At Drexel University, this Thursday and next Thursday evenings. Six speakers bring a variety of expertise to cover different facets of the use of, and rationale for, facilitated communication (FC/RPM/S2C) in individuals with autism!
With the help of my readers, I’ve found out about several typos in my recent books that went undetected by me, my editors, and my early readers. They also went undetected by Microsoft Word and Grammarly. (I have not found Grammarly helpful for style, but it is useful for catching some typos).
But what about ChatGPT? Surely a technology that can mimic human texts so convincingly that professors are to turning to AI detection tools (to determine whether their students actually wrote their papers themselves) should be able to take an existing paper and detect all its typos.
In my last four posts, I critiqued the arguments in Gernsbacher and Yergeau’s 2019 article that ToM (Theory of Mind) tests lack empirical validity—in particular, that the original test results with autistic subjects have failed to be replicated, and that the tests themselves fail to converge on a meaningful psychological construct and fail to predict autism-related traits and empathy and emotional understanding.
Gernsbacher and Yergeau’s final line of argument concerns the question of whether the ToM tests, as is generally claimed, tap into the ability of autistic people to infer other people’s goals and desires. Here they return to the argument made in Gernsbacher et al. (2008), and claim that “autistic people of all ages skillfully understand other persons’ intentions, goals, and desires.” In support of this claim, they cite several dozen studies. The problem here is that, as I discussed earlier, the kinds of intentions, goals, and desires are all basic, instrumental level goals, intentions, and desires—the kind represented by instrumental physical activities like reaching, pulling apart, and inserting. Thus, we are not talking about social goals and intentions like making a good impression, or complex psychological desires like romantic interest.
The elimination or downplaying by more and more colleges of applicant SAT scores, along with a recent article on why that’s a bad idea, reminded me of an old OILF post.
The article highlights how the SATs used to benefit a type of student that today we might call “neurodivergent”:
the kind who is bright and talented but who had failed to live up to their potential in class. These students tended to be the brilliant dreamers; they were the ones in possession of uncommon cognitive skills, but who performed poorly in knowledge-based exams because of bad time management, resistance to the indignities of organised education, or an inability to prioritise school over their own interests. For decades, excellent SAT scores got students into colleges that they wouldn’t ordinarily get into, creating opportunities to find diamonds in the rough who had perhaps never found their footing in school.
In a recent article at the New York Post, “free range kids” proponent Lenore Skenazy inadvertently promotes what all the available evidence suggests is the opposite of a free range childhood: spending hours drifting one’s finger over a letterboard and, in response to subtle subconscious cues and not so subtle prompts from the person holding up the board, slowly picking out one letter after another in sequences that sometimes number several dozen letters long.
Talk about helicopter parenting! This is about as bad as it gets.
In recent posts, cross-posted at FacilitatedCommunication.org, I critiqued the arguments in Gernsbacher and Yergeau’s 2019 article (“Empirical Failures of the Claim That Autistic People Lack a Theory of Mind”) that ToM tests lack empirical validity—in particular, that the original test results with autistic subjects have failed to be replicated, and that the tests themselves fail to converge on a meaningful psychological construct and fail to predict autism-related traits.
I decided to begin the new year by asking ChatGPT two questions that I broached in a long-ago blog post.
1. Should students learn touch typing?
2. Should students do multiple revisions of their papers?
On the first question, the AI chatbot replied:
Yes, it is a good idea for students to learn touch typing. Touch typing is the ability to type quickly and accurately without looking at the keyboard. It is a valuable skill to have because it allows you to focus on what you are writing rather than where to find the keys on the keyboard. It also increases your typing speed and efficiency, which can be helpful in school and in the workplace. There are many resources available online to help students learn touch typing, including typing games and typing tutorials.
Here’s a follow-up post to my first “sad legacy of Everyday Math” post, in which I concluded by saying that
You can’t blame the mathematical deficiencies of these 4th and 5th graders on their parents: both the private school and the after school program select for parents who care about education. You can’t blame it on the kids: my kids, who clearly wanted to learn, had been admitted [to our after school program] in part based on their behavior.
[Everyday Math, I gather, is still very much in use, and so I thought it worthwhile to recycle this old post from Out in Left Field.]
Twice this past week I saw shocking examples of the cumulative effects of Everyday Math. Last Thursday I visited a nearby private school with sliding scale tuition and a diversity of students. For years the school had used Everyday Math, but recently, with the encouragement of a friend and colleague of mine who advises schools on math curricula, they’d begun to use Singapore Math. They’re phasing it in gradually, however, and currently don’t introduce it until 4th grade. For the first few grades, like nearly every other school in Philadelphia, they use Everyday Math.
I suspect the rejection of true remediation has only grown over the years since I posted this on Out in Left Field, as schools, bowing to the Common Core standards, increasingly expect nearly all students to engage with the same material based not on academic readiness, but on what year and month they happened to be born in.
Another false choice in remediation: “addition and subtraction over and over again” or Marxism and Shakespeare
In my previous post on Gernsbacher and Yergeau’s 2019 paper, Empirical Failures of the Claim That Autistic People Lack a Theory of Mind, I discussed problems with the authors’ arguments that the original studies that showed Theory of Mind deficits in autism have failed to replicate and been overturned by later studies. As the article continues, the authors embark on a second line of argumentation—this one concerning the inherent validity of the various ToM tests.