More scientific discovery as dreaming and serendipity

Archimedes in his bathtub; Newton under an apple tree. We prefer to see these brief oments of serendipitous inspiration as the engines of mathematical and scientific discovery. It's romantic to think so; and so much more preferable than to harp on the importance of long, hard years of knowledge acquisition and failed or inconclusive experiments.

As Rivka Galchen, for example, has written:

I wonder if we can really teach someone to be a biologist. I mean, sure, we can say, This is what a cell is, and here’s this thing called RNA, and here’s this thing called DNA, and here’s this technique called agarose gel electrophoresis that will separate your DNA and RNA fragments by size — but will teaching really produce the next Charles Darwin or Rachel Carson or Francis Crick? A real scientist follows her own visionary gleam. Penicillin was discovered when Alexander Fleming returned to his messy lab after a long vacation and made sense of a moldy petri dish most people would have thrown out as contaminated. The structure of the benzene ring came to the chemist Friedrich August Kekule after a daydream about a snake biting its own tail. You can’t teach that kind of dreaming. [Emphasis added]

Science as gleams and dreams. It takes only a milligram of skepticism to identify two highly questionable claims here, and only a moment of Googling around to see whether it's justified.

As this archived excerpt from Wikipedia explains, returning to the messy lab was only the first step in "discovering" penicillin, and the "sense" that Fleming made of his mold was rather preliminary:

Fleming recounted that the date of his discovery of penicillin was on the morning of Friday, September 28, 1928. It was a fortuitous accident: in his laboratory in the basement of St. Mary's Hospital in London (now part of Imperial College), Fleming noticed a Petri dish containing Staphylococcus plate culture he mistakenly left open, was contaminated by blue-green mould, which formed a visible growth. There was a halo of inhibited bacterial growth around the mould. Fleming concluded the mould released a substance that repressed the growth and caused lysing of the bacteria. He grew a pure culture and discovered it was a Penicillium mould, now known to be Penicillium notatum. Charles Thom, an American specialist working at the U.S. Department of Agriculture, was the acknowledged expert, and Fleming referred the matter to him. Fleming coined the term "penicillin" to describe the filtrate of a broth culture of the Penicillium mould. Even in these early stages, penicillin was found to be most effective against Gram-positive bacteria, and ineffective against Gram-negative organisms and fungi. He expressed initial optimism that penicillin would be a useful disinfectant, being highly potent with minimal toxicity compared to antiseptics of the day, and noted its laboratory value in the isolation of Bacillus influenzae (now Haemophilus influenzae). After further experiments, Fleming was convinced penicillin could not last long enough in the human body to kill pathogenic bacteria, and stopped studying it after 1931. He restarted clinical trials in 1934, and continued to try to get someone to purify it until 1940. [Emphasis added.]

And as this second Wikipedia excerpt makes clear, the supposed daydream was only a small step in the process--and a highly questionable one at that, with a possible origin in parody. When Kekulé spoke of how he came up with his theory

He said that he had discovered the ring shape of the benzene molecule after having a reverie or day-dream of a snake seizing its own tail (this is a common symbol in many ancient cultures known as the Ouroboros or Endless knot). This vision, he said, came to him after years of studying the nature of carbon-carbon bonds. This was 7 years after he had solved the problem of how carbon atoms could bond to up to four other atoms at the same time. It is curious that a similar, humorous depiction of benzene had appeared in 1886 in the Berichte der Durstigen Chemischen Gesellschaft (Journal of the Thirsty Chemical Society), a parody of the Berichte der Deutschen Chemischen Gesellschaft, only the parody had monkeys seizing each other in a circle, rather than snakes as in Kekulé's anecdote. Some historians have suggested that the parody was a lampoon of the snake anecdote, possibly already well known through oral transmission even if it had not yet appeared in print. (Some others have speculated that Kekulé's story in 1890 was a re-parody of the monkey spoof, and was a mere invention rather than a recollection of an event in his life. [Emphasis added.]

And as the New York Times itself reported over 25 years ago:

[A]t least one historian now believes that Kekule never dreamed the snake dream, and that, in any case, the benzene ring had already been described by other chemists at the time Kekule claimed to have discovered it. That is the conclusion of Dr. John H. Wotiz, a professor of chemistry at Southern Illinois University who has made an exhaustive study of the documents and lore Kekule left to his scientific heirs. [Emphasis added.]

Of course, it takes less than a milligram of skepticism to realize that we shouldn't treat fiction writers like Galchen as our primary sources for the history of science. But when a highly articulate writer repeats, in such a highly visible forum as the New York Times, ideas that are already popular misperceptions, particularly ones that resonate so fully with today's education trend-setters, those misperceptions become all the more convincing, and the misguided practices they foster, all the more entrenched.

Greatly

Most of the messages generated by facilitated communication are about as interesting as ChatGPT. They consist largely of abstract words and earnest bromides. And they lack the analogies, similes, metaphors, and concrete examples that might put flesh on abstract ideas.

But unlike ChatGPT, the authors of facilitated messages are generally human. And humans are perhaps (perhaps!) more susceptible to quirky memes than ChatGPT is. One meme that has insinuated itself into the messages generated (mostly unwittingly) by facilitators is that autistic individuals see the world through a kind of fragmented synesthesia. Another is an idiosyncratic use of certain adverbs --particularly "greatly."

As far as I can tell, the odd use of "greatly", etc., originates with the person facilitating this individual, where it occurs with great frequency, for example:

I greatly decided to use their questions as the basis for this piece.

But it seems to have spread to the facilitated messages of this person:

I need people to greatly understand that autism hampers communication.

Greatly curious, I just prompted ChatGPT with the following:

Write a response about how intelligent you are that sounds like a message generated by facilitated communication.

ChatGPT's reply:

I am so happy to communicate with you! I have many ideas and thoughts that I want to share. Even though I sometimes struggle to find the right words, I know that I have a lot of intelligence and knowledge inside me. With support and encouragement, I am able to express myself and show the world what I am truly capable of. Thank you for taking the time to listen to me and understand the value that I bring to the world.

If ChatGPT eventually picks up on the "greatly" meme, we might eventually get:

I am greatly happy to communicate with you! I have many ideas and thoughts that I tremendously want to share. Even though I sometimes struggle to find the right words, I greatly know that I have a lot of intelligence and knowledge. With support and encouragement, I am able to eagerly express myself and show the world what I am truly capable of. Thank you for taking the time to listen to me and understand the value that I bring to the world.

More on the Special Needs Kids and the Common Core Straightjacket

A bunch of years ago I published a piece in the online Atlantic in which I argue that the Common Core State Standards (CCSS) essentially straightjacket special needs students. Those concerns, as far as I can tell, are as relevant now as they were back then.

Various commenters, however, have objected that the standards are more flexible than I let on.

One commenter, for example, cites the following passage from the Common Core State Standards as allowing "a huge amount of leeway":

Teachers will continue to devise lesson plans and tailor instruction to the individual needs of the students in their classrooms.

The commenter adds: 

The Standards set grade-specific standards but do not define the intervention methods or materials necessary to support students who are well below or well above grade-level expectations. No set of grade-specific standards can fully reflect the great variety in abilities, needs, learning rates, and achievement levels of students in any given classroom. However, the Standards do provide clear signposts along the way to the goal of college and career readiness for all students.

It is also beyond the scope of the Standards to define the full range of supports appropriate for English language learners and for students with special needs. At the same time, all students must have the opportunity to learn and meet the same high standards if they are to access the knowledge and skills necessary in their post–high school lives.

Another commenter writes:

I work with students with significant cognitive and behavioral disabilities at an elementary school in a Common Core state. And I don't recognize the scenario described here. There is no forcing, spoon feeding, lock-stepping, or even much hand-wringing about curriculum. We do the best we can, provide the resources we have to meet the individual needs of the students, enabling their participation in the general curriculum, in the least restrictive environment, to the greatest extent possible. Students have IEPs based on their strengths, needs, and goals, developed in accordance with state and federal guidelines. Maybe things just look different on the ground than from 40, 000 feet. But Common Core just doesn't seem to be a curricular strait-jacket for my students.

Another writes:

The Common Core doesn't preclude in any way the provisions that now exist for individual education plans for special needs students. Those plans can provide for an individual pacing of standards, instructional practices that are best suited for the child involved and assessment mechanisms that are best suited for the child involved. In other words, the Common Core is simply a set of standards that can be applied with all of the flexibility with which any present set of standards can be applied.

None of these people, however, address the specific points I make in my piece:

1. The fact that large numbers of special ed students are mainstreamed into regular classrooms based on calendar age rather than mental age. I.e., if you turned 13 by September 1st and are not so severely intellectually impaired that you spend all your time in a special ed classroom, you attend 8th grade classes even if cognitive testing shows you reading at a 4th grade level.

2. The fact that specific CC standards are pegged to specific grade levels (e.g., 8th grade).

3. The fact that the CCSS names specific sets of texts, including Shakespeare and America's Founding Documents, that all students should read, as well as specific levels of reading passage complexity, exemplified by sample texts (and sample reading assignments) in its well-known Appendix B, and, again pegged to specific grade levels (e.g., 8th grade).

Putting it all together, we have all mainstreamed 13-14-year-olds, even those reading at a 4th grade level, expected to make their way through passages whose complexity matches that of Mark Twain's Tom Sawyer, for example, this one:

Inspired by the splendor of his own act, he took without an outcry the most merciless flaying that even Mr. Dobbins had ever administered; and also received with indifference the added cruelty of a command to remain two hours after school should be dismissed—for he knew who would wait for him outside till his captivity was done, and not count the tedious time as loss, either.

So is it really the case that teachers have "tremendous leeway"?  More importantly, do most teachers perceive that they have tremendous leeway?  Here's how I open my article:

In a discussion board thread on reading comprehension challenges in autism, a special-education teacher commented that her students can’t understand the assigned reading passages. “When I complained, I was told that I could add extra support, but not actually change the passages,” she wrote. “It is truly sad to see my students’ frustration.”

This student isn't alone; she's echoing what I'm hearing from a great many students, most of whom are already teachers of special needs students, many of whom are extremely frustrated by the CC Standards.

Are all of them misinterpreting the Standards?

To some extent, the answer to that question is irrelevant. When large numbers of flesh and blood students are deprived of the developmentally appropriate reading assignments that they depend on in order to maximize their progress in reading, it doesn't matter whether or not this deprivation occurred because of correct or incorrect interpretations of the Common Core Standards. All that matters is that they aren't getting what they need.

Furthermore, there's flexibility and then there's flexibility. Letting teachers decide what reading level is appropriate for their students is one thing; the Common Core does not do this. Instead, it tells them what the reading level has to be and leaves it up to them to somehow figure out what "supports" or "intervention methods" or "materials" will somehow give all students meaningful access to texts at this reading level. This is a very different sort of "flexibility."

Imagine being told: "You need climb this 200 foot cliff, but don't worry, we're giving you all the flexibility you want, because we're not telling you how to do it or providing you with any specific materials."

Of course, some people may simply helicopter their way to the top of the cliff. Likewise, some educators may, as I discuss in my article, essentially give away the answers or otherwise fake their way through things. Or they may convince themselves that students have attained standards when objective, independent testing would reveal otherwise.

But the ultimate problem, the one that trumps all others, is that no amount of "supporting" and "intervening" and "differentiating" and IEP writing makes any difference in the world if the curricula assigned to special needs students doesn't match their levels of developmental readiness.

An inside look at S2C: “We actually discourage them from using their speech while they are spelling”

(Cross-posted at FacilitatedCommunication.org).

I recently came across a curious blog post at Age of Autism. Dating back to 2021, it offers an inside look at Spelling to Communicate (S2C) and at some of its practitioners.

The post’s author, Dara Berger, is the mother of an autistic boy, the author of Preventing Autism, a believer in the (debunked) vaccine injury theory of autism, and an ally of the S2C and vaccine-injury-evangelist, J.B. Handley, whose book, Underestimated: An Autism Miracle, is the basis for the forthcoming S2C-promoting movie Spellers.

As Berger states towards the end of her post:

My experience is not meant to dissuade anyone from doing S2C.  I am elated for all the children and adults it has helped and will continue to.  There is nothing sweeter than to hear a person who previously could not communicate has now found a way to get their voice heard.  I encourage everyone to look into it and read JB Handley’s book.

But Berger’s own experience with S2C was not so positive.

Her autistic son, a homeschooled sophomore, is able to speak. He also “has great print and cursive penmanship.” His linguistic limitations are, rather, in his ability to initiate conversations.

My son already spoke but there was no initiation of language.  This means he can answer questions all day long but will not initiate language on his own.

Given her son’s oral and written strengths, why did Berger turn to S2C? Indeed, some of the commenters on her post raise precisely this question.

The answer is that Berger thought that S2C would address her son’s weakness in verbal initiation. And while she does not explain where this impression came from, a quick look S2C’s main website, Growing Kids Therapy Center, (GKTC) is suggestive.

The clients that GKTC advertises itself as serving include those who are “minimally speaking.” A minimally speaking person, per GKTC, is one who “may be able to use some speech to produce a number of words or phrases but does not have enough speech for robust and flexible communication.” As GKTC’s FAQ page elaborates, “minimal speech is often used for requesting wants and needs or providing short answers to questions.”

Given this, we can understand why Berger might reasonably have concluded (1) that her son, who, again, “can answer questions all day long but will not initiate language on his own,” qualifies as minimally speaking; (2) that S2C’s goals include developing the “robust and flexible communication” that minimal speakers lack; and (3) that “robust and flexible communication” includes initiating conversations.

In other words, if we set aside these two inconvenient facts:

• S2C lacks empirical validity

• All the available evidence indicates that the communication partners are authoring the typed messages

Berger had good reasons for thinking that S2C would address her son’s needs.

But despite her continued faith in the overall validity of S2C, Berger was dismayed at what she personally experienced.

The first red flag occurred after several months of mostly remote sessions with an S2C practitioner from GKTC:

[M]y son was using a lot more speech in his lessons.  He would answer the questions verbally instead of using the letter board.  Now you can imagine just how excited this made me.  Things were finally paying off I thought. 

To Berger’s surprise, however,

[H]is S2C practitioner did not share the same enthusiasm as me.  In fact, she blew it off and ignored the fact that he was doing this.  Not only that, she pretty much discouraged his speech by ignoring that he said the answer and told me to have him spell it anyway. 

Berger called off the session and expressed her concerns to the S2C practitioner, “Kara” (a pseudonym). Kara, she reports, “kept saying that he just needed to get better at the letter board,” while she “kept insisting this is every parents [sic] dream to hear them answer questions verbally on their own.”

So Berger consulted her son’s SLP. In practice for over 40 years, “Andrew” is “very familiar with letter boarding and one of those very special therapists who actually presumes competence.” Furthermore, Andrew had “recently seen a few young adults go on to college successfully using a keyboard.” Nonetheless, after some careful consideration, Andrew “could not hold back.” He stated that the S2C practitioner was “wrong”; that in cases where her son gave an oral response, “he should not be made to spell it like he did something wrong”. Her son’s oral responses “need[] to be accepted period.”

But when Berger brought this up with Kara, “she blew me off and said this is how we do it and he needs to get better at letter boarding.” Worse, during the session, her son stopped giving oral answers. After all, Berger points out, “Why would he when they were not being accepted anyway.”

Meanwhile, another S2C mother tells her about some “great online classes for spellers,” including such courses as Ancient Civilizations and Cultural Literature. Berger, seeing these as great additions to her home schooling curriculum, signed up right away. As she describes them:

These group classes were set up similar to his individual spelling class in that she reads us a paragraph from a lesson and then gives the students a few questions to answer.  The spelling partner types the child’s answer in the chat area. 

However:

[T]o my surprise Dylan preferred to answer verbally [orally] once again and did so for the entire class.  It was interesting that away from Kara this was his immediate reaction to speak.  I listened to his speech therapist and honored every answer and did NOT make him spell it afterwards.  He did the same thing in the next class we took. 

But then when they took a group class taught by Kara, her son reverted back to spelling without speaking.

Once again, Berger brought up her concerns with Kara:

And lo and behold she had the same reaction as the first time.  But I told her that her answer wasn’t good enough and she had to speak with her boss (who developed the technique).

(That boss would be Elizabeth Vosseller, founder of GKTC and “inventor” of S2C.)

Berger excerpts the long reply she received from Kara, highlighting key points about how speech is not the goal of S2C, how speech is unlikely to be her son’s primary mode of communication, and how

when working with a speller, we actually discourage them from using their speech while they are spelling, because focusing on the motor of pointing to letters while trying to speak is too much motor to focus on at once.

Perhaps most notably, Kara’s message notes how Elizabeth Vosseller herself confirms that:

[S]he too, when a speller in the acquisition phase uses their voice to answer a question, has them spell it, just for practice. "Now let's use your arm!”

In the end, Berger turns to other ways to work on verbal initiation:

We do all kinds of creative writing to help put his thoughts on paper.  His OT has him texting and emailing during sessions to use the keyboard, which he types well on. 

As for S2C:

I don’t know if we will continue with S2C.  It’s hard to go work with another practitioner when I know they all receive the same training from the woman who developed it and will be taught the same as Kara.

We’ve already seen troubling instances where a facilitated person’s spoken words are ignored in favor of what is extracted through FC. What stands out in this case is that the FCed individual seems to have had quite a bit more speech than most S2C clients—enough to be able to speak out answers to questions about ancient history and cultural literature. And yet, because the goal was for him to become a fluent letterboard user, and because his S2C practitioner was certain that his speech would never be as good as his typing would eventually become, that speech was dismissed.

We can guess at the real reasons for that dismissal. It is, after all, much harder (if not impossible) to cue the mostly invisible vocal apparatus involved in speech than to cue a single extended index finger hovering over a keyboard.

A couple of the reader comments at the end of this post are suggestive. Two of them stress the purported motor issues and apraxia that purportedly justify S2C , and how S2C helps “myelinate” motor pathways—a claim confidently made, without a shred of evidence, by S2C proponents.

One commenter writes:

Asking your son to spell his answer rather than say it is not a “punishment”; it’s the goal of S2C... It’s practicing the gross motor required for letter boarding. It’s mylenating [sic] those motor pathways.

Another, making the same spelling mistake, writes:

The motor planning ability required to produce robust, purposeful, open-ended speech on demand is really high. In persons with any degree of apraxia or dyspraxia, the demand can be too high or close to impossible. S2C works to create and mylenate [sic] the motor pathways in the brain that are needed to get robust and reliable communication. Reliable communication is the ultimate goal, NOT speech per se. If regular speech therapy worked, these kids with apraxia would be more verbal and more conversational. Unfortunately it doesn’t always work, and much of the time speech is unreliable and/or inaccessible to the child/adult with apraxia. So again, in S2C you are teaching them a new way to communicate.

On a different note, an SLP in New Hampshire writes:

I have one man who will type anything that comes out of his mouth, regardless of context. It results in nonsensical jargon. When I ask him to suppress his speech, his typed words are eloquent. I then ask him to speak what he typed. I accept any reliable speech. I also see a 13 year old girl whose speech is rote and repetitive. When she types, she speaks each letter before she types it, and then repeats the entire sentence.

Of course, the simplest explanation here is that the SLP is unwittingly cueing her clients—and doing so more successfully when they suppress their speech. Notably, these clients are perfectly capable of producing speech sounds--and of reading the names of the appropriate letters—but only after they’ve likely been cued.

Perhaps the most intriguing comment gives an account of how Elizabeth Vosseller stumbled upon S2C. While there are still traces on the Internet of how Vosseller started out as a student of RPM-founder Soma Mukhopadhyay, something she no longer acknowledges, this is the first time I’ve heard an account of the details (assuming they are reliable). This commenter, an RPM-enthusiast who had her first session with Soma in April, 2013, reports that:

Soma asked if we wanted to join 5 other families who would meet with her in our area, once a month for 18 months. We were allowed to bring people to be trained by her to those sessions. Guess who I brought to be trained? EV. I had hired her about 2 months previously to help me create a homeschool program for my son. I asked her to join my Soma sessions so I could begin RPM for my son.

Fast forward and EV has taken what was invented by Soma and renamed it and marketed it S2C. Unfortunately, in the new rebrand of Soma’s method a lot has been compromised. Soma’s lessons are always individualized and have multiple components that support the different sensory channels of each student and are oriented toward the individual motor challenges specific to each person. Her lessons are never one size fits all and she would never just read a paragraph of information and have a student answer questions while someone is holding a board for them. RPM is a complex teaching method that is always evolving and Soma is nothing short of a genius. She does not have the marketing skills, nor business acumen that SC2 has going for it, but believe me, you would not have had an experience like this under her or one of her certified practitioners.

Another commenter corroborates this:

S2c is just a knock off version of RPM, there is a lot more depth to RPM. Soma would never discourage speech and in fact has written a book on working with verbal students because it can be so different from teaching non-verbal students and it is very important to adapt to what the student needs and not be so rigid

And, in fact, several commenters recommend RPM as superior to S2C.

Sadly, of course, it isn’t. As a thorough perusal of our research pages will indicate, the amount of empirical evidence for RPM is no greater than that for S2C, in both cases totaling zero.

Not letting school interfere with your education

A common slogan of the school-of-life, experiential-learning-based Unschooling Movement is Mark Twain’s “I have never let my schooling interfere with my education.” (See, for example, here.)

And, indeed, it’s natural to picture Mark Twain getting his real education first as a Tom Sawyer-like boy playing hooky along the banks of the Mississippi, and then, after dropping out of school at the age of 11, as a printer's apprentice, a steamboat pilot, and a silver miner out in Nevada. But what this narrative leaves out is what Twain did when he wasn’t at work. According to his Wikipedia entry, Twain “educated himself in public libraries in the evenings, finding wider information than at a conventional school.”

Wider information than at a conventional school: this casts Twain’s famous adage in a whole new light. Instead of seeing him rafting or steamboating down the Missippi, we now see him sitting at a lamp-lit library table, engrossed in Carlyle’s French Revolution or William Edward Hartpole Lecky’s History of European Morals.

Even Tom Sawyer, who, when asked by his Sunday school teacher for the names of the first two apostles, famously calls out “David and Goliath,” is better read than many students today. Here he is playing hooky with his friend, quoting lines memorized from a book about the adventures of Robinhood:

Just here the blast of a toy tin trumpet came faintly down the green aisles of the forest. Tom flung off his jacket and trousers, turned a suspender into a belt, raked away some brush behind the rotten log, disclosing a rude bow and arrow, a lath sword and a tin trumpet, and in a moment had seized these things and bounded away, barelegged, with fluttering shirt. He presently halted under a great elm, blew an answering blast, and then began to tiptoe and look warily out, this way and that. He said cautiously—to an imaginary company:

"Hold, my merry men! Keep hid till I blow."

Now appeared Joe Harper, as airily clad and elaborately armed as Tom. Tom called:

"Hold! Who comes here into Sherwood Forest without my pass?"

"Guy of Guisborne wants no man's pass. Who art thou that—that—"

"Dares to hold such language," said Tom, prompting—for they talked "by the book," from memory.

"Who art thou that dares to hold such language?"

"I, indeed! I am Robin Hood, as thy caitiff carcase soon shall know."

"Then art thou indeed that famous outlaw? Right gladly will I dispute with thee the passes of the merry wood. Have at thee!"

Later:

The boys dressed themselves, hid their accoutrements, and went off grieving that there were no outlaws any more, and wondering what modern civilization could claim to have done to compensate for their loss. They said they would rather be outlaws a year in Sherwood Forest than President of the United States forever.

Indeed.

In an age in which presidents leave no child behind and compulsory education extends through age 16, a more up-to-date image of a child not letting school interfere with his education shows that child secretly reading Gulliver’s Travels or Popular Science behind his Pearson Leveled Reader, his Everyday Math Student Math Journal—or (if possible) his Common Core Ipad Initiative tablet.

In an archived blog post, Joanne Jacobs writes:

I went through school before the invention of “gifted and talented education.” There was no tracking till high school. I read in class, which made it possible to go through 10 books every two weeks. (When the library gave us three weeks, I started reading longer books.) It’s the core of my education. 

Most of the best-educated people here in America were and are voracious independent readers, and most of what they read is (or was) in addition to, or instead of, what’s assigned at school. We might think of accomplished people who “didn't let school interfere” as free-spirited geniuses who spent their youths tinkering and daydreaming. But, for most of them, book learning was key, and the careful, organized reading and rereading, concentration, and recall practice that this requires, requires, in turn, great discipline.

Nor is reading the only way in which those who become highly educated in spite of school, in fact, show much more discipline than those who merely pay the kind of attention, and do the kind of work, that classroom teachers expect of them. I know mathematicians who taught themselves calculus in middle school; writers who wrote and self-edited notebook upon notebook of prose as tweens; and painters who, as teenagers, painstakingly copied scores of great paintings—all on their own initiative. In the process, these people also experience more structure and direct instruction than most kids do in today's classrooms.

As Mike S writes in his comment on Joanne Jacobs’ post about the Nobel Prize-winning physicist Richard Feynman:

Feynman was terribly bored in high school physics, and so his teacher took him aside and gave him a graduate level book on advanced calculus. Feynman would ignore the class and sit off to the side working through the extremely difficult problem sets.

Nor do autodidacts eschew things like regurgitation and drill. Benjamin Franklin reports teaching himself how to write by reconstructing model texts from memory; other polymaths I know regularly use flashcards.

Ironically, at a time in which schools claim to be following child-centered learning principles, it’s getting harder and harder for children to not let school interfere with their education. New obstacles include:

1. Increased homework loads, increased busywork within those homework assignments (such that smart kids can’t just breeze through them quickly), the growing influence of homework completion (as opposed to final exam grades) on course grades, and the growing competition for spots at the best colleges. All these make it harder for those who aspire to the top colleges to find time for extra-curricular activities.

2. The rise of pod-based seating arrangements, hands-on and group-based activities, teachers circulating through the classroom instead of mostly standing at the front of it, and the decline of textbooks and workbooks. All these make it harder to sneak your own books behind those textbooks and workbooks and secretly learn on your own.

3. The growing resistance to letting kids work independently and get ahead of their peers academically. Very few teachers today would do for a budding science genius what Feynman’s teacher did for him.

The rise of computers and tablets in the classroom, you might think, would open up broad new realms for self-teaching—assuming the school's firewall doesn't block information-rich sites like Wikipedia. All the distractions of the Internet, however, make Internet-based self-teaching workable only for the most self-disciplined of autodidacts. Also, classroom technology is increasingly turning grade school classrooms into Panopticons in which the teacher can monitor everything that goes on. We have software that projects onto the teacher’s desktop computer what’s happening on every student’s screen tracks where students are looking and what kinds of facial expressions they are displaying in response.

In short, however student-centered our schools claim to be, it's getting harder and harder for today's kids to not them interfere with their education.

FC conference, part deux

Part 2 happens tomorrow, from 7:00 pm to 8:30. Howard Shane will discuss FC vs. augmentative and alternative communication (AAC), Elizabeth Serpentine will discuss FC, reasonable accommodations, and the IDEA, and I’ll discuss what we know about language and literacy acquisition in autism and how it relates to FC.

It’s free and virtual, with q and a at the end, and you can register here.

Here's something I just wrote in response to someone in a Facebook group who asked me to ensure that there would be no inaccuracies in Part 2, as she claimed there had been numerous inaccuracies in part 1:

There were no inaccuracies that I am aware of. There *were* inaccuracies in people's interpretations of what they heard--e.g., that Dr. Todd was comparing autistic people to horses, or that Dr. Lutz was shaming people with autism, or that evidence-based concerns about authorship are ableist. And there were inaccuracies in the various criticisms given in the feedback forms that we provided--e.g., that the primary factors interfering with communication in autism are sensory-motor rather than the autism symptomology as spelled out in the DSM; or that the fact that many of the studies invalidating FC are 30 years old somehow makes them irrelevant today. (Studies showing that smoking causes lung cancer are even older). Unfortunately, though we do our best to present our evidence clearly and respectfully, this is such a charged topic that some people will inevitably misinterpret our words. I encourage you to listen carefully to what's being presented and make sure you aren't reading things into our presentations that simply aren't there.

 

How not to forget about the Holocaust

In this time of renewed debate about what students should learn about history, I think we're once again missing the bigger point. Most American students aren't being taught in ways that result in their remembering much of anything about history. Here's a post from a decade ago.

How not to forget the Holocaust

So how best to address so few of today's students knowing about the Holocaust? By today's students, I mean, of course, American students in particular, notorious the world over for their supreme ignorance of world events.

First of all, what's responsible for this ignorance? There are surely a number of factors, some of them having mostly to do with "kids these days"--things like pathetic reading habits and a preference for all other forms and genres of media (unprecedented in number and variety) over the news media--especially the sort of news media that brings in any kind of historical perspective.

But it's also "schools these days." Current trends in social studies have teachers shying away from the kinds of quizzes and tests that motivate students to internalize and systematize core knowledge or risk low grades. And current trends also have teachers teaching thematically rather than chronologically, with themes like Slavery or Revolution or Dictatorship or Equality. A particular factor is lifted out of a bunch of different times and places, each instance of that factor thus stripped of its historical and cultural contexts. The different instances of Slavery, etc., are discussed in terms of the tired generalities they share rather than the particularities that make them distinctly memorable. Even when the theme is Genocide, the conflation of the genocides in Rwanda and Armenia and that of the Holocaust doesn't result in students remembering when the Holocaust happened, what led up to it, how many people were murdered, and what consequences are still playing out to this very day. The takeaway, instead, is something more like "people sometimes let bad people come to power and turn grassroots prejudices into complicity in mass murder, with citizens self-interestedly obeying authority and following orders." The banality of evil is very far from the whole story.

That's the problem with what I fear these renewed calls for mandatory Holocaust instruction will result in: taking the Holocaust out of context and focusing on what it says about man's capacity for dehumanizing prejudice and massive evil, which, important though this message is, risks coming at the expense of analyzing what actually led up to the Holocaust in particular. If one of the reasons to remember the Holocaust is to make sure it never happens again, people need to learn what factors made early 20th century Germany particularly susceptible to perpetrating it.

Teaching history chronologically may seem boring, but teaching major events within their proper chronological contexts, and creating a vivid sense of the times and places in which they occur, actually make them much more meaningful and memorable. If we want students to actually remember key historical events and not just appreciate them, then our objective shouldn't be for them to cram these events down their throats and regurgitate them in the short term, but for them to chew these events over on their own over time. If students see historical events as sufficiently vivid and significant, they will think about them from time to time after class is over, and the spaced repetition and recall practice that solidifies things into long term memory will be largely self-motivated.

For lasting effects on memory, history poses a particular challenge. It's less skills-based than math and language arts. It contains much more factual content than even the most fact-intensive of other grade school courses (say, biology and chemistry). And it's less cumulatively repetitive than (traditional) math, which has students re-applying the standard algorithms of arithmetic all the way through algebra, and algebraic techniques well into calculus.

In other countries, history is the centerpiece of social studies instruction throughout school, taught yearly, with other fact-rich social studies courses--geography and economics--reinforcing it rather than replacing it. And there's at least some revisiting of previously taught material. In today's French schools, I recently learned, this revisiting happens yearly. Starting at least as early as middle school (and perhaps earlier) history courses survey all of world history. First it's just a general outline, but with each succeeding year new material is added. This strikes me as a promising way to create a solid scaffolding for long term memory and then systematically build it up through spaced repetition--very much in line with current findings in cognitive science about what makes for stable long-term memories.

But here in America, except for certain favored topics in early American history, from Columbus to the Pilgrims to the Civil War and Reconstruction, most American students encounter major bodies of historical knowledge--ancient history, the Roman Empire, the rise of modern China, the colonization and post-colonization of Africa, etc---only once, if at all. With American teachers teaching less systematically (thank theme-based instruction) and less fact-intensively (thank the mere-facts-vs-higher-level-thinking, 21st-Century-Skills, and you-can-always-look-it-up-on-the-Internet mentalities), American students encounter far fewer facts than their counterparts overseas. With American teachers covering content less efficiently (thank child-centered learning), and students getting bogged down in big projects and project presentations (thank Project Based Learning), many students never get past one or both World Wars, or breeze over most of the 20th century too quickly to find it interesting--let alone compelling enough to follow through into current events.

Returning now to the basic question: what to do about students not knowing about the Holocaust? The short answer is to look at the world more systematically. Look at it more systematically both in terms of its history, and in terms of how other countries teach history. And, in particular, how they manage to raise students who are so much more historically aware than ours are.

Is there really no Theory of Mind deficit in autism? Part VI: problematic references

I spent my last five posts (besides the post announcing tomorrow and next Thursday’s FC conference) critiquing the arguments made by Gernsbacher and Yergeau in their 2019 article, “Empirical Failures of the Claim That Autistic People Lack a Theory of Mind.” Gernsbacher and Yergeau’s central argument is that ToM tests lack empirical validity. They argue, in particular, that (1) the original test results with autistic subjects have failed to replicate, (2) the tests themselves fail to converge on a meaningful psychological construct, and (3) the tests fail to predict autism-related traits, empathy and emotional understanding, and the ability to infer other people’s goals. In my earlier posts, I attempt to show how, to the extent that any of this holds true, it doesn’t override most of the empirical evidence for a Theory of Mind deficit that is fundamental to autism.

Morton A. Gernsbacher, Professor of Psychology, University of Wisconsin

In this final installment of my “Gernsbacher posts”, I turn to the bigger picture. That is, I’ll discuss how many of the articles that Gernsbacher and Yergeau cite to support their claims also report additional findings that undermine Gernbacher’s FC-friendly take on autism. This FC friendly take, which emerges from the eight Gernsbacher articles I’ve reviewed here and which we also see in other more explicitly FC-friendly articles, is that autism is not a socio-cognitive disorder, but something else: some sort of sensorimotor disorder and/or (at least in some cases) some subtype of language delay.

Ironically, many of the articles cited by Gernsbacher and Yergeau only add to the large body of evidence that autism is, in fact, fundamentally a social cognitive disorder.

Burnside et al. (2017), for example, found that their autistic participants, in contrast to their non-autistic counterparts, did not exhibit a preference for faces. Salter et al. (2008) note that, although their autistic participants used “mentalizing” language in the Triangle Animations as well as their non-autistic counterparts did, “the content of their descriptions was significantly less appropriate.” Colombi et al. (2009) found that children with autism responded less to bids for cooperative behavior than did children with other developmental disabilities. Peterson (2014) reports that her “[r]esults showed that children with ASD were significantly less empathic, according to their teachers, than typically developing children.”

Berger and Ingersoll (2014), in reporting that their autistic subjects attended less to social stimuli to distinguish between intentional and unintentional acts, note how this resonates with research showing a tendency in autism not to orient to social stimuli (they cite Dawson et al., 2004) and “provides support for the social motivation theory of ASD.” Li et al. (2019), in their discussion of moral judgments, found that autistic individuals were more upset when objects, as opposed to people, were the recipients of damaging acts.

Even Kerr and Durkin (2004), who concluded from their problematic thought-bubble study (see my last post), that young autistic children are able to pass explicit, nonverbal ToM tests, add:

This is not to deny, of course, that children with autism do manifest profound social impairment, including characteristics associated with poor attention to the presence and interests of others (such as lack of eye gaze and pointing, joint attention problems) and impaired ability on many tests of theory of mind...

In one sense, Gernsbacher and Yergeau are correct. Children with autism do not uniformly and absolutely “lack a theory of mind.” Those autistic individuals who have participated in experiments—which generally exclude the most severely autistic individuals—have shown varying abilities to infer intent, at least when it comes to the kinds of instrumental intent involved in actions like reaching for objects or opening them up. Most are able to map basic emotions to facial expressions that don’t depend on the region around the eyes for interpretation: emotions like happy, sad, angry, scared. And many higher functioning autistic people are able to pass explicit Theory of Mind tests—though they:

1. first require significantly higher levels of linguistic mastery than non-autistic individuals require
2. still fail to automatically shift their gaze in the right direction in implicit versions of some of these ToM tests
3. still continue to experience ToM difficulties in more naturalistic, real-world settings.

In addition, some of the papers that Gernsbacher and Yergeau cite highlight problems with some of the ToM measurements—in particular the picture-sequencing test, which has failed replication; the Eyes test, in which vocabulary is the biggest factor; and the second-order ToM tests, which do not distinguish individuals with autism from those with ADHD. Furthermore, there appears to be some degree of disjunction between performance on socio-perceptual tasks like emotion recognition and socio-cognitive tasks like perspective taking.

But none of this contradicts the long-standing findings that autism is a socio-perceptual and socio-cognitive disorder involving diminished attention to social stimuli, diminished joint attention, diminished social motivation, and diminished automatic, intuitive perspective-taking.

True, to a large extent these differences are matters of degree, with significant variation across the spectrum and, often, significant improvement in the course of development. And there are additional complications. First, autism is not a smooth spectrum shading seamlessly from mild into severe. Within its multiple dimensions, the spectrum gets lumpy in places, showing evidence of distinct groups. For example, Lombardo et al. (2015) discovered of two discrete subgroups with respect to performance on the Eyes test. Wittke et al (2017) discovered two discrete subgroups among those who can put words together but struggle with syntax. Perhaps most importantly, individuals with high-functioning autism (HFA) differ significantly from those with severe autism. Indeed, a presentation at INSAR by Evdokia Anagnostou in Spring, 2022 suggests that the brains of HFA individuals have more in common with those of individuals with ADHD than with those of individuals with severe autism. Studies of HFA individuals—including those that Gernsbacher and Yergeau cite as evidence for intact ToM skills in autism—may well not generalize across the spectrum.

In addition, non-autism-related personality factors as well as gender surely play a role, perhaps interacting with autism traits like frequency of eye contact and joint attention, on one hand, and degree of social motivation, on the other. Furthermore, variations in executive functioning and linguistic mastery both affect—and are affected by—autism symptomology. Regarding language in joint attention and language ability (see Tomasello and Todd, 1983) “high-functioning” means being “at the high end of the joint attention skill spectrum.”

But despite all this variation and despite all these confounds, there emerges from the bulk of the research, including the bulk of the research cited here by Gernsbacher and Yergeau, a consistent theme.

Autism is a spectrum of diminished social motivation and of difficulty with social cognition.

And this, for those who wish to promote and/or to believe in FC, is an inconvenient truth.

---

REFERENCES:

Anagnostou, E. (2022). Exploring Heterogeneity in ASD: From Bench to Clinic to Stakeholder Priorities. Keynote address, International Society for Autism Research.

Berger, N. I., & Ingersoll, B. (2014). A further investigation of goal-directed intention understanding in young children with autism spectrum disorders. Journal of Autism and Developmental Disorders, 44, 3204–3214. https://doi.org/10.1007/s10803-014-2181-z

Burnside, K., Wright, K., & Poulin-Dubois, D. (2017). Social motivation and implicit theory of mind in children with autism spectrum disorder. Autism Research, 10, 1834–1844. https://doi.org/10.1002/aur.1836

Gernsbacher, M. A., & Yergeau, M. (2019). Empirical Failures of the Claim That Autistic People Lack a Theory of Mind. Archives of scientific psychology, 7(1), 102–118. https://doi.org/10.1037/arc0000067

Kerr, S., & Durkin, K. (2004). Understanding of thought bubbles as mental representations in children with autism: Implications for theory of mind. Journal of Autism and Developmental Disorders, 34, 637–648. https://doi.org/10.1007/s10803-004-5285-z

Li, T., Decety, J., Hu, X., Li, J., Lin, J., & Yi, L. (2019). Third-party sociomoral evaluations in children with autism spectrum disorder. Child Development. Advance online publication. https://doi.org/10.1111/cdev.13206

Tomasello, M., & Todd, J. (1983). Joint attention and lexical acquisition style. First Language, 4(12, Pt 3), 197–211. https://doi.org/10.1177/014272378300401202

Wittke, K., Mastergeorge, A. M., Ozonoff, S., Rogers, S. J., & Naigles, L. R. (2017). Grammatical language impairment in autism spectrum disorder: Exploring language phenotypes beyond standardized testing. Frontiers in psychology, 8, 532. https://doi.org/10.3389/fpsyg.2017.00532