Awaiting

I was reading an article on Christian Nationalism, and this lead me to an interesting paper on The Rise of the New Apostolic Reformation and Its Implications for Adventist Eschatology. The paper is some thirty pages, so I didn't read it carefully all the way through, but it was interesting nevertheless. Reading it, I was reminded of an article that I'd read in Slate, back in the day, Full House at King of Kings Assembly. There was a quote in it, that reads as follows:

There's something in the bloodstream of American Christianity that looks for, and reacts to, signs of the apocalypse. To me, it's not a great thing to herald the end of the world while I'm living here. I have kids. I want to see them grow up.

While Full House at King of Kings Assembly was about Christian Zionism, that desire to see the end of the world (or at least the end of the present world) come as quickly as possible is still prevalent in Christian Nationalism, which also wants to bring about the return of the messiah. And this seems driven, at least in part, by a notable hostility to the world as it currently is. Which makes sense once you learn a little bit about their theology. This is, after all, a worldview that holds that "much of the world is under demon control, which includes many individuals, people groups, nations, territories, false religions and ideologies." I suspect that if I believed that literal demons were leading most of the world around me, I would be pretty hostile to it, too. Especially if I saw a number of post-Enlightenment changes, such as acceptance of homosexuality, religious pluralism, and separation of church and state, as being the result of supernatural "evil influences."

But the thought that I kept coming back to while reading the paper was: "Man. That has to suck." Because it simply can't be a pleasant experience to look at the world around oneself and understand that a good deal of what one sees as being the result of the enemies of what is just and right. The world can sometimes come across as a pretty miserable place even when one grants that everyone has good intentions and is doing their best. Seeing people as in thrall to literal forces of evil, of their own doing or not, has to make the world into a much darker and more hostile place that it would be otherwise.

Untimed

The problem with the idea that the moral failures of people in the past were the result of their negligence in understanding the self-evident moral principles that were present (although often not widely held) in their world is that it presumes that today is the end of moral history; or at least a history with any clarity. Either today's moral viewpoints become the indisputable, universal, and eternal strictures that somehow eluded the whole of humanity before us, despite having been in plain sight, or we somehow have the misfortune of encountering hidden moral truths that won't be uncovered until later generations discover them. Both of these options strike me as unlikely; accordingly, judging yesterday by the moral standards of today seems hold past generations to a standard many deny the present should meet, all in the service of the pretense that 50 years from now, the 2020s won't be found as morally wanting as many people today find the 1970s.

Accounting

The other day, I did another experiment with Generative A.I., this time around a question that I'd been looking to answer for some time.

I asked "A.I.": "How many grocery stores are there in Washington State?"

In keeping with the original experiment, I asked the Usual Suspects: Bing, Copilot, ChatGPT and Gemini. Alexa had been included in the original experiment, but I don't own an Alexa-enabled device and don't want the application on my phone, so it was excluded. In it's place, I added Perplexity, which I'd just heard about recently. I also asked Google, which was part of the original experiment, but had been excluded from my trials, as it's primarily a search engine. (This time, as expected, Google simply give me a list of web links. I was curious if it would present any inline answers, but it didn't.)

When the question first occurred to me, several months ago, I'd asked Bing, and it didn't really give me an answer, but it did offer some not-particularly helpful links. This time both Bing and Copilot appeared to dodge the question. Rather than even attempt to answer the question as asked, they focused on "notable" local stores, providing what seemed like ad copy for Trader Joe's, Grocery Outlet and Haggen. The wording was different between the two, with Copilot being more verbose, but they offered (unsurprisingly) fundamentally the same answer.

ChatGPT flat-out admitted that it didn't have the information, and offered places where I might be able to find current statistics. (But, since it's not a search engine, no direct links.)

Perplexity gave an interesting answer, informing me of how many independent grocers and food co-ops were in the State in 2019. It also gave the number of Kroger and Albertson's stores in the state that would be sold to C&S Wholesale Grocers if the merger were to go through. But it said "The state is also home to various top grocery chains like Amazon Go Grocery, Safeway, and Haggen," so its clarity and timeliness may need to be updated.

Gemini offered a verbose and nuanced answer, noting that how many stores qualify depends on the definition of "grocery store," and offered a range "between several hundred and a few thousand." But it was able to find a source that gave a definitive number (2,313, if you're curious), explained how they arrived at that number, and noted the potential shortcomings of that methodology. (It also took a moment to plug Google Maps and search {natch}, but that can be forgiven.)

In the end, finding specific information that someone else hasn't already packaged up and put out there is still outside the capabilities of "A.I." The various systems mostly fell back on behaving like search engines. The information they gave me was well-presented, but there was no attempt to problem solve. I can think of a few ways that I'd come up with a count, if I could access information as quickly as modern computerized systems do.

Deleveraged

"We're eager to continue working with the [Security] Council on this proposal, one that would see a temporary cease-fire as soon as practicable, based on the formula of all hostages being released," [U.S. Ambassador to the U.N. Linda Thomas-Greenfield] said after the vote. The proposal "would get aid into the hands of those Palestinians who so desperately need it," she added.
The U.S. has again vetoed a U.N. resolution demanding an immediate cease-fire in Gaza

So... let me get this straight...

Israel to Hamas: You release all of the hostages that you still hold, and we'll temporarily stop trying to kill all of you.

United States to Hamas: It's a good deal. You should take it.

There's clearly something here that I don't understand, because I'm having a hard time seeing why anyone thinks that Hamas would agree to this, as Ambassador Thomas-Greenfield laid it out. When the United States vetoed Algeria's proposed resolution calling for a humanitarian cease fire, the Ambassador argued that in order for their to be a durable peace, Hamas had to release the remaining hostages. So if the plan expects Hamas to release hostages, why not offer a durable peace, rather than a temporary cease-fire?

The more the United States wants to be seen as instrumental in creating "peace in the Middle East," the more I suspect that the process would do better were the United States to stay out of it. Because in order to be able to work with both sides, the United States has to be seen as an honest broker, and no-one outside of the State Department or the government of Israel sees the nation that way. And with good reason. One can debate the cause, but it's pretty clear that the effect is that the United States is pushing for a settlement that is acceptable to Israel, without regard for what anyone else wants. The White House and other elements within the government make occasional noises about a "two-state solution," but that seems to be the one option that American administrations are unwilling to put any political capital behind.

In the end, the Palestinians have no good options. They can't fight their way into a position that would allow them to deal with Israel as equals, but it seems unlikely that even if they completely gave up the fight, that they'd be granted equal status, given that current Israeli policy insists that any independent Palestine be effectively a client-state of Israel. Palestine can't win a war of attrition; attempting to do so will likely only end in their gradual extermination and/or expulsion from the land they currently hold. If this is really a state of affairs the United States wants to avoid, something needs to change. And Washington is as good a place to start changing things as any.

Snuck

Trump's high-top sneakers sell out hours after launch

Personally, this seems more like an advertisement for Brand Trump than something that would be filed under "Politics & Policy," but maybe that's just me. Presuming that this is a legitimate news story, what I would like to know is: What are the sources? As near as I can tell, the only way the Axios reporter knows that the shoes are sold out is that they went to the website, and saw the "Sold Out" stamp on the picture of the shoes.

But that's not proof that the shoes are sold out. Only that they've been marked as such. Granted, with the ability to buy three pairs at a time, only a few hundred people needed to make purchases to buy the 1,000 pairs reportedly available for sale.

Still, anyone can go to a website, see a "Sold Out" stamp, and then come up with two hundred words. Axios didn't even seem to bother looking into the company that's reportedly selling the shoes, "CIC Ventures LLC." (Which, according to one X sleuth, is headquartered at Trump International Golf Club in West Palm Beach.) Instead, they simply copy and paste a statement from the website seeking to put some distance the business and Donald Trump.

This isn't a story, it's journalistic filler. Which I get. After all, filler content is cheaper than material that actually takes work to put together. But it seems like part of the death spiral that news outlets find themselves in.

On the Seventh Day

Last week, I replicated an experiment with "A.I." conducted by a user on LinkedIn. The question was: "How many days between 2000-03-09 and 2002-09-30?"

Basically, ChatGPT 3.5 got the answer all kinds of wrong. It had come up with workable steps to find the number, but made errors in each one, resulting in it being off by 100 days. But it showed its work, so one could see where it went off the rails.

This morning, I asked again, and this time, ChatGPT's answer was only slightly off from the ones originally provided by Bing, Alexa, Copilot, and Gemini, answering 934 days. (By my math, it's off by 1.) Again, it gave the steps, but this time, it didn't show its work.

I then decided to test a theory of mine about generative A.I., and asked: "How many numbers are there between 1 and 100?" This is a trick question. For starters, it's ambiguous, because I don't define "number." So the answer could be "an infinite number." I also suspected that ChatGPT wasn't going to leave out 1 and 100, because this isn't the way people normally interact with numbers like this. Sure enough: "Therefore, there are 100 numbers between 1 and 100, inclusive."

(Just to check, I asked it: "Is 1.5 a number?" To which it responded "Yes, 1.5 is indeed a number. It is a decimal number representing the value one and a half. In mathematical terms, it's a rational number and can be expressed as the fraction 3/2.")

Curious as to how ChatGPT parsed the word "between" I asked: "How many days are there between Sunday and Saturday?" The answer came back as: "There are 6 days between Sunday and Saturday, inclusive." So it seems that the use of "inclusive" changed, from counting both 1 and 100 in the number question to counting Sunday or Saturday in the days of the week question.

To be sure, these are simple questions. But they point to the idea that ChatGPT, at least, because of the data that it's been trained on, tends to use language in the same inconsistent ways that people commonly use language. And this is why I suspect that prompt engineering is such an important piece of the puzzle. Getting to the "right answer" is likely going to mean constraining the system, especially if the "Temperature" and/or "Top_p" settings of a system are set to allow for more variability in the answers given.

Wingman

I watched Microsoft's Super Bowl commercial for Copilot. It's a good spot, well put together with a clear message. But I'm not sure that the message conveyed is really the one that Microsoft wants to send.

The basic format of the spot is this: it shows a number of individuals, recounting the doubts that other have about them. It focuses on one person, and her succinct response: "Watch me." Cue the inspirational music as we're shown how Copilot can empower people to achieve more.

For the people who dream of doing big things that are hard to achieve by oneself, Copilot positions itself as something that can help. But it does that, not by making the people in the spot better at what they're already doing, but by allowing them to do things that they'd otherwise ask of others. Commercials operate by showing a need, and offering a solution, and this one is no exception. But the need it appears to be solving is that of human collaboration. At no point in the ad does the viewer see two or more people collaborating on anything. In the world that the commercial shows, there are no teams... only individuals and Copilot. I can see the appeal to people who enjoy working alone, but I suspect it will heighten anxiety for others. If one's fear is that technology will drive isolation, or that AI will render one's skills obsolete, the message of this commercial is not reassuring.

It's the difference between speaking to the target audience and the total audience.

In one scene, a young man asks for sign ideas for his classic truck repair shop. Copilot takes on the role of graphic designer. That scene would have been just as powerful showing Copilot helping a graphic designer to create even more ideas. Or helping "Mike" source specific information on a model of truck that he's repairing. It's A.I. as complement, rather than competitor. By showing Copilot as helping people be productive with the skills they already have, a commercial can avoid the appearance of pitting people against one another, or devaluing the knowledge and talents that they bring to the table. It speaks to the total audience.

The primary fear that many people have of A.I. technology is that it's going to obsolesce their skills and damage their employment and/or income prospects. And, to be sure, it's going to take more than well-crafted commercials to assuage those concerns. Be that as it may, there's value in not feeding those concerns. Creating an advertisement that implies that Copilot can replace people, and expecting those people not to notice, was a misstep, if for no other reason than it implies that destroying people's livelihoods will be a known side effect of rolling out the technology.

The disruption to labor markets of Generative A.I. systems, and possibly Artificial General Intelligence is not a matter of "if," but of "when" and "how intensely." If A.I. companies don't position the technology as something that benefits broad sections of society, as opposed to further concentrating wealth at the top of the income distribution, people will push back against the threat they perceive it to pose. Messaging that speaks to a target audience, but leaves out others, plays into that sense of threat,

Missed Messaging

A few hours ahead of Sunday's Super Bowl game, Donald Trump posted the following to his "Truth Social" platform:

There's no way [Taylor Swift] could endorse Crooked Joe Biden, the worst and most corrupt President in the History of our Country, and be disloyal to the man who made her so much money.

So far, so Donald Trump. I've already opined about the fact that I don't think that Taylor Swift is as much of a political kingmaker as Right-wing/Republican paranoia makes her out to be, so I won't belabor that point here. The point of interest this time is National Public Radio, and their impression of Mr. Trump's words, which they first describe as "Trump's appeal to Swift" and then later as "Trump's plea."

It had caught my attention because it seemed like they were soft-pedaling Mr. Trump's tone. I saw nothing in Mr. Trump's words that came across as an appeal, let alone pleading. So I conjectured that maybe NPR didn't want to arouse the ire of the Make America Great Again crowd by calling him out for being aggressive towards Ms. Swift. But on re-reading, it occurred to me that maybe they just didn't know what to make of it all. NPR was framing the post as if Taylor Swift were the audience, rather than simply the subject, even though there is nothing about it that would indicate this. Donald Trump is perfectly capable of speaking to people when that is his intent. And that doesn't seem to be the intent here. If anything, given the fact that it refers to Ms. Swift in the third person, it's priming his followers to be angry with her in the even that she does decide to endorse President Biden. It's simply Donald Trump publicly reinforcing the idea that many of his supporters already have, that Taylor Swift has no business in politics.

To be sure, he's being circumspect about it; he avoids saying any directly negative about Ms. Swift. Given his penchant for name calling, he could have easily come up with some playground derogation and attached it to her, then railed against her. But he doesn't. Rather, his tone is one of assuring his followers that Taylor Swift owes him, and therefore, their concerns that she'll turn her legions of followers against the Republicans this fall are misplaced. In other words, Donald Trump's not appealing to Ms. Swift, he's speaking to pretty much the only people he ever speaks to; the people who want him to be President again. It's odd that NPR seems to have missed that.

Full Page

But Little’s decades of impunity underscore a troubling truth about the U.S. criminal justice system: It is possible to get away with murder if you kill people whose lives are already devalued by society.
The Perfect Victim

This is the sort of “troubling truth” that I, personally, am not troubled by. Not in the sense that I support the idea that law enforcement should be unequal, but because I understand why it is unequal, and being troubled by basic facts of life is bad for one’s mental health.

For all that advocates for poor and minority communities, and other groups commonly referred to as “marginalized,” claim that they don’t want less attention and fewer resources to be devoted to investigating the disappearances and deaths of young, attractive, white, and upper middle class women, maintaining the levels of public interest (and thus, media coverage) and law enforcement engagement for every disappearance and death would require a level of resourcing that I suspect would quickly become unsustainable. Accordingly trade-offs have to be made. And, as with pretty much all trade-offs, those made by the criminal justice system respond to the incentives that are placed before it.

But open talk of trade-offs tends to be avoided. The Washington Post’s choice of words speaks to this in the formulation of: “people whose lives are already devalued by society.” This characterizes “value” as something that starts high, and is, intentionally or not, lowered. If all people are going to be valued equally, than everyone should be valued as much as those people who are now considered most valuable. While I’m sure that there have been instances where someone has been described as “overvalued” by society, I haven’t come across one.

Criminal justice requires trade-offs because resources are limited. There simply aren’t the personnel, nor the money to pay for them, to apply a consistently high level of effort to every disappearance or death in which foul play is known, let alone suspected. And so law-enforcement agencies put their resources where there will be the loudest complaints of under-resourcing. And that tends to be those cases with the most attention from the public and the media. But it’s not only a one-way street. Part of the reason for the differential in how society values people is a justification of who resources are expended on. When the public focuses on women who are seen as mothers, daughters, students, and contributors to their communities, that’s done in part to justify granting investigations into what happened to them a greater slice of the resource pie.

Samuel Little, was, quite simply, bright enough to understand that, if he was going to indulge his recurring desires to choke girls and women to death, he had to be careful in who he selected.

For example, he said, “I’m not going to go over there into the White neighborhood and pick out a little teenage girl.”

Because murdering a little teenage white girl would have created incentives for more resources to be applied to both finding her, and finding who had victimized her. I’m not a fan of that incentive structure, but being actively troubled by it would mean not sleeping at night. After all, it’s a very common phenomenon.

In the end, the Post article (which, by the way, is from late 2020, before Samuel Little died in prison) is about casting law enforcement and the criminal justice system as indifferent, sometimes apparently deliberately. It’s the sort of thing that’s designed to highlight an injustice, while making it clear that the reader is absolved of any responsibility for it. That’s why it’s a “troubling truth about the U.S. criminal justice system” rather than a illustrative example of how societies choose to expend resources when hemmed in by constraints. If the United States, as a nation, wishes to avoid future instances of a serial murderer using the incentives that society creates to cover their tracks in the service of committing crime after crime, the populace as a whole is going to have to change those incentives. And to the degree that being troubled by them tend to disincentivize examining and understanding them, it acts to hasten, rather than prevent, the next series of killings.

And Statistics

One of the side effects of regularly listening to the 538 Politics Podcast, especially their "Good or Bad Use of Polling" segments, is that I've become better able to understand data when it's being presented in the media. Because few things are really what they're cracked up to be. Take the following story from Axios:

Married people are happier than single adults: survey

Brought to you by the wedding-industrial complex. Not really. It's actually brought to you by a conservative think-tank, that's looking "to strengthen marriage and family life." Because headlines need to be punchy, Axios somewhat misstates things.

Gallup, the organization that conducted the surveys, doesn't set out to directly measure happiness. What they're measuring are people's self-reported positioning on the "Cantril Self-Anchoring Scale," which asks respondents to place themselves on a 0-10 scale of worst to best possible lives for themselves 1) in the present and 2) in five years time. Using these scores, Gallup places people into one of three buckets: Thriving, Struggling or Suffering.

What the Institute for Family Studies is touting, is the fact that the Gallup data show a correlation between being married, and attaining a "Thriving" rating in the Gallup groupings. Their point, which is to be expected, given their mission is that "In America at least, it looks like well-being ebbs and flows with marriage." The column does, however make an important caveat: "Marital status is not randomly assigned." And this is important, because the article is at pains to point out "that marital status is a stronger predictor of well-being for American adults than education, race, age, and gender." While it notes that the data can't prove a causal relationship, the piece maintains that marriage is an overall good. Which makes sense for an organization that's looking to boost marriage.

Looking at the actual data, what stood out for me was 2017. With the exception of divorcées, this is the high-water mark for all groups' thriving percentages. And 2018 was a bit worse for all groups. 2020 was a disaster for everyone, and only the never married cohort continued their recovery into 2023. Divorcées were on track to take over the second-place spot before the pandemic derailed everything, and they've barely recovered any ground since 2020. All groups are much lower in the rankings as of last year than they were in 2017, and married couples are on a downward trend. The Institute for Family Studies article speaks to none of this. Which is unfortunate, because there is likely to be insight there.

Instead, it shifts, and focuses on the fact that "People living in metropolitan areas with higher rates of marriage enjoy higher subjective wellbeing." To demonstrate this, it take the metropolitan areas with the ten highest and ten lowest rates of marriage, and plots their Gallup "Thriving" rates, along with their rates of "deaths of despair," defined here as "deaths from suicide, drug or alcohol poisoning, or overdose." (As an aside, "deaths of despair" has become something of a buzzword, and like most buzzwords, it's not strictly accurate. After all, drug and alcohol poisoning/overdose deaths may also happen at parties.) But to do this, it relies on an analysis done for The Brookings Institution. That analysis shows something that the Institute for Family Studies alludes to; the deaths of despair rates for the top and bottom ten metro areas by "Thriving" rates. Provo-Orem, Utah holds the number one spot on both lists, having the highest percentage of married households and of people who say that they are thriving. But, notably, other than that, none of the top ten metro areas for "Thriving" show up on the top ten list for marriage rates, and there is no overlap at all in the lists for the bottom 10 metros. Brookings, rather than focusing on rates of marriage when evaluating whether people are likely to self-report as thriving, points to demographics and location, noting that different ethnic groups have different "Top Ten" lists. It doesn't mention marriage at all as a factor.

In the end, I found myself looking for a data point that wasn't there. Mainly because I don't believe that Gallup asks about it in their survey. Is there a correlation between whether people want to to be married or not, and whether they report themselves to be thriving? Policies designed to help people who want to be married become married would look significantly different than policies designed with marriage for everyone in mind.

Coverage of the benefits of marriage, especially when promoted by marriage boosters, tend to view the institution as something that's good for everyone, regardless of other concerns. "Married people are happier than single adults" and "Married People Are Living Their Best Lives" being just two examples. But "People who have the relationships they want are happier than other adults" and "People Who Have the Relationships They Want Are Living Their Best Lives" are just as likely to be true.

Year of the Dragon

It's been a while since I've done any figure photography, and these Dragons seemed on theme for the upcoming Yin lunisolar calendar New Year. I'm going to have to work on finding a good backdrop in my current place, especially given that my cameras default to opening the aperture, even in reasonably bright light, resulting in very shallow depth of field. To get around that, I'll need to have a place where I can set up my tripods properly. Either that, or get some reflectors to raise the light levels.

Days Without Number

A Product Director from Amazon posted on LinkedIn that he'd "asked Google, Bing, ChatCPT, Alexa, Copilot (Bing), and Gemini (Google): 'How many days between 2000-03-09 and 2002-09-30'," and "got four different answers."

When someone hands you an experiment that seems interesting, Step 1 is to replicate it. So I did. I don't have an Alexa device, so I posed the question "How many days between 2000-03-09 and 2002-09-30?" to the other four. (The base Google search doesn't try to answer the question, it simply points the user to other resources... it is a search engine, after all.)

Bing and Gemini returned the same answer: "There are 935 days from/between March 9, 2000 to September 30, 2002," only the syntax was slightly different, with Bing using "from" and Gemini using "between."

Bing Copilot gave a slightly different, and more detailed answer, noting: "There are 936 days between 2000-03-09 and 2002-09-30, excluding the end date. If you include the end date, there are 937 days." Copilot was also interesting in that it returned the dates in the same format that they were given.

ChatGPT (3.5) went to town, giving me the entire process by which it arrived at its answer:

To calculate the number of days between March 9, 2000, and September 30, 2002, we can use the following steps:

1. Calculate the number of days in full years between the two dates.
2. Add the number of days from March 9, 2000, to the end of 2000.
3. Add the number of days from January 1, 2002, to September 30, 2002.

Here's the calculation:

Full years between 2000 and 2002: 2001 and 2002 (2 years).
Total days for full years: 2 years * 365 days/year = 730 days.

Days from March 9, 2000, to the end of 2000:
March 9 to March 31 = 31 - 9 + 1 = 23 days.

Days from January 1, 2002, to September 30, 2002:
January 1 to September 30 = 31 (Jan) + 29 (Feb - leap year) + 31 (Mar) + 30 (Apr) + 31 (May) + 30 (Jun) + 31 (Jul) + 31 (Aug) + 30 (Sep) = 284 days.

Now, summing up all the days:

730 (full years) + 23 (days in 2000) + 284 (days in 2002) = 1037 days.

So, there are 1037 days between March 9, 2000, and September 30, 2002.

One of these answers is not like the others... ChatGPT was way off.

Which kind of gets to the thing with generative "A.I." The artifice is there, and fairly impressive. But they aren't intelligent systems, in the sense of having an understanding of what they're working with. The idea to start with full years in Step 1 was sound, but going January 1st through December 31st for both 2001 and 2002 was erroneous. Step 2 was flawed from the jump, as ChatGPT seemed to think that March 31st was the last day of the year 2000. (How's that for a Y2K bug?) And given that 2002 wasn't a leap year, Step 3 was also incorrect, although here it was only off by a single day. But this was the nice thing about Chat GPT showing its work. That work was wrong, but since it was possible to follow what it was doing, it was pretty clear why it was wrong; the errors were evident enough that one didn't need an idea of what the right answer should have been to realize that it was miscounting. The transparency that ChatGPT demonstrated was useful in that regard.

By the way, I did the math myself, and found that the answer is 935, or 937 days if you count both March 9th, 2000 and September 30th, 2002. So other than ChatGPT, the programs got it correct, but it does depend on how they read the question, since that determines the days on which they start and end their counts.

Escalations

Charles Darwin identifies three basic conflicts that made up the Struggle for Survival. They can be summed up as interspecies conflicts, intraspecies conflicts and conflicts versus the environment. I think one of the things that makes the concept of "evil" so compelling is that it elevates conflicts between people, either individuals or populations, from the personal to matters of the life and death of the species as a whole. And when the stakes are suddenly that high, it's easy to conclude that there's no such thing as extremism.

Aside:

For those of you who weren't here when I started The Short Form, it's mainly an antidote to my tendency to be wordy. Sometimes, thinking about what would otherwise be a long post helps me distill it down into a sentence or two, that says what I want to say, perhaps with a bit if context thrown in for added clarity.

Booted

A child's boot, abandoned in a parking lot.

The thing about found object photography is the knowledge that behind every object there is a story; one that will likely never be known.

Plotted Out

Generally speaking, people tend to write off those they consider to hold conspiracy theories as uncritical thinkers at best, and of dangerously questionable mental health at worst. Conspiratorial thinking, the logic goes, exists mainly to offer simple explanations to complex phenomena or questions.

But it's also worth noting that alleged conspiracies offer insight into the anxieties of the people who hold them. Consider the (relatively) new conspiracy theory concerning singing star Taylor Swift. You've likely heard of it, it's being covered all over the place. I won't bore you with the details (everyone else is looking to do that), but suffice it to say that for many people in the Make America Great Again crowd, the Deep State is at it again, in order to ensure that President Biden wins another illegitimate term in the White House.

While it wouldn't surprise me to learn that there was a drinking game at the bottom of all of this, I think that there is something of interest here. Namely, the fear among Trump supporters that Taylor Swift could manage to mobilize a significant number of people that Trump campaign was counting on not voting. After all, what tends to prevent the United States from sliding leftward is the fact that young people, who are the most likely to lean left, tend not to vote. Granted, there's been something of a bifurcation in "the youth vote" recently, with younger men drifting to the Right, while young women drift Left, but the fact remains that a substantial number of votes that would normally wind up in the "D" column are never cast. I suspect that people on the Right have realized that Taylor Swift has at least some power to change that.

And this is important in this election cycle because Donald Trump, while he can turn out the people who already want him to be President, has pretty much given up on making his case to people outside of that group. That is to say, for people who aren't already Trump-style populists, or deeply frightened of or enraged at the Democrats, the Trump movement has nothing to offer. In fact, one can make the case that Trumpism actively alienates people outside of Trump's base. A lot of those people were likely disinclined to vote anyway, given their general disaffection from the Democratic Party. But an endorsement from Taylor Swift could upend that.

If you'd asked me a month ago whether such an endorsement from Taylor Swift could have such an impact on this November's Presidential election, I would have told you "no." And quite honestly, I'm still mostly of that opinion. But the emergence of what looks like a state of open panic over the possibility tells me that there are a decent number of people who believe it. For the record, I'm not convinced that, say, Vivek Ramaswamy is dim enough to actually buy into this. But I think that he understands that if he's going to maintain enough support among Donald Trump's voters to land a cabinet position or the Vice-President's job, he has to talk the talk. And he's not the only one. And I think that as the people who seek to remain influential in the current Republican Party openly espouse the conspiracy, more and more Republican voters will see it as legitimate.

Which, to circle back, is part of their problem. I don't think that Taylor Swift really has the power to sink Donald Trump's chances of winning the November election. The insularity of the Trumpist base is doing that work for her. I know a few people who are big on Trump, and, even more so than most people I know who are politically active, outreach to people who don't already agree with them is simply not on the menu. I'm of the opinion that this is a bigger problem for them than any celebrity.

But Wait, There's More

I was out at a happy hour yesterday. For the food basically, I never learned to drink. The televisions were on, muted, and turned to the local broadcast channels. The evening news was on. The number of crime stories that ran was somewhat surprising. I know that news outlets have a tendency to run crime stories; "if it bleeds, it leads" and monetizing scaring people, and all that. But it seemed that more than half the newscast was simply one crime story after another. Given that the sound was off, I didn't get any of the details, but they wouldn't have been informative anyway.

But it explains why people in the local area claim to be afraid to go into Seattle unless they're armed. Which strikes me as ludicrous, but I suppose if  one sees "Man shot after walking past homeless encampment," multiple times in an evening (it seems that they run these stories on repeat), it starts to make a certain level of sense.

The faceless 'burb that I live in is dull by pretty much any standard. In the nearly two years I've lived in my current place I've seen the police mainly because they seem to show up across the street on a recurring basis. The only time other than that I'd seen officers in the neighborhood was when they were talking to the homeless guy who used to live in a van around the corner. (He cleared out just prior to the cold snap that landed in back in January, and hasn't returned.) So I'm always somewhat amused when people openly wonder if it's "safe." But then again, I'm a native of Chicago... and lived there when violent crime peaked nationwide back in the early 1990s. Nothing that happens here phases me.

But I've also stopped watching broadcast news, which always seems able to find a slew of random crime stories important enough that everyone needs to know about, but not enough so to be genuinely informative. This makes me less informed about "dangers" in the local area than some people like, but I find that I sleep better, so it's been a worthwhile trade.