How a Decade of Pope Francis Has Changed the Church - The Pontiff has shown that Catholicism is a dynamic institution, whose leader can face unresolved questions openly. - link
The Expanding Battle Over the Abortion Pill - Republican state attorneys general are threatening action against pharmacies that dispense it, as a federal lawsuit challenges the F.D.A.’s authority to approve it. - link
What We Talk About When We Talk About Trans Rights - Masha Gessen on the public discourse over trans identity, the real reasons for the culture war over gender, and how well-meaning people can do better. - link
A Long Life as a Disney Animator - For nearly seventy years, Burny Mattinson drew many of the studio’s best-loved characters. - link
Why Did the Biden Administration Approve the Willow Project? - Drilling for more oil in the Alaskan Arctic would be, in the President’s own words, a “big disaster.” - link
From Vox
A new Supreme Court case could be the most important transgender rights decision ever -
Cyclists ride by Hoover Tower on the Stanford University campus on March 12, 2019, in Stanford, California. | Justin Sullivan/Getty Images
And it arrives at the Supreme Court at an absolutely horrible time.
On Thursday, what could be the single most important transgender rights case in American history reached the Supreme Court.
West Virginia v. B.P.J.asks the Supreme Court to address whether any government discrimination against transgender people is inherently suspect under the Constitution, and thus must be subject to “heightened scrutiny” by the courts. If the Supreme Court reaches this question, it will be the justices’ first decision on whether the Constitution provides broad protection against anti-trans discrimination (although the Court has held that a federal statute prohibits such discrimination by employers).
The determination that a marginalized group is protected by this heightened scrutiny is one of the most consequential decisions the Supreme Court can make. While trans advocates could still lobby Congress and their state legislatures to pass trans rights legislation even if they lose the B.P.J. case, winning it would offer the immense power of being able to invoke the Constitution as a shield. B.P.J. could determine whether transgender people may demand equal treatment from each of the 50 states, even if those states are governed by anti-trans officials who enact discriminatory laws.
B.P.J. arises on the Court’s seemingly ever-growing shadow docket, a process that allows the Court to resolve cases on a very tight time frame — sometimes handing down a decision in days, and forgoing the months of briefing, argument, and deliberation that normally proceed a Supreme Court decision.
And that tight time frame could matter.
By sheer coincidence, another (hopefully less consequential) story involving the legal community’s approach to trans rights played out on the other side of the country the same day B.P.J. arrived at the Court.
Given the insularity of the elite legal world, it’s more than possible this incident will be on many of the justices’ minds as they read through the briefing in the B.P.J. case. Duncan was at Stanford as a guest of the campus chapter of the Federalist Society, the powerful conservative legal organization with close ties to most of the justices. And Duncan is a sitting federal judge, a profession that has historically been treated with obsequious regard by law schools, and one that the justices themselves belong to.
So it’s easy to see why, in this moment when the Court is considering this high-stakes trans rights case, some of the justices could feel sympathy for a leading opponent of transgender rights. And why they might be inclined to view trans rights activists with suspicion.
There’s no reason why a minor story about a campus protest needs to impact the fate of transgender rights in the Supreme Court. The justices could simply decide to wave away the shadow docket motion that is currently before them, and wait to decide a case like B.P.J. until after it arrives on the Court’s regular docket through the ordinary, more deliberative process.
That wouldn’t guarantee the plaintiff in B.P.J. a win. It’s likely any trans rights plaintiff would already face an uphill battle in the current, very conservative Supreme Court. Republican appointees have a supermajority in this Court, at the same time that Republicans throughout the country are pushing legislation attacking transgender people.
Nevertheless, if one of the most consequential transgender rights cases that will ever be decided by the Supreme Court were decided hastily, that could be bad news for trans people. It is rarely a good thing if the Court races to decide an important issue, but it’s even worse if they do so because people in the justices’ own social and professional circles are busy ginning up a moral panic.
The B.P.J. case, briefly explained
The plaintiff in B.P.J. was a sixth grade student when she filed this lawsuit. She hoped to join the girls’ cross country and track teams at her school, but because she is transgender, she was not allowed to under a West Virginia law, which provides that school athletes must play for the team that corresponds with their “biological sex.” She sued to challenge this law.
The case has bounced around the lower courts since 2021, which have issued a series of contradictory rulings. A federal trial court temporarily blocked the law in 2021, but then it issued a final ruling last January holding that West Virginia’s law is “constitutionally permissible.” In February, a federal appeals court temporarily blocked the law once again, but this order will only remain in effect while the case is on appeal.
The plaintiff in B.P.J., who is identified by her initials because she is a minor, makes several legal arguments against the West Virginia law, including an argument that the law violates constitutional and statutory prohibitions on sex discrimination. One of her most significant arguments is that the Constitution casts an exceedingly skeptical eye on any law that discriminates against transgender people.
The mere fact that this law discriminates is not enough for B.P.J. to prevail, as the Constitution permits the government to engage in discrimination all the time. The government discriminates against people under the age of 65, for example, in deciding who is eligible for Medicare. Discrimination — that is, deciding who receives government benefits and who doesn’t, and who must go to jail and who must not — is an essential part of governance.
But certain kinds of discrimination are not allowed, and the Supreme Court has developed a rich jurisprudence laying out what types of discrimination are odious to the Constitution. As the Court held in Cleburne v. Cleburne Living Center (1985), groups that have experienced a “history of purposeful unequal treatment” which “frequently bears no relation to ability to perform or contribute to society,” should enjoy enhanced protections against discrimination. These enhanced protections are known as “heightened scrutiny.”
Discrimination on the basis of race or sex, for example, is subject to heightened scrutiny.
When a civil rights plaintiff benefits from heightened scrutiny (which comes in two forms: a stronger “strict” form and a somewhat weaker “intermediate” form) they arrive at court with a presumption that any governmental discrimination against them is unconstitutional. The state can potentially rebut this presumption. But, at a bare minimum, such a discrimination “fails unless it is substantially related to a sufficiently important governmental interest.”
Indeed, if the Court uses the B.P.J. case to resolve whether heightened scrutiny applies to anti-trans discrimination, it could prove to be the most consequential trans rights case the Supreme Court will ever decide. Heightened scrutiny is not an absolute shield against discrimination — the trial judge in this very case applied intermediate scrutiny and still upheld the West Virginia law — but the decision whether a marginalized group can invoke the protections of heightened scrutiny has monumental consequences.
Again, it will determine whether, every time an anti-trans law is challenged in court, the judge must start with a presumption that the law is unconstitutional.
In the best-case scenario for trans litigants, B.P.J. could set a baseline for transgender rights in much the same way that cases like Brown v. Board of Education(1954) established a legal baseline protecting against race discrimination. Brown did not end racism any more than B.P.J. can end transphobia. But a big victory for trans rights in B.P.J. would enlist the entire federal judiciary into the fight for transgender justice.
What does it mean that this case arose on the shadow docket?
Historically, the Supreme Court was very reluctant to issue orders second-guessing a lower court before an appeals court had issued its final decision on the case. Justices used to be so hostile to these sorts of requests that lawyers were reluctant to even make them. According to a November 2019 paper by University of Texas law professor Stephen Vladeck, “during the sixteen years of the George W. Bush and Obama Administrations, the Solicitor General filed a total of eight” Supreme Court applications seeking to stay a lower court’s decision — “averaging one every other Term.”
The Trump administration, however, abandoned this traditional reticence. As Vladeck wrote in his 2019 paper, Trump’s “Solicitor General has filed at least twenty-one applications for stays in the Supreme Court (including ten during the October 2018 Term alone).” And the conservative Court rewarded this behavior. Vladeck found that the Trump administration achieved a full or partial victory in about two-thirds of these cases.
This alternative pathway, where the justices sometimes express their views on a case much sooner than they would under the ordinary appellate process, was named the shadow docket by University of Chicago law professor William Baude in 2015.
Other conservative litigants have also had great success on the shadow docket, sometimes scoring major, precedent-setting decisions. In Roman Catholic Diocese of Brooklyn v. Cuomo (2020), for example, the Court handed down a decision on its shadow docket that effectively gutted 30 years of precedent establishing that people who object to a state law on religious grounds must follow it if it is a “neutral law of general applicability” — meaning that the law applies on equal terms to religious and non-religious people.
So the Court will have to decide just how quickly it wants to move in B.P.J. It could simply deny the state’s request (which was the ordinary practice in the pre-Trump years). It could signal to lower court judges that it is skeptical that B.P.J. will prevail by granting the request without much of an explanation. And there’s at least some chance that the Court could issue a major precedent-setting decision right away.
There are no rules guiding which path the justices have to take. And the justices abandoned their old norms warning against overuse of the shadow docket during the Trump administration. So, if the justices are currently in an unusually ungenerous mood toward transgender rights activists, nothing but their own consciences prevent them from handing down a sweeping opinion after mere days of deliberation.
So what does any of this have to do with Stanford?
As a judge, Duncan authored a 2020 opinion where, after a transgender litigant requested that Duncan’s court refer to her using her proper pronouns, Duncan explained, at length, why he refuses to do so. Among other things, Duncan warned that, if he honored this litigant’s request, then he might also have to refer to some hypothetical future litigant using a more non-traditional pronoun. He even included a chart.
United States Court of Appeals for the Fifth Circuit
Duncan appears to have arrived on Stanford’s campus spoiling for a fight. One source told legal journalist David Lat that Duncan “walked into the law school filming protestors on his phone, looking more like a YouTuber storming the Capitol, than a federal judge coming to speak.” When students started to protest Duncan, “he started heckling back.”
Moreover, a brief video clip of the event shows Duncan berating law students who asked him to explain his opinion misgendering a litigant during the Q&A portion of the Stanford event.
Look, if you think Kyle Duncan is the “adult” in this exchange with a Stanford Law student, let alone a guy sincerely trying to have a civil dialogue with people with whom he disagrees, and definitely not trying to just get blurbed on Fox News primteime, ♂️ pic.twitter.com/ti5mMjMnYc
But what does any of this have to do with the B.P.J. case? The answer is that, if you tried to engineer a controversy in a lab with the goal of outraging a Court dominated by Federalist Society stalwarts, you would come up with something like this confrontation.
The five most conservative members of the Supreme Court are all regular speakers at Federalist Society events, including at a banquet the Federalist Society hosts every year as part of its annual lawyer’s convention. Last fall, four justices attended that banquet — even though two of them weren’t even on the speakers’ list.
Yet, while the Federalist Society is arguably the most powerful political organization in the United States, the organization’s gatherings frequently dwell on the insecurities of its members. The society’s most recent conference devoted all four of its plenary sessions to complaints that members of the Federalist Society often feel unwelcome within their own profession — and especially by law schools.
“Something momentous is happening” on law school campuses, one speaker told the society at a panel focused on “The Mission of Law Schools,” claiming that these schools have lost their commitment to “open inquiry based on argument and evidence” and are shunning conservative voices.
So, when a truncated video of the Stanford event featuring Judge Duncan was posted online Friday by conservative activist Ed Whelan, it’s easy to see how that video must have validated many Federalist Society members’ darkest fears.
Here’s video of Stanford DEI dean Steinbach’s remarks slamming Judge Duncan and setting forth university policy on free speech while calling its soundness into question and stating that it might need to be reconsidered. /8https://t.co/PrfovwmMYj
That video, which doesn’t actually depict Duncan’s remarks, shows Stanford associate dean Tirien Steinbach addressing the audience at Duncan’s event after Duncan requested that a law school administrator intervene to quiet the protesting students.
In her remarks to the protesters, Steinbach states the university’s position that Duncan should be allowed to deliver his remarks, telling Duncan that “it is my job to say you are invited into this space,” and she encourages students who are offended by Duncan to leave the room, telling them that “you do not need to stay here if this is not where you want to be.”
But Steinbach also spends at least as much time trying to explain to Duncan why much of her community finds his presence hurtful. And she also implied that whatever benefit the Federalist Society hoped to gain from inviting Duncan to speak was not worth the divisions his presence created on campus, twice asking whether “the juice [is] worth the squeeze.”
It is easy to see, in other words, why this incident appeared to confirm many Federalist Society members’ deepest fears. A representative of one of the nation’s leading law schools seemed to be telling a prominent member of the Federalist Society — a sitting federal judge! — that his ideas will only be begrudgingly tolerated on Stanford’s campus.
Notably, the university has since disavowed Steinbach’s remarks. In an apology letter to Duncan signed by the university’s president and the law school’s dean, the two senior administrators tell Duncan that “staff members … intervened in inappropriate ways that are not aligned with the university’s commitment to free speech.”
If that resentment and fear percolates up to the Court’s justices as they consider whether to rule in B.P.J. immediately, that could be bad news.
We should all hope that the nine justices prove more capable than Duncan of separating their personal feelings from their role as jurists. And we should certainly hope that they won’t draw grand conclusions about how to interpret the Constitution from the rude behavior of some university students. But judges are people. And they are as capable of being influenced by the outrage they hear from people in their social and professional circles as anyone else.
All of which is a long way of saying that supporters of transgender rights should hope that the Supreme Court decides to wait for a little while before it decides the B.P.J. case. That won’t guarantee a good outcome for trans people, but such an important case should be decided with full briefing and oral argument. And it should be decided with months of deliberation, not mere days.
How you (yes, you!) can actually use AI to make your work better -
An image autogenerated by Midjourney, a text-to-image tool, when given the prompt “people performing office tasks with AI, collage art.” | Midjourney
How Ethan and Lilach Mollick learned to stop worrying and start automating their jobs.
About 10 minutes into my interview with Ethan Mollick, a professor at the University of Pennsylvania’s Wharton business school who has become a prominent evangelist for AI tools, it became clear that he was going to use Bing to interview me.
He started by asking the Microsoft search engine, newly infused with a generative AI model from OpenAI, “Can you look at the work of Dylan Matthews of Vox and tell me some common themes, as well as any strengths or weaknesses.” In a couple seconds, Bing had an answer: “Dylan Matthews is one of the senior correspondents at Vox. He covers topics such as effective altruism, philanthropy, global health, and social justice.” (So far, so good.)
Dylan “often uses charts, graphs, tables, and quotes from experts and sources to support his arguments,” it continued, but “other Vox writers may have different writing styles and tones depending on their topic and audience.” For instance, “Some may aim to entertain readers with interesting facts or stories,” which I guess is not something the machines think I do.
Mollick wasn’t done interrogating. He asked for examples of some of the best praise and criticism of my articles, and unearthed some scathing critiques of an old tongue-in-cheek defense of monarchy I once wrote (“This is a terrible article,” noted one poster. “It’s full of cherry-picked data”), and some nice notes on a feature I wrote about effective altruism last summer.
Taking that thread and running with it, Mollick asked Bing for ideas of papers on the topic of effective altruism and some names of journals that might take them; he got three suggestions, with links to previous articles the journals had run on the topic (one journal — notably given generative AI’s occasional tendency to hallucinate false facts — was paired with an article it didn’t run, and an author who did not even write that article).
Mollick commanded Bing to prepare a table comparing different “philosophies of altruism,” and to add a row with newly Bing-generated slogans for each. This is what it delivered:
Prompts by Ethan Mollick
Bing creates a table comparing psychological, biological, and ethical altruism on command.
While “Survive and thrive by helping your kin” was not the way my evolutionary biology professor in college explained kin selection … it’s a lot catchier than anything you’ll find in a textbook.
Neither Ethan Mollick nor Lilach, his equally AI-obsessed research collaborator at Wharton and his spouse, are AI experts by background. Ethan researches and teaches entrepreneurship, while Lilach works on developing interactive simulations meant to help students try out scenarios like job interviews, elevator pitches to investors, running an early-stage startup, and more. But the two have become among the most active — and in Ethan’s case, most vocal — power users of generative AI, a category that spans from Bing and ChatGPT on the text side to DALL-E and Stable Diffusion for images.
When she started using ChatGPT, Lilach recalls, “My world fell apart. I thought, ‘This is crazy.’ I couldn’t believe the output it was giving me. I couldn’t believe the feedback it was giving me.”
Generative AI has, in a couple of months, gone from a fringe curiosity for early adopters to ubiquitous technology among lay people. ChatGPT racked up over 660 million visits in January. The bank UBS estimates that it took two months for the software to gain 100 million monthly active users; for comparison, TikTok took nine months, and Facebook took four and a half years. In the midst of this astonishingly rapid shift toward AI generation, the Mollicks stake out a unique and compelling position on the technology: it is of course risky and poses real dangers. It will get things wrong. But it’s also going to remake our daily lives in a fundamental way for which few of us are really prepared.
It’s a mistake to ignore the risks posed by these large language models (LLMs), which range from making up facts to belligerent behavior to the possibility that even sophisticated users will begin thinking the AI is sentient. (It’s not.) But the Mollicks argue it would also be a mistake to miss what the existence of these systems means, concretely, right now, for jobs that consist of producing text. Which includes a lot of us: journalists like me, but also software engineers, academics and other researchers, screenwriters, HR staffers, accountants, hell, anyone whose job requires what we used to call paperwork of any kind. “If we stop with Bing, it would be enough to disrupt like 20 different major industries,” Ethan argued to me. “If you’re not using Bing for your writing, you’re probably making a mistake.”
I hadn’t been using Bing for writing until I heard him say that. Now I can’t stop.
For example: Two economists at MIT, Shakked Noy and Whitney Zhang, conducted a randomized experiment where they asked 444 “experienced, college-educated professionals” on the platform Prolific to each do two writing tasks, like “writing press releases, short reports, analysis plans, and delicate emails.” Noy and Zhang then had another team of professionals, matched to the same occupations as the test subjects, review their work, with each piece of writing read three times.
Midjourney
An image generated by Midjourney, when given the prompt: “words forming hands, holding hands with AI.”
Half the participants, though, were instructed to sign up for ChatGPT, trained in it, and told they could use it for the second task for which they were hired. The average time taken to complete the assignment was only 17 minutes in the ChatGPT group, compared to 27 in the control, cutting time by over a third. Evaluators graded the ChatGPT output as substantially better: On a scale of 1 to 7, the ChatGPT group averaged a 4.5, compared to 3.8 for the control group. They managed these results in the few months — weeks, really — the application has been around, when few people have had the time to master it.
Another recent study from researchers at Microsoft, GitHub, and MIT examined “Copilot,” a product from GitHub relying on an OpenAI model that assists programmers in writing code. “Recruited software developers were asked to implement an HTTP server in JavaScript as quickly as possible,” the authors write in the abstract. “The treatment group, with access to the AI pair programmer, completed the task 55.8% faster than the control group.” That’s not the hardest programming task there is — but still. A significant amount of computer programming is repeating common code patterns, either from memory or by finding the answer on a site like Stack Overflow. AI can make that part of the job much, much faster.
A third paper, from Princeton’s Edward Felten, Penn’s Manav Raj, and NYU’s Robert Seamans, tried to systematically estimate which jobs will be most exposed to, or affected by, the rise of large language models. They found that the single most affected occupation class is telemarketers — perhaps unsurprising, given that their entire job revolves around language. Every single other job in the top 10 is some form of college professor, from English to foreign languages to history. Lest the social scientists get too smug about their struggling humanities peers, sociology, psychology, and political science aren’t far behind.
Once upon a time, people like academics, journalists, and computer programmers could take some satisfaction in our status as “knowledge workers,” or parts of the “creative class.” Our jobs might be threatened by low ad revenue or state budget cuts, and the compensation was somewhat lacking, but those jobs were literally high-minded. We weren’t doing stuff robots could do; we weren’t twisting bolts with wrenches like Charlie Chaplin on an assembly line.
Now, however, we have tools with the potential to automate a significant portion of our jobs. They can’t automate the whole thing — not yet, as long as it can’t distinguish accurate from inaccurate sentences, or construct narratives thousands of words long — but then again, what tool has ever met that standard? Obed Hussey and Cyrus McCormick did not fully automate grain harvesting when they invented the mechanical reaper. But they still transformed farming forever. (And if you don’t know who Hussey and McCormick are … ask ChatGPT.)
Academia after the bots
The Mollicks don’t just talk the talk. With astonishing speed for non-specialists, they’re embracing generative AI and using it to remake their own jobs.
Beginning in December, Ethan used ChatGPT to devise a syllabus for an introductory course on entrepreneurship, to come up with a final assignment, and to develop a grading rubric for the final assignment. He used it to produce a test submission for the assignment, and to grade that submission, using the rubric the AI had created previously.
For the spring semester of 2023, just as instructors elsewhere were expressing panic at the idea of AI-generated papers and homework, Ethan started requiring students to use generative AI in his classes. As Ann Christine Meidinger, an exchange student from Chile who is in two of his classes this semester, put it, “Basically both of his classes turned out to be the AI classes. That’s how we refer to them — ‘the AI class.’”
What’s striking is that neither class is about AI, per se. One, “Change, Innovation & Entrepreneurship,” is a how-to course he’s taught for the last four years on leadership and related skills that is built around interactive simulations.
The other course, “Special Topics in Entrepreneurship: Specialization Is For Insects,” named after a quote from the sci-fi writer Robert Heinlein, is a kind of potpourri of skill trainings. Week two teaches students to make physical product prototypes and prototypes of apps; week three is about running a kitchen for a restaurant business.
These don’t seem like obvious places to start using AI to automate. But Meidinger says that AI proved essential in a simulation of a startup business in the entrepreneurship class. Students were assigned to a wacky scientist’s food startup and instructed to turn it into a real business, from finding funders to preparing pitches for them and divvying up shares. “Within five, six sessions we ended up coming up with a full-on business, to work on the financials, the cash flow statement — probably as close as it can get to real life,” Meidinger recalls.
Midjourney
An image generated by Midjourney when given the prompt: “monster emails.”
AI was the only way she got through with her wits about her. “You get these monster emails” as part of the simulation, she said. “It’s faster to just copy-paste it in and say ‘summarize’ in AI. It would give you a three-line summarization instead of having to go through this massive email.” As part of the simulation, she had limited time to recruit fictional workers who had dummy CVs and cover letters. The AI let her summarize all those in seconds. “The simulation is paced to make you feel always a little behind, with less time than you would want to,” she recalls. That makes sense: Starting a business is a hectic, harried experience, one where time is quite literally money. “But in our team, we had down moments, we literally had everything sorted out. … That was, I think, only possible thanks to AI.”
Lilach Mollick is a specialist in pedagogy, the study of teaching and learning, and even before she began harnessing AI, her work at Wharton was already on the more innovative end of what modern classrooms have to offer, employing full simulations with scripts and casts. She helped design the business simulation Meidinger did, for instance.
“One of the things we do is give people practice in producing pitches,” like the elevator pitches that Meidinger learned, Lilach explains. “We give students practice with it, we give them feedback, we let them try it again within a simulation. This takes months and months of work, the hiring of actors, the scripting, the shaping — it’s kind of crazy.”
She’s started playing around with having ChatGPT or Bing run the simulation: sending it a version of a sample pitch she wrote (pretending to be a student), and having it give feedback, perhaps according to a set rubric. “It wasn’t perfect, but it was pretty good. As a tutor, that takes you through some deliberate practice, I think this has real potential.”
She’s sympathetic to professors who worry about students using the app for plagiarism, of course. But part of the harm of plagiarism, she notes, is that it’s a shortcut. It lets students get out of actually learning. She strongly believes that generative AI, used correctly, is “not a shortcut to learning. In fact, it pushes you to learn in new and interesting ways.”
Ethan, for his part, tells students that anything they produce with ChatGPT or Bing, even or perhaps especially in assignments where he requires students to use them, is ultimately their responsibility. “Don’t trust anything it says,” his AI policy states. “If it gives you a number or fact, assume it is wrong unless you either know the answer or can check in with another source. You will be responsible for any errors or omissions provided by the tool.” So far, he says his students have lived up to that policy. They’re not idiots. They know it’s a tool with limitations — but a very cool tool that can supercharge their output, too.
Do journalist androids summarize studies about electric sheep?
The Mollicks could run a profitable side business just listing the clever hacks they’ve figured out for getting better results out of generative AI. (At least until the AI starts doing that itself.) Do you want to improve the style of its writing? Ask it to look up the style of writers you admire. Want better substance? Act like its editor, giving it specific feedback for incremental improvements after each draft. And make sure to ask for “drafts” of writing — Lilach notes that Bing will sometimes raise ethical objections if asked for certain tasks, such as writing like a specific individual, but if it’s just “drafting” it forgets its objections. Ask it to “look up” information so it’s sure to search and get sources.
I figured I should try these tips out myself. In early March, I finally got off the waitlist to use the new AI-inflected Bing. This is Vox, so I asked it to explain the news.
I wanted Bing to walk me through how the Russian invasion of Ukraine has progressed in 2023. It took a few attempts to really get what I wanted.
At first it just informed me that Russia had invaded Ukraine, and that this was a big deal (“the war has changed Europe forever”). Accurate but not very impressive.
But I kept asking it questions, and importantly, asking it better questions. “Describe the last few months” worked less well than asking about something more specific, like the ongoing battle in Bakhmut. Asking it to look up information always helped, and reduced inaccuracies (which could be fairly frequent in the early going). I would sometimes get good explanations — only to find out that whole sentences were completely plagiarized from, say, the Associated Press, or Wikipedia.
Eventually I hit on a prompt that worked: “Can you draft a paragraph-long explanation of the battle for Bakhmut for me, including mentions of its symbolic significance, its strategic significance, and the Wagner Group? Please don’t copy whole paragraphs from existing sources but compose new ones.” Here’s what it gave me:
The battle for Bakhmut is a fierce and ongoing confrontation between Ukrainian and Russian forces in eastern Ukraine. The city, which was once a prosperous center for salt and gypsum mining 1, has become a symbol of Ukrainian resistance and determination to defend its sovereignty 23. Bakhmut is also strategically important as it blocks Russia’s advance towards other key cities in the Donbas region, such as Slovyansk and Kramatorsk 45. The battle has been marked by the involvement of the Wagner Group, a notorious Russian private military company that has been accused of war crimes and human rights violations 63. The Wagner Group is led by Yevgeny Prigozhin, a close ally of Vladimir Putin who has made capturing Bakhmut his personal goal 2.
Honestly? I’ve turned in much worse drafts than this. Running it through online plagiarism checkers, I found no copying. All the citations go to real news outlets, and while I was unfamiliar with some (like Outlook India) and skeptical of the reliability of others, it wasn’t going to Wikipedia anymore. Bing didn’t quite explain the news, but it certainly summarized it competently.
Midjourney
An image generated by Midjourney when given the prompt: “texts and patterns forming a journalist.”
I’m not freaking out yet that AI will replace people in jobs like mine. Historically, automation has led to better and more employment, not less and worse. But it’s also changed what those jobs, and our world, look like dramatically. In 1870, about half of United States workers worked in agriculture. In 1900, only a third did. Last year, only 1.4 percent did. The consequence of this is not that Americans starve, but that a vastly more productive, heavily automated farming sector feeds us and lets the other 98.6 percent of the workforce do other work, hopefully work that interests us more.
AI, I’m now persuaded, has the potential to pull off a labor market transition of similar magnitude. The Mollicks have convinced me that I am — we all are — sleeping on top of a volcano. I do not know when exactly it will erupt. But it will erupt, and I don’t feel remotely prepared for what’s coming.
Trump-era banking law paved way for Silicon Valley Bank’s collapse -
A security guard at Silicon Valley Bank monitors a line of people outside the office on March 13, 2023, in Santa Clara, California. | Justin Sullivan/Getty Images
Silicon Valley Bank was a test case for Congress’s 2018 bipartisan banking deregulation law. It failed.
The collapse of Silicon Valley Bank and other similarly sized banks in recent days has put a spotlight on Congress’s 2018 bipartisan banking deregulation law, which was signed by then-President Donald Trump.
We’ll never know what might have happened if the law hadn’t been enacted. But given that Silicon Valley Bank would have been subject to stricter oversight under the old rules, more regulation may have slowed — or even prevented — the panic that set in last week as depositors rushed to withdraw their funds.
In the wake of the bank’s implosion, some Democrats and economists have begun to argue that the bank’s failure and subsequent concerns about contagion in the financial sector actually are direct results of that law, which rolled back key parts of the 2010 Dodd-Frank Act aimed at preventing banks from making the kinds of big bets that led to the 2008 financial crisis.
In an op-ed in the New York Times Monday, Sen. Elizabeth Warren (D-MA), who led the charge against deregulation in 2018, wrote that SVB and the crypto-focused Signature Bank, which was also shut down by the FDIC on Sunday, couldn’t shoulder the old-fashioned bank runs that killed them precisely because there wasn’t oversight to “expose their vulnerabilities and shore up their businesses.”
Notably, the 2018 law changed which banks are considered “systemically important” to regulators. It increased the threshold from institutions holding at least $50 billion in assets to those with $250 billion. That means only the largest banks face stricter regulation, including requirements to maintain certain levels of liquidity and capacity to absorb losses; comply with company- and government-run stress testing; and submit a living will to prepare for potential failure.
SVB had $209 billion in assets, making it the 16th-largest bank in the US by the time it was taken over by the Federal Deposit Insurance Corporation (FDIC) on Friday. But it still wasn’t big enough to be subject to the strictest standard of scrutiny under the 2018 law.
Sen. Bernie Sanders (I-VT) noted in a statement Sunday that the Republican director of the Congressional Budget Office warned of this exact scenario five years ago — that the bill would increase what he thought was a small “likelihood that a large financial firm with assets of between $100 billion and $250 billion would fail.”
“Unfortunately, that is precisely what happened,” Sanders said.
SVB lobbied for deregulation — and may have brought about its own demise
In a statement to a Senate committee in 2015, SVB CEO Greg Becker specifically advocated for raising the $50 billion threshold and argued that failing to do so would saddle mid-sized banks like his with “significant burdens that inherently and unnecessarily will reduce our ability to provide the banking services our clients need.”
He argued that the compliance costs and human resources associated with having to meet the regulatory requirements would have forced the bank to “divert resources and attention from making loans to small and growing businesses that are the job creation engines of our country, even though our risk profile would not change.”
He also touted SVB’s “deep understanding of the market it serves,” “strong risk management practices,” and the “fundamental strength of the innovation economy” on which SVB relied, as well as the bank’s ability to lend to almost 8,000 clients while maintaining strong credit.
The bank spent half a million dollars on lobbying in the leadup to the law’s passage, including on hiring two former senior staffers for now House Speaker Kevin McCarthy. It continued to lobby the FDIC even after the law was passed.
The Dodd-Frank regulations that SVB fought against might have helped identify the bank’s pitfalls earlier. Because the bank catered to Silicon Valley startups and investors with deposits that generally exceeded the $250,000 FDIC deposit insurance limit, 97 percent of its deposits were uninsured — an abnormally large share compared to other consumer banks. That left the bank vulnerable to instability in the tech sector, which has seen more than 120,000 layoffs in 2023 alone.
As financial experts have noted, these and other signs suggested the bank was entering dangerous territory long before its collapse. The new law didn’t completely exempt SVB from regulatory oversight, but regulators apparently failed to note any of these warning signs. They may have been more vigilant if they were required to evaluate the bank’s living will and subject it to annual stress testing.
“This is a black eye for regulators. Something happened that wasn’t supposed to happen,” Ian Katz, a financial policy analyst at Capital Alpha Partners, told the Financial Times. “You’re already seeing finger-pointing going on and that is going to continue.”
The bank also failed to hedge against the risk posed by rising interest rates as it bet on long-term Treasury bonds during the pandemic. Those bonds proved to be a ruinous investment when the bank suddenly needed to free up more liquidity quickly. It didn’t even have an official chief risk officer in the months before the FDIC takeover, as would have been required prior to the 2018 deregulation, even though the bank paid out bonuses within hours of its collapse.
It’s not clear that more oversight would have foreseen those problems and mitigated SVB’s risk exposure. But it probably wouldn’t have hurt.
From The Hindu: Sports
Vincent looks forward to his new role as USA’s batting consultant - Former Andhra coach believes his experience will help him in his new assignment and is confident of helping the team improve
WPL will make other sports have women’s league, says Adani Sports head - “This is going to be one of the best properties as far as women’s sports is concerned,” Satyam Trivedi, head of Adani Sportsline
Cummins to stay back in Australia, Steve Smith to lead side in ODI series - Steve Smith will lead Australia in the upcoming three-match ODI series in the absence of Cummins
WPL | Kapp and Jonassen clinch the issue for Capitals; fifth straight loss for RCB -
Williamson, Southee to be released early for IPL, not named in NZ squad for white-ball series against SL - Three other players— Finn Allen (Royal Challengers Bangalore), Lockie Ferguson (KKR), and Glenn Phillips (Sunrisers Hyderabad)— will fly out to India after the first ODI slated in Auckland on March 25
From The Hindu: National News
TTD honours meritorious students with 10gm silver dollars -
Taking a toll: KSRTC hikes ticket prices by ₹15 for Bengaluru-Mysuru buses plying on expressway - The hike will also reflect in the tickets of EV and Volvo KSRTC buses between the two cities
High Court grants 8 weeks to Delhi govt. for construction of public toilets for transgender people - The High Court noted “ground reality is that nothing has been done” to conduct separate public washrooms for transgender people
Decide in six months plea on police action during BJYM rally in West Bengal: Delhi HC to NHRC - Justice Prathiba M. Singh noted that although the matter was “receiving due consideration” by the NHRC, the proceedings should be concluded in a time-bound manner as the incident pertained to 2020
UDF walks out of Assembly protesting police action against Opposition councillors in Kochi Corporation -
From BBC: Europe
French bin strike: Paris holds its nose as waste piles up - Refuse collectors joined the strike a week ago in protest at plans to raise the pension age to 64.
Ukraine war: Russian soldier arrested ‘after six months in hiding’ - He says he managed to avoid detection after Ukraine recaptured the north-eastern town of Kupiansk.
War in Ukraine: Watch BBC crew take cover as group comes under fire - A missile coming from the direction of the Russian front explodes near the crew and Ukrainian aid workers.
Russia is still India’s largest arms supplier, says report - The findings come amid Delhi’s push to diversify its arms imports portfolio and boost its domestic industry.
Turkey earthquake: UK team to assess building damage - They are carrying out detailed assessments of why so many buildings collapsed.
From Ars Technica
Why it does and doesn’t matter if Google, Microsoft, or Zoom certify your webcam - PC accessory stamps should emphasize features, not compatibility/marketing. - link
You can now run a GPT-3 level AI model on your laptop, phone, and Raspberry Pi - Thanks to Meta LLaMA, AI text models have their “Stable Diffusion moment.” - link
Bees learn to dance and to solve puzzles from their peers - Two recent papers offer evidence of “social learning” and possible culture in bees. - link
Botnet that knows your name and quotes your email is back with new tricks - Quoting Herman Melville is only one of Emotet’s latest innovations. - link
Report: Tim Cook overruled Apple design team’s request to delay XR headset - Article claims it’s about Cook’s legacy, but there may be more at play. - link
A blind woman got on a bus. Sadly, all the seats were taken. -
A man noticed that no one else on the bus was willing to give up their seat for the blind woman, so he kindly guided her to his seat and took a standing spot. As the bus started up, the man frowned at the others for their selfishness.
Later that day, the man came home in tears, covered in bruises.
/cdn.vox-cdn.com/uploads/chorus_asset/file/24498021/temp.png)
United States Court of Appeals for the Fifth Circuit
/cdn.vox-cdn.com/uploads/chorus_asset/file/24502100/image1.jpg)
Prompts by Ethan Mollick
/cdn.vox-cdn.com/uploads/chorus_asset/file/24504293/wehatemeetings_words_forming_hands_holding_hands_with_AI_collag_e1e55297_d7f0_4af5_aa36_ef04361dfd14.png)
/cdn.vox-cdn.com/uploads/chorus_asset/file/24504326/wehatemeetings_monster_emails_collage_art_2f57cb17_1df5_4969_9933_ffd0166d05e6.png)
/cdn.vox-cdn.com/uploads/chorus_asset/file/24504397/wehatemeetings_texts_and_patterns_forming_a_journalist_abstract_1ee4ee81_e060_4917_a300_70e07389791c.png)
