Monthly Archives: June 2023

Good riddance to rubbish writing

Posted on by

In Gen Z never learned cursive. The effects of this are more widespread than you think (which references an October 2022 Atlantic article, Gen Z Never Learned To Read Cursive), the author describes the potential effects of discontinuing cursive writing instruction. In truth, the first article mentioned just expands a bit on one or two of the points made in the Atlantic article.

A note before I continue. Cursive is actually any form of connected writing. What most Americans refer to as “cursive” is the Palmer Method script that was introduced in the early 20th century, that most of us learned to fear and loathe, and many of us (myself included) can’t write legibly today. In the text below, I use “cursive” to mean that Palmer Method and its variants.

The Palmer Method, by the way, is a refinement of the Spencerian Method of writing that was introduced in the 1840s. Both are teaching a method of writing that’s optimized for 17th century pens. A primary consideration is keeping the pen on the paper because every time the pen was lifted and then placed back onto the paper, the ink tended to blot. These methods go to sometimes absurd lengths to keep the pen on the paper, even when doing so is less than optimum. The introduction of the inexpensive mass-produced ball point pen eliminated the ink blotting problem and thus the necessity to always keep the pen on the paper. But the script lives on.

The big complaint about no longer teaching cursive is that “the past is presented to us indirectly.” That is, because historical documents are written in script that students aren’t taught to read and write, they have to depend on transcription if they want to read the documents. There’s also some complaint that kids won’t be able to read letters from grandma.

And it’s true: without instruction and practice, cursive writing is difficult or impossible to read. Fortunately, it takes about a week to learn how to read it. Maybe a bit of practice after that, but if a child knows how to read block printing, learning to read the cursive script that’s been the mainstay of elementary writing instruction for a century is very easy.

In addition, the cursive script that’s been taught since the early 1900s isn’t even the same script that was used in our founding documents. The Declaration of Independence, perhaps the most oft-cited historical document cited in this argument, was written in Round hand, a script that originated in England in the 17th century. Learning to read modern cursive writing certainly helps in reading that document, but it still requires a bit more puzzling out.

Point is, the important historical documents all have been rendered in a typewritten font. There’s little or nothing to be gained for most people in reading the originals. There’s the incredibly weak argument that scholars will have to be taught cursive like they’re taught Elizabethan, Medieval, or ancient Cuneiform script. My response is, “duh.” Digging deeply into the past requires specialized skills. The ability to read cursive today is just a little bit more important than knowing how to hitch a horse to a buggy.

The “past is presented indirectly” argument for learning cursive writing just doesn’t fly. It’s as relevant to day-to-day life as the idiotic argument that those who can’t drive a car with manual transmission are somehow not “real” drivers. Ranks right up there with the, “when I was a boy, we had to trudge through three feet of snow, in the dark, uphill both ways to use the bathroom” stories we laugh about.

To be fair, there are benefits of learning cursive. First, it’s much faster than block printing, and there is that ability to read letters from grandma. It helps in developing fine motor skills, and studies show that students with dyslexia find learning cursive helps with the decoding process. However, people with dysgraphia are hindered by being forced to write in cursive.

Although I haven’t had to depend on my ability to write in cursive for at least 40 years, I do agree that many people must be able to write legibly and more quickly than they can with just block printing. But we should be teaching kids a different method. There are other connected writing systems that are easier to learn, faster, and easier to write legibly than the antiquated loopy Palmer Method that was designed 100 years ago for writing with a quill pen: a technology that was obsolete before the Palmer Method was introduced. (The ball point pen was invented in the 1880s.) For example, Getty-Dubay Italic, introduced in 1976, is much easier to read and write, and doesn’t require the loops and other forms that were necessary in older scripts to prevent the ink from blotting. There are other, similar, writing styles that are optimized for today’s writing instruments.

Whether those newer methods carry with them the benefits of developing fine motor skills and assistance to dyslexic students is an open question. I think it likely. I also suspect that it would have less of a negative impact on those with dysgraphia because the letter forms are so similar to the printed letter forms. As for letters from grandma, that’s becoming irrelevant, too. At 62, I’m older than a lot of grandmas and I’ll tell you from experience that a lot of them write cursive as well and as often as I do: illegibly and almost never. Letters from grandma that are written in cursive will pretty much cease to exist in my lifetime.

It’s true that trying to write those modern scripts using a 17th century quill pen would be as disastrous as taking a horse and buggy on an Interstate highway. Sometimes you have to discard old things and embrace the unquestionable benefits of new technology. Unless you like having to check for black widow spiders after trudging through the snow to the outhouse.

Translation difficulties

Posted on by

I get it: translation is hard. Heck, I’m a reasonably bright native English speaker and often have difficulty translating my own thoughts into understandable English.

This is a message that was posted in a woodcarving group:

“Hello, I am writing a message to help my father. And I see myself. Only on the American or Canadian woodcarving site and no response. It’s just for the books. And politeness. It’s when it’s repetitive that it’s not funny. But you how many millions to be connected. I find that very embarrassing. Administrators must take their jobs seriously. I have already reported them, I pass the imfermire contest as if I was going to sew up a person at any time, have a nice day everyone.”

The author’s native language is, I think, Italian. Or perhaps French. I suspect not an English speaker, although it’s possible that his grasp of English is better than my grasp of his native language. I cannot tell if the message is the result of automatic translation, or if the author did the translation himself with the help of a Italian-to-English dictionary. Either way, I cannot make any sense of it.

Which is weird. I’ve seen bad translations before. But usually I can get the gist of a message that’s been automatically translated: a “hook” that gives me a broad idea, and from there puzzle out a few details. For example, the word “imfermire” in the above text looked promising. It looks like a misspelling of the Italian word “infermiere,” meaning “nurse.” The best I can guess is that the author is having trouble getting some woodcarving books for his father. Not sure where the nurse comes in.

The author’s responses to comments provide no useful information. Which isn’t too much of a surprise. I imagine he has to translate the question, then write and translate a response. The combined errors inherent in that process aren’t conducive to understanding. Automatic translation software is especially bad at round-tripping because errors accumulate very quickly.

Can the technology that powers the new crop of generative AIs be put to good use in the automatic translation space? I imagine feeding an Italian-to-English translation to a tool that can leverage its knowledge of translation errors and spit out a short and meaningful summary. Is such a tool within our grasp?

Ask an AI: whittling or wood carving?

Posted on by

A friend of mine asked a generative AI (Nova: Powered by ChatGPT & GPT 3.5 Turbo) about the difference between whittling and wood carving. This is the response she got:

Wood carving and whittling have been practised for thousands of years, dating back to ancient civilizations such as the Egyptians and Greeks. The early humans used wood carving to make various objects like weapons, tools, utensils, and figurines.

It is believed that the practice of carving wood began as an extension of the use of stone tools, as people realized that wood was a more versatile material than stone. Over time, wood carving became a widely practiced art form, with artisans developing diverse styles and techniques.

Whittling, on the other hand, is a type of wood carving that involves using a knife to remove a small amount of wood from a larger piece. It is believed to have originated in Europe during the Middle Ages, where it was primarily used to make simple household objects like wooden spoons, bowls, and cups.

Whittling gained popularity in the United States during the 18th and 19th centuries, when it became a popular hobby for colonists and pioneers. Today, wood carving and whittling remain popular artistic expressions, and practitioners continue to develop new styles, techniques, and forms.

This reminds me of something a not-very-bright fourth grader would turn in after consulting the encyclopedia and visiting the local branch library. Bad paraphrasing of randomly selected factual (or maybe not) statements strung together into paragraphs that are tenuously cohesive and sometimes self-contradictory. With a little fluff thrown in to show that it really was the student’s work. The student would receive a “C” for such work if the teacher were especially kind and impressed with the diligent research, good spelling (although there’s that curious use of “practised” rather than “practiced”), and penmanship.

That said, the article does answer the question: whittling is a type of wood carving. The rest of the article is mostly gibberish, sprinkled as it is with unsupported factual statements, uninformed speculation, and known falsehoods. But whittling really is a type of wood carving.

Exactly what constitutes whittling is an open question. Merriam-Webster defines “whittle” as a transitive verb:

1a. to pare or cut off chips from the surface of (wood) with a knife
1b. to shape or form by so paring or cutting
2.  to reduce, remove, or destroy gradually as if by cutting off bits with a knife

By that definition, whittling is wood carving done with a knife. If you are carving wood with a knife, you are whittling. According to the dictionary. But that definition is not universally accepted. If you ask five wood carvers the difference, you’re going to get at least five answers. In my experience, most of those answers are of the “I know it when I see it” variety. Some say that it has to do with the level of planning involved. But everybody’s line is set differently. To some, anything more complex than a sharpened stick is “carving.” To others, anything carved from a stick found on the ground is “whittling.” Some put a time limit on it. Others base their judgement on the quality or purpose of the final product. My primitive carved knives and forks might be “whittling,” for example, but my friend’s beautifully carved and decorated (all using just a knife) replica dagger is a “carving.”

I like the dictionary definition. All the other definitions implicitly and sometimes not so implicitly make value judgements that amount to “whittling is just passing time, whereas carving is creating something of value.”

In any case, I’d be interested to know if anybody would find the AI-generated response to be anything other than gibberish. Elementary and secondary educators should be exposing students to this type of answer and pointing out the obvious flaws (unsupported and contradictory statements, wandering paragraphs, etc.) so that students can learn to spot them. It’ll be a while (decades, at least) before these generative AIs can write a freshman term paper that would get past an instructor who’s paying attention. It’s probably a good idea to be able to spot AI-generated content so you don’t make the mistake of depending on it.