The invention of atomic energy posed a novel global challenge: could the technology be controlled to avoid destructive uses and an existentially dangerous arms race while permitting the broad sharing of its benefits? From 1944 onwards, scientists, policymakers, and other technical specialists began to confront this challenge and explored policy options for dealing with the impact of nuclear technology. We focus on the years 1944 to 1951 and review this period for lessons for the governance of powerful technologies, and find the following: Radical schemes for international control can get broad support when confronted by existentially dangerous technologies, but this support can be tenuous and cynical. Secrecy is likely to play an important, and perhaps harmful, role. The public sphere may be an important source of influence, both in general and in particular in favor of cooperation, but also one that is manipulable and poorly informed. Technical experts may play a critical role, but need to be politically savvy. Overall, policymaking may look more like “muddling through” than clear-eyed grand strategy. Cooperation may be risky, and there may be many obstacles to success.
That is by Waqar Zaidi and Allan Dafoe, at the Centre for Governance of AI, exactly the kind of work people should be doing.
But I’ve gotten really disgruntled with the “prestige TV” landscape and am trying to redirect my content consumption accordingly. One thing that makes movies really great in my view is that before they shoot a movie, they write a screenplay and the screenplay has an end. Both the screenwriter and other people have read that screenplay all the way from beginning to end and they’ve tweaked and changed it and gotten it into a position where they are ready to start production. Then after a movie is filmed, the editor and director work with the footage and come up with a complete movie that has a beginning, a middle, and an end. They then ship the movie out, and it’s screened by critics who watch the entire movie before writing their review.
This does not guarantee that every movie that comes out is good. But it does guarantee that if someone tells you “‘The Menu’ is good,” they are evaluating a completed product…
By contrast, TV shows have this quasi-improvisational quality where the showrunners are constantly needing to come up with new balls to toss into the air. In old-fashioned non-prestigious “adventure of the week”-type shows, this actually works fine because the writers are not building up tension or setting unexplored plots in motion. But as serialized TV storytelling has gotten more and more common, we’re more and more often asked to show patience through early episodes or to try to find things intriguing with no ability to know whether any of it will pay off. Creators often have no idea where they’re going with the story.
Back in HBO’s heyday, the tradeoff was that The Sopranos and The Wire got to paint on a giant canvas and tell stories that are just too capacious for the movie format. But eventually networks got tired of spending that kind of money and cut back the sizes of the casts to something more normal for television.
That is from his Friday mailbag ($). The bottom line is that, like Matt, you should watch more movies and less TV.
Did printing transform the Ottoman Empire? And what took the Ottomans so long to print? Much of the scholarship surrounding the topic of Ottoman printing, or the occurrence of printing within the Ottoman Empire (1453–1922), is structured around these two related frameworks. In this essay, I argue that these frameworks are ahistorical because they predicate Ottoman printing on the European experience of print. To support this point, I examine the disproportionate role played by certain early modern European accounts of Ottoman printing within Western and Arabic historiography. In particular, I examine the life cycle of scholars’ belief that Ottoman sultans banned printing, which I contrast with extant documentation for the imperial Porte’s stance on printing. I argue that the sources available to scholars today do not support the notion that the sultans banned printing. Rather, they demonstrate that this claim arose from early modern European scholars’ search to articulate their sense of Ottoman inadequacy through explanations for why Ottomans did not print. The history of this particular line of inquiry is significant, I argue, because many scholars continue to probe the issue of why Ottomans did not print. In so doing, they maintain the expectation that print would revolutionize society, even though they have begun questioning the existence of the ban.
Degree-educated millennials in London are 41 per cent less likely to own a home than degree-educated boomers were at the same age. And if you think that’s bad, pity the non-graduate under-40s in London, just 20 per cent of whom own a home (among non-graduate boomers of the same age, 60 per cent were homeowners).
The Nuclear Non-Proliferation Treaty, activated in 1970, has been relatively successful in limiting nuclear proliferation. When it comes to nuclear weapons, it is hard to find good news, but the treaty has acted as one deterrent of many to nation-states acquiring nuclear arms. Of course the treaty works, in large part, because the United States (working with allies) has lots of nuclear weapons, a powerful non-nuclear military, de facto control of SWIFT, and so on. We strongly encourage nations not to go acquiring nuclear weapons — just look at the current sanctions on Iran, noting the policy does not always succeed.
One approach to AI risk is to treat it like nuclear weapons and also their delivery systems. Let the United States get a lead, and then hope the U.S. can (in conjunction with others) enforce “OK enough” norms on the rest of the world.
Another approach to AI risk is to try to enforce a collusive agreement amongst all nations not to proceed with AI development, at least along certain dimensions, or perhaps altogether.
The first of these two options seems obviously better to me. But I am not here to argue that point, at least not today. Conditional on accepting the superiority of the first approach, all the arguments for AI safety are arguments for AI continuationism. (And no, this doesn’t mean building a nuclear submarine without securing the hatch doors.) At least for the United States. In fact I do support a six-month AI pause — for China. Yemen too.
It is a common mode of presentation in AGI circles to present wordy, swirling tomes of multiple concerns about AI risk. If some outside party cannot sufficiently assuage all of those concerns, the writer is left with the intuition that so much is at stake, indeed the very survival of the world, and so we need to “play it safe,” and thus they are lead to measures such as AI pauses and moratoriums.
But that is a non sequitur. The stronger the safety concerns, the stronger the arguments for the “America First” approach. Because that is the better way of managing the risk. Or if somehow you think it is not, that is the main argument you must make and persuade us of.
(Scott Alexander has a new post “Most technologies aren’t races,” but he doesn’t either choose one of the two approaches listed above, nor does he outline a third alternative. Fine if you don’t want to call them “races,” you still have to choose. As a side point, once you consider delivery systems, nuclear weapons are less of a yes/no thing than he suggests. And this postulated take is a view that nobody holds, nor did we practice it with nuclear weapons: “But also, we can’t worry about alignment, because that would be an unacceptable delay when we need to “win” the AI “race”.” On the terminology, Rohit is on target. Furthermore, good points from Erusian. And this claim of Scott’s shows how far apart we are in how we consider institutional and also physical and experimental constraints: “In a fast takeoff, it could be that you go to sleep with China six months ahead of the US, and wake up the next morning with China having fusion, nanotech, and starships.”)
Addendum:
As a side note, if the real issue in the safety debate is “America First” vs. “collusive international agreement to halt development,” who are the actual experts? It is not in general “the AI experts,” rather it is people with experience in and study of:
1. Game theory and collective action
2. International agreements and international relations
3. National security issues and understanding of how government works
4. History, and so on.
There is a striking tendency, amongst AI experts, EA types, AGI writers, and “rationalists” to think they are the experts in this debate. But they are only on some issues, and many of those issues (“new technologies can be quite risky”) are not so contested. And because these individuals do not frame the problem properly, they are doing relatively little to consult what the actual “all things considered” experts think.
I have read only about 30 pp. so far, but this is clearly one of the best science books I have read, ever. It is clear, always to the point, conceptual, connects advances in math to the broader history, explains the math, and full of interesting detail. By Reviel Netz. Here is a brief excerpt:
And this is how mathematics first emerges in the historical record: the simple, clever games accompanying the education of bureaucrats.
One of the best books of the year, highly recommended.
1. “We find that using algorithmic responses changes language and social relationships. More specifically, it increases communication speed, use of positive emotional language, and conversation partners evaluate each other as closer and more cooperative. However, consistent with common assumptions about the adverse effects of AI, people are evaluated more negatively if they are suspected to be using algorithmic responses.” Link here.
And perhaps it did not start in the United States? Here is more from David Rozado, including a full research paper:
Great Awokening is a global phenomenon. No evidence it started in US media. Analysis of 98 million news articles across 36 countries quantifies. Exception: state-controlled media from China/Russia/Iran using wokeness terminology to criticize/mock the Westhttps://t.co/yHwPMSR4D0pic.twitter.com/RF30c2UmWQ
She joined Tyler to discuss if there are any useful gender stereotypes in science, distinguishing between productive and unproductive ways to encourage women in science, whether science Twitter is biased toward men, how AI will affect gender participation gaps, how Wikipedia should be improved, how she judges the effectiveness of her Wikipedia articles, how she’d improve science funding, her work on chiral materials and its near-term applications, whether writing a kid’s science book should be rewarded in academia, what she learned spending a year studying art in Florence, what she’ll do next, and more.
Here is the opening bit:
COWEN: Let’s start with women in science. We will get to your research, but your writings — why is it that women in history were so successful in astronomy so early on, compared to other fields?
WADE: Oh, that’s such a hard question [laughs] and a fascinating one. When you look back at who was allowed to be a scientist in the past, at which type of woman was allowed to be a scientist, you were probably quite wealthy, and you either had a husband who was a scientist or a father who was a scientist. And you were probably allowed to interact with science at home, potentially in things like polishing the lenses that you might use on a telescope, or something like that.
Caroline Herschel was quite big on polishing the lenses that Herschel used to go out and look at and identify comets, and was so successful in identifying these comets that she wanted to publish herself and really struggled, as a woman, to be allowed to do that at the end of the 1800s, beginning of the 1900s. I think, actually, it was just that possibility to be able to access and do that science from home, to be able to set up in your beautiful dark-sky environment without the bright lights of a city and do it alongside your quite successful husband or father.
After astronomy, women got quite big in crystallography. There were a few absolutely incredible women crystallographers throughout the 1900s. Dorothy Hodgkin, Kathleen Lonsdale, Rosalind Franklin — people who really made that science possible. That was because they were provided entry into that, and the way that they were taught at school facilitated doing that kind of research. I find it fascinating they were allowed, but if only we’d had more, you could imagine what could have happened.
COWEN: So, household production you think is the key variable, plus the ability to be helped or trained by a father or husband?
The discussion of chirality and her science work is very interesting, though hard to summarize. I very much like this part, when I asked her about her most successful unusual work habit:
But just writing the [Wikipedia] biography of the person I was going to work with meant that I was really prepped for going. And if I’m about to see someone speak, writing their biography before means I get this. That’s definitely my best work habit — write the Wikipedia page of what it is that you are working on.
I don’t agree with her on the environment/genes issue, but overall a very good CWT, with multiple distinct parts.
This paper examines the authorship of post-publication criticisms in the scientific literature, with a focus on gender differences. Bibliometrics from journals in the natural and social sciences show that comments that criticize or correct a published study are 20-40% less likely than regular papers to have a female author. In preprints in the life sciences, prior to peer review, women are missing by 20-40% in failed replications compared to regular papers, but are not missing in successful replications. In an experiment, I then find large gender differences in willingness to point out and penalize a mistake in someone’s work.
Ufuk Akcigit and Nathan Goldschlag (my co-author and former student) have an important new paper on the employment and invention dynamics of US inventors. Amazingly they link data on inventors from patents to census data using anonymized, person-level identifiers, known as Protected Identification Keys (PIKs) so they also have individual data on earnings and employment and they link that data to data on firms.
Ultimately, we observe the employment histories of approximately 760 thousand inventors associated with 3.6 million patents granted between 2000 and 2016.
What they find is twofold. First, an increasing number of inventors are being hired by large incumbent firms (left below). Second, when inventors move to large incumbent firms they earn more but they invent less, compared to similar inventors who go to young firms (right below). Why would an incumbent firm pay more for less productive workers? One possible answer is the Arrow replacement effect, namely a monopolist has less incentive to innovate than a competitive firm becasue the monopolist has a bigger opportunity cost, namely it’s own profits. As Arrow put it: “The preinvention monopoly power acts as a strong disincentive to further innovation.” A logical extension is that a monopolist will be willing to pay not to innovate and one way of doing that is to hire inventors who, if they worked at an entrant, would threaten their monopoly profits.
This is an important paper on declining dynamism in the US economy.
One model of a future course is a super-textbook: lectures, exercises, quizzes, and grading all available on a tablet with artificial intelligence routines guiding students to lectures and
exercises designed to address that student’s deficits and with human intelligence—tutors—on call on an as-needed basis, possibly for extra marginal fees.
…last week, the private Khan Lab School campuses in Palo Alto and Mountain View welcomed a special version of the [GPT] technology into its classrooms.
Rather than solve a math problem for a student, as ChatGPT might do if asked, Khanmigo is programmed to act like “a thoughtful tutor that’s actually going to move you forward in your work,” says Salman Khan, the technologist-turned-educator who founded Khan Academy and Khan Lab School.
Khanmigo was developed in concert with OpenAI, the nonprofit tech start-up that created GPT-4, the underlying technology for the latest version of ChatGPT. OpenAI did not respond to a request for comment on the partnership.
Kevin Kelly (born 1952) is the founding executive editor of Wired magazine, and a former editor/publisher of the Whole Earth Review. He has also been a writer, photographer, conservationist, and student of Asian and digital culture…
Among Kelly’s personal involvements is a campaign to make a full inventory of all living species on earth, an effort also known as the Linnaean enterprise. He is also sequencing his genome and co-organizes the Bay Area Quantified SelfMeetup Group.
How should you choose your next trip? I can see a few general philosophies on the table:
1. Prioritize those countries and regions you haven’t visited yet. For me that might mean Montenegro, Lithuania, Bangladesh, and Saudi Arabia. But the downside is waking up one morning and saying “Hey, what the hell am I doing in Sardinia!?”
2. Get to know some of your favorite places truly in depth, most of all major cities that are easy to reach and often are connected to free or paid invitations. For me that would imply more trips to London, Paris, Tokyo, Berlin — you get the picture. Under this view, the returns to variety are diminishing. And have I ever regretted stopping in on those places?
3. Try to visit “events,” especially temporary events. Right after the Berlin Wall came down, I did a big car trip around Eastern Europe. Loved it. Perhaps these days I should be stopping in at Neom, flying to Lviv, and so on. Those historical moments will never be recaptured. And usually such trips are memorable.
4. Do more trips with the friends you value most, and go wherever will maximize their interest and participation. You already know the world, people are what make life special, and now it is time to “give back” your expertise.
5. Figure out, within the bounds of safety and reasonable expense, where you really don’t want to go. Then go there! Expectations and surprise are everything, right? And how else are you to develop a truly diversified portfolio? Won’t you this way learn the most?
I am indebted to Ben Casnocha for a relevant conversation here, though without holding him liable for any of these views.
Addendum: GPT-4 opts for #3:
As an experienced traveler, if I were to pick only one of the philosophies, I would choose to visit events and historical moments (Philosophy 3). The reason for this choice is that it allows for unique, once-in-a-lifetime experiences that capture the essence of a particular time and place. Such trips often become memorable stories that you’ll cherish for a lifetime.
By prioritizing events and historical moments, you immerse yourself in situations that reveal the true character of a destination and its people, as well as provide valuable insights into the forces that shape societies and cultures. Additionally, this approach can lead to a greater appreciation for the world’s interconnectedness, as you witness firsthand the impact of global events on different regions.
While this philosophy might not cover all aspects of a well-rounded travel experience, it offers a powerful way to engage with the world and create lasting memories that will enrich your life beyond the confines of a single trip.
Somehow missed this the first time I looked, but GPT-4 got *significantly worse* at microeconomics after it was trained to tell you what you want to hear. pic.twitter.com/8tDtTwf1II
Fifty years ago today, on March 23, 1973, Alexander P. Butterfield, the Administrator of the Federal Aviation Administration, issued a rule that remains one of the most destructive acts of industrial vandalism in history.
“No person may operate a civil aircraft at a true flight mach number greater than 1 except in compliance with conditions and limitations in an authorization to exceed mach 1 issued to the operator under Appendix B of this part.”
This text was slightly modified in 1989 and again in 2021, but the upshot remains the same. The rule imposed a speed limit on US airspace. Not a noise standard, which would make sense. A speed limit.
This speed limit has naturally distorted the development of civil aircraft. For fifty years, the aviation industry has worked to improve subsonic aviation. Commercial passenger aircraft are safer and more economical today than they were in 1973, but they are no faster.
If we had propagated the rate of growth in commercial transatlantic aircraft speeds that existed from 1939 to the mid-1970s, we would have Mach-4 airliners by now. But the overland ban put an end to all that. It made small supersonic aircraft, which need to fly shorter overland routes, essentially illegal, closing off the iteration cycle that could drive progress in the industry.
That’s Eli Dourado who notes that modern designs greatly reduce sonic boom. I would also add the following. In 2019 there were 811 million passengers on US domestic flights and 241 million passengers on US international flights. The average duration of a domestic flight is about 2.5 hours and an international fight about 7.3 hours so Americans spend about 3.7 billion hours every year on airplanes. If we could cut even 20% of that time that’s a saving of 757 million hours which has to be weighed against a few people experiencing sonic booms near airports. Indeed, since the people on the airplane are subjected to a lot of the noise the total amount of noise experienced could easily go down with faster aircraft!
The central claim of our work is that GPT-4 attains a form of general intelligence, indeed showing sparks of artificial general intelligence. This is demonstrated by its core mental capabilities (such as reasoning, creativity, and deduction), its range of topics on which it has gained expertise (such as literature, medicine, and coding), and the variety of tasks it is able to perform (e.g., playing games, using tools, explaining itself…). A lot remains to be done to create a system that could qualify as a complete AGI.
Login
FreshRSS 