Wednesday, August 30, 2023

Mass disability - dysfunctional web sites, apps for everything

I last wrote about "mass disability" and the Left Behind in a 2021 post. The concept has sometimes seemed on the edge of going mainstream but it's never quite made it. Maybe we're getting closer; a recent Michael Tsai post (No App, No entry) reminded me of my Mastodon thread from a few weeks ago:

What is the crazy that drives Trumpism and the many global equivalents?
It is that the minimal IQ to function well in the modern world is now about 120 and that eliminates most people.

This is both the most important fact of our time and the least palatable. It is the thing that cannot be said and it will be ruin of us if we don't say it ...

I've been saying this for years. Today I was reminded of it while doing some travel booking.
During the bookings I encountered:
1. A web site that didn't work with my older version of Safari (I knew what was wrong and switched to Chrome. 
2. A Delta web site bug (I recognized it as a bug and knew what to do). 
3. Place that was out of rental cards but I new Expedia would have some contracts that would let me find one. 
4. Travel web sites that all needed new credentials...
... These are all routine parts of modern life including maintaining flaky computer systems (let me tell you ...) and phones ...

It was not like this even 35 y ago. Travel agents handled travel complexity. There were no smartphones. Computers were very limited. There was no internet for most. By necessity everyday life was much simpler. Most people could cope with it.

Now most cannot cope.

This is the most important feature of our time. And nobody can talk about it. 

I remember some good discussions on this thread but I can't find any of them now. Perhaps by design Mastodon has a limited memory. (My home instance has no search, so I had to download my archive and search it to find the date of the post. Then I could slowly navigate to it.)

I expanded on the theme a bit later:

Hotel laundry year 2000

1. Insert quarters to buy detergent, operate washer and dryer.

IQ requirement: 65 (my son could do this after a demonstration)

Hotel laundry year 2023

1. Scan QR code to download app whose profit comes from unspent funds.

2. Install app, create account with Apple ID

3. Figure out cryptic UX so can deposit funds (several odd unintuitive steps)

3. Deposit funds, paying just enough to cover this sesh. Pat the 25 cent low transaction penalty... 

4. Spot the scam behind app and avoid it (eg find at minimum)

5. Diagnose why after paying money and confirming machine it’s still not working

6. Authorize specific transaction

7. Start laundry.

(My son could not do this)

8. When complete delete app. 

IQ requirement: minimum 110, higher to spot the scam. 

This is why America is burning.

People are scared and angry and feeling left behind -- and they can't come out and say they are unable to manage their tech. Because that's the ultimate shame.

See also:

Monday, July 03, 2023

Long Distance Cycling Tips from Paul M

The following is copied with permission from a Facebook post by Paul McCormick (Group cycling over 60, July 3 2023). I didn't want to see this kind of shared experience stuck on Facebook. The text in square brackets is my commentary. I haven't done bike touring for perhaps 35y or so, but this all seems familiar to me.

Once a year or so I take myself away on a long (6-8 weeks) cycle tour, generally somewhere in Europe. In the last seven years I've cycled from Stamford to.... Turkey, Sardinia, Italy, Corsica and Majorca to name just a few places. On these tours I carry everything I need to be self-sufficient on the road, including a tent and sleeping bag, food and water and spare parts for my bicycle.

Here are my 'top ten' tips for long-distance cycle touring!

Planning 
It is important to have a plan! It gives you focus and direction and ensures you don't overlook anything. Plans should be flexible and include contingency arrangements; something will inevitably arise that will require changes to your plan.

Route 
Have a route in mind. It can be as general or as detailed as you wish, but it is helpful to know where you are going, how you are going to get there and how long it is going to take.

Navigation 
Having made a plan and a route you now need to follow your route. There are lots of cycle navigation Apps out there. I use Komoot on my phone and select the road cycle option (as the touring option often takes you on rough tracks and/or bridleways). I then export the route to my Garmin and have both devices mounted on my handlebars. Garmin is great for data and is generally sufficient for navigation, but I find it is easier to take a look at Komoot when I need to zoom in and out on the map.

Bike 

You need a tourer! Generally, tourers are steel-framed and have mounting points for front and rear luggage carriers. Steel is both strong and flexible and so will absorb the shocks on the road far better than anything else; important when you are on the road for 6-8 hours!

[These days in the US these are better known as gravel bikes. They are mostly carbon however, which many long distance cyclists distrust and have limited pannier capacity. Or they are alloy, which is uncomfortable on long rides. I'm fond of the Salsa Vaya (cable disk brakes).]

Luggage 
My preference is for four panniers: two at the rear and two at the front, for balance. I also have a large saddle bag that sits on my rear carrier for my tent. My two front panniers contain everything I might need for the day, and the two rear panniers for stuff I'll need at the end of the day. One of my front panniers contains my wallet, passport, charging cables, electronic devices etc. That pannier is always with me wherever I go - shop, Bar, toilet!

Riding 
You are prospectively riding 80km-100km a day. That's a long way, and a long day in the saddle! I like to be on the road by 8.00am and to split my day into four 'two hour' riding chunks, separated by 30 minute coffee/food stops. In each riding chunk I'll cycle circa 20km - 30km depending on the terrain and weather conditions. 

Don't chase the miles; let the miles come to you! Heart rate zone 2 for touring all the time.

Nutrition/Diet 
Just eat and drink little and often. It doesn't really matter what you eat. Eat absolutely everything you are offered and don't worry about over-eating; I always come back from a tour far lighter than when I left. Expensive energy bars aren't necessary; just get the calories down you. And don't forget to drink regularly. [I can't afford to lose weight so I need to eat a LOT when I'm doing something like this]
Oh, and if you have too much for breakfast, wrap it up for lunch!

Hills 
You will almost certainly encounter hills, and some of them will be long and with a lot of ascent. Make sure you have appropriate gearing and try as far as possible to pedal at a high cadence in heart rate zone 2. When that is no longer possible stop for a short rest as often as you need to. Focus on good pedalling technique and controlled, steady breathing. Remember, don't chase the miles, let the miles comes to you!

Mechanical problems 
Something will inevitably go wrong. Don't panic, everything and anything can be fixed! Take a deep breath, sit down and think clearly. Google the problem. Find a solution. Ask a stranger for help. Call a friend. Be inventive. Hitch a ride. You have a Credit Card!

Oh, and if you can't change an inner tube, don't even think about touring!

Mindset 
Long tours can, at times, be lonely! Social Media allows you to keep in touch with family and friends, and writing a blog on your journey gives you something to focus on when you're not cycling. But you'll need to make an effort to talk to people and initiate a conversation with a stranger, otherwise your only human contact will be when you buy a cake and a coffee in a café!

I belong to a Cycling Touring network called Warmshowers and, as far as possible, I stay overnight with members of that network. So, in addition to being offered a bed, shower, evening meal and breakfast with a host I have someone to talk to in the evening.

[Hostels used to be a good way to meet fellow travelers but during my most recent stays everyone was buried in their phones]

Thursday, June 15, 2023

High calorie foods to prevent exercise/training associated weight loss

When I retired I stopped eating high calorie restaurant/cafeteria lunches and took my exercise addiction to another (not all that healthy) level. I started dropping from my target weight to being too slender. To maintain muscle in an old person an extra 1-2% body fat about the 30yo "ideal" is a good idea.

I asked friends, some with similar vices or serious athletic backgrounds, for advice on calorie sources. Here's the current list ...
  • Snickers bars
  • Chocolate bars
  • Whole fat organic Greek yogurt
  • Sports drinks
  • Peanut butter everything including peanut butter monster trail mix
  • Almond butter
  • Avocado things
  • Baby bel cheese, 
  • Nuts: macadamia, cashews, Tahini
  • Ice cream (cheap)
  • Peanut butter granola

Wednesday, May 10, 2023

Home sleep monitoring with Apple Watch and Google (Nest) Home Video in adult with limited ability to describe a nocturnal health issue

I'm changing the details here for privacy reasons, but sharing some technical setup advice.

A special needs adult with limited ability to give reliable history has a medical issue under complex active evaluation. Since the issue often manifests during sleep it has been difficult to observe. This person's parents/guardians are both physicians.

Valuable results have been obtained with a combination of an Apple Watch (already owned), Apple Health App, Heart Reports for iPhoneGoogle Nest Cam (already owned), Google Home app, and a Nest Aware subscription ($12/month for 7 days of continuous monitoring -- camera comes with a 30 day free trial.)

When you set up the camera you need to turn on the continuous video AND (if desired) the continuous audio. The Nest cam's green "active video" notification light may disturb sleep; it cannot be turned off (feature removed 2022) but you can turn down the intensity and cover it with tape.

The patient wears the Apple Watch during sleep. The following day one can review the Apple Watch report using either the native Health App or, as many will prefer, the 3rd party "Heart" Reports App. That last product outputs a wide variety of reports as PDF that can be shared with a healthcare provider; it's $4 one-time and supports family sharing.

With the Apple Watch report and the Nest Aware automated it's possible to scroll through an evening's sleep fairly quickly with special attention to Apple Watch awakening events and Nest Aware event detection.

After a few days of study the Nest Aware subscription can be disabled. The Health app and Video can be shared with providers if needed.

This cannot replace a formal sleep lab observation study but those are rarely done now and are very expensive. This method had a total cost of $16 (less actually since the free trial was active). The technique may be particularly useful for persons whose ability to give history is limited. It may also be useful when sleep labs are not affordable or available.

UPDATE 5/15/2023. We concluded our clinical evaluation and discontinued the trial subscription. Although the video record was very valuable, and although the hardware performed very well, I was unimpressed with Google Home software. In particular:

  1. The iPhone History view really only works in portrait mode, in landscape mode the bottom part of the image doesn't render well. Navigating the history is tedious and the playback can get stuck. Sometimes I had to quit and restart.
  2. The web view is much more limited than the older Nest software and has NO support for history review at all.

Friday, April 28, 2023

Large Language Models - evolutionary tree and selection algorithm 2023

The following two diagrams were taken from Mooler et al's GitHub LLM guide (April 2023). I'm posting them here as a snapshot of this historic moment. The root of the LLM evolutionary tree goes far back in time, almost five years ago. Click image for full res.

Algorithm for selecting an AI technology


LLM Evolutionary Tree

Friday, April 21, 2023

Prosumer digital image management has not progressed to our advantage

Every so often the software market fails. I've had this happen to me a few times. From 1997 to 2007 I used a variety of PalmOS devices for what we used to call "personal information management" (PIM) - including Contacts, Notes, Tasks and Calendaring. My many PalmPilot/Palm handheld stylus devices synchronized by cable connection with Palm desktop software.

PalmOS died around the time the first iPhone came out. That original iPhone was both revolutionary and crappy. Functionally it was a huge regression from PalmOS Calendaring and other PIM solutions, but it was immediately clear that the iPhone was the future (seriously, there were no honest skeptics). Palm had been ailing already, but at that moment it was utterly dead.

It took three years for the iPhone to develop useable solutions for the "PIM-4" that worked across devices (often using either Google or Microsoft Exchange). During that time I had no handheld solution; I returned to using a paper Franklin planner. Finally, in 2010 or so, I was able to transition to the iPhone and iOS.

The market failure of digital image (and video) management has lasted longer and there's no end in site. This means something.

Things were actually looking pretty good for image and video management in 2015. Apple had consumer (iPhoto) and prosumer/professional (Aperture) applications that (mostly) shared the same image library. Things were not perfect -- Aperture had had years of horrible bugs and performance issues, but in retrospect this was a golden age. SSDs were fixing the iPhoto/Aperture performance issues and there were several reasonably priced alternatives including Adobe Lightroom. We didn't know how well we had it.

And then 2015 was when Apple killed both Aperture and iPhoto. There was no replacement for Aperture; users were left stranded with limited ability to migrate to another platform. Photos replaced iPhoto, but in most ways it was a functional regression. There was only one Photos advantage -- it promised a cloud-centric approach to image management with some limited backup features. If your iPhone or laptop was lost or destroyed your Apple Cloud images were probably safe -- as long as you paid for storage or didn't get locked out of iCloud by a phone thief.

Several alternative prosumer image management solutions emerged. But they all had the same problem Aperture had -- they all had severe data lock. If the software were to be discontinued, as happens to most products, there would be no way to extract one's images, image edits, and image metadata (ratings, keywords, titles, descriptions, albums, and on and on). In addition, perhaps inspired by the power of this data lock, many vendors moved to a subscription model. Adobe Lightroom now costs $120 a year, if you don't pay your photo library is essentially dead. Adobe can, if they wish, double or triple that price and customers will simply have to pay up. (I don't know what happens to the image library when a subscriber dies.)

I hoped Apple Photos would mature and develop more advanced features, but it has essentially languished. Recently Apple introduced a "Shared Library" model that is complex to use and, in my experience, has weird bugs and permission problems. (Lesson to users - if you ask Apple for something be prepared to regret your request.)

Eight years after Aperture died there still is not a great prosumer photo management solution for macOS customers. All the options have Hotel California Syndrome -- you can check-in but you can never leave. Apple's only option, the most natural fit for a macOS users, is dreadful and may be deteriorating. Many choices are subscription based and it's very easy for vendors to raise costs.

It's not hard to create a new standards and file based photo management solution. The file system does much of the work. Adobe has an open specification for image metadata management (XMP). Image to album, project, folder relationships are simple row triples. We've known how integrate external image editors for decades [1].

It's not hard ... but it hasn't happened. No vendor has decided to disrupt the marketplace and no open source (really open data structure is what we care about) solution has emerged.

Why not?

My best guess is that the Cloud is the problem. We've only gradually learned how to build responsive synchronizing Cloud products and they are not intrinsically file based. Development is much more challenging and the data lock advantage is irresistible for incumbents.

In the absence of a decent solution vendors are starting to build around the Apple Photos framework. This week Power Photos has a migration and access project. CYME Peakto is some mixture of Photos extension and standalone management solution. Houdah Photos Workbench adds a minuscule number of missing features to Photos.app. I can sort of imagine who these products might work, but Photos is a terrible foundation on which to build.

It's easy to image ways Apple could help, but they've been butchering photo management for a long time. They appear to be broken. The more realistic hope is that it will become easier for open source and other vendors to implement a standards based Cloud solution that would allow library migration between cooperating vendors - either through direct Cloud-Cloud communication or (better) a file based interchange format (what's a TB or two between friends?). I would be happy to pay a $200/year subscription fee for that kind of data freedom solution.

I've spent 7-8 years sitting on Mojave preparing to migrate to Apple Photos. The more I use Apple Photos the less I like this idea.  At this point I expect to convert my beloved 2015 MacBook Air to a non-networked Aperture machine and purchase a new M2 machine for my other work. Since Ventura Photos.app no longer supports importing Aperture Libraries. I'll be looking for other migration options over the next one to two years. Maybe some vendor will decide to disrupt the data-lock. In the meanwhile I'll test Power Photos migration by periodically migrating my Aperture library to Photos.

[1] For each image store original, the proprietary image editor non-destructive edit recipe, and the most recent edited version in a user-defined format (lossy or lossless). If the editor is or changed the edit recipe is useless, bu the edited version is good.

Monday, April 03, 2023

We need a new word for the historical singularity.

TLDR: The "technological singularity" was an important and useful term with a clear meaning. Then it became the "Rapture of the Nerds". We need a new term.

--

I first heard the word "singularity" in the context of black hole physics; it dates back at least to the early 20th century:

ChatGPT 4 2023: "At the singularity, the laws of physics as we know them, including space and time, break down, and our current understanding of the universe is insufficient to predict what happens within it."

Not much later, in the 1950s, the term was applied by von Neumann in a technological context (from a 1993 Vernor Vinge essay):

Stan Ulam paraphrased John von Neumann as saying: "One conversation centered on the ever-accelerating progress of technology and changes in the mode of human life, which gives the appearance of approaching some essential singularity in the history of the race beyond which human affairs, as we know them, could not continue."

Brad Delong used to write about this kind of non-AI historical singularity. My favorite description of what it would be like to a approach at technological singularity was Vinge's short story "Fast Times at Fairmount High". (This prescient story appears to be lost to time; he wrote a similar full length novel but I think the short story was better).

The core idea is there's a (virtuous?) recursive loop where technology improves technology with shorter and shorter cycle times. Many processes go exponential and even near term developments become unpredictable. One may assume social end economic structures train to keep pace. The historical singularity exponential curve was part of The Economist's y2K Millennium issue GDP per person historical graph:


In a January 1983 essay for Omni Magazine Vinge focused on a particular aspect of the the technological singularity arising from superhuman intelligence (aka "super intelligence"):

We will soon create intelligences greater than our own ... When this happens there will be a technological and social transition similar in some sense to "the knotted space-time at the center of a black hole" 

A decade later, in his 1993 essay later published in Whole Earth Review (non-Olds cannot imagine what Whole Earth Review was like), Vinge revised what he meant by "soon":

... Based on this trend, I believe that the creation of greater-than-human intelligence will occur during the next thirty years. (Charles Platt has pointed out that AI enthusiasts have been making claims like this for thirty years. Just so I'm not guilty of a relative-time ambiguity, let me be more specific: I'll be surprised if this event occurs before 2005 or after 2030.) ...

So by the year 2000 we had the concept of a historical technological singularity (eminently sensible) that had become focused on a specific kind of self-improving technology - the superhuman intelligence with an upper-case S Singularity (presumably AI). Those were useful concepts - "technological singularity" and "superintelligence" Singularity. 

In 1993 Vinge predicted the Singularity would happen before 2030, later experts like Scott Aaronson predicted after 2080. (Aaronson has since revised that prediction and works for OpenAI; Vinge's 2030 dates looks pretty good.)

After 2000 though the word Singularity went off the semantic rails. It came to be used for for a peculiar future state in which human minds were uploaded into simulation environments that were usually described as pleasant rather than hellish. This is, of course, antithetical to the original idea of unpredictability! This peculiar meaning of "The Singularity" came to be known as "The Rapture of the Nerds" based on the title of a book by Charles Stross and Cory Doctorow. More recently that vision underlies a weird cult called longtermism that seems to have infected some vulnerable minds.

The "Rapture" meaning of "Singularity" has effectively taken over. We no longer have a term for the original von Neumann concept of self-reinforcing technological change that makes even the near term future unpredictable. That perversion of meaning is why I use the tag "Whitewater world" rather than Singularity for my own blog posts (and "Skynet" rather than super intelligence).

So we need a new term. I don't think "whitewater world" is it.

Anyone have a new term? We probably have a few years in which it might still be useful.

Thursday, March 30, 2023

The IRS "Free Tax" scam and the hilarious reason why Turbo Tax is the only good free solution.

I wrote this for Facebook friends but I keep seeing people praising the "Free Tax" program and dissing Turbo Tax -- without any actual knowledge. So reprinting it here:

We did B's tax returns for 2022 using the IRS "Free Tax" program. This being America is kind of a scam. Sharing this as a guide to the unwary.

We used "TaxAct". She had state income tax forms for MN and CO. At the very end of the process you learn it costs $40 to print each state return. (Be careful when navigating, at first it seemed Federal eFile was not free; if you defer the state returns you just completed then the free option is available.)

MN is supposed to support Free File [1] but even after we removed Colorado from her form TaxAct still wanted $40 to print the state return. So reentering on the paper form.[2]

[1] Free File program are Arkansas, Arizona, Georgia, Idaho, Indiana, Iowa, Kentucky, Massachusetts, Michigan, Minnesota, Missouri, Mississippi, Montana, New York, North Carolina, North Dakota, Oregon, Rhode Island, South Carolina, Vermont, Virginia and West Virginia, plus the District of Columbia.

[2] If you start at the MN site they don't include TaxAct on their list of FreeFile options. So if one chooses a vendor from MN site you might get a better results.

Hilariously, if you hunt around you can find the free and effective Turbo Tax program for simple returns. It's free because Intuit is in litigation and need to keep it free until that's done

ChatGPT's 155 IQ and passing the Sebastian's children puzzle

A Scientific American contributor found ChatGPT (probably 3) scored 155 on a standard IQ test:

Estimated on the basis of five subtests, the Verbal IQ of the ChatGPT was 155, superior to 99.9 percent of the test takers who make up the American WAIS III standardization sample of 2,450 people. As the chatbot lacks the requisite eyes, ears and hands, it is not able to take WAIS’s nonverbal subtests. But the Verbal IQ and Full Scale IQ scales are highly correlated in the standardization sample, so ChatGPT appears to be very intelligent by any human standards.

We don't need to worry though because it couldn't answer this question:

ChatGPT easily fails at obvious riddles, such as “What is the first name of the father of Sebastian’s children?” (ChatGPT on March 21: I’m sorry, I cannot answer this question as I do not have enough context to identify which Sebastian you are referring to.) It seems that ChatGPT fails to reason logically and tries to rely on its vast database of “Sebastian” facts mentioned in online texts.

This is what happened when I tried the Sebastian test on GPT-4:

Ah, I understand now. This riddle is a classic play on words. The answer is "Sebastian" himself, as he is the father of his children.

Ok, so that's reassuring.

Update 4/12/2023: ChatGPT4 (C4) recently did well in some blinded advanced undergraduate exams.

A response to Scott Aaronson's rejection of an AI pause.

Scott Aaronson, who works on AI safety for OpenAI, wrote a critique of AI Pause that was not up to his usual standards. Here's what I wrote as a comment:

Hi Scott — I was confused by your post. I’m usually able to follow them. I won’t defend the letter directly and Yudkowsky/TIME is not worth a mention but maybe you could clarify some things…

1. 6m seems a reasonable compromise given the lifespan of humans, the timescales of human deliberation and the commercial and military pressure to accelerate AI development. Short enough to motivate urgent action, but long enough that reflection is possible. (I doubt we actually pause, but I agree with the principle. China isn’t going to pause of course.)

2. Let’s assume GPT 5 with an array of NLP powered extensions exceeds the reasoning abilities of 95% of humanity in a wide variety of knowledge domains. That’s a shock on the scale of developing fire, but it’s occurring in a hugely complex and interdependent world that seems always on the edge of self-destruction and actually has the capabilities to end itself. We’re not hunter gatherers playing with fire or Mesopotomians developing writing. There’s no precedent for the speed, impact and civilizational fragility we face now.

3. It’s not relevant that people who signed this letter were previously skeptical of the progress towards AI. I recall 10 years ago you were skeptical. For my part I’ve been worried for a long time, but assumed it was going to come in 2080 or so. 60 years early is a reason to pause and understand what has happened.

Lastly, I read the OpenAI statement. That seems consistent with a pause.

Tuesday, March 14, 2023

Everything is just fine.

The ad-funded internet is collapsing. It's been ailing for years but, as seems to the rule, the last bit is happening quite quickly. I'm guessing advertisers, who must be kind of dim, finally realized they were wasting their money. They did much better funding special interest magazines but those are gone now. Much of Silicon Valley has been funded by a now defunct business model. So maybe this is not a good time to be there. (Or, if you are young and have some money, maybe this is the best time to be there.)

Meanwhile human-cognition level AI has arrived. About 60 years earlier than I'd hoped. And some people thought "Don't Look Up" was about climate change. As a guide I recommend the movie Superintelligence; particularly the protagonist's approach to the end of the world. (Spoiler: It's a rom-com. Her world does not end.)

It's whitewater world all over now. On the bright side, we don't need to waste too much time on longterm planning. I retired in August of 2022 so I think I'll focus on mountain bike trail maintenance and, like Superintelligence's Carol Peters, on the needs of friends and family.

Sunday, March 12, 2023

I ask ChatGPT about the next step.

 Not a bad response.

”Describe what happens when ChatGPT is enhanced with natural language processing and domain-specific knowledge modules.”

--


When ChatGPT is enhanced with natural language processing and domain-specific knowledge modules, it gains several capabilities that allow it to better understand and respond to user input.


Natural language processing (NLP) is a field of artificial intelligence that focuses on enabling computers to understand and interpret human language. By incorporating NLP into ChatGPT, the model can better analyze and interpret user input, including understanding sentence structure, recognizing named entities, and determining the meaning of words in context. This allows ChatGPT to generate more accurate and relevant responses to user queries.


Domain-specific knowledge modules provide ChatGPT with specialized knowledge related to a particular field or topic. For example, if ChatGPT is enhanced with a medical knowledge module, it can better understand medical terminology and provide more accurate and relevant responses to medical-related queries. By incorporating domain-specific knowledge modules, ChatGPT can tailor its responses to specific user needs, making it a more effective conversational agent.


Together, these enhancements enable ChatGPT to better understand and respond to user input, providing more accurate and relevant information to users. This can lead to a more engaging and satisfying user experience, as well as improved productivity and efficiency in a wide range of applications.”

Monday, February 20, 2023

Be afraid of ChatGPT

TL;DR: It's not that ChatGPT is miraculous, it's that cognitive science research suggests human cognition is also not miraculous.

"Those early airplanes were nothing compared to our pigeon-powered flight technology!"

https://chat.openai.com/chat - "Write a funny but profound sentence about what pigeons thought of early airplanes"

Relax

Be Afraid

ChatGPT is just a fancy autocomplete.

Much of human language generation may be a fancy autocomplete.

ChatGPT confabulates.

Humans with cognitive disabilities routinely confabulate and under enough stress most humans will confabulate. 

ChatGPT can’t do arithmetic.

IF a monitoring system can detect a question involves arithmetic or mathematics it can invoke a math system*.


UPDATE: 2 hours after writing this I read that this has been done.

ChatGPT’s knowledge base is faulty.

ChatGPT’s knowledge base is vastly larger than that of most humans and it will quickly improve.

ChatGPT doesn’t have explicit goals other than a design goal to emulate human interaction.

Other goals can be implemented.

We don’t know how to emulate the integration layer humans use to coordinate input from disparate neural networks and negotiate conflicts.

*I don't know the status of such an integration layer. It may already have been built. If not it may take years or decades -- but probably not many decades.

We can’t even get AI to drive a car, so we shouldn’t worry about this.

It’s likely that driving a car basically requires near-human cognitive abilities. The car test isn’t reassuring.

ChatGPT isn’t conscious.

Are you conscious? Tell me what consciousness is.

ChatGPT doesn’t have a soul.

Show me your soul.

Relax - I'm bad at predictions. In 1945 I would have said it was impossible, barring celestial intervention, for humanity to go 75 years without nuclear war.


See also:

  • All posts tagged as skynet
  • Scott Aaronson and the case against strong AI (2008). At that time Aaronson felt a sentient AI was sometime after 2100. Fifteen years later (Jan 2023) Scott is working for OpenAI (ChatGPT). Emphases mine: "I’m now working at one of the world’s leading AI companies ... that company has already created GPT, an AI with a good fraction of the fantastical verbal abilities shown by M3GAN in the movie ... that AI will gain many of the remaining abilities in years rather than decades, and .. my job this year—supposedly!—is to think about how to prevent this sort of AI from wreaking havoc on the world."
  • Imagining the Singularity - in 1965 (2009 post.  Mathematician I.J. Good warned of an "intelligence explosion" in 1965. "Irving John ("I.J."; "Jack") Good (9 December 1916 – 5 April 2009)[1][2] was a British statistician who worked as a cryptologist at Bletchley Park."
  • The Thoughtful Slime Mold (2008). We don't fly like bird's fly.
  • Fermi Paradox resolutions (2000)
  • Against superhuman AI: in 2019 I felt reassured.
  • Mass disability (2012) - what happens as more work is done best by non-humans. This post mentions Clark Goble, an app.net conservative I miss quite often. He died young.
  • Phishing with the post-Turing avatar (2010). I was thinking 2050 but now 2025 is more likely.
  • Rat brain flies plane (2004). I've often wondered what happened to that work.
  • Cat brain simulator (2009). "I used to say that the day we had a computer roughly as smart as a hamster would be a good day to take the family on the holiday you've always dreamed of."
  • Slouching towards Skynet (2007). Theories on the evolution of cognition often involve aspects of deception including detection and deceit.
  • IEEE Singularity Issue (2008). Widespread mockery of the Singularity idea followed.
  • Bill Joy - Why the Future Doesn't Need Us (2000). See also Wikipedia summary. I'd love to see him revisit this essay but, again, he was widely mocked.
  • Google AI in 2030? (2007) A 2007 prediction by Peter Norvig that we'd have strong AI around 2030. That ... is looking possible.
  • Google's IQ boost (2009) Not directly related to this topic but reassurance that I'm bad at prediction. Google went to shit after 2009.
  • Skynet cometh (2009). Humor.
  • Personal note - in 1979 or so John Hopfield excitedly described his work in neural networks to me. My memory is poor but I think we were outdoors at the Caltech campus. I have no recollection of why we were speaking, maybe I'd attended a talk of his. A few weeks later I incorporated his explanations into a Caltech class I taught to local high school students on Saturday mornings. Hopfield would be about 90 if he's still alive. If he's avoided dementia it would be interesting to ask him what he thinks.

Saturday, February 18, 2023

Tips for the geriatric CrossFit addict (Update: a parallel essay by ChatGPT 4)

My 10 year CrossFit anniversary is two months away. A few months after I started as an old man of 53 I wrote:
... I now do CrossFit twice a week; that's about as much as I have been able to safely handle ... physically I perform and feel more like I did at 44 than at 54. That's a big difference; if I feel at 62 the way I was at 52 I'll be content...  At 54 I'm into managed-decline rather than improvement ... Will I still be doing CrossFit at 64? It seems unlikely, but it's not impossible ... I  rather doubt I'll be doing "Murph" in this life ...
Almost 10 years later I don't go twice a week, I go four or five times a week. I am better and stronger at all CrossFit things now than I was at 53. I didn't do "managed decline", I improved in most things until I was about 60 to 61; I set a lifetime record for my front squat at 63. Barring a surprising injury I'll probably be doing CrossFit at 64. I've done Murph many times, albeit not with a weighted vest.

I've run into a few issues along the way. I inherited my mother's arthritis; my left wrist now limits my bench press and I now do pushups off a dumbbell rather than the floor (aka "true pushups").  I squashed a lumbar disc and even though the minor foot drop went away (took 2 years but they aren't supposed to resolve so I'm happy) I now limit my lifts to under 250 lbs. I've seen a physical therapist a few times over the years and I developed a somewhat extreme back maintenance program. On the other hand my body has bounced up from a few mountain bike crashes and my back has been much better than it was from 1980 to 2009.

In other words, I've been successful so far at geriatric CrossFit. Here's what I do to get by: (I'm a puny guy by the way, my lifetime best lifts are warmups for many men and women in their 40s and well beyond.)
  1. I lift 10 lb weights carefully. That's because I once injured my back carelessly lifting a 10 lb weight! Olds get hurt taking plates off the barbell -- because they don't pay attention to such a small weight.
  2. I substitute reps for weight. My current weight cap is about 250 lbs, so rather than try a 300 lb deadlift I'll do several reps at 245. If my arthritic wrist is limiting my bench press I'll find a weight I can lift with wrist comfort and stability and then do reps until I fail. I miss the fun of the 1 rep max but they don't build functional strength so subbing reps isn't all bad.
  3. I've become an amateur physical therapist (it helps to be a physician). With my experience and some online resources I can treat most overuse issues myself. If I'm not succeeding I see a professional.
  4. I generally follow a blend of the Rx (elite) women's and men's standard but if I'm on my third day in a row I've beaten my ego back enough to super-scale. That gives me 80% of the benefit and 5% of the overuse risk.
  5. I start my personal warmup 30-40 minutes before the class warmup starts. It helps to be retired. If we're doing a power lift I'll work up to 80% of my target weight during the warmup.
  6. I rarely do more than 3 consecutive days of CrossFit. I like to do two days on, one day off. During my off days I do other things - bicycling, hockey, inline, skiing, etc.
  7. I do protein drinks and morning eggs and the usual protein things. Olds need more protein. It seems to help. (I exercise enough that I usually eat 4 meals a day.)
  8. This isn't really a geriatric CrossFit thing but it's probably worth mentioning that puny guys like me should never try to out-lift an elite woman CrossFitter. That way lies humiliation and broken bits.
  9. It takes a while for my cardio system to engage. In cardio workouts I usually start slow and finish better. I do 90% of my capacity rather than 100% -- I don't like having my blood pressure drop out when my heart can't keep up.
  10. Don't laugh when the super-fit 40yo next to you complains about being old (a small ironic smile is ok). In general don't talk about age unless asked. Your younger colleagues don't need to know and Oldness is kind of a downer. Also, whether you like it or not, you are often their model for what they want to be in 20 or 30 years. They may talk about you. So suck it up.
That's my list of tips for now, I'll update this post if I think of some others. Please note I'm not actually recommending CrossFit as a great activity for 60+. I enjoy CrossFit, but there are less extreme group exercise programs that are probably safer. Just a lot less fun and a lot less effective.

UPDATE 3/28/2023. I asked ChatGPT to create something like this blog post. Damn but it's not bad. It's more generic than my tips, but it didn't actually have my blog post (knowledge base is 2021). It had to have 10 items on the list of course.

Prompt

Write a list of tips for persons over 60 years old doing CrossFit to maximize benefit and minimize injury. Write in the style of the blog at notes.kateva.org.

Result (ChatGPT 4, March 28, 2023)

CrossFit for the Golden Generation - Maximize Benefits and Minimize Injuries After 60

CrossFit is an excellent way for individuals of all ages to stay active and maintain their fitness. For those in their golden years, taking up CrossFit can be an empowering and effective way to promote overall well-being. However, it's important to be aware of certain precautions and modifications to ensure a safe and enjoyable experience. Here are some tips for those over 60 years old embarking on their CrossFit journey:
  1. Consult your doctor: Before you jump into a CrossFit routine, consult your physician to determine whether you have any health conditions or physical limitations that may require modifications.
  2. Choose a suitable CrossFit gym: Look for a CrossFit gym (or "box") that is known for catering to a diverse range of ages and abilities. A good gym will have experienced coaches who understand the unique needs of older adults.
  3. Start slow and steady: Don't rush into high-intensity workouts. Begin with lower intensity exercises to build up your strength, endurance, and flexibility gradually.
  4. Prioritize form over intensity: As an older adult, it's essential to focus on proper form and technique to reduce the risk of injury. Don't hesitate to ask for guidance from your coach.
  5. Modify exercises when needed: Be mindful of your limitations and work with your coach to modify or scale exercises as needed. There's no shame in scaling back to protect your body.
  6. Emphasize mobility and flexibility: Incorporate stretching and mobility exercises into your routine to improve your range of motion and decrease the risk of injury.
  7. Listen to your body: Pay attention to any pain or discomfort you experience during your workouts. If something doesn't feel right, stop and consult your coach or a medical professional.
  8. Stay hydrated and nourished: As you age, your body may require more time to recover from strenuous activities. Ensure you're staying hydrated and consuming a balanced diet to aid in recovery and overall health.
  9. Rest and recover: Give your body ample time to recover between workouts. Schedule rest days and prioritize sleep to allow your body to repair itself and avoid overtraining.
  10. Build a supportive community: Surround yourself with like-minded individuals who share your fitness goals and can offer encouragement, camaraderie, and motivation.
By following these tips, you can maximize the benefits of CrossFit while minimizing the risk of injury. Embrace this new challenge and enjoy the journey to better health and fitness in your golden years!

Wednesday, November 02, 2022

What I learned about managing catalytic converter theft: OEM vs aftermarket vs universal

The catalytic converter on my much loved 2010 Kia Sedona van was stolen. (I think there are two and the rear converter was removed. I'm not a car guy.) It's an every day thing around here.

This is what I learned about this problem.

  1. Manufacturers only stock OEM converters for 10y post model date. So there's no OEM solution.
  2. The normal option to an OEM converter is a "bolt-on" aftermarket product. This is typically installed by a service garage or muffler shop. In Nov 2022 there are none available for the Kia Sedona and many other vehicles. It's a national shortage.
There are three remaining options:
  1. A "straight pipe": This is illegal but in our fallen times nobody seems to care. (Mad Max didn't even have a muffler.) Done by some muffler shops and by guys working out of their home. Oxygen sensor is a common issue, there are probably others. Not so good for the environment, but neither is replacing the vehicle.
  2. A "universal catalytic converter". Insurance companies will send customers to a muffler shop that will install (weld I think) a "universal converter". These are not a perfect match to the vehicle so they may cause performance issues and trigger a check engine light. For this reason service shops avoid them in normal times. That "we don't go there" rule can cause some bad advice in post-apocalyptic times.
  3. Sell or junk the vehicle and pay $50,000 for a new van. If sell then the buyer does one of the above.
Our garage mechanic didn't mention the "universal catalytic converter" option because "they don't do that". Sadly he hadn't updated his algorithm to deal with the national shortage. Now we have a new mechanic (He did apologize for his error, but hd didn't think to offer a retention incentive. I think he'll give better advice in the future.)

If you do replace a catalytic converter it may, of course, be stolen again. Consider a weld-on cage so thieves choose a neighboring vehicle instead. Or a straight pipe so they don't bother. It's handy to have a junk car when parking in unsecured lots in metro Minneapolis St Paul.

[Political aside: property crime will elect the GOP in America. Don't get fooled into thinking that only violent crime rates matter.]