Steve Miller

Steve Miller Shares the Stories Behind His Greatest Hits (Parade)

Image: Tim Mosenfelder/Getty Images

[ed. Quite a musical life, right there at the ascendance of the Chicago blues scene and widely respected by Muddy Waters, Hubert Sumlin, Howlin' Wolf, Charlie Musselwhite, Mike Bloomfield, Paul Butterfield, et al. See also: Born In Chicago (NYT).]

Five decades ago, in the summer of 1973, a nervous Steve Miller entered the studio to record an album he thought might very well bring his career to a close. By that point he had released seven worthy albums that only attracted a cult audience. “I definitely felt this record was my last shot,” Miller said by phone the other day, before a show on his current sold-out tour. “I was at the end of my recording contract, and I wasn’t hearing anything from the label. If this didn’t work, I thought I might be teaching high school English the next year.”

Instead, he wound up giving the world a master class in how to make a smash hit. The first song he recorded, “The Joker,” was the ‘70s equivalent of a viral sensation, taking off at radio stations around the country on impact, eventually soaring to No. 1. That turned out to be just the beginning. Over the next decade, Miller and The Steve Miller Band racked up a string of ingeniously upbeat singles like “Rock’n Me” (another No. 1 score), “Fly Like an Eagle,” “Jet Airliner,” “Take the Money and Run,” “Jungle Love” and “Abracadabra” (a chart-topper in 1983).

To mark the start of his dramatic turnaround 50 years ago, Miller has just released J50: The Evolution of The Joker, a collection that marries the album’s original tracks to 27 previously unreleased recordings from the same sessions. To Miller, the secret to his late-breaking success had to do both with having nothing to lose and with finally gaining control over the recording process. While his earlier work had been produced by others, on “The Joker” he called all the shots. “Just going in with the band and doing it on my own was so much less cumbersome,” he said. “The whole process of making the album was 17 days, start to finish.”

Another key element was his eagerness to learn how to hone hits. “I had always enjoyed the art of making singles, but the more I did it, the more I learned,” he said. “I felt that you need at least five hooks in a single. And the first ten notes have to make people go, ‘What’s that?’ It’s quite a puzzle to put all that together.”

With a boyish enthusiasm that belies his 79 years, Miller told Parade the stories behind the key songs that have made him one of America’s biggest hit-makers.

"The Joker" (1973)

In Miller’s first No. 1 score, nearly every sound you hear is a hook, from the lazy bass to the loopy guitar to the quirky vocal. “I wasn’t consciously going for all that,” Miller said. “Everything just came together quickly and naturally. The song had a great chorus. It had this slide guitar. It had a different-sounding, lazy groove. It’s only in hindsight where you go, ‘well, that was brilliant!’”

For another draw, Miller quoted a racy line from an old hit by the vocal group The Clovers—“really love your peaches/wanna shake your tree.” He didn’t realize, however, that this would mean sharing the publishing royalties with its authors. “I thought it was just a tip of the hat,” he said. Despite the sexiness of the line, and a drug reference elsewhere in the lyrics, Miller said “nobody at radio questioned it. I think every kid that heard it got it, but no adult knew what it was about.” One thing that did get everyone’s attention was a line that later became famous in which Miller preached “the pompatus of love.”

“It sorta sounded like pompous,” the singer said of the nonsensical word he made up. “I get letters from lawyers all the time asking me to define it because lawyers always want to know what things mean. To me, it’s just funny.”

“Fly Like an Eagle” (1976)

One of Miller’s biggest hits was also the first to feature a new instrument—the ARP synthesizer—which he used to create a spacey sound that undulates throughout the song. “I was a huge electronic music fan, going back to Stockhausen in the early ‘60s,” Miller said. “The electronics I used back on the [earlier FM-radio hit] ‘Space Cowboy’ sounded like somebody turning over a car carburetor under water. But the new ARP was so much easier. It was a natural to become a pop hook.”

The catchy riff in “Eagle” had actually appeared in another Miller song, “My Dark Hour,” seven years earlier. That track featured none other than Paul McCartney on drums, bass and backing vocal, though few knew it. The improbable Miller-Beatles connection came about because his producer, Glyn Johns, was the audio engineer on “Let It Be.” In 1969, when Miller was in London to record with Johns, the producer introduced him to the Fab Four. “They were meant to record some tracks one day, but John and Ringo didn’t show,” Miller said. “I’d never seen guys not show up to a booked recording session before. That was unbelievably wasteful.”

To make use of the session time, Johns suggested Paul and Miller jam, resulting in “My Dark Hour.” “It was like we’d been playing together forever,” Miller said. “Anything Paul played was just right.”

Miller felt disappointed, though, when the Beatle only allowed himself to be pseudonymously credited on the song as “Paul Ramon.” Regardless, Miller thought this was “going to be the biggest single of my life! Instead, it was like it was dropped down the mail chute of the Empire State Building straight into hell.”

To compensate, Miller said the riff he repurposed for “Fly Like an Eagle” was “so much better.” It was so good, in fact, that the song went platinum and inspired a cover by Seal in 1996. “He didn’t do anything different with it,” Miller said. “So, I wasn’t impressed.”

by Jim Farber, Parade |  Read more:

Image: Tim Mosenfelder/Getty Images; Wikipedia
[ed. From the video comments re: "My Dark Hour"]

"This was recorded at Olympic Studios, Barnes, on the night of the 9th May 1969, when the four Beatles had an enormous bust-up about Allen Klein becoming their manager; they were all at the studios, when producer/engineer Glyn Johns, detecting an impending argument, left the room, and the conversation turned from music to business - the contract for Klein to manage them had been signed by John, George and Ringo, but Paul - who had been warned by Mick Jagger about Klein and didn't trust or like him - baulked at the 20% Klein was demanding, saying to the other Beatles that Klein should be offered 15%, because "we're a big band" and refused to sign. The other three thought it was another example of Paul stalling and derailing the contract negotiations, and a huge argument ensued, with them all verbally laying into Paul, and basically storming out while all individually telling him to 'fuck off'. He was sat alone in the studio, feeling pretty beaten up and isolated, betrayed by his three best mates and sorry for himself, when Steve Miller breezed in, looking for some studio time - Paul knew Steve and asked if he could play on the track, so did drums (which he'd previously done on several Beatles' tracks when Ringo had walked out of the White Album sessions for a week; most notably 'Back in the USSR'), bass, some guitar and backing vocals. The other three Beatles went ahead with assigning Klein as manager, and although John Lennon was the driving force in appointing Klein, years later he admitted Paul was right to be suspicious. He appeared on this track as 'Paul Ramon', which was first used as a stage name by Paul when the 'Silver Beetles' (then still with Stuart Sutcliffe on bass and Tommy Moore as a stand-in drummer) toured Scotland in May 1960, as the backing band to a Larry Parnes' act, Johnny Gentle (real name John Askew). John Lennon was 'Long John', George was 'Carl Harrison' (after his hero Carl Perkins) and Stuart was Stuart de Stael (after French-Russian artist Nicolas de Stael)."

Ninety-Five Theses on AI

Ninety-five theses on AI (Samuel Hammon/Second Best)

Image: uncredited

[ed. A lot to unpack here re: all things AI, from the micro-to-macro with broad insights and predictions concerning the technology, industry, issues, debates, politics, and other "theses" surrounding AI now and going forward (with many good links, as well). Highly recommended. Excerpts:]

Most proposed “AI regulations” are ill-conceived or premature

1. There is a substantial premium on discretion and autonomy in government policymaking whenever events are fast moving and uncertain, as with AI.

2. It is unwise to craft comprehensive statutory regulation at a technological inflection point, as the basic ontology of what is being regulated is in flux.

3. The optimal policy response to AI likely combines targeted regulation with comprehensive deregulation across most sectors.

4. Regulations codify rules, standards and processes fit for a particular mode of production and industry structure, and are liable to obsolesce in periods of rapid technological change.

5. The benefits of deregulation come less from static efficiency gains than from the greater capacity of markets and governments to adapt to innovation.

6. The main regulatory barriers to the commercial adoption of AI are within legacy laws and regulations, mostly not prospective AI-specific laws.

7. The shorter the timeline to AGI, the sooner policymaker and organizations should switch focus to “bracing for impact.”

8. The most robust forms of AI governance will involve the infrastructure and hardware layers.

9. Existing laws and regulations are calibrated with the expectation of imperfect enforcement.

10. To the extent AI greatly reduces monitoring and enforcement costs, the de facto stringency of all existing laws and regulations will greatly increase absent a broader liberalization.

11. States should focus on public sector modernization and regulatory sandboxes and avoid creating an incompatible patchwork of AI safety regulations.

AI progress is accelerating, not plateauing

1. The last 12 months of AI progress were the slowest they’ll be for the foreseeable future.

2. Scaling LLMs still has a long way to go, but will not result in superintelligence on its own, as minimizing cross-entropy loss over human-generated data converges to human-level intelligence.

3. Exceeding human-level reasoning will require training methods beyond next token prediction, such as reinforcement learning and self-play, that (once working) will reap immediate benefits from scale.

4. RL-based threat models have been discounted prematurely.

5. Future AI breakthroughs could be fairly discontinuous, particularly with respect to agents.

6. AGI may cause a speed-up in R&D and quickly go superhuman, but is unlikely to “foom” into a god-like ASI given compute bottlenecks and the irreducibility of high dimensional vector spaces, i.e. Ray Kurzweil is underrated.

7. Recursive self-improvement and meta-learning may nonetheless give rise to dangerously powerful AI systems within the bounds of existing hardware.

8. Slow take-offs eventually become hard.

A Beginner’s Guide to Sociopolitical Collapse - Or, How (Not) to End Up in the Ash Heap of History

“A society does not ever die ‘from natural causes,’ but always dies from suicide or murder—and nearly always from the former.” — D. C. Somervell.

À propos of nothing, I have found myself wondering recently what it would be like to live through a collapse. Would I see it coming? What would be the signs?

A number of times in human history, a society has gone from a relatively high level of sociopolitical complexity to a much lower one—rapidly, within the span of a few decades. This is what we will call collapse. Collapse manifests as a lower degree of social differentiation and economic specialization, less centralized control, less behavioral control, less investment in art and monuments, a lower flow of information within society, less sharing and trading of resources, a lower degree of social coordination and organization, and territorially smaller political units. And a lot of people probably starve, if they don’t meet more violent ends.

Collapse is a fate that befell at least the Western Zhou empire; the Harappan civilization of the Indus Valley; medieval Mesopotamia in parts of the Abbasid caliphate, including the Anarchy at Samarra; the Egyptian Old Kingdom; the Hittites; the Minoans; the Mycenaeans; the Western Roman empire; the Olmecs; the Lowland Classic Maya; Teotihuacan, Monte Albán, and Tula in the Mesoamerican highlands; Casas Grandes in northern Mexico; the Chacoans in what is today New Mexico; the Hohokam in southern Arizona; the Eastern Woodlands civilization, including the Mississippians centered on Cahokia in today’s East St. Louis; the Huari and Tiahuanaco in Peru; the Kachin of highland Myanmar, who oscillated between complex and egalitarian social forms as described by James C. Scott; and the Ik of northern Uganda, who have simplified society to such an extent that they allegedly reject familial bonds, although this has been disputed.

Collapse has happened often enough that it is not likely to be a series of flukes, but a general feature of human social organization. Not every society eventually suddenly collapses; it may be the case that when one does it is because some particular conditions obtain. What are those conditions? Can we come up with a general explanation? And while the subject is interesting as a pure matter of social science, we all want to know: could it happen here?

The GOAT on the topic of collapse is archeologist Joseph Tainter. His 1988 book The Collapse of Complex Societies weaves together historical and prehistorical fact, an insistence on explaining the cross-sectional variation, rigorous theorizing including an embrace of marginal analysis, and generally great social scientific judgment. It is a tour de force. If you want to understand why it has lived rent-free in my head for the last few months, as several friends can attest, read on.

Why complexity?

If we’re going to understand why societies sometimes spontaneously simplify, we must first have a solid theory about why they become complex in the first place. In both a historical and analytical sense, simple human societies arise first. These simple societies are highly egalitarian and non-hierarchical. Why do they move toward greater hierarchy, stratification, inequality, and complexity?

There are broadly two views on this question. One view is dominated by class conflict. The state reflects domination and exploitation based on divided interests. A ruling class coercively subjugates the population out of greed and selfishness. Marxists are not the only exponents of this view, but they are perhaps the most vehement, viewing society as sharply divided between workers who engage in social production and elites who appropriate the output. Of course, subjugation of subpopulations happens—American slavery is a gruesome example. The pure class conflict view is that subjugation explains the entirety of society, which is composed of ruling elites and subject populations.

At the other end of the spectrum are integrationist or functionalist views, which are based on shared interests between members of society. Even an egalitarian society is going to face problems, and many of these problems are most readily addressed by creating some form of hierarchy and social division of labor. For example, limited water resources may require the creation and maintenance of an irrigation system, including the need to mobilize and direct labor. The threat of invasion may require the establishment of military defense, including a command and control system. In general, society faces some problem, which requires the creation of public goods, which requires the creation of administrators, who are rewarded for realizing the benefits of centralization. Complexity solves social problems and serves population-wide needs.

Tainter adopts a moderate position, one that leans integrationist but also includes a role for class conflict. Complexity in society does exist to solve problems and provide benefits to the populace. And yet, “compensation of elites does not always match their contribution to society, and throughout their history, elites have probably been overcompensated relative to performance more often than the reverse.” Public choice considerations mean that even if complexity arises to solve broad-based social problems, the ultimate distribution of the benefits can be influenced by greed and power. “Integration theory is better able to account for distribution of the necessities of life, conflict theory for surpluses.”

Although the distribution of the social surplus is not always fair, in what follows, the role of complexity in society as a problem-solving mechanism is what is most important. Without this foundation, collapse is no big deal, or good, or perhaps it is even the ascension of society to a Marxist anarcho-primitivist Utopia. We can sympathize with this view when true subjugation is occurring, while recognizing that, in the general case, complex society exists to solve social problems.

Collapse theory

There are many non-general or underspecified theories of collapse. Tainter goes through these exhaustively, but I’ll run through a few of them that deserve special mention.

1. Depletion of a vital resource. These explanations are popular with environmentalists, and feature strongly in books like Jared Diamond’s Collapse (which came out 16 years after Tainter’s). Tainter has contempt for depletion arguments as a causal mechanism, because, as we have just discussed, the complexity of society exists to solve problems including resource depletion. What about all the times that resources are effectively stewarded? Is it not true that for most resource/society/time period combinations, societies do just fine in not collapsing due to resource depletion? Depletion arguments don’t explain the cross-sectional variation, why sometimes societies effectively manage resources and other times they don’t. “If a society cannot deal with resource depletion (which all societies are to some degree designed to do) then the truly interesting questions revolve around the society, not the resource. What structural, political, ideological, or economic factors in a society prevented an appropriate response?”

2. Insufficient response to circumstances. Suppose a society is faced with a problem, perhaps depletion of a vital resource. Not responding to the problem can lead to collapse. But why does this insufficient response occur? Often, historians have argued that a society is a lumbering dinosaur, a runaway train, or a house of cards—static, incapable of changing directions, or fragile. While these theories rightly recognize that collapse depends more on the characteristics of a society than on its stresses, they too do not explain the cross-sectional variation. After all, societies sometimes do respond to serious problems in dynamic, agile, and robust ways. What explains why they would suddenly stop doing that?

3. Elite mismanagement. To some extent, exploitation and misadministration is a normal feature of hierarchical societies. Even if we take a class conflict view, shouldn’t elites, if they are even slightly rational, view the support population as a vital resource? If so, then the problem becomes the same as in the “vital resource” explanation given above. If we blame elite greed and self-aggrandizement, why should we assume that this is variable, and if it is variable, how can we explain it? Again, allegations of mere elite mismanagement do not explain the cross-sectional variation.

Tainter discusses many other theories, and holds particular contempt for decadence theories of collapse, which are common in the literature, but which he considers mystical and non-scientific. They too do not explain the cross-sectional variation.

So what does explain the cross-sectional variation? Tainter develops a theory based on diminishing marginal returns. Diminishing marginal returns are ubiquitous in economic analysis and indeed in life. The first bite of a pecan pie is sublime; the 20th may be cloying. The same principle operates in countless domains. The exceptions are usually temporary, yielding increasing returns to scale over some range, but eventually succumbing to diminishing returns. Tainter argues that there are diminishing returns to complexity itself.

Society adds complexity to address problems and stresses. In an American context, this is easy to understand. When drugs are unsafe, we increase the stringency of FDA review. When federal projects are too polluting, we pass the National Environmental Policy Act. When there is an oil shock, we create a federal Department of Energy. Terrorist attack? Department of Homeland Security. Financial crisis? CFPB.

This added complexity accumulates. As it does so, it requires resources—Tainter emphasizes energy and fiscal resources—to maintain. Often, the resource demands of one piece of complexity necessitate more complexity, as when a higher tax rate necessitates new resources to be put into legitimization and coercion. The complexity accumulates as a system. At first, the cost-benefit ratio of this added complexity is very favorable, and the marginal benefits are high. As more complexity is added, the marginal benefits diminish, then go to zero, before turning negative.

A society that is past complexity level C2 on the graph above is in a very precarious position. Many members of a society at C3 would rather be at C1, although there is no direct path there because, as just noted, the complexity itself behaves as a system. As Tainter puts it, “when the marginal cost of participating in a complex society becomes too high, productive units across the economic spectrum increase resistance (passive or active) to the demands of the hierarchy, or overtly attempt to break away.” He emphasizes that this can be equally true across the income spectrum; everyone from the peasants to the merchant class to the nobility will be tempted to defect from the current system. “A common strategy is the development of apathy to the well-being of the polity.”

The situation can spiral out of control quickly. An overtaxed peasantry may put up little resistance to invaders. Increasing costs can make public services unsustainable. An increasing share of resources may have to be devoted to legitimation and control. The economy weakens. The ability or desire to meet new challenges evaporates. Collapse is only one new problem away.

According to Tainter, collapse can temporarily be prevented by the acquisition of a new technological capability or energy subsidy. With the additional resources afforded by the technology or subsidy, societies can support a higher degree of complexity. I think Tainter’s graphical representation of this point gets it wrong, but the image below from Ben Reinhardt accurately captures how I envision it.

Even this possibility, however, does not change the logic that the returns to complexity eventually diminish and go negative. If a society keeps increasing its level of complexity, it will inevitably get to a point at which the population would prefer less complexity.

by Eli Dourado |  Read more:

Images: Carole Raddato; Ben Reinhardt

via:

Translation: Yakiton (grilled pork skewers)
via:

Miguel Carbonell Selva, Death of Sappho, 1881 
via:

Asking AI Some Questions

[ed. I'm aware that there's an art to extracting detailed and actionable information from AI queries, and this probably illustrates that point. I found it very hard, despite repeated requests for specificity, to get ChatGPT to produce anything other than what sounds like a McKinsey powerpoint demonstration. Anyway, you be the judge of how useful these answers are:]

***

[ed. Given the entire arc of history and various economic, political and social efforts to develop an ideal society, what would you suggest as being the best way forward, especially given the advent of AI and other technologies? Be as specific as possible.]

ChatGPT

Developing an ideal society in the context of the advent of AI and other emerging technologies requires a multifaceted approach. This approach should focus on fostering equitable economic growth, enhancing political participation and transparency, and promoting social well-being and ethical considerations. Here are specific steps that can be taken to move forward:

Economic Strategies

Universal Basic Income (UBI):

• Implement a UBI to ensure all citizens have a safety net, mitigating the displacement caused by automation and AI.

• Conduct pilot programs to study the effects and optimize the implementation of UBI on a larger scale.

Upskilling and Lifelong Learning:

• Invest in education systems to prioritize skills relevant to the digital and AI-driven economy.

• Encourage partnerships between governments, educational institutions, and private companies to provide continuous learning opportunities.

Progressive Taxation and Wealth Redistribution:

• Reform tax systems to ensure that wealth generated by AI and technology benefits society at large.

• Use tax revenues to fund public services, infrastructure, and social safety nets.

Political Strategies

Inclusive and Transparent Governance:

• Develop policies that encourage public participation in decision-making processes through digital platforms.

• Implement AI to analyze public feedback and improve transparency in governance.

Ethical AI Regulation:

• Establish regulatory bodies to oversee the ethical development and deployment of AI technologies.

• Create international frameworks for AI ethics, ensuring cooperation and consistency across borders.

Decentralized Governance:

• Promote decentralized decision-making through blockchain technology to enhance transparency and reduce corruption.

• Encourage local governance models where communities have more control over local issues.

Social Strategies

Digital Literacy and Equity:

• Ensure access to digital tools and the internet for all citizens to reduce the digital divide.

• Promote digital literacy programs to empower individuals to navigate the digital landscape effectively.

Healthcare and Well-being:

• Leverage AI in healthcare to provide personalized and efficient medical services.

• Implement policies that promote mental health and well-being, recognizing the psychological impacts of rapid technological changes.

Cultural and Ethical Education:

• Integrate ethics and cultural studies into educational curriculums to foster a society that values diversity and ethical behavior.

• Encourage public discourse on the ethical implications of AI and technology.

Technological Integration

AI for Social Good:

• Invest in AI projects that address social issues such as climate change, poverty, and healthcare.

• Support open-source AI initiatives that allow for collaborative problem-solving.

Sustainable Development:

• Use AI and technology to enhance sustainable practices in agriculture, energy, and transportation.

• Promote the development of green technologies and support policies that aim for environmental sustainability.

Resilient Infrastructure:

• Develop smart cities that utilize AI to improve urban planning, transportation, and resource management.

• Ensure that infrastructure projects are resilient to future technological and environmental changes.

Ethical and Philosophical Considerations

Human-Centric AI Development:

• Ensure that AI development prioritizes human values and societal well-being.

• Engage in multidisciplinary dialogues involving ethicists, technologists, and the public to guide AI development.

AI and Job Displacement:

• Develop strategies to address job displacement caused by AI, focusing on creating new job opportunities and re-skilling the workforce.

• Promote sectors that are less likely to be automated, such as creative industries, healthcare, and personal services.

Global Cooperation

International Collaboration:

• Foster international cooperation on AI research, development, and regulation to address global challenges.

• Participate in global forums and organizations dedicated to the ethical use of AI.

Cross-Cultural Exchange:

• Encourage cultural exchange programs to foster global understanding and collaboration.

• Support initiatives that promote cultural diversity and mutual respect in the context of a globalized, technologically advanced society.

Conclusion

The best way forward involves a balanced approach that integrates economic, political, social, and technological strategies. It requires active participation from governments, private sectors, educational institutions, and civil society. By prioritizing ethical considerations and ensuring equitable access to the benefits of AI and other technologies, society can progress towards an ideal state where technology enhances human life and fosters a just, sustainable, and inclusive world.

***

[ed. Again, given history, do you think humans are capable of achieving all this? Be specific.]

ChatGPT

The question of whether humans are capable of achieving an ideal society, especially in the context of advancing technologies like AI, is complex and multifaceted. History provides both optimism and caution. Here are specific factors that influence the likelihood of success:

Factors Supporting Human Capability

Historical Progress: Technological Advancements: 

Humans have consistently developed and integrated new technologies, such as the printing press, electricity, and the internet, which have significantly improved living standards and facilitated societal progress.

Social Movements: The abolition of slavery, the civil rights movement, and the advancement of gender equality demonstrate humanity's capacity for moral progress and societal change.

Institutional Frameworks: Democratic Governance: Democracies, despite their imperfections, have shown a capacity for self-correction and responsiveness to citizens' needs, which can facilitate the implementation of inclusive policies.

International Cooperation: Institutions like the United Nations, WHO, and various international treaties show that global cooperation on critical issues is possible.

Technological Tools: AI and Data Analytics: These technologies offer unprecedented capabilities for solving complex problems, from climate modeling to personalized medicine.

Digital Platforms: Online platforms can enhance civic participation, transparency, and the dissemination of knowledge.

Challenges and Obstacles

Human Nature and Social Dynamics:Resistance to Change: Historical and contemporary examples show that people often resist changes, especially those that threaten established power structures or cultural norms.

Inequality and Power Imbalances: The concentration of wealth and power can lead to policies and innovations that benefit a few at the expense of many, exacerbating inequalities.

Technological Risks: Job Displacement: Automation and AI can lead to significant job displacement, requiring substantial efforts in retraining and social safety nets.

Ethical Concerns: The misuse of AI, such as in surveillance or biased decision-making systems, can undermine trust and exacerbate social tensions.

Environmental and Global Challenges:Climate Change: Despite technological progress, global efforts to mitigate climate change have been slow and inconsistent.

Geopolitical Tensions: Conflicts and competition between nations can hinder cooperation on global challenges like AI ethics and environmental sustainability.

Case Studies: Mixed Successes and Lessons Learned

Nordic Countries: 

Success: Countries like Sweden, Denmark, and Norway have successfully implemented welfare states that combine economic dynamism with social safety nets, demonstrating the potential for balanced societal models.

Challenges: These models may not be directly transferable to larger or more diverse countries without significant adaptations.

Asian Tigers: 

Success: South Korea, Singapore, Taiwan, and Hong Kong achieved rapid economic growth through a combination of state intervention, education, and technology adoption.

Challenges: These successes often came with trade-offs, such as limited political freedoms and intense work cultures.

Silicon Valley: 

Success: The tech industry has driven enormous innovation and economic growth.

Challenges: It has also contributed to income inequality and housing crises, illustrating the need for balanced development policies.

Conclusion: Potential for Achieving an Ideal Society

While achieving an ideal society is an aspirational goal, history suggests that significant progress is possible if humanity leverages its capacity for innovation, learning, and cooperation. However, the path forward requires addressing deep-seated challenges, including inequality, ethical use of technology, and global coordination. 

Specific strategies can mitigate these challenges:Inclusive Policy Development: Ensuring diverse voices are heard in policy-making can create more equitable solutions.

Ethical AI and Technology: Developing robust frameworks for the ethical use of AI can prevent misuse and build public trust.

Education and Lifelong Learning: Investing in education systems that adapt to technological changes can prepare societies for future challenges.

Global Cooperation: Strengthening international institutions and agreements can facilitate collective action on global issues.

In summary, while the journey toward an ideal society is fraught with challenges, history shows that humanity is capable of remarkable progress when driven by collective will, ethical considerations, and innovative solutions.

***

[ed. Those sound like goals more than specific guidance. Be more specific.]

ChatGPT

Certainly! Let's outline specific, actionable steps that can be taken within each domain—economic, political, social, and technological—to move towards an ideal society, especially given the advent of AI and other technologies.

by markk, Duck Soup:

Harvard Students Are Better Than You

[ed. On Affirmative Action - in concept and practice.]

You don't get to be in the position Harvard is without understanding certain games on a deep institutional level, without playing them better than all others. Harvard is no mere technical school, seeking to train domain experts in rigorous ways. No. It's an Ivy League School, and more than that, it's Harvard. Its mission is not to find the best, but to define the best. And with all due respect to Yale and new upstart Stanford, it's been the best in that business since before the founding of the United States. It comes from the heritage and culture of the old British elite, the Oxfords and Cambridges and Etons of the world.

Harvard students, put simply, are better than you. This isn't me saying this, mind: it's the whole holistic edifice of university admissions and university rankings, the Supreme Court and the halls of Congress, really every prestige institution in the country. Ask McKinsey or Deloitte if you need convincing. Check where your professors went to school. Run up to a random passerby on the street and see what they think of a Harvard degree. Like it or not, it's a near-universal symbol of competence.

Some are better than you because of their heritage, some because of their wealth, some because of their connections. Some, in part, because of their race: you cannot maintain credible elite institutions with few black people sixty years after the civil rights movement. And, yes, some because of their academics, their intelligence and their work ethic. What sort of elite would it be, after all, if it did not pay lip service to the ideal of meritocracy that inspires so many of the hoi polloi, did not reassure them that academic skill, too, would be counted among its holistic ranking? Most, to be clear, have a combination of the above, a mix precisely in line with Harvard's dreams. Admit just the right set to render your institution legitimate as the elite.

I've met many Harvard students by now, and to be frank, it was almost always clear quite rapidly why they were attending Harvard while I was not. I'll give their admissions team this: they're good at their jobs. It's comforting to imagine some sort of cosmic balancing, where aptitude in one domain is balanced by struggle in another, but Nature is crueller than that. I won't claim every Harvard student is peerless. But they are, by and large, an extraordinarily impressive group of young people, by any measure. That's what happens when you spend several centuries building a reputation as the best of the best. It is a true signal of excellence, one that any individual, rational, ambitious actor should pursue.

For twelve years, every student in the country toils away in a system shouting egalitarianism at every turn. Look at policy priorities and school budgets and you'll see it: an earmark for the disadvantaged here, a special program there, an outpouring of funding for special education in this district, and of course classroom after classroom where teachers patiently work with the students who just need a bit of extra help.

Then comes admissions season, and with a wink and a nod, the system strips away the whole veneer and asks, "So, just how well did you play the game? ...you were aware you were playing the game, yes?"

Let us not mince words: the role of holistic college admissions is to examine people as whole individuals, to account for every second of their lives and every bit of their cultural context, and to rank them from best to worst. Or, more precisely: to justify and to reify the values Harvard and its co-luminaries use to select best and worst. Not just the most capable academics, mind: are you telling me you want a campus full of nerds? Please. Leave that to MIT and Caltech.

I don't want to be reduced to just a number, you say. Very well, Harvard responds, we will judge the whole of you and find you wanting. Is that better?

Let us return to the question, then: why does Harvard discriminate against Asians?

Set aside every bit of high-minded rhetoric, even understanding that most who give noble justifications have convinced themselves of those justifications. Set aside every bit of idealism, even understanding that most at every level of education are indeed idealists. Harvard discriminates against Asians because it is not just an elite school, but the elite school, and Asians are simply not elite enough.

I try to be cautious in using the phrase "systemic racism"—I find it often abused past the breaking point. But as I've said in terser form before, if you want a pure example of the term, and a pure demonstration of just what game Harvard is playing, look no further than its treatment of Asian Americans. Elite values—the true values underlying an institution like Harvard—are never fully legible and never fully set. In easy cases, they align with the values trumpeted on the surface: we value intelligence, we value hard work, we want to give everyone an equal shot.

One problem: Asian Americans came along and took those values a bit too seriously. They started gaming the system by taking it earnestly at face value and working to align with explicit institutional values. But admit too many, and the delicate balance is upset, the beating heart of elite culture animating the whole project disrupted. Academics-focused students, after all, lack social development and, as Harvard infamously argued in the case, simply have bad personalities.

Harvard's been around long enough to have played this game a few times before. When a new group gets too good at understanding and pursuing the explicit values it uses to grant its project the veneer of legitimacy, it smiles, thanks them for their applications, and then changes its process. (...)

In 2023, it means hyperfocusing on one particular, often self-contradictory, frame of Diversity, on preaching ideals of egalitarianism, social justice, and inclusivity quite at odds with its pedigree. And yes, it means that Asians have stellar academics and extracurriculars but, alas, inviting too many would wreck the vibe.

What galls about this all—and look, how could it not?—what galls is the hypocrisy. What galls is watching some of the most elitist and exclusive institutions in the country preach inclusiveness while closing their doors to all but a minute fraction of those who apply, preach egalitarianism while serving as the finishing schools of the most privileged. (...)

These schools are elite, through and through. They are elite by heritage, by tradition, by definition. Their existence is justified and given meaning by their elitism. Every other value they espouse comes second to that purpose, and every nod towards egalitarianism and fairness in their admissions serves simply to justify that elitism to the public.

To be clear: there will always be an elite. I am not, personally, a terribly devout egalitarian. In broad philosophy if not always in specifics, I admire the MITs, the Caltechs, the Stuyvesants of the world. Excellence is nothing to be ashamed of, and I respect few schools more than those that strive unapologetically for academic excellence. You know the ones: those inconvenient high schools that always seem to be 70% Asian of late. Building an environment of excellence takes serious work; the path to true expertise has never been anything other than arduous, and we are all made richer by institutions that understand and cherish that path.

While I respect many Harvard graduates and much of the academic work that's passed through it, I cannot pretend to any emotion beyond scorn for a school that thinks it is either possible or desirable to holistically gather All The Coolest People together while preaching the virtues of diversity and inclusion.

by Jack Neilson Despain Zhou, TracingWoodgrains | Read more:
Image: uncredited; P. Archidiacono et al./European Economic Review

The Growing Scientific Case for Using Ozempic and other GLP-1s to Treat Opioid, Alcohol, and Nicotine Addiction

GLP-1s have the potential to reach far more patients than existing medications and permanently reduce addiction rates at a society-wide level.

The consistency that I'm hearing from all across patient groups is gain of control, whereas previously, there was a loss of control… All of a sudden they're able to step back and say, 'oh, well I had this shopping phenomenon that was going on, gambling, addiction, or alcoholism, and all of a sudden, it just stopped,'

- Dr. Gitanjali Srivastava, Vanderbilt Medical Center

Evidence that GLP-1 treatments like Ozempic and Mounjaro have strong anti-addictive effects across substances and behaviors has been mounting every month. This article reviews the published studies in the field as well as the strategic opportunity they present to reduce addiction at a society-wide level. The strength of the anti-addictive effect of GLP-1s appears so clear that some physicians are already using these treatments off-label for patients with substance use disorders (SUD), despite ongoing shortages (particularly for Mounjaro / Zepbound) and complications with insurance coverage. (...)

Medications to address addiction only work if people take them. Existing addiction treatments face a number of obstacles to adoption that have severely limited their use, including patient resistance, stigma, side effects, low long-term adherence rates, and, for treatments like methadone, massive cultural resistance that has persisted for over 50 years, despite a mountain of evidence showing the public health benefits of expanded access. As we have seen so clearly in recent debates on vaccines and reproductive rights, it can be far easier to make sustainable progress in science and medicine than in culture and politics. Because GLP-1 drugs are not opioid-based treatments and are not primarily SUD treatments, they are positioned to completely bypass the culture wars surrounding substance use treatment, which will enable them to have a dramatic impact on the global prevalence of addiction, at a scale that existing treatments cannot reach.

We believe that if addiction is truly understood as a disease and a public health emergency, we have both a moral obligation and a strong self-interest as a society to move as quickly as possible to bring effective treatments to patients, at scale. If we can reduce opioid, stimulant, alcohol, and nicotine addiction by just 20%, we would avoid ~150,000 deaths per year and incalculable suffering for families and communities. But we believe even more is achievable. A 40% reduction in harmful addiction over 8 years can be accomplished with a coordinated strategic plan. We will be publishing specific strategy proposals over the coming months. (...)

Surveys and Reports from Providers and Patients

Several human studies of GLP-1s for addiction, detailed below, have been initiated following widespread reports from patients and providers of unexpected anti-addictive effects from semaglutide and tirzepatide. At a high level, what appears to be most tangible about the experience of patients on GLP-1s is an abrupt reduction in cravings and compulsive behaviors and a sense of increased agency: the ability to make conscious decisions about what to consume, whether it is food or other substances, rather than feeling pulled by a strong internal urge. If anecdotal evidence feels like a distraction to you, feel free to skip this section and jump to the research studies. That being said, we do believe that patient narratives provide important clues about the rapid onset of effect and magnitude of effect size across behaviors.

While not a scientific publication, Morgan Stanley recently surveyed 300 GLP-1 users and found that alcohol consumption and cigarette smoking had dropped substantially. As reported by CNBC,

“Notably, the survey also found that 40% of participants reported smoking traditional cigarettes at least weekly before starting a GLP-1, but that number declined to 24% after treatment. Weekly e-cigarette use similarly fell from 30% to 16% of respondents.”

That’s a 40% decrease in cigarette smoking rates as an incidental side effect of a GLP-1. The same survey reported that about 60% of GLP-1 users reported drinking less alcohol since beginning treatment, with 14-18% quitting drinking completely. Morgan Stanley is warning investors that the alcohol companies Molson Coors, Boston Beer Company, Constellation Brands, and Diageo are most at risk of a significant sales decline due to the projected ongoing increase in GLP-1 users.

Here’s one patient’s narrative:

“I (37F) have been a pretty severe alcoholic for a decade or more. The longest I went without drinking in 10 years was 2 weeks. I would drink to blackout maybe 3 nights a week, sometimes more.. 7 to 10 shots of 90 proof vodka. Or more. My tolerance was pretty high. I titrated up to .5 semaglutide this past Friday and haven't had a drink or even a desire to drink since. I caught sight of the vodka bottle under my bed and started gagging… And I have tried medically assisted ways to quit alcohol which never worked. Yes there is such thing as booze chatter for me, and I no longer have it.” - Semaglutide patient

It is important to distinguish these reports from a typical placebo effect. When patients report a dramatic reduction in opioid cravings from a drug that was prescribed for a different condition (diabetes or obesity), it is unlikely to be a placebo effect because the reduction in cravings was not the goal or an expected impact of the treatment. In addition, patients frequently report that the reductions in substance use cravings occur immediately when they increase their dose and sometimes report that cravings return weekly as they reach day 5 or 6 before taking their next injection on day 7. Furthermore, patients report that substance cravings fully return with cessation of treatment and disappear again when treatment is resumed.

Beginning with Ozempic, and now reported even more strongly from patients taking Mounjaro and Zepbound, the sudden reduction of cravings that occurs at initiation or dose increase is perhaps best compared to the accidental discovery of Viagra. First developed for hypertension, patients in clinical trials for Viagra kept reporting that something… ‘interesting’ was happening when they took the drug. This was a specific and unexpected side effect, reported by a large percentage of patients, and, again, less likely to be a placebo effect. What we’re hearing from GLP-1 patients today is similarly specific, widespread, and unexpected. You can read our compilation of patient reports here and these are a few more representative examples:

“My pretty problematic drinking has reduced to very little comparatively. If my husband didn’t drink I probably wouldn’t at all… I’ll drink half a glass and then literally Saran Wrap it and put in the fridge. Compare this to being a nightly bottle of wine-plus drinker before… And this effect happened IMMEDIATELY.” - Semaglutide patient

Patient reports like these don’t just come from people with problematic substance use. Many people simply lose all desire for the occasional cigarette or beer with friends.

“I love drinking. I absolutely do. There's nothing better to me than a summer night outside listening to some live music with your friends enjoying a few beverages. But I just can't anymore. It doesn't make me physically ill at all, my brain just says, "Nope, you're done." I can't even explain it because I want to drink but I'm just completely done after one or two. It's kind of annoying if I'm being honest but I definitely wouldn't go backwards” - Mounjaro patient

“Loving this! My mom started when I did and used to have a drink every night. When I told her about the studies being done into alcohol she realized she hadn’t had a drink in over a week and had no desire for one. She’s not an alcoholic but she just liked having her nightly drink.” - Semaglutide patient

The reduction in desire and compulsion often goes beyond substances to include behaviors.

“I had a REALLY BAD impulse shopping problem. It went away totally when I started Wegovy. It was nuts I could not believe it.” - Wegovy patient

This CNN article has a story that really articulates the immediacy and unexpected nature of the positive impact for many:

A smoker for most of her life, Ferguson started Ozempic 11 weeks ago to try to lose about 50 pounds she’d gained during the Covid-19 pandemic, which had made her prediabetic.

She’d switched from cigarettes to vaping last summer in hopes of quitting but found vapes to be even more addictive. That changed, she said, once she started Ozempic.

“It’s like someone’s just come along and switched the light on, and you can see the room for what it is,” Ferguson said. “And all of these vapes and cigarettes that you’ve had over the years, they don’t look attractive anymore. It’s very, very strange. Very strange.”

by Nicholas Reville and Zarinah Agnew, Recursive Adaptation |  Read more:

Image: Wang et al., 2024 Nature Molecular Psychiatry 

via:

[ed. Love this picture. Ice Bowl. One of the greatest games in NFL history. When I was young, the first book I ever read (when I could read) was Jerry Kramer's Instant Replay, about the Packers' 1967 championship season. Highly recommended. And, a lifetime later, in other football news: The NCAA’s proposal to pay college athletes is fair. That's the problem. (Vox):]

***

"There are over 520,000 college athletes in the US, playing for nearly 20,000 separate teams in more than 20 different sports. College athletics as a whole produce $13.6 billion in revenue, more than any other professional team sport save the gargantuan NFL, while the nearly 200,000 athletic scholarships given each year are worth the equivalent of some $4 billion. In 43 out of 50 US states, a college coach for a big-time team at a top state university — a job that can easily pay eight figures — is that state’s highest-paid public employee. (...)

And all this sits atop an essential contradiction: This entire commercial enterprise, this massive generator of alumni donations and TV rights, is all meant to be amateur. Just athletes playing for the love of the game and maybe a free college education, often struggling to get by or even feed themselves — even as a single top college football team like the University of Alabama’s Crimson Tide can bring in more than $120 million a year. You don’t get any more American than that.

Except, possibly, for this: That contradiction is finally on its way to being resolved, through a multibillion-dollar courtroom settlement. (...)

Last Thursday, the National Collegiate Athletic Association (NCAA) and what are known as the Power Five college athletic conferences — the leagues with the biggest college football teams — reached an agreement that would for the first time allow colleges to pay athletes directly. (College athletes can now legally make money indirectly, after a Supreme Court decision in 2021 forced the NCAA to allow them to be compensated by businesses for the use of their name or likeness, but the NCAA still prohibited colleges from paying them directly.)

The agreement, largely in response to the class-action lawsuit House vs. NCAA, still needs to be approved by the federal judge overseeing the case. But should it go forward, it would represent a fundamental change to how college athletics operates, solving one contradiction while potentially creating a host of other challenges."

The New Generation of Online Culture Curators

[ed. And one old one.]

The current Internet landscape sometimes feels like the Zone in Andrei Tarkovsky’s film “Stalker”: directionless, inexplicable, bound to change in confusing ways. Our social-media feeds don’t offer much except the forward acceleration of algorithmic recommendations. Google and other forms of search are becoming clogged with content generated by artificial intelligence. Knowing what you’re looking for doesn’t always help you chart a path, because niche communities can be difficult to locate and to keep up with. We are in a transitional phase of digital culture, and thus more in need than ever of friendly faces, personable human guides (not unlike a “stalker” in the Zone), to help us navigate this treacherous ground. Such guides go by many names—call them influencers, or content creators, or just “this one guy I follow.” Guided by their own cultivated sense of taste, they bring their audiences news and insights in a particular cultural area, whether it’s fashion, books, music, food, or film.

Perhaps the best way to think of these guides is as curators; like a museum curator pulling works together for an exhibition, they organize the avalanche of online content into something coherent and comprehensible, restoring missing context and building narratives. They highlight valuable things that we less-expert Internet surfers are likely to miss. Andrea Hernández, the proprietor of Snaxshot, a newsletter and social-media account dedicated to “curating the food and beverage space,” told me recently, “Curation is about being able to filter the noise.” (I follow Hernández for her skill at discovering the wildest examples of direct-to-consumer drinks startups, such as Feisty, a purveyor of “protein soda.”) She continued, “I go out and I scour through the Internet and I come to you with my offerings.” Unlike a museum curator, however, the digital personalities I have taken to following also become the faces of their work, broadcasting recordings of themselves, on TikTok and Instagram, as a way of building a trusting relationship with their followers. (...)

Curation takes work, and like any other kind of labor it is only sustainable if it’s reasonably compensated. Gee monetizes his account by creating sponsored content on TikTok, primarily for audio-equipment brands. Magasin earns the majority of its revenue from affiliate marketing—for every reader who clicks a link to, say, a new Proenza Schouler cashmere sweater, and buys one, Reilly earns a commission based on a small percentage of the sale price. Before Magasin, Reilly worked in e-commerce fashion writing at the magazine InStyle, highlighting new product releases and deals. That approach provided inspiration for her newsletter, and set her apart from other solo fashion commentators: “I didn’t want it to be something that was a diary; I wanted it to be a service,” she said.

In a previous era of the Internet, we might have thought of figures like these simply as influencers, whose ability to attract large followings online gives them a power that sometimes surpasses that of traditional publications. But the idea of an influencer has, as Reilly put it, become “a little flattened over time,” connoting shallow, uninformed, even misleading content dictated by sponsors. “There’s a distinction between influencing and what I do,” Reilly insisted. The archetypal influencer produces life-style porn of one form or another, playing up the aspirational glamour of their own home or meals or vacations. The new wave of curators is more outward-looking, borrowing from the influencer’s playbook and piggybacking on social media’s intimate interaction with followers in order to address a body of culture beyond themselves. (...)

Shuherk cast the rise of curatorial accounts like his as a failure of the legacy-media ecosystem. The job of providing well-informed recommendations once belonged to professional critics employed by newspapers and magazines. As media companies have struggled to adjust to the digital age, the number of full-time criticism jobs has dwindled, leaving a void that Shuherk and others are filling. We sometimes blame the figure of the influencer for these changes. “One hundred per cent, that’s wrong,” Shuherk told me. Internet users still desire guidance from voices with expertise; it’s just that those experts, lacking other options, are increasingly finding their audiences online. “My option for becoming a book reviewer was sitting down on TikTok,” Shuherk said. “There isn’t really a path for me outside of this.”

The onslaught of online content requires filtering, whether technological or human, and those of us who dislike the idea of A.I. or algorithms doing the filtering for us might think more about how we support the online personalities who do the job well. Structurally, the Internet is not getting better anytime soon; I have not hidden my pessimism about its future. But human creativity persists, even in hostile conditions. Figures like Gee, Reilly, and Shuherk make me hopeful that fun, interesting niches of activity can still survive online. There’s another word that we might apply to such people: “connoisseurs,” in the art-historical sense of passionate observers who shape a discipline through their judgments. We’ve always had connoisseurs, from the radio d.j. to the bookstore clerk, subtly but vitally informing the culture that the rest of us choose to consume. As Shuherk put it, “The person in the nineties working at Blockbuster—we’re the same person.” 

by Kyle Chayka, New Yorker | Read more:
Image: Ariel Davis

[ed. Welcome to Duck Soup, which has been in existence for what, 12-13 years now?

"None of the items posted here are or should be used for commercial purposes (other than at originating sites). They are presented solely to promote the ideas, reporting and art of the people that produced them. Everything posted here is of interest to me and a distillation of a larger sampling effort to find particularly noteworthy items. It's a labor of love that has prompted me to search out and discover new sites and postings that I'd never have expended the effort to find before, and to learn many new things. The result is the blog you're now reading. If there's any underlying theme it's to seek out thoughtful insights from knowledgeable people about the world we live in and highlight an eclectic mix of music, art and other forms of personal expression.

If this website can help direct readers' attention (a precious commodity these days) to important contributors, then all effort put into it will be worthwhile."

***

[ed. If you'll notice, there are no ads of any sort on this site. I don't make a penny (except that one donation from Stephan in Canada about 10 years ago. Thanks, Stephan! I still remember you!). The only thing I ask of readers is that if they find this site useful they'll tell their friends about it, and hopefully those friends will tell other friends. That way we can all learn a little bit more and help contributors find as much of an audience as possible (plus, I get to add pithy/pissy little editorials sometimes, and even longer narratives.]

Marvin Gaye

Pure Marvin
via:

How Microsoft Plans to Squeeze Cash Out of AI

The same way it always has with most everything else — by leveraging our PCs.

Microsoft has invested $13 billion in OpenAI, providing the money-losing start-up with the huge amounts of capital and computing power necessary for its continued operations. In exchange, Microsoft gets access to OpenAI’s technology for use in its own products as well as a real and reputational stake in the AI boom. “We are below them, above them, around them,” Satya Nadella said in March about OpenAI. (...)

AI subscriptions are, so far, the tech industry’s favorite idea for making money from AI. This is conceptually simple — your customers are paying you for access to a new product. The problem is that compute-heavy cloud services like ChatGPT and Copilot remain extremely expensive to run, meaning that in some cases even paying customers might be costing them money. Computing costs are likely to fall, and AI-model efficiency could improve, but, much like the basic assumption that there’s a huge market for these things just waiting to be tapped, these are bets and not particularly safe ones.

This week, Microsoft announced that it would be integrating AI more deeply into even more of its products, including Windows, which, among many other chatbot-shaped things, is set to get a feature called Recall, described by the company as “an explorable timeline of your PC’s past.” This feature, which will be turned on by default for Windows users, records and “recalls” everything you do on your computer by taking near-constant screenshots, processing them with AI, and making them available for future browsing through a conversational interface. (...)

Like smartphones, personal computers already collect and produce vast amounts of data about their users, but this is a big step in the direction of surveillance — constant, open-ended, and mostly unredacted — offered in exchange for a strange feature that Microsoft’s CEO is quite insistent its users will enjoy. Nadella attempts to preempt any concerns by pointing out that the AI models powering Recall run locally — that is, on the user’s device, not in the cloud. This is, at best, a partial solution to a problem of Microsoft’s own creation — a problem Windows users didn’t know they had until this week.

On-device AI processing is interesting to Microsoft for other reasons, too. In a world where AI services are expensive to run, installing them in every popular Microsoft product represents a real risk. In a world where the processing necessary to run chatbots, generate images, or surveil your own computer usage to the maximum possible extent occurs on users’ devices, the cost of deploying AI is vastly lower.

For Microsoft, that is — if it expects to fully utilize these new features that are becoming increasingly integral to the core Window product, customers will have to buy new machines, some of which Microsoft also showed off this week. According to The Verge:

“All of Microsoft’s major laptop partners will offer Copilot Plus PCs, Microsoft CEO Satya Nadella said at an event at the company’s headquarters on Monday. That includes Dell, Lenovo, Samsung, HP, Acer, and Asus; Microsoft is also introducing two of its own as part of the Surface line. And while Microsoft is also making a big push to bring Arm chips to Windows laptops today, Nadella said that laptops with Intel and AMD chips will offer these AI features, too.”

These PCs will come with a “neural processor,” roughly akin to a graphics card, which is a separate hardware feature that can handle AI-related processing tasks more quickly and with lower power use than existing CPUs and GPUs. In conjunction with Microsoft’s shift to more efficient mobile processor architecture for laptops and desktops — something Apple committed to years ago, selling huge numbers of laptops in the process — AI is being used to make the case to its customers that this is the next stage of the upgrade cycle. It’s time to get a new PC, says the company that makes the software that powers most PCs and that sells PCs of its own.

Microsoft, like many other tech giants, says it’s all in on AI, but its approach includes hedges against AI deflation, too. Maybe customers flock to new AI features, in which case Microsoft will have shifted computing expenses back to its billions of customers, improving margins on subscription products and selling lots of Windows licenses in the process. If they don’t, though — if people keep using their Windows machines in approximately the same way they have for decades — Microsoft makes money anyway and leaves its cloud computing capacity free to sell to other firms that want to try their luck building AI tools.

by John Herrman, Intelligencer |  Read more:

Image: Intelligencer; Photo: Microsoft

[ed. Probably the biggest threat from AI - now and the near future - is how people use it. Long before a sentient AI decides - "Hey, maybe this human species isn't that smart after all - not enough to be my Master, anyway" we'll have already proven why. It's possible that AI's greatest achievement, if we allow it, might be protecting us from ourselves. See also: AI Is an Existential Threat—Just Not the Way You Think (Scientific American):]

"Actually, there is an existential danger inherent in using AI, but that risk is existential in the philosophical rather than apocalyptic sense. AI in its current form can alter the way people view themselves. It can degrade abilities and experiences that people consider essential to being human.

For example, humans are judgment-making creatures. People rationally weigh particulars and make daily judgment calls at work and during leisure time about whom to hire, who should get a loan, what to watch and so on. But more and more of these judgments are being automated and farmed out to algorithms. As that happens, the world won’t end. But people will gradually lose the capacity to make these judgments themselves. The fewer of them people make, the worse they are likely to become at making them.

Or consider the role of chance in people’s lives. Humans value serendipitous encounters: coming across a place, person or activity by accident, being drawn into it and retrospectively appreciating the role accident played in these meaningful finds. But the role of algorithmic recommendation engines is to reduce that kind of serendipity and replace it with planning and prediction.

Finally, consider ChatGPT’s writing capabilities. The technology is in the process of eliminating the role of writing assignments in higher education. If it does, educators will lose a key tool for teaching students how to think critically.

Not Dead But Diminished

So, no, AI won’t blow up the world. But the increasingly uncritical embrace of it, in a variety of narrow contexts, means the gradual erosion of some of humans’ most important skills. Algorithms are already undermining people’s capacity to make judgments, enjoy serendipitous encounters and hone critical thinking. [ed. Not to mention providing new ways of making money and securing power in previously unknown and unique ways.] 

The human species will survive such losses. But our way of existing will be impoverished in the process. The fantastic anxieties around the coming AI cataclysm, singularity, Skynet, or however you might think of it, obscure these more subtle costs. Recall T.S. Eliot’s famous closing lines of “The Hollow Men”: “This is the way the world ends,” he wrote, “not with a bang but a whimper.”]

The Briefy Awards

It’s our 100th News Briefing! In celebration, we’re making this Very Special Edition free for everyone to read. We’re also removing the paywalls from our entire back catalog (up to May 10), so those considering subscribing can get a taste of what our news briefing offers.

In honor of our 100th edition, we decided to do something a bit different. Over the course of our first 99 issues we've encountered numerous joys and horrors. We thought that we'd take a look back at some of the most shocking happenings, admirable heroes, and dastardly villains we've encountered so far. And what better way to honor them than through an awards show! That's why we bring to you the first-ever Current Affairs News Briefing BRIEFY AWARDS!

GREATEST INNOVATOR IN POLITICAL CORRUPTION:

There is really no other choice here besides Congressman George Santos, who took the phrase “fake it ‘til you make it” to heart by fabricating basically every aspect of his career and personal life. This is actually not what brought him down, though. He flew a bit too close to the sun by, according to a federal indictment, stealing the credit card information of donors and starting a fake nonprofit whose proceeds he used to buy designer clothing, among other things. (In the United States Congress, being corrupt is perfectly ordinary; the only real crime is being corrupt too loudly, and drawing attention to all the others.) (Oct. 13, 2023)

(DIS)HONORABLE MENTIONS:

• Senator Bob Menendez, and the many bars of gold from shady Egyptian businessmen that were found in his closet. (In a really astonishing bit of excuse-making, Menendez tried to argue he had “intergenerational PTSD” from when his parents fled revolutionary Cuba in the 1950s, which caused him to hoard valuable objects. He might as well have just blamed the dog.) (Sept. 26, 2023 and Jan. 5, 2024)

• North Dakota Governor Doug Burgum, who hacked his way onto the GOP debate stage by paying voters with $20 gift cards to donate to him so he’d reach the small-dollar donations threshold. Burgumania may never have taken off, but we'll always remember him for this. (July 14, 2023)

• Representative Henry Cuellar, who was charged with accepting around $600,000 in bribes from Azerbaijan during its campaign of ethnic cleansing in the Nagorno-Karabakh region. Yikes. (May 7, 2024)

• Texas Attorney General Ken Paxton, who was accused of “hijacking” his office to do various favors for one of his top campaign donors, but narrowly avoided impeachment. Even the corruption, it seems, is bigger in Texas. (September 8, 2023)

MOST DYSTOPIAN ROBOTIC ENTITY:

The newly available flamethrower dog, from the appropriately named company ThrowFlame, which can be purchased in 48 American states. (Apr. 26, 2024)

(DIS)HONORABLE MENTIONS:

• Eric Adams’ NYPD Robot, who patrols the subways for crime at a blistering three mph. (Sept. 26, 2023)

• AI Putin, who appeared at a news conference to ask the real Putin about his opinions on the dangers of artificial intelligence (Dec. 15, 2023)

• “Ask Jesus,” the Twitch chatbot which allows to ask an artificially generated Jesus any question you like. (Aug. 4, 2023)

• nhPredict, the AI that the UnitedHealth Group used to generate lowball estimates for how much care elderly patients “should” require and deny anything above the threshold. (Nov. 21, 2023)

• The holographic versions of KISS that will no doubt haunt the world’s concert venues long after the band itself had departed this earthly plane (Dec. 5, 2023) (...)

COP OF THE YEAR:

Jesse Hernandez, the Florida sheriff’s deputy who mistook the sound of a falling acorn for gunfire, panicked, and emptied the magazine of his service weapon into his own car (while a handcuffed Black man sat inside.) The competition was stiff this year, but nobody else embodied the combination of cowardice, random violence, and reckless disregard for the lives of others that characterize the American police quite so well.

[ed. From the link:] 

"A Florida cop got scared by a falling acorn and opened fire on his own car. The cop in question—a sheriff’s deputy named Jesse Hernandez—apparently mistook the sound of the nut hitting the roof of his patrol car for a gunshot, and unleashed what we might euphemistically call an “officer-involved ballistic-type situation.” In the bodycam video from the incident, we can hear Hernandez yell “shots fired!”, drop to the ground and roll, and then proceed to empty the magazine of his service pistol into his own car, firing around 15 shots in the general direction of the sound.

This alone would be pretty ridiculous, but the story gets worse: there was an unarmed, handcuffed Black man sitting in the car at the time, who Hernandez apparently assumed was shooting at him. His name was Marquis Jackson, and he’d been arrested earlier in the day. Miraculously, Jackson survived Hernandez’s hail of bullets, but posted on Facebook that he’s been “damaged for life” by the traumatic experience.

 
Of course, it’s not exactly news that the U.S. police are twitchy and paranoid. In 2016, Harper’s Magazine published a long list of innocuous items they’ve mistaken for guns over the years, including wallets, phones, sunglasses, a sandwich, and even a pair of underwear. Now we can add “acorns” to the inventory. Many of those past cases ended with the police shooting someone, and a lot of the victims were Black men like Marquis Jackson. There are several reasons for this. It’s partly a consequence of the ridiculous training a lot of cops go through, which emphasizes a so-called “warrior mentality” and teaches police to see everyone around them as potential enemies. It’s partly just plain old racism. And it’s partly the blurred line between police and the military—according to The Washington Post, Jesse Hernandez “didn’t have any prior law enforcement experience,” but was in the Army Special Forces for 10 years before becoming a deputy. Taken together, these factors make police more of a danger to the wider community than they are protectors of it."

by Current Affairs Staff: Stephen Prager, Alex Skopic, Nathan J. Robinson, Lily Sánchez, Cali Traina Blume, and Justin Ward  |  Read more:

Images: Various CA staff

[ed. I haven't read all the links, but there are a ton more...]