What I am up to these days - Smartphones for all (updated)

Update 12/29/2023

I've retired the Smartphones for all project, at least for now. I really couldn't find much interest in the topic, so I came to feel I was writing something just for myself. I have retired the sphone4all.com domain, it will be soon available for others (including, certainly, spammers can scammers - no way to avoid that).

I have moved archived the WordPress site as a subdomain of another domain I own. If for any reason you'd like to see the archives they are at:

https://www.sphone.bethebestyoucanbe.us/

I've removed the URLs from the post below.

Original: 4/2018

This blog is quieter than it used to be. There are a few reasons for that, but mostly I’m spending blogging time slogging away on the Smartphones for All book project — which is now iPhone specific. I publish chapter excerpts on a blog there every few weeks. Here are a few recent examples:

• Chapter excerpt: Location Sharing for Explorers – techniques – Smartphones for All
• Chapter excerpt: The ethics of location sharing – Smartphones for All
• Chapter excerpt: managing phone spam for special needs iPhone users – Smartphones for All
• Voice and Video options for iPhone Explorers – Smartphones for All
• Creating contacts for an Explorer – Smartphones for All

You can follow that project by blog feed, or on Facebook or visit the blog to see all the recent posts.

I no longer make predictions as to when I’ll be done. I know the topics to cover, I write and revise, one day it will be finished. I plan to do the Amazon self-publishing thing.

AI and special needs adults: The AI Guardian is in sight

Over the past decade I've written on social media about the concept of an AI Guardian, but I realize I've never put it into a blog post [4]. With the release of the LLM AIs [1] including ChatGP4, ChatGPT plugins,  and recently GPT Agents (GPTs) the AI Guardian is much closer than I'd expected. So it's time to write something.

First, of course, I decided to ask ChatGPT. I've never seen the concept of an AI Guardian online, but evidently I've been looking in the wrong places. As of its April 2023 incarnation ChatGPT4 has quite a bit to say:

You: What do you know about the concept of an "AI Guardian" for special needs adults?

ChatGPT

The concept of an "AI Guardian" for special needs adults, particularly those with low IQ or autism, revolves around using artificial intelligence to provide support and assistance in various aspects of daily life. This concept is still emerging, but it has several potential applications: 

Safety Monitoring: AI can be used to monitor the individual’s environment for safety hazards or emergencies, alerting caregivers or authorities when necessary.

Routine and Schedule Management: AI systems can help in managing daily routines, providing reminders for medication, appointments, and other important activities.

Behavioral Analysis and Support: For individuals with autism, AI can analyze behavior patterns to predict and mitigate potential stressors or overstimulation.

Communication Aids: AI-driven tools can assist in communication, especially for non-verbal individuals or those with speech difficulties, by interpreting signs, gestures, or other forms of non-verbal communication.

Learning and Skill Development: AI can offer personalized learning experiences and skill development activities, tailored to the individual’s needs and learning pace.

Social Interaction Facilitation: AI can help in guiding and facilitating social interactions, which can be challenging for some individuals with special needs.

Health and Wellness Monitoring: Continuous monitoring of physical health, including vital signs, sleep patterns, and physical activity, ensuring prompt response to health issues.

This concept is still in its nascent stages and raises important considerations regarding privacy, ethical use, and the need for human oversight. It's crucial to balance the benefits of AI assistance with the dignity and autonomy of the individuals being assisted. As a physician with experience in health informatics [2], you'd appreciate that while AI can provide valuable tools, it cannot fully replace the nuanced understanding and empathy provided by human caregivers.

Well, that covered the bases. I would love to know what ChatGPT4 has been reading on this topic.

In our family iPhones and narrow focus AIs like Google Maps have been both an essential tool for independence and a screen addiction curse [3]. The ability to locate our children was key to them learning to navigate by bike and bus. Mapping tools compensated for very limited navigation ability. Calendaring helped with anxiety and organization. Notes and Reminders helped with memory and recall limitations. Beyond the obvious advantages of messaging we discovered both our children were better able to process text messages than verbal communication -- especially for difficult topics.

Now there is the near term prospect of far more support going forward. Monitoring email, messaging and apps for the scams and frauds that live on the cognitively disadvantaged. Monitoring financial transactions for worrisome trends and events. Monitoring home environments for worsening or dangerous conditions. Encouraging better diet and activity.  Acting as a job coach. Appropriately paced and reinforced lifelong learning. Guiding our children through the vast complexity of medical care. Even providing a form a companionship in time or facilitating finding company in the physical world. Doing, in other words, what Emily and I do after we are incapacitated or (inevitably) dead.

In the absence of personal immortality for Emily and I the AI Guardian is the best hope for our children's longterm health and happiness. Even as I have profound concerns about the disruption that comes with the rise of the modern AI I also have hope for a better options for the cognitively disadvantaged.

- fn -

[1] Some dislike applying the term "AI" to Large Language Models because they don't appear to be conscious or sentient.  Much of my professional career was loosely related to precursors of modern AI and there is absolutely no doubt that in 1995 we'd have called ChatGPT a bloody scary AI. The goalposts are mobile. LLMs are AIs by any reasonable definition. Insofar as we understand human cognition we do much of the same things that LLMs do.

[2] This "as a physician" bit startled me until I remembered that I'd given ChatGPT4 that information as a persistent context for our sessions.

[3] I tried writing a book on how best to balance these harms but I gave up when I finally accepted that there was absolutely no interest in such a book from the community I was writing for.

[4] A 2015 post on Google Inbox was the closest I could find on the topic of AI assistance. I tagged that nsAI for non-sentient AI.

Email cleanup - reducing predation opportunities

After falling prey to a predatory "Second Swing" (golf) promotion #1 agreed to let me cleanup his email stream.  He's fond of signing up for email but, inevitably, there was more garbage than he could handle.

I unsubscribed from about 20 lists and deleted perhaps 5000 messages -- all junk.

I'm hoping he'll let me do this periodically. He's particularly vulnerable to email marketing but he does use his email and he dislikes clutter.

Explosions and anxiety: Adult special needs life is a tough haul

My 26yo son, "#1", is pretty solidly in the 3-4th (bottom) percentile of cognitive abilities. It's a cognitive continuum of course; what's true of the 3rd percentile can also be true of the 10th or the 20th -- especially when lack of sleep or alcohol is involved. So this isn't just about special needs adults. It's something useful to understand for tens of millions of Americans.

The other day he exploded. No harm came of it, except to him. It's a behavior we've known from childhood though it's only with time we came to understand how closely tied it is to his anxiety.

It happened during an ice hockey game. We play together at local pickup games. He's a good mid-level adult hockey player, a step above me and our usual pickup skaters, but he's not a fitness guy. He gets tired towards the end of a game and, unlike a neurotypical player, he doesn't push himself. He just takes it easy. (This logical but socially wrong behavior isn't unique to #1.) This can irritate teammates who expect him to perform well.

In this case a teammate made a mildly inappropriate (for this kind of hockey) criticism of #1s lackadaisical play. Once upon a time I'd have made a similar comment, but I've learned it doesn't work. What works is to praise the things he does well. (This simple principle took me forever to learn and apply.)

I get those kinds of comments myself from better players sometime -- but I enjoy them.  It means I can guilt my critic into being a reluctant game-long coach. (Sadly this only works once, they don't really want to coach.) Or, if it's late in the game, I'll laugh and say "yeah, I suck". 

That's advanced stuff. In this case #1 was tired. He exploded with a red faced rant and various scary seeming threats. I was nearby though, so I sat between him and his critic and explained to the poor guy that my son was a special needs adult and that I'd sort things out. #1 hates to hear himself described that way (you would too) but the moment passed for everyone but my son. For him these things endure.

I've learned not to criticize these behaviors -- for him it's all about extinction-reinforcement. I was able to walk him through how I'd have handled the comment. It wasn't over though. He's been kind of wreck since. He's complaining of a variety of physical symptoms consistent with somatization (or some horrible disease that we'll feel very bad about -- my wife and I are both physicians). It's hard to understand his internal reasoning but his behavior is consistent with shame, guilt, and a deep fear of exploding again. His usual response to an episode like this is to replay it for years and avoid the setting. I don't know if he'll continue to do the pickup hockey. For now we're managing what we think is somatization (and not, say, some post-COVID neuropathy or lymphoma [1] or whatever) and working on resetting him.

Not a good day, but also not avoidable. But it could have gone much worse. It does go much worse. A lot of men with limited cognitive or emotional control can melt down like this. If police are involved and aren't at the top of their game it can escalate very badly. Even if police aren't involved it can turn into a physical fight with all of the problems that come from that. Most special needs adults, and most men, don't have a 60+ neurotypical father to sit between them and the guy they are excessively angry with.

It's a hard world out there. If you're one of the lucky guys with good emotional control and understanding it might help to know how this goes. If you're a cop -- I hope you're getting the autism/special needs training now being introduced into high performing police forces.

- fn -

[1] That's physician humor. Any symptom can always be early lymphoma.

See also:

• The Explosive Child and other books (2007)