The Universe of Discourse

A descriptive theory of seasons in the Mid-Atlantic

[ 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. ]

The canonical division of the year into seasons in the northern temperate zone goes something like this:

• Spring: March 21 – June 21
• Summer: June 21 – September 21
• Autumn: September 21 – December 21
• Winter: December 21 – March 21

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.

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.

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.

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.

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.

So my first cut would look something like this:

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 beginning of winter, which I just find perplexing. December 1 is not the very coldest part of winter, but it certainly isn't autumn.

There is something to be said for it though. I think I can distinguish several subseasons — ten in fact:

Dominus Seasonal Calendar

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 every year and I wonder why they never seem to catch on.)

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.

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!

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.

However

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.

[Other articles in category /calendar] permanent link

Claude and I write a utility program

Then I had two problems…

A few days ago I got angry at xargs for the hundredth time, because for me xargs 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 /tmp and I wanted to use GPG to encrypt some of them, something like this:

    gpg -ac $(ls *.pdf | menupick)

menupick 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 the shell sucks. Also because gpg probably only does one file at a time.

I could have done it this way:

    ls *.pdf | menupick | while read f; do gpg -ac "$f"; done

but that's a lot to type. I thought “aha, I'll use xargs.” Then I had two problems.

    ls *.pdf | menupick | xargs gpg -ac

This doesn't work because xargs wants to batch up the inputs to run as few instances of gpg as possible, and gpg only does one file at a time. I glanced at the xargs 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.

I think now that I needed -n 1 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 xargs 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.

(In hindsight I should perhaps have looked to see if gpg's --multifile 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.)

xar is a worse version of xargs, but worse is better (for me)

First I wrote a comment that specified the scope of the project:

    # 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

There! It will do one thing well, as Brian and Rob commanded us in the Beginning Times.

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.)

The result was this:

    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)

Short, clean, simple, easy to use. I called it xar, ran

    ls *.pdf | menupick | xar gpg -ac

and was content.

Now again, with Claude

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 xar 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.

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.

On the whole it went extremely well. The complete transcript is here. 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.

Phase 1

First I just told Claude what I wanted and let it write the program from scratch.

Let's write a program in Python called xar. It will be a stripped-down version of the standard Unix xargs utility, but it will do less and be simpler to use.

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.

Any questions?

Default Claude is very chatty and I am going to omit most of its chatty comments, which make me impatient.

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.

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.

Here's Claude's initial version:

    #!/usr/bin/env python3

    import sys
    import subprocess
    import shlex

    def main():
        if len(sys.argv) < 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()

Claude's version had numerous comments, which I have omitted. I later told it to stop putting in comments, which it did.

Claude's use of check here was not what I wanted, because that makes subprocess.run 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:

        res = subprocess.run(substitute_percents(command, filename), check=False)
        return res.returncode == 0

        …

        if not run_command_with_filename(template, line):
            ok = False

Claude's program pulled in shlex without noticing that it was unused. But Claude did teach me about str.rstrip('\n') which I had not known about before (or maybe had forgotten), so that was one small win already.

Argument parsing

The next step was a big win. Python's library for command-line argument handling is called argparse and it is really nice. If I were still writing programs in Perl, I would implement a Perl version of argparse because Perl has 29 available argument parsing libraries and they are all loathsome. The one problem with argparse is I never remember off the top of my head how to use it. I think the module is called argparse but it provides a class called Argparser but I often get these backward and try to use argparser and Argparse.

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.

But this time I didn't have to do that. Instead, I just said to Claude:

This is good, now please add code at the top to handle argument parsing with the standard Argparse library, even though there are no options yet.

Claude handed me back pretty much the same program, but with the argument parser at the top:

    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()

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.

I make some changes

It bothered me that the command-line arguments were being taken implicitly from sys.argv; 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 main function, and then for the runtime to call main(sys.argv[1:]) instead of just main(). That way you can test the program without having to fake up sys.argv. 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:

Good so far. I have adjusted your source code in several ways:

1. I removed the comments.
2. I removed the exception handling for the subcommand. If one of the subcommands fails, that no longer terminates the main loop
3. Command-line arguments are passed to the main() function rather than being accessed directly

Here is the code. Tell me if you see any problems or if you have any questions about it

I had also sabotaged the code with at least one likely error. Python's subprocess.run 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 result.exitcode, which I handed off to Claude even though I thought was probably wrong.

Claude's reply said:

Here are a couple of issues I noticed:

There's an error in the error handling code - you're using result.exitcode but in the subprocess.run() function, the attribute is called returncode not exitcode

Awesome, now I don't have to remember that name of that component.

Claude continued:

The parse_arguments() function definition is missing in the pasted code, but it would need to be updated to accept the argv parameter

I had passed sys.argv[1:] to main, and then had main call parse_arguments(argv). But I hadn't changed parse_arguments 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:

    #!/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)

Handling NUL-separated values

I said

It's great, thanks for catching those errors. Now let's add a -0 command-line option that tells the program to split the input on "\0" characters instead of at line breaks.

Recall that my handwritten xar did not do this yet; I had left that feature for another day. Claude just added it for me, adding

    parser.add_argument(
        "-0", "--null",
        action="store_true",
        help="Input items are terminated by a null character instead of by newline"
    )

to the argument parser and changing the main loop to:

    # 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

        …

I was tired of Claude's comments, so I said

Give me the same thing, with no comments

which it did, so I said

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.

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.

Template filling

Now I told Claude to add the % feature:

I changed if not item to if item == "". Now let's make the following change:

• If the command template includes any % characters, each of these should be replaced with the input item.
• Otherwise, if there were no % characters, the input item should be appended to the end of the command as in the current version

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:

    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)

Even without the list comprehension, I would have factored out the common 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)

But I am not going to complain, my code is simpler but is doing unnecessary work.

Claude also took my hint to change item == "" even though I didn't explicitly tell it to change that.

At this point the main loop of the main function was 15 lines long, because Claude had stuck all the %-processing inline. So I said:

Good, let's extract the command template processing into a subroutine.

It did this right, understanding correctly what code I was referring to and extracting it into a subroutine called process_command_template. More science fiction: I can say "command template processing" and it guesses what I had in mind!

This cut the main loop to 7 lines. That worked so well I tried it again:

Good, now let's extract the part of main that processes stdin into a subroutine that returns the items array

It pulled the correct code into a function called process_stdin. It did not make the novice mistake of passing the entire args structure to this function. In the caller it had process_stdin(args.null) and inside of process_stdin this parameter was named use_null_delimiter,

YAGNI?

At this point I was satisfied but I thought I might as well ask if it should do something else before we concluded:

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 xargs which is very complicated.

Claude had four suggestions:

1. A -p or --parallel option to run commands in parallel

2. A -n or --max-args option to specify the maximum number of items to pass per command

3. A simple -v or --verbose flag to show commands as they're executed

4. A way to replace the command's standard input with the item instead of adding it as an argument

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.)

Parallelization

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

    $workers{spawn()} = 1 while delete $workers{wait()};

where the workers hash maps process IDs to dummy values. A child exits, wait() awakens and returns the process ID of the completed child, which is then deleted from the map, and the loop starts another worker.

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:

   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

What's so great about this? What's great is that I hadn't known about concurrent.futures or ProcessPoolExecutor. 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.

If someone had asked me to write the --parallel option, I would have had to have this conversation with myself:

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.”

When I put all that uncertainty on a balance, and weigh it against the known costs of doing it myself, which one wins?

The right choice is: I should do the research, find the good module (A1, not F6), and figure out how to use it.

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.

Let me repeat, it is quicker to do it myself. But that is still the wrong choice.

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 today. 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 other programmer on the project — including perhaps myself six months later — so would be the wrong thing to use.

I'm really good at hacking this stuff up. Which is a problem. It makes me want to hack stuff up, even when I shouldn't.

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.

And now I know about concurrent.futures.ProcessPoolExecutor! 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 this one. That is valuable knowledge.

Claude flubs

While testing the program I did

    xar --parallel=2 bash -c '...'

which didn't work because the argparse library tried to parse the -c as a flag to xar, when I wanted it to be a flag to bash. This was my fault, and there is a standard way around it, which is that I should have said

    xar --parallel=2 -- bash -c '...'

which tells argparse to drop the -- and take everything after it literally with no interpretation.

I thought I'd see what Claude had to say about this, and it dropped the ball in a very LLM sort of way.

I asked:

When I did xar --parallel=2 bash -c '...' it misunderstood the arguments. It thought I was trying to pass -c to xar and failed with unrecognized arguments. What should I do about that?

Claude replied:

There are two main approaches to handle this:

1. Use the -- separator to indicate the end of arguments for xar: …
2. Modify your code to handle this case specifically by looking for a command terminator in the argument parser.

Here's how you could modify your code to implement the first approach:

And then it followed with the same, unmodified code…

Which was correct, because -- is already handled by argparse, so no change was actually required to implement the first approach! But Claude's characterization of it as a modification was misleading, wrong, and potentially very confusing.

I said:

I don't see what the difference is in that argument parsing code as compared to what I had before.

and Claude got into the LLM tail-chasing mode where it got more and more confused:

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.

To fix the issue with xar --parallel=2 bash -c '...', you need to actually implement support for the -- separator in your 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: …

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 -- separator” is flat wrong. I pointed this out and Claude got more confused. Oh well, nobody is perfect!

Lessons learned

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. (I wrote an article about the surprising reasons to use the syntax coloring.)

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.

Claude's code is good enough, but it is not a magic oracle

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.

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.

I did not notice any mistakes on Claude's part — at least this time.

At one point my testing turned up what appeared to be a bug, but it was not. The testing was still time well-spent.

Claude remembers the manual better than I do

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.

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 bash manual. This time I just asked in plain English “What's the bash option that tells the script to abort if a command fails?” Claude told me, and we went back to what we were doing.

Claude can talk about code with me, at least small pieces

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.

When I told Claude to stop commenting every line, it did. I wonder, if I had told it to use if not expr only for Boolean expressions, would it have complied? Perhaps, at least for a while.

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

     parser.add_argument(
        "-p", "--parallel",
        nargs="?",
        const=5,
        type=int,
        default=1,
        help="Run up to N commands in parallel (default: 5)"
    )

Wait, I said, I know what the const=5 is doing, that's so that if you have --parallel with no number it defaults to 5. But what is the --default doing here? I just asked Claude and it told me: that's used if there is no --parallel flag at all.

This was much easier than it would have been for me to pick over the argparse manual to figure out how to do this in the first place.

More thoughts

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.

I don't know how well it will work for larger systems. Possibly pretty well if 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.

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!

Will my programming skill atrophy?

Folks at Recurse Center were discussing this question.

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.

Starting decades ago I have repeatedly told people

You cannot just paste code with no understanding of what is going on and expect it to work.

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?

Will I lose anything from having Claude write that complex parser.add_argument call for me? Perhaps if I had figured it out on my own, on future occasions I would have remembered the const=5 and default=1 specifications and how they interacted. Perhaps.

But I suspect that I have figured it out on my own in the past, more than once, and it didn't 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.

The biggest win Claude gave me was that I didn't know about this ProcessPoolExecutor thing before, and now I do. That is going to make me a better 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.

My skill at writing ad-hoc process pool managers might atrophy, but if it does, that is good. 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.

Conclusion

This works.

Perfectly? No, it's technology, technology never works perfectly. Have you ever used a computer?

Will it introduce new problems? Probably, it's new technology, and new technology always introduces new problems.

But is it better than what we had before? Definitely.

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.

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.

Because it works.

[Other articles in category /tech/gpt] permanent link

A puzzle about balancing test tubes in a centrifuge

!!\def\nk#1#2{\left\langle{#1 \atop #2}\right\rangle} \def\dd#1{\nk{12}{#1}} !!

Suppose a centrifuge has !!n!! slots, arranged in a circle around the center, and we have !!k!! test tubes we wish to place into the slots. If the tubes are not arranged symmetrically around the center, the centrifuge will explode.

(By "arranged symmetrically around the center, I mean that if the center is at !!(0,0)!!, then the sum of the positions of the tubes must also be at !!(0,0)!!.)

Let's consider the example of !!n=12!!. Clearly we can arrange !!2!!, !!3!!, !!4!!, or !!6!! tubes symmetrically:

Equally clearly we can't arrange only !!1!!. Also it's easy to see we can do !!k!! tubes if and only if we can also do !!n-k!! tubes, which rules out !!n=12, k=11!!.

From now on I will write !!\nk nk!! to mean the problem of balancing !!k!! tubes in a centrifuge with !!n!! slots. So !!\dd 2, \dd 3, \dd 4, !! and !!\dd 6!! are possible, and !!\dd 1!! and !!\dd{11}!! are not. And !!\nk nk!! is solvable if and only if !!\nk n{n-k}!! is.

It's perhaps a little surprising that !!\dd7!! 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 !!\dd3!! and !!\dd4!!, easy.” But that doesn't work because two groups of the form !!3i+j!! and !!4i+j!! always overlap.

For example, if your group of !!4!! is the slots !!0, 3, 6, 9!! then you can't also have your group of !!3!! be !!1, 5, 9!!, because slot !!9!! already has a tube in it.

The other balanced groups of !!3!! are blocked in the same way. You cannot solve the puzzle with !!7=3+4!!; you have to do !!7=3+2+2!! as below left. The best way to approach this is to do !!\dd5!!, 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 !!\dd5!! into !!\dd{12-5}=\dd7!!.

Given !!n!! and !!k!!, how can we decide whether the centrifuge can be safely packed?

Clearly you can solve !!\nk nk!! when !!n!! is a multiple of !!k>1!!, but the example of !!\dd5!! (or !!\dd7!!) shows this isn't a necessary condition.

A generalization of this is that !!\nk nk!! is always solvable if !!\gcd(n,k) > 1!! since you can easily balance !!g = \gcd(n, k)!! tubes at positions !!0, \frac ng, \frac{2n}g, \dots, \frac {(g-1)n}g!!, then do another !!g!! tubes one position over, and so on. For example, to do !!\dd8!! you just put first four tubes in slots !!0, 3, 6, 9!! and the next four one position over, in slots !!1, 4, 7, 10!!.

An interesting counterexample is that the strategy for !!\dd7!!, where we did !!7=3+2+2!!, cannot be extended to !!\nk{14}9!!. One would want to do !!k=7+2!!, but there is no way to arrange the tubes so that the group of !!2!! doesn't conflict with the group of !!7!!, which blocks one slot from every pair.

But we can see that this must be true without even considering the geometry. !!\nk{14}9!! is the reverse of !!\nk{14}{14-9} = \nk{14}5!!, which impossible: the only nontrivial divisors of !!n=14!! are !!2!! and !!7!!, so !!k!! must be a sum of !!2!!s and !!7!!s, and !!5!! is not.

You can't fit !!k=3+5=8!! tubes when !!n=15!!, but again the reason is a bit tricky. When I looked at !!8!! directly, I did a case analysis to make sure that the !!3!!-group and the !!5!!-group would always conflict. But again there was an easier was to see this: !!8=15-7!! and !!7!! clearly won't work, as !!7!! is not a sum of !!3!!s and !!5!!s. I wonder if there's an example where both !!k!! and !!n-k!! are not obvious?

For !!n=20!!, every !!k!! works except !!k=3,17!! and the always-impossible !!k=1,19!!.

What's the answer in general? I don't know.

Addenda

20250502

Now I am amusing myself thinking about the perversity of a centrifuge with a prime number of slots, say !!13!!. If you use it at all, you must fill every slot. I hope you like explosions!

While I did not explode any centrifuges in university chemistry, I did once explode an expensive Liebig condenser.

Condenser setup by Mario Link from an original image by Arlen on Flickr. Licensed cc-by-2.0, provided via Wikimedia Commons.

20250503

• Michael Lugo informs me that a complete solution may be found on Matt Baker's math blog. I have not yet looked at this myself.

• Omar Antolín points out an important consideration I missed: it may be necessary to subtract polygons. Consider !!\nk{30}6!!. This is obviously possible since !!6\mid 30!!. But there is a more interesting solution. We can add the pentagon !!{0, 6, 12, 18, 24}!! to the digons !!{5, 20}!! and !!{10, 25}!! to obtain the solution $${0,5,6,10,12,18, 20, 24, 25}.$$

  Then from this we can subtract the triangle !!{0, 10, 20}!! to obtain $${5, 6, 12, 18, 24, 25},$$ a solution to !!\nk{30}6!! which is not a sum of regular polygons:

  

• Thanks to Dave Long for pointing out a small but significant error, which I have corrected.

20250505

• Robin Houston points out this video, The centrifuge Problem with Holly Krieger, on the Numberphile channel.

[Other articles in category /math] permanent link

Proof by insufficient information

Content warning: rambly

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 Heron's formula to compute the area from that.

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, because there is not enough information:

These three quadrilaterals have the same vertices, but different areas. Just knowing the vertices is not enough; you also need their order.

I suppose one could abstract this: Let !!f!! be the function that maps the set of vertices to the area of the quadrilateral. Can we calculate values of !!f!!? No, because there is no such !!f!!, it is not well-defined.

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:

Let !!ε!! be the smallest [real / rational] number strictly greater than !!0!!…

which appears on Math SE quite frequently. Another one I remember is someone who asked about the volume of a polyhedron with exactly five faces, all triangles. 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.

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.

Anyway, I'm digressing. The interesting part of the quadrilateral thing, to me, is not so much that !!f!! doesn't exist, but the specific reasoning that demonstrates that it can't 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.

There is a proof, the so-called “information-theoretic proof”, that a comparison sorting algorithm takes at least !!O(n\log n)!! time, based on comparing the amount of information gathered from the comparisons (one bit each) with that required to distinguish all !!n! !! possible permutations (!!\log_2 n! \ge n\log_2 n!! 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.

Addenda

20250430

Carl Muckenhoupt suggests that logical independence proofs are of the same sort. He says, for example:

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.

This is just the sort of thing I was looking for.

20250503

Rik Signes has allowed me to reveal that he was the source of the memorable disparagement of Anselm's dumbass argument.

[Other articles in category /math] permanent link

Willie Singletary will you please go now?

(Previously: [1] [2])

Welcome to Philadelphia! We have a lot of political corruption here. I recently wrote about the unusually corrupt Philadelphia Traffic Court, 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:

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.

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:

(Click for uncropped version)

VOTES FOR THIS CANDIDATE WILL NOT BE COUNTED

DEAR VOTERS:

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.

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.

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.

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.

Before that, when he was campaigning for the Traffic Court job, he was caught on video promising to give favorable treatment to campaign donors.

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 "The Parker administration supports every person’s right to a second chance in society.”

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.

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!

Addendum 20250501

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:

Date:   Sat Apr 26 14:24:19 2025 -0400

    Willie Wingletsray finally ready to go

And now, because Git, it's written in stone.

[Other articles in category /politics] permanent link

How our toy octopuses got revenge on a Philadelphia traffic court judge

[ Content warning: possibly amusing, but silly and pointless ]

My wife Lorrie wrote this on 31 January 2013:

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.

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.)

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:

    my $fenchurch = Octopus->new({
                        arms => 8,
                        hearts => 3,
                        favorite_food => "crab cakes"
                    });

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.

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.

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.

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.

“Where are you from?”

“Ohio.”

“Do they have stop signs in Ohio?”

“Uh, yes.”

“Do you know what they look like?”

“Yes.”

“Do they look like the stop signs we have here?”

“Yes.”

“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.”

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.

“What does that thing mean?”

“It doesn't mean anything, it's just an earring.”

“Is that what everyone is doing now?”

“I don't know what everyone is doing.”

“How long ago did you get it?”

“Thirteen years.”

“Huh. … Well, you did have insurance, so I'm dismissing your ticket. You can go.”

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.

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!”

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.

Lorrie continues:

Husband has been following news about this judge (now retired) and his family ever since, and periodically he gives me updates.

(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.)

And we made up a story that Fenchurch was traumatized by this guy after being ticketed for parking in a No Buggy zone.

So today, he was charged with corruption after a three-year FBI probe. The FBI even raided his house

I understood everything when I read that Perri accepted graft in many forms, including shrimp and crab cakes.

OMG. No wonder my little blue octopus was wroth. No wonder he swore revenge. This crooked thief was interfering with his food supply!

Lorrie wrote a followup the next day:

I confess Husband and I spent about 15 minutes last night savoring details about Fortunato N. Perri's FBI bust. Apparently, even he had a twinge of conscience at the sheer quantity of SHRIMP and CRAB CAKES he got from this one strip club owner in return for fixing tickets. (Husband noted that he managed to get over his qualms.)

Husband said Perri hadn't been too 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.

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.

Epilogues

• Later that year, the notoriously corrupt Traffic Court was abolished, its functions transferred to regular Philadelphia Municipal Court.

• In late 2014, four of Perri's Traffic Court colleagues were convicted of federal crimes. They received prison sentences of 18 to 20 months.

• Fortunato Perri himself, by then 78 years old and in poor health, pled guilty, and was sentenced to two years of probation.

• 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 if they had been found guilty.

  The judges in their appeal were not impressed with this argument. See United States v. Hird et al..

• 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.

  (Update 20250426: Willie Singletary, ladies and gentlemen!)

[Other articles in category /law] permanent link

Does someone really have to do the dirty jobs?

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.

And the saying continues: “Iron on Tuesday, mend on Wednesday”. Routine management of clothing takes half of the six-day work week.

For this reason, washing is the work of last resort for the poorest and most marginal people. Widows are washerwomen. Prisons are laundries. Chinese immigrants run laundries. Anyone with enough money to outsource their laundry does so.

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.

“Eskimo child with wooden tub and washboard”, c. 1905, by Frank Hamilton Nowell, public domain, via Wikimedia Commons.

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.

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 without 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.

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?

[Other articles in category /misc] permanent link

The mathematical past is a foreign country

A modern presentation of the Peano axioms looks like this:

1. !!0!! is a natural number
2. If !!n!! is a natural number, then so is the result of appending an !!S!! to the beginning of !!n!!
3. Nothing else is a natural number

This baldly states that zero is a natural number.

I think this is a 20th-century development. In 1889, the natural numbers started at !!1!!, not at !!0!!. Peano's Arithmetices principia, nova methodo exposita (1889) is the source of the Peano axioms and in it Peano starts the natural numbers at !!1!!, not at !!0!!:

There's axiom 1: !!1\in\Bbb N!!. No zero. I think starting at !! 0!! may be a Bourbakism.

In a modern presentation we define addition like this:

$$ \begin{array}{rrl} (i) & a + 0 = & a \\ (ii) & a + Sb = & S(a+b) \end{array} $$

Peano doesn't have zero, so he doesn't need item !!(i)!!. His definition just has !!(ii)!!.

But wait, doesn't his inductive definition need to have a base case? Maybe something like this?

\begin{array}{rrl} (i') & a + 1 = & Sa \\ \end{array}

Nope, Peano has nothing like that. But surely the definition must have a base case? How can Peano get around that?

Well, by modern standards, he cheats!

Peano doesn't have a special notation like !!S!! for successor. Where a modern presentation might write !!Sa!! for the successor of the number !!a!!, Peano writes “!!a + 1!!”.

So his version of !!(ii)!! looks like this:

$$ a + (b + 1) = (a + b) + 1 $$

which is pretty much a symbol-for-symbol translation of !!(ii)!!. But if we try to translate !!(i')!! similarly, it looks like this:

$$ a + 1 = a + 1 $$

That's why Peano didn't include it: to him, it was tautological.

But to modern eyes that last formula is deceptive because it equivocates between the "!!+ 1!!" 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.

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 !!1!!, are the same operation: the successor operation is just adding !!1!!.

But to us, !!Sa!! and !!a+S0!! 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 !!S!! 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.

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.

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 closure, 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 !!G_1\cup G_2!! 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, !!G_1\cup G_2!! is perfectly ordinary, because !!G_1!! and !!G_2!! 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.

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.

Addendum 20250326

Simon Tatham reminds me that Peano's equivocation has come up here before. I previously discussed a Math SE post in which OP was confused because Bertrand Russell's presentation of the Peano axioms similarly used the notation “!!+ 1!!” for the successor operation, and did not understand why it was not tautological.

[Other articles in category /math] permanent link

Baseball on the Moon

We want to adapt baseball to be played on the moon. Is there any way to make it work?

My first impression is: no, for several reasons.

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.

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 !!36!! 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?

Fielding the ball will be more difficult. Note that even though the vacuum prevents the pitch from breaking, the batted ball can still take unexpected hops off the ground.

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.

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.

Well, here's a thought. What if instead of four bases, arranged in a !!90!!-foot square, we had, I don't know, eight or ten, maybe !!200!! or !!300!! 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.

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.

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 long and to take another he has to jump high into the air and come down again.

It would work better than Quiddich, anyway.

[Other articles in category /games] permanent link

Hangeul sign-engraving machine

Last summer I was privileged to visit the glorious Letterpress Museum in Paju Book City, where I spent several hours and took a collection of photos that are probably not of interest to anyone but letterpress geeks, and perhaps not even to them.

Looking back at the photos it's not always clear to me why I took each one. But some of them I can remember. For example, this one:

This is not exactly letterpress. It is a device for engraving lettered signs on thin strips of metal or perhaps plastic. Happily I don't have to spend too much time explaining this because Marcin Wichary has just published an extensively-illustrated article about the Latin-script version. The only thing different about this one is the fonts, which are for writing Korean in Hangeul script rather than English in Latin script.

(Here's my real-quick summary. There is no ink. A stylus goes into the grooves of those brass templates. The stylus is attached with a pantograph to a router bit that rests on the object that the operator wants to engrave. When operator moves the stylus in the template grooves, the router bit follows their motions and engraves matching grooves in the target object. By adjusting the pantograph, one can engrave letters that are larger or smaller than the templates.)

Hangeul has an alphabet of 24 letters, but there's a difficulty in adapting this engraving technique for written Hangeul: The letters aren't written in a simple horizontal row as European languages are. Instead, they are grouped into syllables of two or three letters. For example, consider the consider the Korean word “문어”, pronounced (roughly) "moon-aw". which means “octopus”. This is made up of five letters ㅁㅜㄴㅇㅓ, but as you see they are arranged in two syllables 문 ("moon") and 어 ("aw"). So instead of twenty-four kinds of templates, one for each letter, the Korean set needs one for every possible syllable, and there are thousands of possible syllables.

Unicode gets around this by… sorry, Unicode doesn't get around it, they just allocate eleven thousand codepoints, one for each possible syllable. But for this engraving device, it would be prohibitively expensive to make eleven thousand little templates, then another eleven thousand spares, and impractical to sort and manage them in the shop. Instead there is a clever solution.

Take a look at just one of these templates:

This is not a Hangeul syllable.

Rather, it is five. The upper-right letter in the syllable is the vowel, and the template allows the operator to engrave any of the five vowels

ㅣㅓㅏㅕㅑ

to produce the syllables

잉 엉 앙 영 양

pronounced respectively "ing", "ông", "ang", "yông", and "yang".

Similarly this one can produce six different syllables:

The upper-left part can be used to engrave either of the consonants ㅅ or ㅈ and the upper-right part can be used to engrave any of the vowels ㅣㅓㅏ, to produce the combined set 싱 성 상 징 정 장. I'm not sure why this template doesn't also enable vowels ㅕㅑ as the other one did.

In the picture at top you can see that while the third template can be used to engrave any of the three syllables 송 승 숭 the operator has actually used it to engrave the first of these.

This ingenious mechanism cuts down the required number of templates by perhaps a factor of five, from ten boxes to two.

Addendum 20250325

A great many of the 11,000 Unicode codepoints are for seldom-used syllables that contain four or even five letters, such as 둻. I studied Korean for a while and I think I learned only one with with more than three letters in a syllable: 닭 means “chicken”.

I don't see templates for these syllables in any of my photographs, which probaby accounts for much of the great reduction in templates from the 11,000 possible syllables. But there must have been some way to engrave the syllables with the machine.

Maybe there was a template that had a small four small ㄷsymbols, one in each of the four corners of the template, and another with four ㄹ symbols, and so on? Then the operator could have composed 닭out of bits from four different templates.

[Other articles in category /IT] permanent link

Claude and Merle Miller let me down

Claude

My relationship with Claude has its ups and downs, and I'm still trying to figure out what to use it for and what not. It's great at rewriting my job application cover letters to sound less like an awkward nerd.

Last week I was in the supermarket and decided to try asking it something I've been wondering for a long time:

MJD: What is the song "Mercy Street” about? What is the connection with Anne Sexton? Who is "Mary"?

I thought Claude might do well with this. I had had a conversation with it a while back about Pixies songs, which I was satisfied with. But this time Claude let me down:

Claude: … The "Mary" referenced in the song is likely Mary Gray Staples, who was the name of Sexton's childhood doll. …

(I thought: What? Am I supposed to believe that

Dreaming of the tenderness
The tremble in the hips
Of kissing Mary's lips

is about a doll?)

MJD: Mary Gray Staples is an unusual name for a doll. Are you sure about that?

Claude: You're right to question this - I made an error. Mary Gray was actually Anne Sexton's great-aunt, not the name of her doll. … The doll references in Gabriel's song likely connect to Sexton's imagery in other poems, but Mary specifically refers to her great-aunt.

MJD: I don't remember a doll in Gabriel's song.

Claude: You're absolutely right - I apologize for the error. There isn't actually a reference to a doll in Peter Gabriel's "Mercy Street" lyrics. … The "Mary" referenced in the song is indeed Anne Sexton's great-aunt Mary Gray…

MJD: Are you sure? Wikipedia says that Mary Gray Staples was the birth name of Sexton's mother.

Claude: You're absolutely right, and I apologize for the confusion. …

Claude just flubbed over and over.

I wonder if the grammatical error in “Mary Gray Staples, who was the name of …” is a kind of a tell? Perhaps Claude is fabricating, by stitching together parts of two unrelated sentences that it read somewhere, one with “Mary Gray Staples, who was…” and the other “… was the name of…”? Probably it's not that simple, but the grammatical error is striking.

Anyway, this was very annoying because I tend to remember things like this long past the time when I remember where I heard them. Ten years from now I might remember that Anne Sexton once had a doll with a very weird name.

Merle Miller

A while back I read Merle Miller's book Plain Speaking. It's an edited digest of a series of interviews Miller did with former President Truman in 1962, at his home in Independence, Missouri. The interviews were originally intended to be for a TV series, but when that fell through Miller turned them into a book. In many ways it's a really good book. I enjoyed it a lot, read it at least twice, and a good deal of it stuck in my head.

But I can't recommend it, because it has a terrible flaw. There have been credible accusations that Miller changed some of the things that Truman said, embellished or rephrased many others, that he tarted up Truman's language, and that he made up some conversations entirely.

So now whenever I remember something that I think Truman said, I have to stop and try to remember if it was from Miller. Did Truman really say that it was the worst thing in the world when records were destroyed? I'm sure I read it in Miller, so, uhh… maybe?

Miller recounts a discussion in which Truman says he is pretty sure that President Grant had never read the Constitution. Later, Miller says, he asked Truman if he thought that Nixon had read the Constitution, and reports that Truman's reply was:

I don't know. I don't know. But I'll tell you this. If he has, he doesn't understand it.

Great story! I have often wanted to repeat it. But I don't, because for all I know it never happened.

(I've often thought of this, in years past, and whatever Nixon's faults you could at least wonder what the answer was. Nobody would need to ask this about the current guy, because the answer is so clear.)

Miller, quotes Truman's remarks about Supreme Court Justice Tom Clark, “It isn't so much that he's a bad man. It's just that he's such a dumb son of a bitch.” Did Truman actually say that? Did he just imply it? Did he say anything like it? Uhhh… maybe?

There's a fun anecdote about the White House butler learning to make an Old-fashioned cocktail in the way the Trumans preferred. (The usual recipe involves whiskey, sugar, fresh fruit, and bitters.) After several attempts the butler converged on the Trumans' preferred recipe, of mostly straight bourbon. Hmm, is that something I heard from Merle Miller? I don't remember.

There's a famous story about how Paul Hume, music critic for the Washington Post, savaged an performance of Truman's daughter Margaret, and how Truman sent him an infamous letter, very un-presidential, that supposedly contained the paragraph:

Some day I hope to meet you. When that happens you'll need a new nose, a lot of beef steak for black eyes, and perhaps a supporter below!

Miller reports that he asked Truman about this, and Truman's blunt response: “I said I'd kick his nuts out.” Or so claims Miller, anyway.

I've read Truman's memoirs. Volume I, about the immediate postwar years, is fascinating; Volume II is much less so. They contain many detailed accounts of the intransigence of the Soviets and their foreign minister Vyacheslav Molotov, namesake of the Molotov Cocktail. Probably 95% of what I remember Truman saying is from those memoirs, direct from Truman himself. But some of it must be from Plain Speaking. And I don't know any longer which 5% it is.

As they say, an ice cream sundae with a turd in it isn't 95% ice cream, it's 100% shit. Merle Miller shit in the ice cream sundae of my years of reading of Truman and the Truman administrations.

Now Claude has done the same. And if I let it, Claude will keep doing it to me. Claude caga en la leche.

Addendum

The Truman Library now has the recordings of those interviews available online. I could conceivably listen to them all and find out for myself which things went as Miller said.

So there may yet be a happy ending, thanks to the Wonders of the Internet! I dream of someday going through those interviews and producing an annotated edition of Plain Speaking.

[Other articles in category /tech/gpt] permanent link

Reflector grids

Around here, these metal things are commonly found on streetside utility poles, attached maybe a meter off the ground.

Metal reflector

Plastic reflector

When I first noticed one of these I said “I wonder what the holes are for. Maybe to make it more visible? And what do they do with all the leftover rectangles after they've made one?”

I eventually got a better idea: The little metal rectangles are the primary product, and after they have been die-cut out of the metal sheet, there is this waste material left over with all the holes. Instead of throwing it away someone nails it to a utility pole to make the pole easier to see at night. I felt a bit silly that my first idea had been exactly backwards.

I later learned that only the older ones are made of sheet metal. Newer ones are made of some sort of plastic, maybe polyethylene or vinyl or something, about the same thickness. They look pretty much the same. I can only tell them apart by feeling them.

Still I wondered what the little rectangles had been used for. It turns out that the purpose is this:

That's according to an old Philadelphia Inquirer article, Why yellow grids are on some Philly-area utility poles. (Patricia Madej, Aug. 31, 2019.) But I measured them to make sure. They matched.

The answer came as a bit of a surprise to Jay Lipschutz, 73, of Northeast Philly …

His wife, Ruth, he said, had insisted they’re reflectors for drivers to see. She was right.

Jay, my friend, your wife is smarter than you are. Listen to her.

The article also tells us that the rectangular leftover is called a “grid reflector”. With a little more research I learned that one manufacturer of grid reflectors is Almetek. They cost $3.50 each. Pricey, for something they would have had to throw away. (Here's the old South Philly Review article that put me on to Almetek.)

What kicked off this article was that I was walking around and I saw this similar reflector grid, which felt to me like it was a bit of a farce, like a teenager sneaking into a bar wearing a fake mustache:

Hey, those aren't holes! When I saw this one I wondered for a moment if I was suffering some sort of mental collapse, or if none of the others had had real holes either. But no, they had, and this one really did have fake holes.

(Also, it has been installed sideways. Normally they are oriented as the two above.)

This isn't the first time I have written about ID numbers on utility poles hereabouts.

[Other articles in category /misc] permanent link