Sleep, play, AI
Sleep: Yearnings
AI: On Peter Grey; Education
Amazon buys a Nuclear Power plant
Marc Andreessen on AI, Capitalism, jobs
Home Education / non-mainstream Education UnConference, London on April 27th, (Free)
Sleep. Sleep. I’ve always loved sleep. Long sleep energises me for the day. The half-sleep slumber feels comforting. The half-wake dreaming zone nurtures new ideas for me.
JP’s difficulties for sleep are an on-going challenge. This week in particular for me. In moments where I can pull it together I think about Samantha Harvey (more recently) and Charlotte Moore (of more long ago).
Harvey wrote The Shapeless Unease (Amazon link; Guardian review; pre-cursor essay)
“Harvey’s examination of her year-long insomnia is an excavation of the emotions that might cause sleeplessness. It’s a kind of philosophical detective story strewn with submerged clues. Lying awake at 3am, she circles the shrinking perimeter of her mind for answers, like “a polar bear in its grubby blue-white plastic enclosure with fake icecaps and water that turns out to have no depth” (Grant in Guardian)
I’ve rarely had sleepless nights without JP being the cause, so my sleepless roots are different but still I latched on to her writing. Her words giving some comfort and resonance. The forms of her words also resonate with me as they verge on the poetic; both in structure, form and word-smithing. The, in places, fractured, shifting form reflecting that nature of sleeplessness.
I read Charlotte Moore around 2012. Her book on family life (column here, amazon here; YT on Moore speaking, 2012) with two autistic, one typical son is an insightful, elegiac read. Moore has a whole chapter on sleep “Did you sleep well, dear?” I paraphrase but one notion that stuck with me “Once I gave up the expectation of a good night’s sleep, the night was easier to handle”. When I feel I have enough water in my soul-well, I cling to this idea and it helps. The whole chapter resonated and resonates still.
Sleep torture seemingly only works when the enforcement is against your will. If you can bend it, and bend expectations, maybe you can feel better - although easier said than done.
The new version of the generative AI Claude was released earlier in March. Claude 3 has the same expertise as GPT-4 with different flavours etc. Once you have used Claude / GPT for at least 10 hours or so, so you can try out prompts and learn how to use it, it’s very much like having a generalist under-graduate to postgraduate level assistant on any topic. The more esoteric, the more powerful. It could really change education and home education could be very positively affected.
JP also uses it for entertainment. He chats with it in his own way and finds this pretty amusing. It can be pretty useful for self-directed exploration.
This is GPT-4 on Peter Grey:
Peter Gray is a well-known research professor of psychology at Boston College and an influential figure in the field of educational psychology. His work primarily focuses on the role of play in learning, the importance of autonomy for children's development, and the critique of traditional schooling systems. Here are some of the best and main ideas Gray has contributed to the field:
1. **The Importance of Play**: Gray argues that play is not just a leisure activity for children but a critical component of their learning and development. He believes that through play, children learn social skills, problem-solving abilities, and gain emotional resilience. Play allows children to explore, experiment, and understand the world around them in a natural and enjoyable way.
2. **Self-Directed Education**: One of Gray's central ideas is that children are naturally curious and capable of directing their own learning. He advocates for self-directed education, where children are given the freedom to pursue their interests and passions. This approach contrasts sharply with traditional education systems, which often follow a standardized curriculum and assessment method.
3. **Critique of Conventional Schooling**: Gray is a vocal critic of the conventional schooling system, which he argues stifles creativity, curiosity, and intrinsic motivation. He points out that the compulsory, one-size-fits-all education model does not accommodate individual learning styles and interests, leading to disengagement and stress among students.
4. **The Role of Play in the Evolution of Human Societies**: Gray extends his analysis of play beyond individual development to its role in the evolution of human societies. He suggests that the capacity for play has been crucial for the development of human culture, innovation, and cooperation.
5. **Freedom to Learn**: In his book "Freedom to Learn," Gray outlines how a learning environment that respects children's natural ability to learn through play and exploration can be more effective than traditional education methods. He emphasizes the importance of trust in children's innate drive to learn and how environments that support autonomy and choice foster a lifelong love for learning.
6. **The Decline of Play and Rise of Mental Health Issues**: Gray has raised concerns about the decline of free play in children's lives due to increased academic pressures, structured extracurricular activities, and screen time. He links this decline to the rising rates of mental health issues among young people, suggesting that the loss of play contributes to stress, anxiety, and depression.
7. **Evolutionary Perspective on Education**: Gray often takes an evolutionary perspective, arguing that the ways children are biologically designed to learn—through play and exploration—have been honed over millennia. He believes that educational systems should align more closely with these natural learning processes.
Gray's ideas have sparked significant discussion and debate in educational circles, influencing parents, educators, and policy makers to reconsider the structure and purpose of education in promoting children's well-being and learning.
This was Marc Andreessen on AI; also on capitalism in a recent chat with Tyler Cowen. Marc is very positive, and remains skeptical that this would be bad for the kids etc.
On AI:
how will AI make our world different five years from now? What’s the most surprising way in which it will be different?
ANDREESSEN: [chuckles] There’s a great breakdown on adoption of new technology that the science-fiction author Douglas Adams wrote about years ago. He says any new technology is received differently by three different groups of people. If you’re below the age of 15, it’s just the way things have always been. If you’re between the ages of 15 and 35, it’s really cool, and you might be able to get a job doing it. If you’re above the age of 35, it’s unholy and against the order of society and will destroy everything.
AI, I think, so far is living up to that framework. What I would like to tell you is AI is going to be completely transformative for education. I believe that it will.
Having said that, I did recently roll out ChatGPT to my eight-year-old. I was very, very proud of myself because I was like, “Wow, this is just going to be such a great educational resource for him.” I felt like Prometheus bringing fire down from the mountain to my child. I installed it on his laptop and said, “Son, this is the thing that you can talk to anytime, and it will answer any question you have.” He said, “Yes.” I said, “Well, no, this is a big deal. It answers questions.” He’s like, “Well, what else would you use a computer for?” I was like, “Oh, God, I’m getting old.”
I actually think there’s a pretty good prospect that kids are just going to pick this up and run with it. I actually think that’s already happening, right? ChatGPT is fully out, and Bard and Bing and all these other things. I think kids are going to grow up with basically — you could use various terms, assistant, friend, coach, mentor, tutor, but kids are going to grow up in this amazing back-and-forth relationship with AI.
Anytime a kid is interested in something, if there’s not a teacher who can help with something or if they don’t have a friend who’s interested in the same thing, they’ll be able to explore all kinds of ideas. I think it’ll be great for that. I think it’s obviously going to be totally transformative and feels like warfare, and you already see that. The concern, quite honestly — I actually wrote an essay a while ago on why AI won’t destroy all the jobs.
The short version of it is because it’s illegal to do that because so many jobs in the modern economy require licensing and are regulated. I think the concern would be that there’s just so much glue in the system now that prevents change. It’ll be very easy to not have AI healthcare or AI education or whatever because, literally, some combination of doctor licensing, teacher unions, and so forth will basically outlaw it. I think that’s the risk.
On capitalism via James Burnham:
Burnham is not famous, but he should be famous. Burnham has a fascinating story. He’s a thinker in the 20th century who talked a lot about these issues. He started out life, as a lot of people do in the 1920s and ’30s, as a dedicated Trotskyite, full-on communist. He’s a very special guy. Burnham was a very brilliant guy. He was such a dedicated communist that he was close personal friends with Leon Trotsky, which is how you really know how you’ve made it when you’re a communist.
He would have these huge arguments with Trotsky, which is not the safest thing in the world to do. Apparently, he got away with it. Very enthusiastic communist revolutionary through the ’30s. Then in the ’40s, he’s a very smart guy and he started to figure out that was a bad path. He went through this process of rethinking everything. By the 1950s, he was so far to the right that he was actually a co-founder of National Review magazine with William Buckley, who always said he was the intellectual leading light at National Review.
He’s got works that he wrote that will accommodate the full spectrum of politics. In his middle period where he was trying to figure out — this is like in the 1940s — he was trying to figure out where things are going. There were enormous questions in the 1940s because it was viewed as a three-way war for the future between communism on the far left, fascism on the far right, and then liberal democracy floating around there somewhere.
His best, most well-known book is called The Managerial Revolution, which talks a lot about the issues we’ve been discussing, and it was written in 1941. It’s fascinating for many reasons, part of which is, he was still mad about communism. He debunks communism in it. Also, they didn’t know who was going to win World War II. It talks about this battle of ideologies as if it were still an open topic, which is super interesting.
He did this very Marxian analysis of capitalism. He made the observation that I see every day, which is there are fundamentally two types of capitalism. There’s the original model of capitalism, which he calls bourgeois capitalism, which you could think like Henry Ford is the archetype of that. A capitalist starts a company, runs the company, name on the door, ownership of the company, control the company, dictator of the company, complete alignment of a company with an individual.
Then he talks about this other emerging form of capitalism at that time called managerial capitalism. In managerial capitalism, you think about today’s modern public companies. Think about Walmart or whatever, any public company where, in theory, there are shareholders. Really, what there are is, there are millions and millions of shareholders that are incredibly dispersed. Everybody in this room owns some three shares of Walmart stock in a mutual fund somewhere.
You don’t wake up in the morning wondering what’s happening to Walmart. It doesn’t even occur to you to think about yourself as an owner. What you get instead is this managerial class of actually both investors like fund managers and then also executives and CEOs who actually run these companies. They have control, but without ultimate responsibility, without ultimate ownership.
The interesting thing he said about that is, he said, “Look, managerialism is, basically, it’s not that it’s good or bad. It just is necessary because companies and institutions and governments and all the rest of it get to the point where they’re just too big and too complicated for one person to run everything. You’re going to have the emergence of this managerial class who’s going to run things.”
There’s a flip side of it, which is, the people who are qualified to be managers of large organizations are not themselves the kind of people who become bourgeois capitalists. They’re the other kind of person. They’re often good at running things, but they generally don’t do new things. They generally don’t seek to disrupt or seek to create or seek to invent.
One way of thinking about what’s happened in our system is, capitalism used to be bourgeois capitalism. It got replaced by managerial capitalism without actually changing the name. That will necessarily lead to stagnation. By the way, that may be necessary that that happens because the systems are too complicated, but that will necessarily lead to stagnation.
Then what you need is, basically, the resumption of bourgeois capitalism to come back in and, at the very least, poke and prod everybody into action. That, aspirationally, is what we do and what our startups do.
This is GPT-4 on Burnham - no way of including the interesting context of Trotsky, but good on the main ideas.
James Burnham (1905-1987) was an influential American philosopher and political theorist, particularly known for his work "The Managerial Revolution: What is Happening in the World" (1941). In this book, Burnham explored the transformation of capitalism into a new socioeconomic order that he termed "managerial society." Below are some of his most important ideas, including those on types of capitalism as elaborated in his work:
### Managerial Revolution
- **End of Capitalism:** Burnham argued that traditional capitalism, characterized by private ownership and control of the means of production, was being replaced. He suggested that control was shifting away from owners (capitalists) and into the hands of a new class of professional managers and bureaucrats.
- **Rise of Managerial Society:** This new society was not based on ownership of capital but on the management and control of the production and distribution processes. According to Burnham, this shift would lead to a societal structure where managerial elites hold the real power, rather than traditional capitalists or the state.
- **Types of Managerial Societies:** Burnham believed that this transformation could lead to different forms of managerial societies. He identified three types—capitalist managerialism (where managers run businesses but operate within a capitalist framework), state capitalism (where the state takes on the managerial role, as seen in Nazi Germany and the Soviet Union of his time), and workers' control (a less likely outcome from his perspective).
### Predictions and Impact on Political Theory
- **State's Role in Economy:** Burnham's work anticipated the increasing intervention of the state in economic affairs, a trend that became more pronounced in the mid-20th century with the rise of welfare states and mixed economies.
- **Cold War Dynamics:** Although initially a Trotskyist, Burnham's views evolved, and he became a leading anti-communist voice in the United States. His analysis of the Soviet Union as a form of state capitalism influenced discussions on the nature of Soviet society and the broader dynamics of the Cold War.
- **Influence on Neoconservatism:** Later in his career, Burnham's ideas would influence the development of neoconservatism. His emphasis on the role of elites and skepticism towards popular democracy resonated with many in the neoconservative movement.
Burnham's ideas, particularly those articulated in "The Managerial Revolution," have had a lasting impact on discussions about the evolution of capitalism and the nature of modern power structures. His conceptualization of a post-capitalist, managerial society remains a reference point for analyses of contemporary economic and political systems.
Optimistic thinkers tend to be optimistic on jobs. Partly as they have a nuanced take on what “comparative advantage” means for jobs. Here is Noah Smith on this:
“…when I cheerfully tell them that it’s very possible that regular humans will have plentiful, high-paying jobs in the age of AI dominance — often doing much the same kind of work that they’re doing right now — technologists typically become flabbergasted, flustered, and even frustrated. I must simply not understand just how many things AI will be able to do, or just how good it will be at doing them, or just how cheap it’ll get. I must be thinking to myself “Surely, there are some things humans will always be better at machines at!”, or some other such pitiful coping mechanism.
But no. That is not what I am thinking. Instead, I accept that AI may someday get better than humans at every conceivable task. That’s the future I’m imagining. And in that future, I think it’s possible — perhaps even likely — that the vast majority of humans will have good-paying jobs, and that many of those jobs will look pretty similar to the jobs of 2024.
At which point you may be asking: “What the heck is this guy smoking?”
Well, I’ll tell you.
In which I try to explain the extremely subtle but incredibly powerful idea of comparative advantage
When most people hear the term “comparative advantage” for the first time, they immediately think of the wrong thing. They think the term means something along the lines of “who can do a thing better”. After all, if an AI is better than you at storytelling, or reading an MRI, it’s better compared to you, right? Except that’s not actually what comparative advantage means. The term for “who can do a thing better” is “competitive advantage”, or “absolute advantage”.
Comparative advantage actually means “who can do a thing better relative to the other things they can do”. So for example, suppose I’m worse than everyone at everything, but I’m a little less bad at drawing portraits than I am at anything else. I don’t have any competitive advantages at all, but drawing portraits is my comparative advantage.
The key difference here is that everyone — every single person, every single AI, everyone — always has a comparative advantage at something!
To help illustrate this fact, let’s look at a simple example. A couple of years ago, just as generative AI was getting big, I co-authored a blog post about the future of work with an OpenAI engineer named Roon. In that post, we gave an example illustrating how someone can get paid — and paid well — to do a job that the person hiring them would actually be better at doing:
Imagine a venture capitalist (let’s call him “Marc”) who is an almost inhumanly fast typist. He’ll still hire a secretary to draft letters for him, though, because even if that secretary is a slower typist than him, Marc can generate more value using his time to do something other than drafting letters. So he ends up paying someone else to do something that he’s actually better at.
(In fact, we lifted this example from an econ textbook by Greg Mankiw, who in turn lifted it from Paul Samuelson.)
Note that in our example, Marc is better than his secretary at every single task that the company requires. He’s better at doing VC deals. And he’s also better at typing. But even though Marc is better at everything, he doesn’t end up doing everything himself! He ends up doing the thing that’s his comparative advantage — doing VC deals. And the secretary ends up doing the thing that’s his comparative advantage — typing. Each worker ends up doing the thing they’re best at relative to the other things they could be doing, rather than the thing they’re best at relative to other people.
This might sound like a contrived example, but in fact there are probably a lot of cases where it’s a good approximation of reality…”
Amazon bought a nuclear powered data centre:
“One of the US’s largest nuclear power plants will directly power cloud service provider Amazon Web Services’ new data center.
Power provider Talen Energy sold its data center campus, Cumulus Data Assets, to Amazon Web Services for $650 million. Amazon will develop an up to 960-megawatt (MW) data center at the Salem Township site in Luzerne County, Pennsylvania.
The 1,200-acre campus is directly powered by an adjacent 2.5 gigawatt (GW) nuclear power station also owned by Talen Energy.
The 1,075-acre Susquehanna Steam Electric Station is the sixth-largest nuclear power plant in the US. It’s been online since 1983 and produces 63 million kilowatt hours per day.”
The consensus now seems to be that while nuclear is not renewable like solar, it is clean with respect to carbon / GhG; and its baseload qualities means it is an important and useful part of the energy mix.
Cultural attitudes to nuclear are in flux and depends on nations. France is fairly pro, Germany is anti. In this particular transaction there is a challenge of “additionality” has Amazon done anything additional? In some respects not the nuclear power station is already built, but it is probably a positive signal there will also be a new data centre which is additional to some extent.
If you can not make it, do consider writing for the blog/essay prizes on ideas or experiences you have.
We are offering up to 10 prizes of £100 for work relating to the theme of non-mainstream education. Everyone is welcome to take part but young people are particularly encouraged to submit entries. At least 5 prizes are intended for young people (21 and under).
These could be essays, videos, blogs or talks about non-mainstream (or even mainstream pedagogy) education. Anything is open, for instance: How should we think about home education? The pros and cons of maths circles and their application outside maths? What would Dewey think of the education landscape today? How will AI change education? What Unschooling can teach us?
Submission Form is here.
Links:
On my last climate pod
https://x.com/benyeohben/status/1763568031010029698?s=46&t=8d36mwn7wEu1Kwy6I5vyag
On Taylor Swift and the left
https://x.com/benyeohben/status/1768272976082849999?s=46&t=8d36mwn7wEu1Kwy6I5vyag
Mark Ravenhill on Derek Bond
https://x.com/markravenhill2/status/1764988548770406622?s=46&t=8d36mwn7wEu1Kwy6I5vyag
On Claude tests
https://x.com/michael_nielsen/status/1764739746432229490?s=46&t=8d36mwn7wEu1Kwy6I5vyag
Ben- Thanks for sharing this. Never thought Sleep, play, AI would ever be a sequence of words I'd hear. I guess we're living in these times now. Hope you're well this week. Cheers, -Thalia
Hey Ben - would you be mind if I clone your UnConference project for Honolulu? Might have a few parents would be interested in doing a half day event...