Thursday, May 30, 2024
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:
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.
- 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.
- 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:
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.
- 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.
- 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:
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.
- 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.
- 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.
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.
- 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.
- 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.
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.
- 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:
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.
- 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.
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:
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.]
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.
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,
Here’s one patient’s narrative:
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:
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 patientIt 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 patientPatient 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 patientThe 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 patientThis 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
Wednesday, May 29, 2024
[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):]
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."
***
"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.]
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.]
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:
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.
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.”]
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.
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!
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)
The newly available flamethrower dog, from the appropriately named company ThrowFlame, which can be purchased in 48 American states. (Apr. 26, 2024)
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:]
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:]
by Current Affairs Staff: Stephen Prager, Alex Skopic, Nathan J. Robinson, Lily Sánchez, Cali Traina Blume, and Justin Ward | Read more:"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."
Images: Various CA staff
[ed. I haven't read all the links, but there are a ton more...]
Tuesday, May 28, 2024
Was the 401(k) a Mistake?
Jen Forbus turned 50 this year. She is in good health and says her life has only gotten better as she has grown older. Forbus resides in Lorain, Ohio, not far from Cleveland; she is single and has no children, but her parents and sisters are nearby. She works, remotely, as an editorial supervisor for an educational publishing company, a job that she loves. She is on track to pay off her mortgage in the next 10 years, and having recently made her last car payment, she is otherwise debt-free. By almost any measure, Forbus is middle class.
Still, she worries about her future. Forbus would like to stop working when she is 65. She has no big retirement dreams — she is not planning to move to Florida or to take extravagant vacations. She hopes to spend her later years enjoying family and friends and pursuing different hobbies. But she knows that she hasn’t set aside enough money to ensure that she can realize even this modest ambition.
A former high school teacher, Forbus says she has around $200,000 in total savings. She earns a high five-figure salary and contributes 9 percent of it to the 401(k) plan that she has through her employer. The company also makes a matching contribution that is equivalent to 5 percent of her salary. A widely accepted rule of thumb among personal-finance experts is that your retirement income needs to be close to 80 percent of what you earned before retiring if you hope to maintain your lifestyle. Forbus figures that she can retire comfortably on around $1 million, although if her house is paid off, she might be able to get by with a bit less. She is not factoring Social Security benefits into her calculations. “I feel like it’s too uncertain and not something I can depend on,” she says.
But even if the stock market delivers blockbuster returns over the next 15 years, her goal is going to be difficult to reach — and this assumes that she doesn’t have a catastrophic setback, like losing her job or suffering a debilitating illness.
She also knows that markets don’t always go up. During the 2008 global financial crisis, her 401(k) lost a third of its value, which was a scarring experience. From the extensive research that she has done, Forbus has become a fairly savvy investor; she’s familiar with all of the major funds and has 60 percent of her money in stocks and the rest in fixed income, which is generally the recommended ratio for people who are some years away from retiring. Still, Forbus would prefer that her retirement prospects weren’t so dependent on her own investing acumen. “It makes me very nervous,” she concedes. She and her friends speak with envy of the pensions that their parents and grandparents had. “I wish that were an option for us,” she says.
The sentiment is understandable. With pensions, otherwise known as defined-benefit plans, your employer invests on your behalf, and you are promised a fixed monthly income upon retirement. With 401(k)s, which are named after a section of the tax code, you choose from investment options that your company gives you, and there is no guarantee of what you will get back, only limits on what you can put in. This is why they are known as defined-contribution plans. Pensions still exist but mainly for unionized jobs. In the private sector, they have largely been replaced by 401(k)s, which came along in the early 1980s. Generally, contributions to 401(k)s are pretax dollars — you pay income tax when you withdraw the money — and these savings vehicles have been a bonanza for a lot of Americans.
Not all companies offer 401(k)s, however, and millions of private-sector employees lack access to workplace retirement plans. Availability is just one problem; contributing is another. Many people who have 401(k)s put little if any money into their accounts. With Americans now aging out of the work force in record numbers — according to the Alliance for Lifetime Income, a nonprofit founded by a group of financial-services companies, 4.1 million people will turn 65 this year, part of what the AARP and others have called the “silver tsunami” — the holes in the retirement system are becoming starkly apparent. U.S. Census Bureau data indicates that in 2017 49 percent of Americans ages 55 to 66 had “no personal retirement savings.”
The savings shortfall is no surprise to Teresa Ghilarducci, an economist at the New School in New York. She has long predicted that the shift to 401(k)s would leave vast numbers of Americans without enough money to retire on, reducing many of them to poverty or forcing them to continue working into their late 60s and beyond. That so many people still do not have 401(k)s or find themselves, like Jen Forbus, in such tenuous circumstances when they do, is proof that what she refers to as this “40-year experiment with do-it-yourself pensions” has been “an utter failure.”
It certainly appears to be failing a large segment of the working population, and while Ghilarducci has been making that case for years, more and more people are now coming around to her view. Her latest book, “Work, Retire, Repeat: The Uncertainty of Retirement in the New Economy,” which was published in March, is drawing a lot of attention: She has been interviewed on NPR and C-SPAN and has testified on Capitol Hill.
It is no longer just fellow progressives who are receptive to her message. Ghilarducci used to be an object of scorn on the right, once drawing the megaphonic wrath of Rush Limbaugh. Today, though, even some conservatives admit that her assessment of the retirement system is basically correct. Indeed, Kevin Hassett, who was a senior economic adviser to President Trump, teamed up with Ghilarducci not long ago to devise a plan that would help low- and middle-income Americans save more for retirement. Their proposal is the basis for legislation currently before Congress.
And Ghilarducci recently found her critique being echoed by one of the most powerful figures on Wall Street. In his annual letter to investors, Larry Fink, the chairman and chief executive of BlackRock, one of the world’s largest asset-management companies, wrote that the United States was facing a retirement crisis due in no small part to self-directed retirement financing. Fink said that for most Americans, replacing defined-benefit plans with defined-contribution plans had been “a shift from financial certainty to financial uncertainty” and suggested that it was time to abandon the “you’re on your own” approach.
While that isn’t likely to happen anytime soon, it seems fair to ask whether the country as a whole has been well served by the 401(k) revolution. The main beneficiaries have been higher-income workers; instead of making an economically secure retirement possible for more people, 401(k)s have arguably become another driver of the inequality that is a defining feature of American life.
In 2024, annual pretax contributions for employees are capped at $23,000, but with an employer match and possibly also an after-tax contribution (which is permitted under some plans), the maximum can reach $69,000. Workers 50 and over are also allowed to kick in an additional $7,500, potentially pushing the total to $76,500. Needless to say, only a sliver of the U.S. work force can contribute anything like that to their 401(k)s.
Still, she worries about her future. Forbus would like to stop working when she is 65. She has no big retirement dreams — she is not planning to move to Florida or to take extravagant vacations. She hopes to spend her later years enjoying family and friends and pursuing different hobbies. But she knows that she hasn’t set aside enough money to ensure that she can realize even this modest ambition.
But even if the stock market delivers blockbuster returns over the next 15 years, her goal is going to be difficult to reach — and this assumes that she doesn’t have a catastrophic setback, like losing her job or suffering a debilitating illness.
She also knows that markets don’t always go up. During the 2008 global financial crisis, her 401(k) lost a third of its value, which was a scarring experience. From the extensive research that she has done, Forbus has become a fairly savvy investor; she’s familiar with all of the major funds and has 60 percent of her money in stocks and the rest in fixed income, which is generally the recommended ratio for people who are some years away from retiring. Still, Forbus would prefer that her retirement prospects weren’t so dependent on her own investing acumen. “It makes me very nervous,” she concedes. She and her friends speak with envy of the pensions that their parents and grandparents had. “I wish that were an option for us,” she says.
The sentiment is understandable. With pensions, otherwise known as defined-benefit plans, your employer invests on your behalf, and you are promised a fixed monthly income upon retirement. With 401(k)s, which are named after a section of the tax code, you choose from investment options that your company gives you, and there is no guarantee of what you will get back, only limits on what you can put in. This is why they are known as defined-contribution plans. Pensions still exist but mainly for unionized jobs. In the private sector, they have largely been replaced by 401(k)s, which came along in the early 1980s. Generally, contributions to 401(k)s are pretax dollars — you pay income tax when you withdraw the money — and these savings vehicles have been a bonanza for a lot of Americans.
Not all companies offer 401(k)s, however, and millions of private-sector employees lack access to workplace retirement plans. Availability is just one problem; contributing is another. Many people who have 401(k)s put little if any money into their accounts. With Americans now aging out of the work force in record numbers — according to the Alliance for Lifetime Income, a nonprofit founded by a group of financial-services companies, 4.1 million people will turn 65 this year, part of what the AARP and others have called the “silver tsunami” — the holes in the retirement system are becoming starkly apparent. U.S. Census Bureau data indicates that in 2017 49 percent of Americans ages 55 to 66 had “no personal retirement savings.”
The savings shortfall is no surprise to Teresa Ghilarducci, an economist at the New School in New York. She has long predicted that the shift to 401(k)s would leave vast numbers of Americans without enough money to retire on, reducing many of them to poverty or forcing them to continue working into their late 60s and beyond. That so many people still do not have 401(k)s or find themselves, like Jen Forbus, in such tenuous circumstances when they do, is proof that what she refers to as this “40-year experiment with do-it-yourself pensions” has been “an utter failure.”
It certainly appears to be failing a large segment of the working population, and while Ghilarducci has been making that case for years, more and more people are now coming around to her view. Her latest book, “Work, Retire, Repeat: The Uncertainty of Retirement in the New Economy,” which was published in March, is drawing a lot of attention: She has been interviewed on NPR and C-SPAN and has testified on Capitol Hill.
It is no longer just fellow progressives who are receptive to her message. Ghilarducci used to be an object of scorn on the right, once drawing the megaphonic wrath of Rush Limbaugh. Today, though, even some conservatives admit that her assessment of the retirement system is basically correct. Indeed, Kevin Hassett, who was a senior economic adviser to President Trump, teamed up with Ghilarducci not long ago to devise a plan that would help low- and middle-income Americans save more for retirement. Their proposal is the basis for legislation currently before Congress.
And Ghilarducci recently found her critique being echoed by one of the most powerful figures on Wall Street. In his annual letter to investors, Larry Fink, the chairman and chief executive of BlackRock, one of the world’s largest asset-management companies, wrote that the United States was facing a retirement crisis due in no small part to self-directed retirement financing. Fink said that for most Americans, replacing defined-benefit plans with defined-contribution plans had been “a shift from financial certainty to financial uncertainty” and suggested that it was time to abandon the “you’re on your own” approach.
While that isn’t likely to happen anytime soon, it seems fair to ask whether the country as a whole has been well served by the 401(k) revolution. The main beneficiaries have been higher-income workers; instead of making an economically secure retirement possible for more people, 401(k)s have arguably become another driver of the inequality that is a defining feature of American life.
***
When it comes to generating wealth, 401(k)s have been an extraordinary success. The Investment Company Institute, a financial-industry trade group, calculates that the roughly 700,000 401(k) plans now in existence hold more than $7 trillion in assets. But the gains have gone primarily to those who were already at or near the top. According to the Federal Reserve, the value of the median retirement-saving account for households in the 90th to 100th income percentile has more than quintupled during the last 30 years and is currently more than $500,000. In one sense, it is not surprising that the affluent have profited to this degree from 401(k)s: The more money you can invest, the more money you stand to make.In 2024, annual pretax contributions for employees are capped at $23,000, but with an employer match and possibly also an after-tax contribution (which is permitted under some plans), the maximum can reach $69,000. Workers 50 and over are also allowed to kick in an additional $7,500, potentially pushing the total to $76,500. Needless to say, only a sliver of the U.S. work force can contribute anything like that to their 401(k)s.
The withdrawal rules have evolved in a way that also favors high earners. You are generally not supposed to begin taking money from a 401(k) before you are 59½; doing so could incur a 10 percent penalty (on top of the income-tax hit). What’s more, you can now put off withdrawing money until age 73; previously, you had to begin drawing down 401(k)s by 70½. Those extra years are an added tax benefit for retirees who are in no rush to tap their 401(k)s.
People in lower-income brackets may have also made money from 401(k)s but hardly enough to retire on with Social Security. In 2022, the median retirement account for households in the 20th through 39th percentile held just $20,000. For this segment of the working population, 401(k)s sometimes end up serving a very different purpose. They become a source of emergency funds, not retirement income. But then, for many of these people, retirement seems like an impossibility.
Laura Gendreau directs a program called Stand by Me, a joint venture between the United Way of Delaware and the state government that provides free financial counseling. She says that when she asks clients if they are putting aside any money for retirement, they often look at her in disbelief: “They say, ‘How do you expect me to save for retirement when I’m living paycheck to paycheck?’” She and her colleagues try to identify expenditures that can be eliminated or reduced so that people can start saving at least a small portion of what they earn. But she says that some clients are having such a hard time just getting by that they can’t fathom being able to retire. Sometimes it does not even occur to them to look into whether their employers offer 401(k)s. “They have no idea,” Gendreau says.
Ghilarducci has been hearing this sort of thing for years. Her career in academia began around the time that 401(k)s first emerged, and from the start, she regarded these savings plans with skepticism. For one thing, she feared that a lot of people would never have access to them. But she also felt that 401(k)s were unsuitable for lower-income Americans, who often struggled to save money or who might not have either the time or the knowledge to manage their own investments. In her judgment, the offloading of retirement risk onto workers was worse than just an economic misstep — it represented a betrayal of the social contract. (...)
In 2008, Ghilarducci proposed replacing 401(k)s with “guaranteed retirement accounts,” a program that would combine mandatory individual and employer contributions with tax credits and that would guarantee at least a 3 percent annual return, adjusted for inflation. Her plan drew the wrath of voices on the right — the conservative pundit James Pethokoukis called her “the most dangerous woman in America.”
But her timing proved to be apt: That year, the global financial crisis imperiled the retirement plans of millions of Americans. Ghilarducci suggested that if the government was going to bail out the banks, it also had an obligation to help people whose 401(k)s had tanked. Her idea inflamed the right: Rush Limbaugh attacked her during his daily radio show, which brought her a wave of hate mail.
Her hostility to 401(k)s is partly anchored in a belief that when it comes to retirement, the country was on a better path in the past. In the 1950s and 1960s, many Americans could count on pensions and Social Security to provide them with a decent retirement. It was a different era, of course — back then, men (and it was almost always men) often spent their entire careers with the same companies. And even at their peak, pensions were not available to everyone; only around half of all employees ever had one. Still, in Ghilarducci’s view, it was a time when the United States put more emphasis on the interests of working-class Americans, including ensuring that they could retire with some degree of economic security.
She portrays the move to defined contribution retirement plans as part of the sharp rightward turn that the United States took under President Ronald Reagan, when the notion of individual responsibility became economic dogma — what the Yale University political scientist Jacob Hacker has called “the great risk shift.” The downside of this shift was laid bare by the great recession. Many older Americans lost their savings and were forced to scavenge for work.
This was the subject of the journalist Jessica Bruder’s book “Nomadland,” for which Ghilarducci was interviewed and that was the basis for the Oscar-winning film of the same title. To Ghilarducci, the portraits in “Nomadland” — of lives upended, of the indignity of being old and having to scramble for food and shelter — presaged the insecure future that awaited millions of other older Americans. And Ghilarducci believes that with record numbers of people now reaching retirement age, that grim future is arriving.
People in lower-income brackets may have also made money from 401(k)s but hardly enough to retire on with Social Security. In 2022, the median retirement account for households in the 20th through 39th percentile held just $20,000. For this segment of the working population, 401(k)s sometimes end up serving a very different purpose. They become a source of emergency funds, not retirement income. But then, for many of these people, retirement seems like an impossibility.
Laura Gendreau directs a program called Stand by Me, a joint venture between the United Way of Delaware and the state government that provides free financial counseling. She says that when she asks clients if they are putting aside any money for retirement, they often look at her in disbelief: “They say, ‘How do you expect me to save for retirement when I’m living paycheck to paycheck?’” She and her colleagues try to identify expenditures that can be eliminated or reduced so that people can start saving at least a small portion of what they earn. But she says that some clients are having such a hard time just getting by that they can’t fathom being able to retire. Sometimes it does not even occur to them to look into whether their employers offer 401(k)s. “They have no idea,” Gendreau says.
Ghilarducci has been hearing this sort of thing for years. Her career in academia began around the time that 401(k)s first emerged, and from the start, she regarded these savings plans with skepticism. For one thing, she feared that a lot of people would never have access to them. But she also felt that 401(k)s were unsuitable for lower-income Americans, who often struggled to save money or who might not have either the time or the knowledge to manage their own investments. In her judgment, the offloading of retirement risk onto workers was worse than just an economic misstep — it represented a betrayal of the social contract. (...)
In 2008, Ghilarducci proposed replacing 401(k)s with “guaranteed retirement accounts,” a program that would combine mandatory individual and employer contributions with tax credits and that would guarantee at least a 3 percent annual return, adjusted for inflation. Her plan drew the wrath of voices on the right — the conservative pundit James Pethokoukis called her “the most dangerous woman in America.”
But her timing proved to be apt: That year, the global financial crisis imperiled the retirement plans of millions of Americans. Ghilarducci suggested that if the government was going to bail out the banks, it also had an obligation to help people whose 401(k)s had tanked. Her idea inflamed the right: Rush Limbaugh attacked her during his daily radio show, which brought her a wave of hate mail.
Her hostility to 401(k)s is partly anchored in a belief that when it comes to retirement, the country was on a better path in the past. In the 1950s and 1960s, many Americans could count on pensions and Social Security to provide them with a decent retirement. It was a different era, of course — back then, men (and it was almost always men) often spent their entire careers with the same companies. And even at their peak, pensions were not available to everyone; only around half of all employees ever had one. Still, in Ghilarducci’s view, it was a time when the United States put more emphasis on the interests of working-class Americans, including ensuring that they could retire with some degree of economic security.
She portrays the move to defined contribution retirement plans as part of the sharp rightward turn that the United States took under President Ronald Reagan, when the notion of individual responsibility became economic dogma — what the Yale University political scientist Jacob Hacker has called “the great risk shift.” The downside of this shift was laid bare by the great recession. Many older Americans lost their savings and were forced to scavenge for work.
This was the subject of the journalist Jessica Bruder’s book “Nomadland,” for which Ghilarducci was interviewed and that was the basis for the Oscar-winning film of the same title. To Ghilarducci, the portraits in “Nomadland” — of lives upended, of the indignity of being old and having to scramble for food and shelter — presaged the insecure future that awaited millions of other older Americans. And Ghilarducci believes that with record numbers of people now reaching retirement age, that grim future is arriving.
by Michael Steinberger, NY Times | Read more:
Image: Tim Enthoven
[ed. I don't have enough insight into other people's experiences to make anything other than broad generalizations, but having a defined benefit retirement plan (which pays out a defined monetary benefit each month, like Social Security) has been one of the luckiest of lucky situations I've ever stumbled into. When 401k's were first introduced I imagined them as a gift to Wall Street - people being forced into the market with nothing but their own financial investing accumen to guide them into retirement security. Maybe you'd make out great, maybe not. If you were into investing, it might've looked like a great opportunity. But even then it was obvious that risk was being transfered from employers to employees, since many if not most employers had a contractual, and sometimes constitutional, obligation to provide a guaranteed retirement income based on job class and years of service. It probably worked out well for some with enough income to invest, but it was clear even to someone as oblivious as me (who didn't much care about financial matters or could even imagine retirement back then) that most people probably wouldn't have either the funds, insight, interest, or sophistication to manage all the various complexities involved in guiding and growing their own retirement accounts. And so it has come to pass. Read the comments for other perspectives.]
Image: Tim Enthoven
[ed. I don't have enough insight into other people's experiences to make anything other than broad generalizations, but having a defined benefit retirement plan (which pays out a defined monetary benefit each month, like Social Security) has been one of the luckiest of lucky situations I've ever stumbled into. When 401k's were first introduced I imagined them as a gift to Wall Street - people being forced into the market with nothing but their own financial investing accumen to guide them into retirement security. Maybe you'd make out great, maybe not. If you were into investing, it might've looked like a great opportunity. But even then it was obvious that risk was being transfered from employers to employees, since many if not most employers had a contractual, and sometimes constitutional, obligation to provide a guaranteed retirement income based on job class and years of service. It probably worked out well for some with enough income to invest, but it was clear even to someone as oblivious as me (who didn't much care about financial matters or could even imagine retirement back then) that most people probably wouldn't have either the funds, insight, interest, or sophistication to manage all the various complexities involved in guiding and growing their own retirement accounts. And so it has come to pass. Read the comments for other perspectives.]
Monday, May 27, 2024
Nvidia’s CEO Could Be the World’s Richest Man Sooner Than You Think
Nvidia is worth $2.6 trillion — larger than two Metas, three Berkshire Hathaways, or five ExxonMobils. Goldman Sachs called it “the most important stock on planet Earth” for its centrality in the booming AI industry, and his company will likely be worth more than Apple in a few months. As of Friday, Huang is the 17th-richest person in the world, with an estimated $91 billion to his name, according to Bloomberg. That’s more than double what he was worth on Christmas. At this rate, Huang — whose public image is far from the flamboyant edgelord tech bro who has become so common among the Silicon Valley’s C-suites — could become richer than Elon Musk by 2025 and his company more valuable than any other in the world. (Or, of course, the stock could stop going straight up, as it did a few weeks ago, since lots of people seem to think it’s gotten way overvalued.)
AI, as a technology, is still pretty uneven. OpenAI’s most advanced public version can pick stocks better than humans, while Google’s new AI-powered chatbot, Gemini, thinks you should eat rocks. (You should not eat rocks.) Huang, though, doesn’t really care very much about that, at least as far as his own personal fortune is concerned. AI software requires a huge amount of processing power, regardless of how right or wrong the actual program’s answers may be, and Huang’s company more or less has the market cornered on making the kinds of computer chips that can handle that. Even the stupidest AI is going to need a lot of Nvidia’s chips, called graphics-processing units.
Since there is such a fervent belief among the Silicon Valley set that AI will one day achieve superhuman intelligence, there’s a tremendous incentive for just about every tech company to make that technology a core part of its operations. Huang’s business, though, is today’s equivalent of selling shovels during a gold rush. Many, if not most, of the companies vying to be the next big thing in A.I. will go bust — and Nvidia will have long pocketed their money.
by Kevin T. Dugan, Intelligencer | Read more:
Image: David Paul Morris/Bloomberg via Getty Images
[ed. See also: Jensen Huang’s Homes: Inside the Nvidia CEO’s Property Portfolio (Mansion Global).] (ed. Mansion Global?). Also, from one of the article's links: Financial Statement Analysis with Large Language Models (pdf):]
Abstract: We investigate whether an LLM can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of future earnings. Even without any narrative or industryspecific information, the LLM outperforms financial analysts in its ability to predict earnings changes. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with the performance of a narrowly trained state-ofthe-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company’s future performance. Lastly, our trading strategies based on GPT’s predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Taken together, our results suggest that LLMs may take a central role in decision-making. (...)
Conclusions: Our results suggest that GPT’s analysis yields useful insights about the company, which enable the model to outperform professional human analysts in predicting the direction of future earnings. We also document that GPT and human analysts are complementary, rather than substitutes. Specifically, language models have a larger advantage over human analysts when analysts are expected to exhibit bias and disagreement, suggesting that AI models can assist humans better when they are under-performing. Humans, on the other hand add value when additional context, not available to the model is likely to be important.
Furthermore and surprisingly, GPT’s performance is on par (or even better in some cases) with that of the most sophisticated narrowly specialized machine learning models, namely, an ANN trained on earnings prediction tasks. We investigate potential sources of the LLM’s superior predictive power. We first rule out that the model’s performance stems from its memory. Instead, our analysis suggests that the model draws its inference by gleaning useful insights from its analysis of trends and financial ratios and by leveraging its theoretical Financial Statement Analysis with Large Language Models 30 understanding and economic reasoning. Notably, the narrative financial statement analysis generated by the language model has substantial informational value in its own right. Building on these findings, we also present a profitable trading strategy based on GPT’s predictions. The strategy yields higher Sharpe ratios and alphas than other trading strategies based on ML models. Overall, our analysis suggests that GPT shows a remarkable aptitude for financial statement analysis and achieves state-of-the-art performance without any specialized training.
Although one must interpret our results with caution, we provide evidence consistent with large language models having human-like capabilities in the financial domain. Generalpurpose language models successfully perform a task that typically requires human expertise and judgment and do so based on data exclusively from the numeric domain. Therefore, our findings indicate the potential for LLMs to democratize financial information processing and should be of interest to investors and regulators. For example, our results suggest that generative AI is not merely a tool that can assist investors (e.g., in summarizing financial statements, Kim et al., 2023b), but can play a more active role in making informed decisions. This finding is significant, as unsophisticated investors might be prone to ignoring relevant signals (e.g., Blankespoor et al., 2019), even if they are generated by advanced AI tools. However, whether AI can substantially improve human decision-making in financial markets in practice is still to be seen. We leave this question for future research. Finally, even though we strive to understand the sources of model predictions, it is empirically difficult to pinpoint how and why the model performs well."
Authors: Kim, Alex G. and Muhn, Maximilian and Nikolaev, Valeri V., Financial Statement Analysis with Large Language Models (May 20, 2024). Chicago Booth Research Paper Forthcoming, Fama-Miller Working Paper, Available at SSRN: https://ssrn.com/abstract=4835311 or http://dx.doi.org/10.2139/ssrn.4835311
Subscribe to:
Posts (Atom)