all the terrible problems of LLM coding arise in larger, more complicated systems. But this program is small and self-contained, with no subtleties, so the LLM could be at its best.</p> <h2>Phase 1</h2> <p>First I just told Claude what I wanted and let it write the program from scratch.</p> <blockquote> <p>Let's write a program in Python called <code>xar</code>. It will be a stripped-down version of the standard Unix <code>xargs</code> utility, but it will do less and be simpler to use.</p> <p>It will get command-line arguments that specify a command template. Then it will read lines from stdin. Each line will be appended to the command template to produce a command. The program will run the resulting command, one command for each line of input.</p> <p>Any questions?</p> </blockquote> <p>Default Claude is very chatty and I am going to omit most of its chatty comments, which make me impatient.</p> <p>The program it wrote it was not what I would have written, but it was good enough. If I had just used it right off the bat, instead of writing my own, it would have been enough, and it would have taken somewhere between 2% and 10% as long to produce.</p> <p>So the one-line summary of this article is: I should stop writing simple command-line utilities, and just have Claude write them instead, because Claude's are good enough, and definitely better than yak-shaving.</p> <p>Here's Claude's initial version:</p> <pre><code> #!/usr/bin/env python3 import sys import subprocess import shlex def main(): if len(sys.argv) &lt; 2: print("Usage: xar command [args...]", file=sys.stderr) sys.exit(1) command_template = sys.argv[1:] for line in sys.stdin: line = line.rstrip('\n') full_command = command_template + [line] try: result = subprocess.run(full_command, check=True) except subprocess.CalledProcessError as e: print(f"Command failed with exit code {e.returncode}: {' '.join(full_command)}", file=sys.stderr) except FileNotFoundError: print(f"Command not found: {full_command[0]}", file=sys.stderr) sys.exit(1) if __name__ == "__main__": main() </code></pre> <p>Claude's version had numerous comments, which I have omitted. I later told it to stop putting in comments, which it did.</p> <p>Claude's use of <code>check</code> here was not what I wanted, because that makes <code>subprocess.run</code> raise an exception when the subcommand fails, and then the exception has to be immediately caught and handled. My original control flow had been simpler:</p> <pre><code> res = subprocess.run(substitute_percents(command, filename), check=False) return res.returncode == 0 … if not run_command_with_filename(template, line): ok = False </code></pre> <p>Claude's program pulled in <code>shlex</code> without noticing that it was unused. But Claude did teach me about <code>str.rstrip('\n')</code> which I had not known about before (or maybe had forgotten), so that was one small win already.</p> <h2>Argument parsing</h2> <p>The next step was a big win. Python's library for command-line argument handling is called <code>argparse</code> and it is <em>really</em> nice. If I were still writing programs in Perl, I would implement a Perl version of <code>argparse</code> because Perl has 29 available argument parsing libraries and they are all loathsome. The one problem with <code>argparse</code> is I never remember off the top of my head how to use it. I think the module is called <code>argparse</code> but it provides a class called <code>Argparser</code> but I often get these backward and try to use <code>argparser</code> and <code>Argparse</code>.</p> <p>Instead of figuring it out every time I usually dig up some previous Python program and then copy-paste the argument parser from there, amending it to suit the purpose.</p> <p>But this time I didn't have to do that. Instead, I just said to Claude:</p> <blockquote> <p>This is good, now please add code at the top to handle argument parsing with the standard <code>Argparse</code> library, even though there are no options yet. </p> </blockquote> <p>Claude handed me back pretty much the same program, but with the argument parser at the top:</p> <pre><code> def parse_arguments(): """Parse command-line arguments using argparse.""" parser = argparse.ArgumentParser( description="A simplified version of xargs that appends each line from stdin to a command template.", prog="xar" ) # Store all positional arguments as the command to execute parser.add_argument( "command", nargs="+", help="The command template to execute for each input line" ) return parser.parse_args() </code></pre> <p>Let's pause for a moment. Maybe you kids are unimpressed by this. But if someone had sent this interaction back in time and showed it to me even as late as five years ago, I would have been stunned. It would have been completely science-fictional. The code that it produced is not so impressive, maybe, but that I was able to get it in response to an unstructured request in plain English is like seeing a nuclear-powered jetpack in action.</p> <h2>I make some changes</h2> <p>It bothered me that the command-line arguments were being taken implicitly from <code>sys.argv</code>; that makes the program hard to test. A better way to do this is to have the list of command-line arguments be a function to the <code>main</code> function, and then for the runtime to call <code>main(sys.argv[1:])</code> instead of just <code>main()</code>. That way you can test the program without having to fake up <code>sys.argv</code>. So I changed that, and while I was making changes I got rid of Claude's comments and the unnecessary exception handling. I pasted the result back at Claude, saying:</p> <blockquote> <p>Good so far. I have adjusted your source code in several ways:</p> <ol> <li>I removed the comments.</li> <li>I removed the exception handling for the subcommand. If one of the subcommands fails, that no longer terminates the main loop</li> <li>Command-line arguments are passed to the main() function rather than being accessed directly</li> </ol> <p>Here is the code. Tell me if you see any problems or if you have any questions about it</p> </blockquote> <p>I had also sabotaged the code with at least one likely error. Python's <code>subprocess.run</code> returns a “result” structure that includes the subcommand's output and exit status, and I can never remember the name of the component that records the exit status. I either look it up or get it by trial-and-error. This time I didn't bother to either, I just guessed that it was <code>result.exitcode</code>, which I handed off to Claude even though I thought was probably wrong.</p> <p>Claude's reply said:</p> <blockquote> <p>Here are a couple of issues I noticed:</p> <p>There's an error in the error handling code - you're using <code>result.exitcode</code> but in the <code>subprocess.run()</code> function, the attribute is called <code>returncode</code> not <code>exitcode</code></p> </blockquote> <p>Awesome, now I don't have to remember that name of that component.</p> <p>Claude continued:</p> <blockquote> <p>The <code>parse_arguments()</code> function definition is missing in the pasted code, but it would need to be updated to accept the <code>argv</code> parameter</p> </blockquote> <p>I had passed <code>sys.argv[1:]</code> to <code>main</code>, and then had <code>main</code> call <code>parse_arguments(argv)</code>. But I hadn't changed <code>parse_arguments</code> to expect an argument list. (I hadn't included it in my paste at all, in fact.) Claude was exactly right, and continued with the corrected version:</p> <pre><code> #!/usr/bin/env python3 import sys import subprocess import argparse def parse_arguments(argv): … return parser.parse_args(argv) def main(argv): # Parse command-line arguments args = parse_arguments(argv) … if __name__ == "__main__": ok = main(sys.argv[1:]) exit(0 if ok else 1) </code></pre> <h2>Handling NUL-separated values</h2> <p>I said</p> <blockquote> <p>It's great, thanks for catching those errors. Now let's add a <code>-0</code> command-line option that tells the program to split the input on "\0" characters instead of at line breaks.</p> </blockquote> <p>Recall that my handwritten <code>xar</code> did not do this yet; I had left that feature for another day. Claude just added it for me, adding</p> <pre><code> parser.add_argument( "-0", "--null", action="store_true", help="Input items are terminated by a null character instead of by newline" ) </code></pre> <p>to the argument parser and changing the main loop to:</p> <pre><code> # Split input based on the delimiter option if args.null: # Split on null characters items = stdin_data.split('\0') else: # Split on newlines items = stdin_data.splitlines() for item in items: if not item: continue … </code></pre> <p>I was tired of Claude's comments, so I said</p> <blockquote> <p>Give me the same thing, with no comments</p> </blockquote> <p>which it did, so I said</p> <blockquote> <p>From now on leave out the comments. I'm a Python expert and I don't need them. If there is something I don't understand I will ask you.</p> </blockquote> <p>Claude complied. If I were going to do use Claude again in the future I would include that in the canned instructions that Claude is given up front. Instead I will probably use a tool better-suited to programming, and do whatever the analogous thing is.</p> <h2>Template filling</h2> <p>Now I told Claude to add the <code>%</code> feature:</p> <blockquote> <p>I changed <code>if not item</code> to <code>if item == ""</code>. Now let's make the following change:</p> <ul> <li>If the command template includes any <code>%</code> characters, each of these should be replaced with the input item.</li> <li>Otherwise, if there were no <code>%</code> characters, the input item should be appended to the end of the command as in the current version</li> </ul> </blockquote> <p>Claude did this. It used an explicit loop instead of the list comprehension that I had used (and preferred), but it did do it correctly:</p> <pre><code> for arg in command_template: if '%' in arg: has_placeholder = True full_command.append(arg.replace('%', item)) else: full_command.append(arg) if not has_placeholder: full_command.append(item) </code></pre> <p>Even without the list comprehension, I would have factored out the common code:</p> <pre><code> for arg in command_template: if '%' in arg: has_placeholder = True full_command.append(arg.replace('%', item)) if not has_placeholder: full_command.append(item) </code></pre> <p>But I am not going to complain, my code is simpler but is doing unnecessary work.</p> <p>Claude also took my hint to change <code>item == ""</code> even though I didn't <em>explicitly</em> tell it to change that.</p> <p>At this point the main loop of the <code>main</code> function was 15 lines long, because Claude had stuck all the <code>%</code>-processing inline. So I said:</p> <blockquote> <p>Good, let's extract the command template processing into a subroutine.</p> </blockquote> <p>It did this right, understanding correctly what code I was referring to and extracting it into a subroutine called <code>process_command_template</code>. More science fiction: I can say "command template processing" and it guesses what I had in mind!</p> <p>This cut the main loop to 7 lines. That worked so well I tried it again:</p> <blockquote> <p>Good, now let's extract the part of main that processes stdin into a subroutine that returns the <code>items</code> array</p> </blockquote> <p>It pulled the correct code into a function called <code>process_stdin</code>. It did not make the novice mistake of passing the entire <code>args</code> structure to this function. In the caller it had <code>process_stdin(args.null)</code> and inside of <code>process_stdin</code> this parameter was named <code>use_null_delimiter</code>,</p> <h2>YAGNI?</h2> <p>At this point I was satisfied but I thought I might as well ask if it should do something else before we concluded:</p> <blockquote> <p>Can you think of any features I left out that would be useful enough to warrant inclusion? Remember this program is supposed to be small and easy to use, in contrast to the existing <code>xargs</code> which is very complicated.</p> </blockquote> <p>Claude had four suggestions:</p> <ol> <li><p>A <code>-p</code> or <code>--parallel</code> option to run commands in parallel</p></li> <li><p>A <code>-n</code> or <code>--max-args</code> option to specify the maximum number of items to pass per command</p></li> <li><p>A simple <code>-v</code> or <code>--verbose</code> flag to show commands as they're executed</p></li> <li><p>A way to replace the command's standard input with the item instead of adding it as an argument</p></li> </ol> <p>All reasonable suggestions, nothing stupid. (It also supplied code for #3, which I had not asked for and did not want, but as I said before, default Claude is very chatty.)</p> <h2>Parallelization</h2> <p>I didn't want any of these, and I knew that #2–4 would be easy to add if I did want any of them later. But #1 was harder. I've done code like this in the past, where the program has a worker pool and runs a new process whenever the worker pool isn't at capacity. It's not even that hard. In Perl you can play a cute trick and use something like</p> <pre><code> &#036;workers{spawn()} = 1 while delete &#036;workers{wait()}; </code></pre> <p>where the <code>workers</code> hash maps process IDs to dummy values. A child exits, <code>wait()</code> awakens and returns the process ID of the completed child, which is then deleted from the map, and the loop starts another worker.</p> <p>I wanted to see how Claude would do it, and the result was an even bigger win than I had had previously, because Claude wrote this:</p> <pre><code> with concurrent.futures.ProcessPoolExecutor(max_workers=args.parallel) as executor: futures = [executor.submit(execute_command, cmd, args.verbose) for cmd in commands] for future in concurrent.futures.as_completed(futures): success = future.result() if not success: ok = False </code></pre> <p>What's so great about this? What's great is that I hadn't known about <code>concurrent.futures</code> or <code>ProcessPoolExecutor</code>. And while I might have suspected that something like them existed, I didn't know what they were called. But now I do know about them.</p> <p>If someone had asked me to write the <code>--parallel</code> option, I would have had to have this conversation with myself:</p> <blockquote> <p>Python probably has something like this already. But how long will it take me to track it down? And once I do, will the API documentation be any good, or will it be spotty and incorrect? And will there be only one module, or will there be three and I will have to pick the right one? And having picked module F6, will I find out an hour later that F6 is old and unmaintained and that people will tell me “Oh, you should have used A1, it is the new hotness, everyone knows that.”</p> </blockquote> <p>When I put all that uncertainty on a balance, and weigh it against the known costs of doing it myself, which one wins?</p> <p>The right choice is: I should do the research, find the good module (A1, not F6), and figure out how to use it.</p> <p>But one of my biggest weaknesses as a programmer is that I too often make the wrong choice in this situation. I think “oh, I've done this before, it will be quicker to just do it myself”, and then I do and it is.</p> <p>Let me repeat, <strong>it is quicker</strong> to do it myself. But that is still the wrong choice.</p> <p>Maybe the thing I wrote would be sooner or smaller or faster or more technically suitable to the project than the canned module would have been. But it would only have been more be technically suitable <em>today</em>. If it needed a new feature in the future it might have to be changed by someone who had never seen it before, whereas the canned module could well already have the needed feature ready to go, already documented, and perhaps already familiar to whoever had to make the change. My bespoke version would certainly be unfamiliar to every <em>other</em> programmer on the project — including perhaps myself six months later — so would be the wrong thing to use.</p> <p>I'm really good at hacking this stuff up. Which is a <strong>problem</strong>. It makes me want to hack stuff up, even when I shouldn't.</p> <p>Claude tips the balance strongly toward the correct side, which is that I should use the prepackaged module that someone else wrote and not hack something up.</p> <p>And now I know about <code>concurrent.futures.ProcessPoolExecutor</code>! The world is full of manuals, how can I decide which ones I should read? One way is to read them all, which used to work back when I was younger, but now I have more responsibilities and I don't have time to read the entire Python library reference including all the useless bits I will never use. But here's Claude pointing out to me that this is something I need to know about, now, today, and I should read <em>this</em> one. That is valuable knowledge.</p> <h2>Claude flubs</h2> <p>While testing the program I did</p> <pre><code> xar --parallel=2 bash -c '...' </code></pre> <p>which didn't work because the <code>argparse</code> library tried to parse the <code>-c</code> as a flag to <code>xar</code>, when I wanted it to be a flag to <code>bash</code>. This was my fault, and there is a standard way around it, which is that I should have said</p> <pre><code> xar --parallel=2 -- bash -c '...' </code></pre> <p>which tells <code>argparse</code> to drop the <code>--</code> and take everything after it literally with no interpretation.</p> <p>I thought I'd see what Claude had to say about this, and it dropped the ball in a very LLM sort of way.</p> <p>I asked:</p> <blockquote> <p>When I did <code>xar --parallel=2 bash -c '...'</code> it misunderstood the arguments. It thought I was trying to pass <code>-c</code> to <code>xar</code> and failed with unrecognized arguments. What should I do about that? </p> </blockquote> <p>Claude replied:</p> <blockquote> <p>There are two main approaches to handle this:</p> <ol> <li>Use the <code>--</code> separator to indicate the end of arguments for xar: …</li> <li>Modify your code to handle this case specifically by looking for a command terminator in the argument parser.</li> </ol> <p>Here's how you could modify your code to implement the first approach:</p> </blockquote> <p>And then it followed with the same, <em>unmodified</em> code…</p> <p>Which was <em>correct</em>, because <code>--</code> is already handled by <code>argparse</code>, so no change was actually required to implement the first approach! But Claude's characterization of it as a <em>modification</em> was misleading, wrong, and potentially very confusing.</p> <p>I said:</p> <blockquote> <p>I don't see what the difference is in that argument parsing code as compared to what I had before.</p> </blockquote> <p>and Claude got into the LLM tail-chasing mode where it got more and more confused:</p> <blockquote> <p>You're right, I apologize for the confusion. There's no difference in the argument parsing code I provided compared to what you had before. The issue is with how argparse handles arguments by default. </p> <p>To fix the issue with <code>xar --parallel=2 bash -c '...',</code> you need to actually implement support for the <code>--</code> separator in your code… </p> <pre><code> # Find the index of '--' if it exists try: separator_index = argv.index('--') xar_args = argv[:separator_index] command_args = argv[separator_index+1:] except ValueError: … </code></pre> </blockquote> <p>Ugh, all wrong in the worst way. The code probably works, but it is completely unnecessary. Claude's claim that “you need to actually implement support for the <code>--</code> separator” is flat wrong. I pointed this out and Claude got more confused. Oh well, nobody is perfect!</p> <h2>Lessons learned</h2> <p>A long time ago, when syntax-coloring editors were still new, I tried one and didn't like it, then tried again a few years later and discovered that I liked it better than I had before, and not for the reasons that anyone had predicted or that I would have been able to predict. (<a href="https://blog.plover.com/prog/syntax-coloring-1998.html">I wrote an article about the surprising reasons to use the syntax coloring</a>.)</p> <p>This time also. As usual, an actual experiment produced unexpected results, because the world is complicated and interesting. Some of the results were unsurprising, but some were not anything I would have thought of beforehand.</p> <h3>Claude's code is good enough, but it is not a magic oracle</h3> <p>Getting Claude to write most of the code was a lot faster and easier than writing it myself. This is good! But I was dangerously tempted to just take Claude's code at face value instead of checking it carefully. I quickly got used to flying along at great speed, and it was tough to force myself to slow down and be methodical, looking over everything as carefully as I would if Claude were a real junior programmer. It would be easy for me to lapse into bad habits, especially if I were tired or ill. I will have to be wary.</p> <p>Fortunately there is already a part of my brain trained to deal with bright kids who lack experience, and I think perhaps that part of my brain will be able to deal effectively with Claude.</p> <p>I did not notice any mistakes on Claude's part — at least this time.</p> <p>At one point my testing turned up what appeared to be a bug, but it was not. The testing was still time well-spent.</p> <h3>Claude remembers the manual better than I do</h3> <p>Having Claude remember stuff for me, instead of rummaging the manual, is great. Having Claude stub out an argument parser, instead of copying one from somewhere else, was pure win.</p> <p>Partway along I was writing a test script and I wanted to use that Bash flag that tells Bash to quit early if any of the subcommands fails. I can never remember what that flag is called. Normally I would have hunted for it in one of my own shell scripts, or groveled over the 378 options in the <code>bash</code> manual. This time I just asked in plain English “What's the <code>bash</code> option that tells the script to abort if a command fails?” Claude told me, and we went back to what we were doing.</p> <h3>Claude can talk about code with me, at least small pieces</h3> <p>Claude easily does simple refactors. At least at this scale, it got them right. I was not expecting this to work as well as it did.</p> <p>When I told Claude to stop commenting every line, it did. I wonder, if I had told it to use <code>if not expr</code> only for Boolean expressions, would it have complied? Perhaps, at least for a while.</p> <p>When Claude wrote code I wasn't sure about, I asked it what it was doing and at least once it explained correctly. Claude had written</p> <pre><code> parser.add_argument( "-p", "--parallel", nargs="?", const=5, type=int, default=1, help="Run up to N commands in parallel (default: 5)" ) </code></pre> <p>Wait, I said, I know what the <code>const=5</code> is doing, that's so that if you have <code>--parallel</code> with no number it defaults to 5. But what is the <code>--default</code> doing here? I just asked Claude and it told me: that's used if there is no <code>--parallel</code> flag at all.</p> <p>This was much easier than it would have been for me to pick over the <code>argparse</code> manual to figure out how to do this in the first place.</p> <h2>More thoughts</h2> <p>On a different project, Claude might have done much worse. It might have given wrong explanations, or written wrong code. I think that's okay though. When I work with human programmers, they give wrong explanations and write wrong code all the time. I'm used to it.</p> <p>I don't know how well it will work for larger systems. Possibly pretty well <em>if</em> I can keep the project sufficiently modular that it doesn't get confused about cross-module interactions. But if the criticism is “that LLM stuff doesn't work unless you keep the code extremely modular” that's not much of a criticism. We all need more encouragement to keep the code modular.</p> <p>Programmers often write closely-coupled modules knowing that it is bad and it will cause maintenance headaches down the line, knowing that the problems will most likely be someone else's to deal with. But what if writing closely-coupled modules had an immediate cost today, the cost being that the LLM would be less helpful and more likely to mess up today's code? Maybe programmers would be more careful about letting that happen!</p> <h2>Will my programming skill atrophy?</h2> <p>Folks at Recurse Center were discussing this question.</p> <p>I don't think it will. It will only atrophy if I let it. And I have a pretty good track record of not letting it. The essence of engineering is to pay attention to what I am doing and why, to try to produce a solid product that satisifes complex constraints, to try to spot problems and correct them. I am not going to stop doing this. Perhaps the problems will be different ones than they were before. That is all right.</p> <p>Starting decades ago I have repeatedly told people</p> <blockquote> <p>You cannot just paste code with no understanding of what is going on and expect it to work.</p> </blockquote> <p>That was true then without Claude and it is true now with Claude. Why would I change my mind about this? How could Claude change it?</p> <p>Will I lose anything from having Claude write that complex <code>parser.add_argument</code> call for me? Perhaps if I had figured it out on my own, on future occasions I would have remembered the <code>const=5</code> and <code>default=1</code> specifications and how they interacted. Perhaps.</p> <p>But I suspect that I <em>have</em> figured it out on my own in the past, more than once, and it <em>didn't</em> stick. I am happy with how it went this time. After I got Claude's explanation, I checked its claimed behavior pretty carefully with a stub program, as if I had been reviewing a colleague's code that I wasn't sure about.</p> <p>The biggest win Claude gave me was that I didn't know about this <code>ProcessPoolExecutor</code> thing before, and now I do. That is going to make me a <em>better</em> programmer. Now I know something about useful that I didn't know before, and I have a pointer to documentation I know I should study.</p> <p>My skill at writing ad-hoc process pool managers might atrophy, but if it does, that is <strong>good</strong>. I have already written too many ad-hoc process pool managers. It was a bad habit, I should have stopped long ago, and this will help me stop.</p> <h2>Conclusion</h2> <p>This works.</p> <p>Perfectly? No, it's technology, technology never works perfectly. Have you ever <em>used</em> a computer?</p> <p>Will it introduce new problems? Probably, it's new technology, and new technology always introduces new problems.</p> <p>But is it better than what we had before? Definitely.</p> <p>I still see some programmers turning up their noses at this technology as if they were sure it was a silly fad that would burn itself out once people came to their senses and saw what a terrible idea it was.</p> <p>I think that is not going to happen, and those nose-turning-up people, like the people who pointed out all the drawbacks and unknown-unknowns of automobiles as compared to horse-drawn wagons, are going to look increasingly foolish.</p> <p>Because it works.</p> https://blog.plover.com/2025/05/01#centrifuge <p><img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdef%5cnk%231%232%7b%5cleft%5clangle%7b%231%20%5catop%20%232%7d%5cright%5crangle%7d%0a%5cdef%5cdd%231%7b%5cnk%7b12%7d%7b%231%7d%7d%0a%24"></p> <p>Suppose a centrifuge has <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"> slots, arranged in a circle around the center, and we have <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> test tubes we wish to place into the slots. If the tubes are not arranged symmetrically around the center, the centrifuge will explode.</p> <p>(By "arranged symmetrically around the center, I mean that if the center is at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%280%2c0%29%24">, then the sum of the positions of the tubes must also be at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%280%2c0%29%24">.)</p> <p>Let's consider the example of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%3d12%24">. Clearly we can arrange <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%242%24">, <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243%24">, <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%244%24">, or <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%246%24"> tubes symmetrically:</p> <div style="margin: auto;"> <img src="https://pic.blog.plover.com/math/centrifuge/n12k2.svg" style="width: 20%; margin: 2%;" alt="twelve small circles arranged around a central point, like a clock; circles 5 and 11 are filled in" /> <img src="https://pic.blog.plover.com/math/centrifuge/n12k3.svg" style="width: 20%; margin: 2%;" alt="cirles 1, 5, and 9 are filled in" /> <img src="https://pic.blog.plover.com/math/centrifuge/n12k4.svg" style="width: 20%; margin: 2%;" alt="circles 0, 3, 6, and 9 are filled" /> <img src="https://pic.blog.plover.com/math/centrifuge/n12k6.svg" style="width: 20%; margin: 2%;" alt="circles 1, 3, 5, 7, 9, and 11 are filled" /> </div> <p>Equally clearly we can't arrange only <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%24">. Also it's easy to see we can do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> tubes if and only if we can also do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%2dk%24"> tubes, which rules out <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%3d12%2c%0ak%3d11%24">.</p> <p>From now on I will write <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%20nk%24"> to mean the problem of balancing <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> tubes in a centrifuge with <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"> slots. So <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd%202%2c%20%5cdd%203%2c%20%5cdd%0a4%2c%20%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd%206%24"> are possible, and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd%201%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd%7b11%7d%24"> are not. And <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%20nk%24"> is solvable if and only if <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%20n%7bn%2dk%7d%24"> is.</p> <p>It's perhaps a little surprising that <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd7%24"> is possible. If you just ask this to someone out of nowhere they might have a happy inspiration: “Oh, I'll just combine the solutions for <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd3%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd4%24">, easy.” But that doesn't work because two groups of the form <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243i%2bj%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%244i%2bj%24"> always overlap.</p> <p>For example, if your group of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%244%24"> is the slots <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%2c%203%2c%206%2c%209%24"> then you can't also have your group of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243%24"> be <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%2c%205%2c%209%24">, because slot <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%249%24"> already has a tube in it. </p> <div style="margin: auto;"> <img src="https://pic.blog.plover.com/math/centrifuge/n12k7x.svg" style="width: 30%;" alt="The k=3 and k=4 diagrams from before, superimposed; there is a small explosion symbol at 9 o'clock where they interfere"> </div> <p>The other balanced groups of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243%24"> are blocked in the same way. You cannot solve the puzzle with <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%3d3%2b4%24">; you have to do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%3d3%2b2%2b2%24"> as below left. The best way to approach this is to do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd5%24">, as below right. This is easy, since the triangle only blocks three of the six symmetric pairs. Then you replace the holes with tubes and the tubes with holes to turn <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd5%24"> into <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd%7b12%2d5%7d%3d%5cdd7%24">.</p> <div style="margin: auto;"> <img src="https://pic.blog.plover.com/math/centrifuge/n12k7.svg" style="width: 25%; margin: 5%;" alt="a triangle filling slots 1, 5, and 9, plus a pair at 0, 6 and another pair at 2, 8" /> <img src="https://pic.blog.plover.com/math/centrifuge/n12k5.svg" style="width: 25%; margin: 5%;" alt="the opposite of the previous diagram, consisting of a triangle filling slots 3, 7, 11 and a pair at 4, 10" /> </div> <p>Given <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24">, how can we decide whether the centrifuge can be safely packed?</p> <p>Clearly you can solve <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%20nk%24"> when <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"> is a multiple of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%3e1%24">, but the example of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd5%24"> (or <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd7%24">) shows this isn't a necessary condition.</p> <p>A generalization of this is that <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%20nk%24"> is always solvable if <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cgcd%28n%2ck%29%20%3e%201%24"> since you can easily balance <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24g%20%3d%20%5cgcd%28n%2c%20k%29%24"> tubes at positions <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%2c%20%5cfrac%20ng%2c%20%5cfrac%7b2n%7dg%2c%20%5cdots%2c%0a%5cfrac%20%7b%28g%2d1%29n%7dg%24">, then do another <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24g%24"> tubes one position over, and so on. For example, to do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd8%24"> you just put first four tubes in slots <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%2c%203%2c%206%2c%209%24"> and the next four one position over, in slots <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%2c%204%2c%207%2c%2010%24">.</p> <div style="margin: auto;"> <img src="https://pic.blog.plover.com/math/centrifuge/n12k8.svg" style="width: 30%;" alt="Two squares this time, as described in the previous paragraph"> </div> <p>An interesting counterexample is that the strategy for <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cdd7%24">, where we did <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%3d3%2b2%2b2%24">, cannot be extended to <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%7b14%7d9%24">. One would want to do <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%3d7%2b2%24">, but there is no way to arrange the tubes so that the group of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%242%24"> doesn't conflict with the group of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%24">, which blocks one slot from every pair.</p> <p>But we can see that this must be true without even considering the geometry. <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%7b14%7d9%24"> is the reverse of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%7b14%7d%7b14%2d9%7d%20%3d%20%5cnk%7b14%7d5%24">, which impossible: the only nontrivial divisors of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%3d14%24"> are <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%242%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%24">, so <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> must be a sum of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%242%24">s and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%24">s, and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%245%24"> is not.</p> <p>You can't fit <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%3d3%2b5%3d8%24"> tubes when <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%3d15%24">, but again the reason is a bit tricky. When I looked at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%248%24"> directly, I did a case analysis to make sure that the <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243%24">-group and the <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%245%24">-group would always conflict. But again there was an easier was to see this: <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%248%3d15%2d7%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%24"> clearly won't work, as <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%247%24"> is not a sum of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%243%24">s and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%245%24">s. I wonder if there's an example where both <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%2dk%24"> are not obvious?</p> <p>For <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%3d20%24">, every <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%24"> works except <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%3d3%2c17%24"> and the always-impossible <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24k%3d1%2c19%24">.</p> <p>What's the answer in general? I don't know.</p> <h2>Addenda</h2> <h3>20250502</h3> <p>Now I am amusing myself thinking about the perversity of a centrifuge with a prime number of slots, say <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%2413%24">. If you use it at all, you must fill every slot. I hope you like explosions!</p> <p>While I did not explode any centrifuges in university chemistry, I did once explode an expensive <a href="https://en.wikipedia.org/wiki/Liebig_condenser">Liebig condenser</a>.</p> <p><a href="https://pic.blog.plover.com/math/centrifuge/condenser.jpg"><img src="https://pic.blog.plover.com/math/centrifuge/condenser-th.jpg" class="center" alt="A chemistry lab apparatus. In the middle thje the Liebig condenser, a pair of long concentric glass tubes, one inside the other, supported by a metal ring stand. At left a heater heats a flash whose top is connected to the upper end of the inner tube of the condenser. The condensate collects in a flask at right. Two rubber tubes connect to the top and bottom of the outer tube, carrying water through it."></a></p> <p><span style="font-size: x-small">Condenser setup by <a href="https://commons.wikimedia.org/w/index.php?title=User:Mario_Link">Mario Link</a> from <a href="https://www.flickr.com/photos/24049265@N00/162821856">an original image</a> by <a href="https://www.flickr.com/photos/arlen/">Arlen on Flickr</a>. Licensed <a href="https://creativecommons.org/licenses/by/2.0/deed.en">cc-by-2.0</a>, provided via <a href="https://commons.wikimedia.org/wiki/File:Distillation_2-3.jpg">Wikimedia Commons</a>.</p> <h3>20250503</h3> <ul> <li><p>Michael Lugo informs me that <a href="https://mattbaker.blog/2018/06/25/the-balanced-centrifuge-problem/">a complete solution may be found on Matt Baker's math blog</a>. I have not yet looked at this myself.</p></li> <li><p><a href="https://mathstodon.xyz/@oantolin/114434195433254052">Omar Antolín points out an important consideration I missed</a>: it may be necessary to <em>subtract</em> polygons. Consider <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%7b30%7d6%24">. This is obviously possible since <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%246%5cmid%2030%24">. But there is a more interesting solution. We can add the pentagon <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5c%7b0%2c%206%2c%2012%2c%2018%2c%2024%5c%7d%24"> to the digons <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5c%7b5%2c%2020%5c%7d%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5c%7b10%2c%2025%5c%7d%24"> to obtain the solution $${0,5,6,10,12,18, 20, 24, 25}.$$</p> <p><img src="https://pic.blog.plover.com/math/centrifuge/n30k9.svg" style="width: 40%;" class="center" alt=""/> Then from this we can <em>subtract</em> the triangle <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5c%7b0%2c%2010%2c%0a%20%2020%5c%7d%24"> to obtain $${5, 6, 12, 18, 24, 25},$$ a solution to <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5cnk%7b30%7d6%24"> which is <em>not</em> a sum of regular polygons:</p> <p><img src="https://pic.blog.plover.com/math/centrifuge/n30k6b.svg" style="width: 40%;" class="center" alt=""/></p></li> <li><p>Thanks to Dave Long for pointing out a small but significant error, which I have corrected.</p></li> </ul> <h3>20250505</h3> <ul> <li>Robin Houston points out this video, <a href="https://www.youtube.com/watch?v=7DHE8RnsCQ8">The centrifuge Problem</a> with Holly Krieger, on <a href="https://www.youtube.com/@numberphile">the Numberphile channel</a>.</li> </ul> https://blog.plover.com/2025/04/30#proof-by-symmetry <p>Content warning: rambly</p> <p>Given the coordinates of the three vertices of a triangle, can we find the area? Yes. If by no other method, we can use the Pythagorean theorem to find the lengths of the edges, and then <a href="https://en.wikipedia.org/wiki/Heron%27s_formula">Heron's formula</a> to compute the area from that.</p> <p>Now, given the coordinates of the four vertices of a quadrilateral, can we find the area? And the answer is, no, there is no method to do that, <em>because there is not enough information</em>:</p> <p><img class="center" border=0 src="https://pic.blog.plover.com/math/proof-by-symmetry/q1.svg" alt="three points arranged in an irregular triangle, with one in the middle. Four of the six possible edges are drawn in, definining a quadrilateral" /> <img class="center" border=0 src="https://pic.blog.plover.com/math/proof-by-symmetry/q2.svg" alt="the same four points, but with three different edges drawn in to define a different quadrilateral with the same vertices" /> <img class="center" border=0 src="https://pic.blog.plover.com/math/proof-by-symmetry/q3.svg" alt="a third quadrilateral with the same vertices as the first two" /></p> <p>These three quadrilaterals have the same vertices, but different areas. Just knowing the vertices is not enough; you also need their order.</p> <p>I suppose one could abstract this: Let <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24f%24"> be the function that maps the set of vertices to the area of the quadrilateral. Can we calculate values of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24f%24">? No, because there is no such <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24f%24">, it is not well-defined.</p> <p>Put that way it seems less interesting. It's just another example of the principle that, just because you put together a plausible sounding description of some object, you cannot infer that such an object must exist. One of the all-time pop hits here is:</p> <blockquote> <p>Let <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%ce%b5%24"> be the smallest [real / rational] number strictly greater than <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%24">…</p> </blockquote> <p>which appears on Math SE quite frequently. Another one I remember is someone who asked about <a href="https://math.stackexchange.com/q/838561/25554">the volume of a polyhedron with exactly five faces, all triangles</a>. This is a fallacy at the ontological level, not the mathematical level, so when it comes up I try to demonstrate it with a nonmathematical counterexample, usually something like “the largest purple hat in my closet” or perhaps “the current Crown Prince of the Ottoman Empire”. The latter is less good because it relies on the other person to know obscure stuff about the Ottoman Empire, whatever that is.</p> <p>This is also unfortunately also the error in Anselm's so-called “ontological proof of God”. A philosophically-minded friend of mine once remarked that being known for the discovery of the ontological proof of God is like being known for the discovery that you can wipe your ass with your hand.</p> <p>Anyway, I'm digressing. The interesting part of the quadrilateral thing, to me, is not so much that <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24f%24"> doesn't exist, but the specific reasoning that demonstrates that it <em>can't</em> exist. I think there are more examples of this proof strategy, where we prove nonexistence by showing there is not enough information for the thing to exist, but I haven't thought about it enough to come up with one.</p> <p>There is a proof, the so-called <a href="https://math.stackexchange.com/a/1313546/25554">“information-theoretic proof”</a>, that a comparison sorting algorithm takes at least <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24O%28n%5clog%20n%29%24"> time, based on comparing the amount of information gathered from the comparisons (one bit each) with that required to distinguish all <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%21%20%24"> possible permutations (<img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%5clog_2%20n%21%20%5cge%20n%5clog_2%20n%24"> bits total). I'm not sure that's what I'm looking for here. But I'm also not sure it isn't, or why I feel it might be different.</p> <h2>Addenda</h2> <h3>20250430</h3> <p>Carl Muckenhoupt suggests that logical independence proofs are of the same sort. He says, for example:</p> <blockquote> <p>Is there a way to prove the parallel postulate from Euclid's other axioms? No, there is not enough information. Here are two geometric models that produce different results.</p> </blockquote> <p>This is just the sort of thing I was looking for.</p> <h3>20250503</h3> <p>Rik Signes has allowed me to reveal that he was the source of the memorable disparagement of Anselm's dumbass argument.</p> <!-- I had previously gotten blanket permission from him in connection with still-unpublished article math/logic/properties.html --> https://blog.plover.com/2025/04/26#Singletary <p>(Previously: <a href="https://blog.plover.com/politics/blago.html">[1]</a> <a href="https://blog.plover.com/law/fortunato-n-perri.html">[2]</a>)</p> <p>Welcome to Philadelphia! We have a lot of political corruption here. <a href="https://blog.plover.com/law/fortunato-n-perri.html">I recently wrote about the unusually corrupt Philadelphia Traffic Court</a>, where four of the judges went to the federal pokey, and the state decided there was no way to clean it up, they had to step on it like a cockroach. I ended by saying:</p> <blockquote> <p>One of those traffic court judges was Willie Singletary, who I've been planning to write about since 2019. But he is a hard worker who deserves better than to be stuck in an epilogue, so I'll try to get to him later this month.</p> </blockquote> <p>This is that article from 2019, come to fruit at last. It was originally inspired by this notice that appeared at my polling place on election day that year:</p> <p><a href="https://pic.blog.plover.com/politics/Singletary/singletary.jpg"><span style="font-size: small;">(Click for uncropped version)<span><br> <img class="center" border=0 src="https://pic.blog.plover.com/politics/Singletary/singletary-cropped-th.jpg" alt=" Cropped version of a notice posted in a Philadelphia polling place, text as below”" /></a></p> <blockquote> <p><strong>VOTES FOR THIS CANDIDATE WILL NOT BE COUNTED</strong></p> <p><strong>DEAR VOTERS</strong>:</p> <p>Willie Singletary, candidate for Democratic Council At-Large, has been removed from the Primary Ballot by Court Order. Although his name appears on the ballot, votes for this candidate will not be counted because he was convicted of two Class E felonies by the United States District Court for the Eastern District of Pennsylvania, which bars his candidacy under Article 2, Section 7 of the Pennsylvania Constitution.</p> </blockquote> <p>That's because Singletary had been one of those traffic court judges. In 2014 he had been convicted of lying to the FBI in connection with that case, and was sentenced to 20 months in federal prison; I think he actually served 12.</p> <p>That didn't stop Willie from trying to run for City Council, though, and the challenge to his candidacy didn't wrap up before the ballots were printed, so they had to post these notices.</p> <p>Even before the bribery scandal and the federal conviction, Singletary had already lost his Traffic Court job when it transpired that he had showed dick pics to a Traffic Court cashier.</p> <p>Before that, when he was campaigning for the Traffic Court job, he was caught on video promising to give favorable treatment to campaign donors.</p> <!-- At that time he had also had his driver's license suspended over $11,000 in unpaid traffic fines, but let's not belabor the point. --> <p>But Willie's enterprise and go-get-it attitude means he can't be kept down for long. Willie rises to all challenges! He is now enjoying a $90,000 annual salary as a Deputy Director of Community Partnerships in the administration of Philadelphia Mayor Cherelle Parker. Parker's spokesperson says <a href="https://www.inquirer.com/news/willie-singletary-leslie-acosta-movita-johnson-harrell-corruption-conviction-philadelphia-20241119.html">"The Parker administration supports every person’s right to a second chance in society.”</a></p> <p>I think he might be on his fourth or fifth chance by now, but who's counting? Let it never be said that Willie Singletary was a quitter.</p> <p>Lorrie once made a remark that will live in my memory forever, about the "West Philadelphia local politics-to-prison pipeline”. Mayor Parker is such a visionary that she has been able to establish a second pipeline in the opposite direction!</p> <h3>Addendum 20250501</h3> <p>I don't know how this happened, but when I committed the final version of this article a few days ago, the commit message that my fingers typed was:</p> <pre><code>Date: Sat Apr 26 14:24:19 2025 -0400 Willie Wingletsray finally ready to go </code></pre> <p>And now, because Git, it's written in stone.</p> https://blog.plover.com/2025/04/24#fortunato-n-perri <p>[ Content warning: possibly amusing, but silly and pointless ]</p> <p>My wife Lorrie wrote this on 31 January 2013:</p> <blockquote> <p>I got an e-mail from Husband titled, "The mills of Fenchurch grind slow, but they grind exceeding small." This silliness, which is off-the-charts silly, is going to require explanation.</p> <p>Fenchurch is a small blue octopus made of polyester fiberfill. He was the first one I ever bought, starting our family's octopus craze, and I gave him to Husband in 1994. He is extremely shy and introverted. He hates conflict and attention. He's a sensitive and very artistic soul. His favorite food is crab cakes, followed closely by shrimp. (We have made up favorite foods, professions, hobbies, and a zillion scenarios for all of our stuffed animals.)</p> </blockquote> <p>In our house it was well-established canon that Fenchurch's favorite food was crab cakes. I had even included him as an example in some of my conference talks:</p> <pre><code> my &#036;fenchurch = Octopus-&gt;new({ arms =&gt; 8, hearts =&gt; 3, favorite_food =&gt; "crab cakes" }); </code></pre> <blockquote> <p>He has a ladylove named Junko whom he takes on buggy rides on fine days. When Husband is feeling very creative and vulnerable, he identifies with Fenchurch.</p> <p>Anyway, one time Husband got a traffic ticket and this Traffic Court judge named Fortunato N. Perri was unbelievably mocking to him at his hearing. Good thing Husband has the thick skin of a native Manhattanite. … It was so awful that Husband and I remember bits of it more than a decade later.</p> </blockquote> <p>I came before Fortunato N. Perri in, I think, 1996. I had been involved in a very low-speed collision with someone, and I was ticketed because the proof of insurance in my glove box was expired. Rather than paying the fine, I appeared in traffic court to plead not guilty.</p> <p>It was clear that Perri was not happy with his job as a traffic court judge. He had to listen to hundreds of people making the same lame excuses day after day. “I didn't see the stop sign.” “The sun was in my eyes.” “I thought the U-turn was legal.” I can't blame Perri for growing tired of this. But I can blame him for the way he handled it, which was to mock and humiliate the people who came before him.</p> <p>“Where are you from?”</p> <p>“Ohio.”</p> <p>“Do they have stop signs in Ohio?”</p> <p>“Uh, yes.”</p> <p>“Do you know what they look like?”</p> <p>“Yes.”</p> <p>“Do they look like the stop signs we have here?”</p> <p>“Yes.”</p> <p>“Then how come you didn't see the stop sign? You say you know what a stop sign looks like but then you didn't stop. I'm fining you $100. You're dismissed.”</p> <p>He tried to hassle me also, but I kept my cool, and since I wasn't actually in violation of the law he couldn't do anything to me. He did try to ridicule my earring.</p> <p>“What does that thing mean?”</p> <p>“It doesn't mean anything, it's just an earring.”</p> <p>“Is that what everyone is doing now?”</p> <p>“I don't know what everyone is doing.”</p> <p>“How long ago did you get it?”</p> <p>“Thirteen years.”</p> <p>“Huh. … Well, you did have insurance, so I'm dismissing your ticket. You can go.”</p> <p>I'm still wearing that earring today, Fortunato. By the way, Fortunato, the law is supposed to be calm and impartial, showing favor to no one.</p> <p>Fortunato didn't just mock and humiliate the unfortunate citizens who came before him. He also abused his own clerks. One of them was doing her job, stapling together court papers on the desk in front of the bench, and he harangued her for doing it too noisily. “God, you might as well bring in a hammer and nails and start hammering up here, bang bang bang!”</p> <p>I once went back to traffic court just to observe, but he wasn't in that day. Instead I saw how a couple of other, less obnoxious judges ran things.</p> <p>Lorrie continues:</p> <blockquote> <p>Husband has been following news about this judge (now retired) and his family ever since, and periodically he gives me updates.</p> </blockquote> <p>(His son, Fortunato N. Perri Jr., is a local civil litigation attorney of some prominence. As far as I know there is nothing wrong with Perri Jr.)</p> <blockquote> <p>And we made up a story that Fenchurch was traumatized by this guy after being ticketed for parking in a No Buggy zone.</p> <p>So today, he was <a href="https://www.philly.com/philly/news/breaking/20130131_Traffic_Court_judges_begin_surrendering_to_FBI.html">charged with corruption after a three-year FBI probe</a>. <a href="https://www.inquirer.com/philly/news/homepage/20100819_FBI_and_IRS_agents_raid_three_prominent_Philadelphia_political_players.html">The FBI even raided his house</a></p> <p>I understood everything when I read that Perri accepted graft in many forms, including <strong>shrimp</strong> and <strong>crab cakes</strong>.</p> <p>OMG. No wonder my little blue octopus was wroth. No wonder he swore revenge. This crooked thief was interfering with his food supply!</p> </blockquote> <p>Lorrie wrote a followup the next day:</p> <blockquote> <p>I confess Husband and I spent about 15 minutes last night savoring details about Fortunato N. Perri's FBI bust. Apparently, <em>even he</em> had a twinge of conscience at the sheer <em>quantity</em> of <strong><em>SHRIMP</em></strong> and <strong><em>CRAB CAKES</em></strong> he got from this one strip club owner in return for fixing tickets. (Husband noted that he managed to get over his qualms.)</p> <p>Husband said Perri hadn't been <em>too</em> mean to him, but Husband still feels bad about the way Perri screamed at his hapless courtroom assistant, who was innocently doing her job stapling papers until Perri stopped proceedings to holler that she was making so much noise, she may as well be using a hammer.</p> <p>Fenchurch and his ladylove Junko, who specialize in avant garde performance art, greeted Husband last night with their newest creation, called "Schadenfreude." It mostly involved wild tentacle waving and uninhibited cackling. Then they declared it to be the best day of their entire lives and stayed up half the night partying.</p> <p><a href="https://pic.blog.plover.com/law/fortunato-n-perri/jf.jpg"><img class="center" src="https://pic.blog.plover.com/law/fortunato-n-perri/jf-th.jpg" alt="Fenchurch, at left, is a bright blue toy octopus with a round body, beady black eyes rimmed in an olive gold color, and no visible mouth. His body and arms are covered with shirt but shaggy plush. Junko, who sits at right, her eight arms entwined with his, is almost exactly the same, except that her plush is hot pink. They are resting on a quilt, presumably on a bed somewhere, and looking directly into the camera."> </a></p> </blockquote> <h3>Epilogues</h3> <ul> <li><p>Later that year, the notoriously corrupt Traffic Court was abolished, its functions transferred to regular Philadelphia Municipal Court.</p></li> <li><p>In late 2014, four of Perri's Traffic Court colleagues were convicted of federal crimes. <a href="https://www.justice.gov/usao-edpa/pr/former-traffic-court-judge-sentenced-lying-fbi">They received prison sentences of 18 to 20 months</a>.</p></li> <li><p>Fortunato Perri himself, by then 78 years old and in poor health, pled guilty, and <a href="https://www.philly.com/philly/news/20150725_Fortunato_Perri_Sr__gets_probation_in_traffic_court_scandal.html">was sentenced to two years of probation</a>.</p></li> <li><p>The folks who supplied the traffic tickets and the seafood bribes were also charged. They tried to argue that they hadn't defrauded the City of Philadelphia because the people they paid Perri to let off the hook hadn't been found guilty, and would only have owed fines <em>if</em> they had been found guilty.</p> <p>The judges in their appeal were not impressed with this argument. See <a href="https://caselaw.findlaw.com/court/us-3rd-circuit/1976350.html">United States v. Hird et al.</a>.</p></li> <li><p>One of those traffic court judges was Willie Singletary, who I've been planning to write about since 2019. But he is a hard worker who deserves better than to be stuck in an epilogue, so I'll try to get to him later this month.</p> <p>(Update 20250426: <a href="https://blog.plover.com/politics/Singletary.html">Willie Singletary, ladies and gentlemen</a>!)</p></li> </ul> <!-- https://www.courierpostonline.com/article/20130131/NEWS/301310051/Feds-Fix-Philly-s-traffic-court?nclick_check=1 --> https://blog.plover.com/2025/03/28#dirty-jobs <p>Doing the laundry used to be backbreaking toil. Haul the water, chop the wood, light the fire, heat the water, and now you are ready to begin the really tough part of the work. The old saying goes "Wash on Monday", because Monday is the day after your day of rest, and otherwise you won't have the strength to do the washing.</p> <p>And the saying continues: “Iron on Tuesday, mend on Wednesday”. Routine management of clothing takes half of the six-day work week.</p> <p>For this reason, washing is the work of last resort for the poorest and most marginal people. Widows are washerwomen. <a href="https://en.wikipedia.org/wiki/Magdalene_laundry">Prisons are laundries</a>. <a href="https://en.wikipedia.org/wiki/Yick_Wo_v%2e_Hopkins">Chinese immigrants run laundries</a>. Anyone with enough money to outsource their laundry does so.</p> <p>The invention of mechanical washing machines eliminated a great amount of human suffering and toil. Machines do the washing now. Nobody has to break their back scrubbing soiled linens against a washboard.</p> <p><img src="https://pic.blog.plover.com/misc/dirty-jobs/washboard.jpg" class="center" alt="The black and white photograph depicts a young child, perhaps two or three years old, standing next to a wooden wash tub and washboard. The child is wearing a fur parka with a fur-trimmed hood.The washboard is positioned at a slight angle, resting partially within the wooden tub. It appears weathered and worn, suggesting frequent use. The tub itself is simple, made of wood staves. A small amount of what looks like clothing or fabric is partially visible inside the tub. The ground is primarily sandy and uneven, with sparse vegetation or debris visible."><span style="font-size: x-small">“Eskimo child with wooden tub and washboard”, c. 1905, by <a href="https://en.wikipedia.org/wiki/Frank_Hamilton_Nowell">Frank Hamilton Nowell</a>, public domain, via <a href="https://commons.wikimedia.org/wiki/File:Eskimo_child_with_wooden_tub_and_washboard,_ca_1905_(NOWELL_167).jpeg">Wikimedia Commons</a>.</span></p> <p>But the flip side of that is that there are still poor and marginalized people, who now have to find other work. Mechanical laundry has taken away their jobs. They no longer have to do the backbreaking labor of hand laundry. Now they have the option to starve to death instead.</p> <p>Is it a net win? I don't know. I'd like to think so. I'd like to free people from the toil of hand laundry <em>without</em> also starving some of them to death. Our present system doesn't seem to be very good at that sort of thing. I'm not sure what a better system would look like.</p> <p>Anyway, this is on my mind a lot lately because of the recent developments in computer-generated art. I think “well, it's not all bad, because at least now nobody will have to make a living drawing pornographic pictures of other people's furry OCs. Surely that is a slight elevation of the human condition.” On the other hand, some of those people would rather have the money and who am I to deny them that choice?</p> https://blog.plover.com/2025/03/25#peano-starts-at-1 <p>A modern presentation of the <a href="https://en.wikipedia.org/wiki/Peano_axioms">Peano axioms</a> looks like this:</p> <ol> <li><img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%24"> is a natural number</li> <li>If <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"> is a natural number, then so is the result of appending an <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24S%24"> to the beginning of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24n%24"></li> <li>Nothing else is a natural number</li> </ol> <p>This baldly states that zero is a natural number.</p> <p>I think this is a 20th-century development. In 1889, the natural numbers started at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%24">, not at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%24">. Peano's <a href="https://archive.org/details/arithmeticespri00peangoog/page/n6/mode/2up"><em>Arithmetices principia, nova methodo exposita</em></a> (1889) is the source of the Peano axioms and in it Peano starts the natural numbers at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%24">, not at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%240%24">:</p> <p><a href="https://pic.blog.plover.com/math/peano-starts-at-1/Peano-1.png"><img src="https://pic.blog.plover.com/math/peano-starts-at-1/axiom-1.png" class="center" alt="screencap of Peano's first axiom from his book. It states “1∈N”."/></a></p> <p>There's axiom 1: <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%5cin%5cBbb%20N%24">. No zero. I think starting at <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%200%24"> may be a Bourbakism.</p> <p>In a modern presentation we define addition like this: </p> <p>$$ \begin{array}{rrl} (i) &amp; a + 0 = &amp; a \\ (ii) &amp; a + Sb = &amp; S(a+b) \end{array} $$</p> <p>Peano doesn't have zero, so he doesn't need item <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%28i%29%24">. His definition just has <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%28ii%29%24">.</p> <p>But wait, doesn't his inductive definition need to have a base case? Maybe something like this?</p> <p>\begin{array}{rrl} (i') &amp; a + 1 = &amp; Sa \\ \end{array}</p> <p>Nope, Peano has nothing like that. But surely the definition must have a base case? How can Peano get around that?</p> <p>Well, by modern standards, he cheats!</p> <p>Peano doesn't have a special notation like <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24S%24"> for successor. Where a modern presentation might write <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24Sa%24"> for the successor of the number <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24a%24">, Peano writes “<img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24a%20%2b%201%24">”.</p> <p>So his version of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%28ii%29%24"> looks like this:</p> <p>$$ a + (b + 1) = (a + b) + 1 $$</p> <p>which is pretty much a symbol-for-symbol translation of <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%28ii%29%24">. But if we try to translate <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%28i%27%29%24"> similarly, it looks like this:</p> <p>$$ a + 1 = a + 1 $$</p> <p>That's why Peano didn't include it: to him, it was tautological.</p> <p>But to modern eyes that last formula is deceptive because it equivocates between the "<img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%2b%201%24">" notation that is being used to represent the successor operation (on the right) and the addition operation that Peano is trying to define (on the left). In a modern presentation, we are careful to distinguish between our formal symbol for a successor, and our definition of the addition operation. </p> <p>Peano, working pre-Frege and pre-Hilbert, doesn't have the same concept of what this means. To Peano, constructing the successor of a number, and adding a number to the constant <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%24">, are the <em>same</em> operation: the successor operation <em>is</em> just adding <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%241%24">.</p> <p>But to us, <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24Sa%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24a%2bS0%24"> are different operations that happen to yield the same value. To us, the successor operation is a purely abstract or formal symbol manipulation (“stick an <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24S%24"> on the front”). The fact that it also has an arithmetic interpretation, related to addition, appears only once we contemplate the theorem $$\forall a. a + S0 = Sa.$$ There is nothing like this in Peano.</p> <p>It's things like this that make it tricky to read older mathematics books. There are deep philosophical differences about what is being done and why, and they are not usually explicit.</p> <p>Another example: in the 19th century, the abstract presentation of group theory had not yet been invented. The phrase “group” was understood to be short for “group of permutations”, and the important property was <em>closure</em>, specifically closure under composition of permutations. In a 20th century abstract presentation, the closure property is usually passed over without comment. In a modern view, the notation <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24G_1%5ccup%20G_2%24"> is not even meaningful, because groups are not sets and you cannot just mix together two sets of group elements without also specifying how to extend the binary operation, perhaps via a free product or something. In the 19th century, <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24G_1%5ccup%20G_2%24"> is perfectly ordinary, because <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24G_1%24"> and <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24G_2%24"> are just sets of permutations. One can then ask whether that set is a group — that is, whether it is closed under composition of permutations — and if not, what is the smallest group that contains it.</p> <p>It's something like a foreign language of a foreign culture. You can try to translate the words, but the underlying ideas may not be the same.</p> <h3>Addendum 20250326</h3> <p>Simon Tatham reminds me that Peano's equivocation has come up here before. <a href="https://blog.plover.com/math/se/2023-10.html#addition-with-successor">I previously discussed</a> a Math SE post <a href="https://math.stackexchange.com/q/4795154">in which OP was confused</a> because Bertrand Russell's presentation of the Peano axioms similarly used the notation “<img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24%2b%201%24">” for the successor operation, and did not understand why it was not tautological.</p> https://blog.plover.com/2025/03/18#lunar-baseball <p>We want to adapt baseball to be played on the moon. Is there any way to make it work?</p> <p>My first impression is: no, for several reasons.</p> <p>The pitched ball will go a little faster (no air resistance) but breaking balls are impossible (ditto). So the batter will find it easier to get a solid hit. We can't fix this by moving the plate closer to the pitcher's rubber; that would expose both batter and pitcher to unacceptable danger. I think we also can't fix it by making the plate much wider.</p> <p>Once the batter hits the ball, it will go a long long way, six times as far as a batted ball on Earth. In order for every hit to not be a home run, the outfield fence will have to be about six times as far way, so the outfield will be <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%2436%24"> times as large. I don't think the outfielders can move six times as fast to catch up to it. Perhaps if there were 100 outfielders instead of only three?</p> <p>Fielding the ball will be more difficult. Note that even though the vacuum prevents the <em>pitch</em> from breaking, the batted ball can still take unexpected hops off the ground.</p> <p>Having gotten hold of the ball, the outfielder will then need to throw it back to the infield. They will be able to throw it that far, but they probably won't be able do it accurately enough for the receiving fielder to make the play at the base. More likely the outfielder will throw it wild.</p> <p>I don't think this can be easily salvaged. People do love home runs, but I don't think they would love this. Games are too long already.</p> <p>Well, here's a thought. What if instead of four bases, arranged in a <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%2490%24">-foot square, we had, I don't know, eight or ten, maybe <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24200%24"> or <img src="https://chart.apis.google.com/chart?chf=bg,s,00000000&amp;cht=tx&amp;chl=%24300%24"> feet apart? More opportunities for outs on the basepaths, and also the middle bases would not be so far from the outfield. Instead of throwing directly to the infield, the outfielders would have a relay system where one outfielder would throw to another that was farther in, and perhaps one more, before reaching the infield. That might be pretty cool.</p> <p>I think it's not easy to run fast on the Moon. On the Earth, a runner's feet are pushing against the ground many times each second. On the Moon, the runner is taking big leaps. They may only get in one-sixth as many steps over the same distance, which would give them much less opportunity to convert muscle energy into velocity. (Somewhat countervailing, though: no air resistance.) Runners would have to train specially to be able to leap accurately to the bases. Under standard rules, a runner who overshoots the base will land off the basepaths and be automatically out.</p> <p>So we might expect to see the runner bounding toward first base. Then one of the thirty or so far-left fielders would get the ball, relay it to the middle-left fielder and then the near-left fielder who would make the throw back to first. The throw would be inaccurate because it has to traverse a very large infield, and the first baseman would have to go chasing after it and pick it up from foul territory. He can't get back to first base quickly enough, but that's okay, the pitcher has bounded over from the mound and is waiting near first base to make the force play. Maybe the runner isn't there yet because one of his leaps was too <em>long</em> and to take another he has to jump high into the air and come down again.</p> <p>It would work better than Quiddich, anyway.</p>