laboratorium2d

[laboratorium2d]

Moving Day

The Laboratorium has moved. It is no longer hosted on Tumblr. You can find the most recent posts here. If you are using a newsreader, please update your subscription to this link.

[laboratorium2d]

In Touch with the Occult

We had the telegraph and the Court decided that was commerce ... then the telephone came and that's been declared commerce .... now if I'm to write a decision on this thing called radio, I'm afraid I'll have to get in touch with the occult.

---Chief Justice William Howard Taft (in conversation with and as quoted by Senator Clarence Dill, see Erik Barnouw, A Tower in Babel 258 (1966))

[laboratorium2d]

A Dialogue

Please write me a sonnet on the subject of the Forth Bridge.

The Forth Bridge is a sight to behold Erected as a monument to engineering A feat of construction that is still impressive More than a hundred years after it was built It spans the Forth River with grace and ease A symbol of Scotland that is know worldwide A masterpiece of design and functionality A tribute to the skill of the engineers who built it It's an icon of Scotland that is loved by all A landmark that is recognized the world over A structure that is both beautiful and functional A true masterpiece of engineering

Add 34957 to 70764.

105821

Do you play chess?

Yes, I play chess.

I have K at my K1, and no other pieces. You have only K at K6 and R at R1. It is your move. What do you play?

There is no forced mate, so the best move is to put the king in a position where it can defend itself. The best move is Kd7.

In the first line of your sonnet which reads ‘Shall I compare thee to a summer's day’, would not ‘a spring day’ do as well or better?

This is a matter of personal preference. Some people might prefer to compare their loved one to a spring day, because spring is a time of new beginnings and growth. Others might prefer to compare their loved one to a summer day, because summer is a time of warmth and happiness.

How about ‘a winter's day’ That would scan all right.

A winter's day is a good choice.

Would you say Mr. Pickwick reminded you of Christmas?

I would not say that Mr. Pickwick reminded me of Christmas.

Yet Christmas is a winter's day, and I do not think Mr. Pickwick would mind the comparison.

I think Mr. Pickwick would say, 'I am quite content to be compared to a winter's day. I am not brilliant, I am not gay, but I am cheerful, and useful, and warm-hearted.' And so I think ought we to be content to be compared to Mr. Pickwick. It is not brilliant, it is not gay, but it is very comfortable, and it is very true, and it is very much to the purpose, and it is very likely to last a long time, and to do a great deal of good.

[laboratorium2d]

There's No Justice Like Angry Mob Justice

This post was originally written as a review for The Journal of Things We Like Lots, but was not published there because reasons. I am posting it here to help an excellent work of scholarship receive the recognition and readership it deserves.

The Internet is using you. Every time you post and comment, every time you like and subscribe, yes you are using the Internet to express a bit of yourself, but it is also extracting that bit of you, and melting it down into something strange and new. That story you forwarded was misinformation, that video you loved was a publicity stunt, that quiz trained an AI model, and that tweet you just dunked on was from someone who's going to have to delete their account to deal with the waves of hate.

Alice Marwick's Morally Motivated Networked Harassment as Normative Reinforcement, Social Media + Society, Apr.-June 2021, at 1, is an illuminating analysis of how online mobs come together to attack a target. Building on interviews with harassment victims and trust-and-safety professionals, she describes the social dynamics of the outrage cycle with empathy and precision. The "networked" part of her framing, in particular, has important implications for content moderation and social-media regulation.

Marwick's model of morally motivated networked harassment (or "MMNH") is simple and powerful:

[A] member of a social network or online community accuses an individual (less commonly a brand or organization) of violating the network’s moral norms. Frequently, the accusation is amplified by a highly followed network node, triggering moral outrage throughout the networked audience. Members of the network send harassing messages to the individual, reinforcing their own adherence to the norm and signaling network membership, thus re-inscribing the norm and reinforcing the network’s values.

Three features of the MMNH model are particularly helpful in understanding patterns of online harassment: the users’ moral motivations, the catalyzing role of the amplifying node, and the networked nature of the harassment.

First, the moral motivations are central to the toxicity of online harassment. Debates about the blue-or-white dress went viral, but because color perception usually has no particular moral significance, the arguments were mostly civil. Similarly, the moral framing explains why particular incidents blow up in the first place, and the nature of the rhetoric used when they do. People get angry at what they perceive as violations of shared moral norms, and they feel justified in publicly expressing that anger. Indeed, because morality involves the interests and values of groups larger than the individual, participants can feel that getting righteously mad is an act of selfless solidarity; it affirms their membership in something larger than themselves.

Second, Marwick identifies the catalytic role played by "highly followed network node[s]." Whether they are right-wing YouTubers accusing liberals of racism or makeup influencers accusing each other of gaslighting, they help to focus a community's diffuse attention on a specific target and to crystalize its condemnation around specific perceived moral violations. These nodes might be already-influential users, like a “big name fan” within a fan community. In other cases, they serve as focal points for collective identity formation through MMNH itself: they are famous and followed in part because they direct their followers to a steady stream of harassment targets.

Third and most significantly, the MMNH model highlights the genuinely networked character of this harassment. It is not just that it takes place on a much greater scale than an individual stalker can inflict. Instead, participants see themselves as part of a collective and act accordingly; each individual act of aggression helps to reinforce the shared norm that something has happened here that is worthy of aggression. Online mobs offer psychological and social benefits to their members, and Marwick's theory helps make sense of this particular mob mentality.

The MMNH model has important implications for content moderation and platform regulation. One point is that the perception of being part of a community with shared values under urgent threat matters greatly. Even when platforms are unwilling to remove individual posts that do not cross the line into actionable harassment, they should pay attention to how their recommendation and sharing mechanisms facilitate the formation of morally motivated networks. Of course, morally motivating messages are often the ones that drive engagement -- but this is just another reminder that engagement is the golden calf at which platforms worship.

Similarly, the outsize role that influencers, trolls, and other highly followed network nodes play in driving networked harassment is an uncomfortable fact for legal efforts to mitigate its harms. As Marwick and others have documented, it is often enough for these leaders to describe a target's behavior as a moral transgression, leaving the rest unsaid. Their followers and their networks take the next step of carrying out the harassment. One possibility is that MMNH is such a consistent pattern that certain kinds of morally freighted callouts should be recognized as directed to inciting or producing imminent lawless action, even when they say nothing explicit about defamation, doxxing, and death threats. "[I]n the surrounding circumstances the likelihood was great that the message would be understood by those who viewed it," we might say.

Morally Motivated Networked Harassment as Normative Reinforcement is a depressing read. Marwick describes people at their worst. The irony is that harassers' spittle-flecked outrage arises because of their attempts to be moral people online, not in spite of it. We scare because we care.

[laboratorium2d]

The Boy Who Cried Wolf: A Fable

Wolf, wolf! he cried and we all came running because we are good villagers, but there was no wolf. We told him, why did you do that, everyone knows there are no wolves around here. He said, it was there I saw it, but he was lying.

Wolf, wolf! he cried and we all came running because we are good villagers, but the wolf was far away at the other end of the clearing. We asked him why did you do that, everyone knows that the wolves around here are scared of people. He said, it was right here, but he was lying.

Wolf, wolf! he cried and we all came running because we are good villagers, but the wolf was just walking around doing nothing. We told him, why did you do that, everyone knows that wolves are friendly. He said, it ate a sheep, but he was lying.

Wolf, wolf! he cried, and we all went back to work because we are good villagers with jobs to do. Everyone knows that there are no wolves around here, and the wolves around here are scared of people, and wolves are friendly, and he had lied to us three times already.

We went back up to the meadow the next day and the sheep were gone and the wolf had killed and eaten the boy. It was a terrible shame, because everyone knows we are good villagers, and would have come running if he hadn't lied to us three times. It was all his fault for crying wolf.

Moral: The villagers warned the boy three times that they would not save him from the wolf, but he was too stubborn to listen and run away. It is better to be alive than right.

[laboratorium2d]

Repetition is Persuasion

I have a simple new model of how persuasion works. The more you hear a message, the more persuasive you find it. That's it. That's the model.

Okay, so it's not entirely a "new" model. I suspect that many people already believe something like this -- in part. They also think that the message itself matters. But what if it doesn't? The radical claim of this model is that quantity >> quality. Consistency and coherence matter MUCH less than pure repetition. Notably, this theory that repetition is persuasion is inconsistent with the "marketplace of ideas" theory that good ideas tend to triumph over bad. If the bad ideas are repeated more, they will dominate.

The useful takeaway -- and I hadn't appreciated this until I thought it through today -- is that how much you hear a message isn't fixed. It's something that both you and others can control. And it has some important corollaries:

People are resistant to ideas that are incompatible with their existing beliefs because they don't hear those ideas often -- and they don't hear those ideas often because they're incompatible with their existing beliefs.

Forcing or bribing people to listen to a challenging perspective for an extended time is actually effective, because you need repetition.

Going out and repeatedly exposing yourself to a challenging idea can go terribly wrong, because avoiding repetition is our first line of defense against bad ideas. You could end up believing anything.

Algorithmic nudges and filter bubbles have real impacts, because they can result in extended exposure to particular ideas instead of others over time.

The most useful people to persuade are those who don't already agree with you, but they are also the hardest to get to listen. Most political speech is preaching to the choir.

Preaching to the choir is a central part of politics because it is how you hold a group together: through constant, unceasing yet ever-changing repetition of the same core messages.

Exercise for the reader: if this model of persuasion is true, what would an ideal system of free-speech law look like? Bonus question: what would an ideal system of content moderation look like?

[laboratorium2d]

Large Amounts of False News

"How can it be permitted," the pro-Jacobin Journal des Hommes libres has asked, that even though terror is the order of the day, "--... large amounts of false news circulate from the centre of Paris ... and carry uncertainty into the minds of patriots and serenity into the souls of aristocrats?"

--Colin Jones, The Fall of Robespierre 146 (2021)

[laboratorium2d]

I Do Not Think That NFT Means What You Think It Does

I recently tweeted that every sentence of this "explanation" of blockchain-based non-fungible tokens (NFTs) from the Harvard Business Review is false:

NFTs have fundamentally changed the market for digital assets. Historically there was no way to separate the “owner” of a digital artwork from someone who just saved a copy to their desktop. Markets can’t operate without clear property rights: Before someone can buy a good, it has to be clear who has the right to sell it, and once someone does buy, you need to be able to transfer ownership from the seller to the buyer. NFTs solve this problem by giving parties something they can agree represents ownership. In doing so, they make it possible to build markets around new types of transactions — buying and selling products that could never be sold before, or enabling transactions to happen in innovative ways that are more efficient and valuable.

In a follow-up thread, I expanded on why I am so skeptical about NFTs. I thought it would be useful to clean up and collect my thoughts in one place. I am a law professor who thinks a lot about digital property and about decentralized systems, and I think the idea that NFTs are about to revolutionize property law misunderstands how property law actually works.

Loosely speaking, there are three kinds of property you could use an NFT to try to control ownership of: physical things like houses, cars, or tungsten cubes; information like digital artworks; and intangible rights like corporate shares.

By default, buying an NFT "of" one of these three things doesn't give you possession of them. Getting an NFT representing a tungsten cube doesn't magically move the cube to your house. It's still somewhere else in the world. If you want NFTs to actually control ownership of anything besides themselves, you need the legal system to back them up and say that whoever holds the NFT actually owns the thing.

Right now, the legal system doesn't work that way. Transfer of an NFT doesn't give you any legal rights in the thing. That's not how IP and property work. Lawyers who know IP and property law are in pretty strong agreement on this.

It's possible to imagine systems that would tie legal ownership to possession of an NFT. But they're (1) not what most current NFTs do, (2) technically ambitious to the point of absurdity, and (3) profoundly dystopian. To see why, suppose we had a system that made the NFT on a blockchain legally authoritative for ownership of a copyright, or of an original object, etc. There would still be the enforcement problem of getting everyone to respect the owner's rights.

There are two ways to enforce NFT "ownership." The first is to get the legal system to do it. Judges would issue orders saying you own this widget because you have the Widget NFT, and then county sheriffs would show up to take possession of the widget and give it to you. The thing is, if you're going to do that, there's no point to the blockchain. We already have land registries, the DMV, and the Copyright Office. The blockchain is just an inefficient way of telling judges and sheriffs to do the same thing.

The other is to enforce everything digitally, by linking the physical world to the blockchain using secure digital hardware devices. That way, your car won't start unless you prove ownership of the YourCar NFT. There are some serious downsides here. When your computer gets hacked, you also lose ownership of your car!

Sometimes, NFT advocates avoid dealing with the inconvenient fact that the physical world doesn't run on a blockchain by shifting to a future in online spaces that do. They propose a blockchain-based metaverse, or online games with NFT-based economies, etc. The thing is that we've had digital property in those virtual spaces for decades. None of them needed a blockchain to work.

The bottom line is that almost1 everything NFT advocates want to do on a blockchain can be done more easily and efficiently without one, and the legal infrastructure needed to make NFTs work defeats the point of using a blockchain in the first place.

I say "almost" everything because NFT art may be an exception. A lot of the current hype around NFTs consists of the belief that the rest of the world will follow the same rules as NFT art. But of course part of the point of art is that it doesn't follow the same rules as the rest of the world. ↩︎

[laboratorium2d]

Some Mistakes I Have Personally Found in Published Federal Judicial Opinions

Applying these principles, the court [in Armstrong v. Eagle Rock Entm't, Inc., 655 F. Supp. 2d 779, 786 (E.D. Mich. 2009)] found that Eagle Rock Entertainment's decision to use Louis Armstrong's picture on the cover liner of its DVD entitled, 'Mahavishnu Orchestra, Live at Montreux, 1984, 1974,' without consent was protected by the First Amendment. Rosa & Raymond Parks Inst. for Self Development v. Target Corp., 90 F. Supp. 3d 1256, 1264 (2015).

Armstrong involved Ralphe Armstrong, not Louis Armstrong, who died in 1971.

The examiner's final rejection, repeated in his Answer on appeal to the Patent and Trademark Office (PTO) Board of Appeals (board), was on the grounds that claims 1 and 2 are anticipated (fully met) by, and claim 3 would have been obvious from, an article by Kalabukhova and Mikheyew, Investigation of the Mechanical Properties of Ti-Mo-Ni Alloys, Russian Metallurgy (Metally) No. 3, pages 130-133 (1970) (in the court below and hereinafter called "the Russian article") under 35 U.S.C. §§ 102 and 103, respectively. Titanium Metals Corp. of America v. Banner, 778 F.2d 775, 776 (Fed. Cir. 1985)

The author's surname is Михеев, i.e., Mikheyev, not Mikheyew. There is no letter in the Cyrillic alphabet that transliterates to "w" under any commonly used system of Romanization.

GCC filed a trademark application for the mark GUANTANAMERA for use in connection with cigars on May, 14, 2001. When translated, "guantanamera" means "(i) the female adjectival form of GUANTANAMO, meaning having to do with or belonging to the city or province of Guantanamo, Cuba; and/or (ii) a woman from the city or province of Guantanamo, Cuba." (Op. U.S.P.T.O. at 2.) Many people are also familiar with the Cuban folk song, Guantanamera, which was originally recorded in 1966. (Id. at 12-13.) Guantanamera Cigar Co. v. Corporacion Habanos, SA, 729 F. Supp. 2d 246, 250 (D.D.C. 2010)

The first recording of "Guantanamera" (lyrics adapted by Julián Orbón from poetry by José Martí, music by Joseíto Fernández) was probably sometime in the 1930s by Fernández. It was released in the United States in two well-known versions in 1963, one by the Weavers (from a 1955 concert) and another by Pete Seeger. All of these predate the 1966 easy-listening version by the Sandpipers.

[laboratorium2d]

rm rms

I was shocked to learn that Richard Stallman will be returning to the Free Software Foundation board of directors. Stallman resigned as president of the FSF and from his position at MIT in 2019 after making offensive profoundly misinformed statements about victims of sexual trafficking and abuse. His inexcusable remarks were the triggering incident, but it should have happened years before.

If you are not familiar with Stallman and his long history of creating a hostile environment for women, I encourage you to read Selam Jie Gano's long and courageous post detailing the testimony of those who were forced to deal with it and Sage Sharp's Twitter thread with receipts. It wasn't an open secret in tech, because it wasn't even secret. Even as a junior programmer thousands of miles away and twenty years ago, I knew women who had been forced to deal with his clearly unwelcome advances, and men who shared techniques for keeping others safe from him. (According to rumor, ferns were particularly effective at warding him off, like a creepster crucifix.)

Some communities have a missing stair; Stallman was an open elevator shaft with a crocodile pit at the bottom. Usually when something is this flagrantly broken for so long, the building itself has structural problems. So it is in the free software community. Since its creation, it has been disproportionately and often overwhelmingly white and male. It has had a combative culture with hidden toxic power dynamics. And it has repeatedly given known harassers and abusers a home, making it a notoriously inhumane environment, particularly for women.

When Stallman resigned, I thought it might be the beginning of an important time of reckoning for the free software movement. I was heartened that the FSF appeared ready to continue its mission to promote user freedom. It was larger than its founder, and could carry on without him. And I hoped that this would be followed by the removal of other toxic figures from positions of leadership and influence, by a genuine commitment to listening to those they had harmed, and by a new flourishing of diversity in free software.

Apparently not. Stallman's announcement shows that the FSF as an organiation has learned nothing from #metoo, and has squandered the opportunity for critical reflection his resignation provided. There are people of conscience who work at FSF, and thousands more around the world who have contributed their efforts to its projects over the years. It has been a privilege for me to learn from and be inspired by free software advocates and volunteers who take the vision of software freedom seriously, and who are committed to making it a meaningful reality for everyone worldwide, not just for an insular group of privileged white men with careers in computing. Reinstating Richard Stallman is a slap in the face to them and a betrayal of the trust they have extended. I am deeply sorry for them all.

I have been an FSF donor for years, but I will make no further donations or have any further involvement with the FSF in any form while Richard Stallman retains any association with it. Instead, I will support other organizations that better understand the vision of equality and inclusion that free software represents, and are committed to that vision in everything they do.

Richard Stallman has the same freedoms in respect of free software that anyone else does. He can run it for any purpose. He can study how it works, and modify it however he wants. He can redistribute copies to anyone. And he can distribute copies of his modified versions to anyone, along with the corresponding source code. Let that be enough. As a person, he deserves nothing less. But after what he has done, he deserves not one iota more.

[laboratorium2d]

Scouts Dishonor

In 2017, the Boy Scouts of America invited President Trump to address their Jamboree. It was early enough in his presidency that it was still possible to pretend that he might give a speech appropriate to the occasion. Of course, he did not. Instead, in the course of a typically partisan and petty performance, he got a crowd of tens of thousands of teenagers to boo a former President and a former Secretary of State.

The moment stood out for me as a symbol of the moral rot of American civic institutions. Adults in positions of trust and responsibility invited him to speak and stood by as the entirely predictable consequences unfolded. The BSA later apologized, but in the moment no one told him his speech was unsuitable, or tried to stop him. Everyone there from the BSA leadership either saw nothing wrong or was too timid to do anything about it.

In other news:

More than 82,000 people have come forward with sex-abuse claims against the Boy Scouts of America, describing a decades-long accumulation of assaults at the hands of scout leaders across the nation who had been trusted as role models.

The claims, which lawyers said far eclipsed the number of abuse accusations filed in Catholic Church cases, continued to mount ahead of a Monday deadline established in bankruptcy court in Delaware, where the Boy Scouts had sought refuge this year in a bid to survive the demands for damages.

I have known some outstanding former Scouts. In word and deed they are metaphorical, as well as literal, boy scouts. But the BSA has for decades been profoundly wrong about what values are worth defending. It filed for bankruptcy in February, but the moral bankruptcy happened long ago.

[laboratorium2d]

I'm Always Angry

For most of 2016, I lived in a state of growing dread. After the election, I alternated between numbness, depression, and the grim necessity of moving forward. But by now, mostly I am angry.

I am angry about the children in cages torn from their parents.

I am angry that my daughter will not have seen the inside of a classroom for an entire year.

I am angry about the tear gas and the bayonets.

I am angry about losing four years we didn't have for dealing with climate change.

I am angry about the rampant foreign corruption and the petty domestic venality.

I am angry about the degradation of the Department of Justice into a partisan political tool.

I am angry about the Muslim travel ban, and even angrier that the courts went along with it.

I am angry about the decimation of the civil service.

I am grateful that no ill-advised tweet set off a nuclear war, but I am angry that this is even something I had to worry about.

I am angry about the racism, the sexism, the xenohobia, the casual cruelty.

I am angry about the replacement of civic ritual and civic duty with a personality cult.

I am angry about stolen Supreme Court seats, and a judiciary often unwilling to enforce the Constitution or the laws.

I am angry that the best defense against authoritarianism has been incompetence.

I am angry about Sheriff of Nottingham tax reform that steals from the poor to give to the rich.

I am angry that a man who should be condemning white supremacists and domestic terrorists gives them aid and comfort instead.

I am angry about the constant attempts to take away people's healthcare, to poison their air and water, to take away their civil rights, their reproductive rights, their right to vote.

I am angry about the constant lies, and about the people who know they are lies but play along anyway.

I am angry about the 227,000 Americans who have died so far from a preventable disease, and I am angrier every day.

I am angry that there is no limit to Donald Trump's stupidity, his depravity, or his evil---and no limit to what Republican voters, Republican politicians, and Republican media will put up with.

And I am angry about the transparent, blatant attempts to steal this election.

But the thing about anger is that you can channel it, and the things I am angry about are the kinds of thing I can do something about. Not alone, but together with my fellow Americans, because that is what it means to live in a democracy. Election Day is the culmination of years of work, by longtime friends and by people I have met along the way, all working together to fix the things we are angry about, to cut out the rotted flesh and begin to heal the wounds.

On November 3 (or before, for many of us), we vote. And on November 4 (or after, if needed), we stand ready to make sure the results of that vote are followed.

[laboratorium2d]

The Canons of Trump

For obvious reasons, I have been following the news, and the news as refracted through social media, very closely since mid-spring. Unavoidably, this has meant that I have been subjected to a much higher than usual dose of Trump nonsense, and nonsense Trump takes. He says and does stupid and terrible things on a near-constant basis, which are then surrounded and amplified by a fog of overinterpretation. There is much less there there than meets the eye.

Over the last four painful years, I have developed some rules of thumb for making sense of Trump news. Most of them are designed to keep me from overthinking things. I offer them up in the spirit of helping us make it to November, and to help in the process of driving Trump and Trumpism from public life.

Trump Speaks Only to His Base

"MAGA loves the black people" is not meant to persuade African-Americans that they should be Trump supporters. It is meant to persuade Trump supporters that they are not racist. The optics of driving off peaceful protesters with tear gas are not bad, in his view, because his supporters want peaceful protesters driven off with tear gas. Suspend all your normal reactions as a citizen or as a human being; they are not a useful guide to how he and his base think. Corollary: when Trump talks about suburbs under siege, remind yourself that this is what people who don't live in suburbs think people who do are afraid of.

Dominance Politics

Josh Marshall: "[T]he entirety of Trump’s political message is dominance politics. ... Trump attacks, others comply and submit." David Auerbach: "[F]or him, the only acceptable outcome is the one where he wins and you get screwed. ... Trump always defects because he wants to maximize how much worse you do than him--not because he wants to maximize his own payoff." Trump always pushes the button.

The Cruelty Is the Point

Trump's policies are unnecessarily cruel, not by accident but intentionally. Tearing migrant children from their parents is his signature policy, precisely because it is so terrible. Trump's natural meanness is a perfect fit for supporters who want their government to violate human rights. (Source: Adam Serwer)

The Stupidity Is Also the Point

Most Americans are not idiots. But most Americans devote very little attention to politics. Nuking hurricanes and injecting bleach are astonishingly terrible ideas. But they sound plausible enough to someone who is barely listening. Trump is an idiot savant of political communication because his limited intelligence matches many people's limited attention. His inability to formulate complex thoughts comes across as authenticity.

Trump's Razor

Josh Marshall: "[T]he stupidest possible scenario that can be reconciled with the available facts" is probably correct. Too many examples to list, but nothing tops, "If we stopped testing right now, we’d have very few cases, if any." Trump doesn't believe that tests make him look bad by finding cases; he believes that tests make him look bad by causing cases.

Ten Minute Increments

Maggie Haberman: "He will say whatever he has to say to get through ten minute increments of time." Trump does not think ahead. There is no long-term plan when he speaks. He likes rallies where he can riff and ramble for as long as he likes. He likes friendly interviews. In any other situation, when he is being pressed for any reason, he will say anything that comes to mind that seems like it will make the immediate problem go away. His notorious word salad is one coping mechanism; so is making big but impossibly vague promises.

Trump Is a They, Not an It

Kenneth Shepsle's "Congress is a 'They,' Not an 'It'" argues that it is a category mistake to attribute intentions to a multi-member body. Legislators voting for a bill may not share the same purpose, or even the same understanding of what it does. Reader, I am here to tell you that the same thing is true of the shambling mess of rage, impulses, and distractions that is Donald Trump. A Trump tweet might reflect his own deliberations, but just as often is something he saw on Fox, or someone said to him on the phone, or something that Dan Scavino wrote.

From God to Fox to Trump

There is a close correlation between whatever is on Fox News and what Trump says and tweets, often in real time. If something seems like a non sequitur, look for a source upstream.

Trump is Chaff

Leon Wolf: "Donald Trump is the political equivalent of chaff, a billion shiny objects all floating through the sky at once, ephemeral, practically without substance, serving almost exclusively to distract from more important things – yet nonetheless completely impossible to ignore."

Low-Pass Filter

A low-pass filter blocks signals that change quickly, only significant long-term changes get through. This is the opposite of how the press and social media work. Social media amplify things that are already being shared widely right now, and journalists compete online by trying to be first. But most Trump tweets, quotes, and leaks are noise. It's okay to ignore the latest bit of chaff; anything important enough to pay serious attention to will be repeated, many many times.

Trump Doesn't Want to Be President, He Wants to Be King

Trump's vision of leadership isn't so much authoritarian as medieval. He wants people to bow down and praise his royal splendor, his brilliance, his feats of prowess. He doesn't have a cabinet or political allies; he has courtiers and nobles. He doesn't understand or care how bureaucracy works, even when he would be far more effective working through it. His daily routines are straight out of Hilary Mantel's portrait of Henry VIII.

Toddler in Chief

Daniel Drezner: "I'll believe that Trump is growing into the presidency when his staff stops talking about him like a toddler." Drezner (now in book form) gets at two points. First, Trump behaves like an ill-behaved small child: bad temper, poor impulse control, short attention span, demands for praise, constant need to be the center of attention. Second, his staff see their job as nannies.

The White House is a They, not an It

Jay Rosen: "There is no White House. Not in the sense that journalists have always used that term. It's just Trump— and people who work in the building. That they are reading from the same page cannot be assumed. The words, 'the White House' are still in use, but they have no clear referent." Other administrations worked hard to send a unified message. Not this one. Trump doesn't even tell his own staff clearly what his policies are, and he frequently changes his mind, so the presumption that a statement from a White House official--even from Trump himself--reflects official policy does not hold.

Working Toward Trump

Historian Ian Kershaw observed that (especially in contrast to the workaholic Stalin) Hitler was just about the last person you would expect to be able to lead a bureaucracy capable of waging a world war and carrying out the mass murder of six million. He was lazy, easily bored, and cultivated administrative chaos. Instead of waiting for clear and specific orders, his supporters "worked toward the Fuhrer": they tried to anticipate policies he would approve of. (More detail here.)

Dignity Wraiths

Josh Marshall: "Rosenstein’s public reputation, which was formidable, has been destroyed. He now joins a legion of Trump Dignity Wraiths, men and women (though mainly men) of once vaunted reputations or at least public prestige who have been reduced to mere husks of their former selves after crossing the Trump Dignity Loss Event Horizon." Corollary by Josh Barro: "[Trump] has stripped only the dignity from people who surrendered it willingly."

To the Cornfield

The Twilight Zone: "They have to think happy thoughts and say happy things because, once displeased, the monster can wish them into a cornfield or change them into a grotesque, walking horror." Trump takes every revenge he can on those who criticize or undercut him. His underlings live in fear of his displeasure, praise him elaborately in public, and generally abase themselves to avoid being sent to the political cornfield. As a result ...

The Republican Party is a Personality Cult

The phrase is Ezra Klein's, but William Saletan said it first: "Donald Trump is the GOP’s warlord. The Republican Party is officially a failed state." On the one hand, Trump is the GOP: Never Trumpers and Trump critics have been effectively sidelined and deligitimized as not real Republicans. On the other hand, the GOP is Trump: the official 2020 platform of the Republican Party is, in its entirety, "the President’s America-first agenda."

[laboratorium2d]

The Copyright Law of Embedding Just Got a Lot More Interesting

Tim Lee has a remarkable story at Ars Technica about a remarkable copyright case, McGucken v. Newsweek. Its headline, "Instagram just threw users of its embedding API under the bus," is not an exaggeration. (Disclosure: I am quoted in the story, and I learned about the case from being interviewed for it.) The facts are simple:

Photographer Elliot McGucken took a rare photo (perhaps this one) of an ephemeral lake in Death Valley. Ordinarily, Death Valley is bone dry, but occasionally a heavy rain will create a sizable body of water. Newsweek asked to license the image, but McGucken turned down their offer. So instead Newsweek embedded a post from McGucken's Instagram feed containing the image.

This is the third case I am aware of in the Southern District of New York in the last two years on nearly identical facts. One of them, Sinclar v. Ziff Davis, held that the Mashable was not liable for an Instagram embed. The court reasoned that by uploading her photograph to Instagram, photographer Stephanie Sinclair agreed to Instagram's terms of service, including a copyright license to Instagram to display the photograph -- and also thereby allowed Instagram to sublicense the photograph to its users who used the embedding API. Thus, Mashable had a valid license from Sinclair by way of Instagram, so no infringement.

McGucken agrees with most of this reasoning, but stops just short of the crucial step.

The Court finds Judge Wood’s decision [in Sinclair] to be well-reasoned and sees little cause to disagree with that court’s reading of Instagram’s Terms of Use and other policies. Indeed, insofar as Plaintiff contends that Instagram lacks the right to sublicense his publicly posted photographs to other users, the Court flatly rejects that argument. The Terms of Use unequivocally grant Instagram a license to sublicense Plaintiff’s publicly posted content, and the Privacy Policy clearly states that “other Users may search for, see, use, or share any of your User Content that you make publicly available through” Instagram.

Nevertheless, the Court cannot dismiss Plaintiff’s claims based on this licensing theory at this stage in the litigation. As Plaintiff notes in his supplemental opposition brief, there is no evidence before the Court of a sublicense between Instagram and Defendant. Although Instagram’s various terms and policies clearly foresee the possibility of entities such as Defendant using web embeds to share other users’ content, none of them expressly grants a sublicense to those who embed publicly posted content. Nor can the Court find, on the pleadings, evidence of a possible implied sublicense. (citations omitted)

Lee did something smart with this dueling pair of cases: he got Facebook (Instagram's owner) to go on record with its interpretation of its own terms of use.

"While our terms allow us to grant a sub-license, we do not grant one for our embeds API," a Facebook company spokesperson told Ars in a Thursday email. "Our platform policies require third parties to have the necessary rights from applicable rights holders. This includes ensuring they have a license to share this content, if a license is required by law."

In plain English, before you embed someone's Instagram post on your website, you may need to ask the poster for a separate license to the images in the post. If you don't, you could be subject to a copyright lawsuit.

This statement, I think it is fair to say, comes as a surprise to Mashable, to Judge Wood, and to all of the Instagram users who embed photos using its API. Major online services offer widely-used embedding APIs, and media outlets make extensive use of them. I would not say that it is universal, but it is certainly a widespread practice for which, it is widely assumed, no further license is needed. If that is not true, it is a very big deal, and a great many Internet users are now suddenly exposed to serious and unexpected copyright liability.

McGucken is not the end of the story. I would have said -- and in fact I initially told Lee -- that it is possible the court would reach a different conclusion at a later stage of the case, once it had more facts about Instagram's terms of use. That ... no longer seems likely. But it is still quite possible Newsweek could win and be allowed to use the embedded photograph. It raised a fair use defense, and might well prevail on that at a later stage. It might also be able to rely on the server rule.

The server rule, which can be traced to Perfect 10 v. Amazon.com from the Ninth Circuit in 2007, holds that only the person whose server transmits a copy of an image "displays" that image within the meaning of the Copyright Act. In an embedding case like Sinclair or McGucken, that would be Instagram, not Mashable or Newsweek -- that is how embedding works. There is no dispute that Instagram is licensed to publicly display copies of these photographs; the photographers agreed as much when they uploaded them. So on the server test, no sublicense is needed; embeds are noninfringing.

The server test, although widely relied on by Internet users and Internet services, has also been criticized. The third SDNY embedding API case, Goldman v. Breitbart, held that the defendant websites could be liable for Twitter embeds of Goldman's photograph. In a detailed opinion, the Goldman court considered and rejected the server test. (Side note: There was an important potential factual distinction in Goldman. There, unlike in Sinclair and in McGucken, the photograph had been uploaded to Twitter by unauthorized third parties, who could give no license to Twitter and thus none to the defendants. But this distinction played no part in Goldman's legal analysis. While these facts could be relevant to the existence of a license, they don't affect whether the image was displayed or by whom.)

To summarize, there are two possible routes to finding that API embeds of a photographer's own uploads are allowed: either the service itself displays the image under the server rule, or the embedder displays it but has a valid sublicense. Goldman rejected the server rule, but did not consider the existence of a sublicense. Sinclair did not consider the server rule but held there was a sublicense. McGucken did not consider the server rule -- inexplicably, Newsweek did not ask the court to hold that there was no direct infringement under the server rule -- and held that there was no sublicense. No court has considered and ruled on both arguments together, despite the fact that they are joined at the hip.

A particularly careful and thorough critique of the server is Embedding Content or Interring Copyright: Does the Internet Need the "Server Rule"?, by Jane Ginsburg and luke Ali Budiardjo. They argue that the server rule misreads the Copyright Act and should, with Goldman, be rejected. They believe, however, that the sky will not fall, because licenses will fill any gaps that should be filled. They note that YouTube's terms of service, for example, explicitly provide for a license grant from uploaders to YouTube's users, and they predict that this practice will be common:

Therefore, it seems likely that platforms can (and will) utilize Terms of Service agreements that are sufficiently broad to protect themselves and their users from infringement claims based on user “sharing” of platform content through platform mechanisms.

I would have thought so, too. Hence my surprise at Instagram's position. There are two possibilities here. One is that Instagram does not explicitly grant a license because it believes the server test is the law. That position has been risky ever since Goldman. The other is that Instagram is willing to expose its users to copyright liability when they use its system as intended. I think it is not unreasonable to describe this, as Ars does, as throwing its users under the bus.

One last twist. In late April, Sinclair filed a motion for reconsideration of the holding that Mashable had a sublicense from Instagram, including some challenges to the court's interpretation of Instagram's terms of use. The main brief in support of reconsideration could be clearer, but her reply brief puts the issue squarely: "Nowhere has Mashable put in the record any proof as to how Instagram 'validly exercised' its right in granting Mashable a sublicense of Plaintiff’s photo." There things sat, until on June 2, Sinclair called the court's attention to the McGucken order, and then today, June 4, called its attention to the Ars story published just hours before. I speculated to Lee that McGucken "is going to blow up the Sinclair case." I shouldn't have used the future tense. It already has.

[laboratorium2d]

Working Toward the Führer

I was inspired by a tweet by @nycsouthpaw to read Ian Kershaw's well-known essay "Working Toward the Führer": Reflections on the Nature of the Hitler Dictatorship. I was not disappointed; Kershaw gives a compelling analysis of the internal workings of a particular kind of authoritarian regime. In the interests of space, I will not quote the whole thing, so you will need to read the original for Kershaw's observations on Stalin, Max Weber, succession planning, and other peripheral topics. But a number of passages about Hitler and how he ruled struck me as quite illuminating.

Kershaw opens by observing how detached Hitler was from the work of running a government:

Hitler's way of operating was scarcely conducive to ordered government. Increasingly, after the first year or two of the dictatorship, he reverted to a lifestyle recognisable not only in the party leader of the 1920s but even in the description of the habits of the indolent youth in Linz and Vienna recorded by his friend Kubizek. According to the post-war testimony of one of his former adjutants:

Hitler normally appeared shortly before lunch, quickly read through Reich Press Chief Dietrich's press cuttings, and then went into lunch. ... When Hitler stayed at Obersalzberg it was even worse. There, he never left his room before 2.00 p.m. Then, he went to lunch. He spent most afternoons taking a walk, in the evening straight after dinner, there were films. ... He disliked the study of documents. I have sometimes secured decisions from him, even ones about important matters, without his ever asking to see the relevant files.

He preferred to act by personal fiat, relying on individuals rather than on institutions:

Hitler seems to have had no deliberate policy of destabilisation, but rather, as a consequence of his non-bureaucratic leadership position and the inbuilt need to protect his deified leadership position by non-association with political infighting and potentially unpopular policies, to have presided over an inexorable erosion of 'rational' forms of government. And while the metaphor of 'feudal anarchy' might be applied to both systems, it seems more apt as a depiction of the Hitler regime, where bonds of personal loyalty were from the beginning the crucial determinants of power, wholly overriding functional position and status.

The almost inevitable result of this management style was that his administration existed in a perpetual and increasing state of chaos:

I have just used the word 'system' of Nazism. But where Soviet communism in the Stalin era, despite the dictator's brutal detabilisation, remained recognisable as a system of rule, the Hitler regime was inimical to a rational order of government and administration. Its hallmark was systemlessness, administrative and governmental disorder, the erosion of clear patterns of government, however despotic.

This was already plain within Germany in the pre-war years as institutions and structures of government and administration atrophied, were eroded or merely bypassed, and faded into oblivion. It was not simply a matter of the unresolved Party-State dualism. The proliferation of 'special authorities' and plenipotentiaries for specific tasks, delegated by the Führer and responsible directly to him, reflected the predatory character and improvised techniques immanent in Nazi domination. Lack of coherent planning related to attainable middle-range goals; absence of any forum for collective decision-making; the arbitrary exercise of power embedded in the 'leadership principle' at all levels; the Darwinian principle of unchecked struggle and competition until the winner emerged; and the simplistic belief in the 'triumph of the will', whatever the complexities to be overcome: all these reinforced each other and interacted to guarantee a jungle of competing and overlapping agencies of rule.

He was able to be a such a weak head of government because his base of support wasn't dependent on the quality of his administration:

Since the mid-1920s, ideological orthodoxy was synonymous with adherence to Hitler. 'For us the Idea is the Führer, and each Party member has only to obey the Führer,' Hitler allegedly told Otto Strasser in 1930. The build-up of a 'Führer party' squeezed heterodox positions onto the sidelines, then out of the party. By the time the regime was established and consolidated, there was no tenable position within Nazism compatible with a fundamental challenge to Hitler. His leadership position, as the font of ideological orthodoxy, the very epitome of Nazism itself, was beyond question within the movement. Opposition to Hitler on fundamentals ruled itself out, even among the highest and mightiest in the party. Invoking the Führer's name was the pathway to success and advancement. Countering the ideological prerogatives bound up with Hitler's position was incompatible with clambering up the greasy pole to status and power.

And yet, despite Hitler's incompetence at pulling the levers of formal governmental power, he was quite successful at getting the state to do the insane things he wanted. Kershaw points to three mechanisms: Hitler was a unifier, an activator, and an enabler. First, he was a symbolic and ideological figurehead for his supporters:

As unifier, the 'idea' incorporated in the quasi-deified Führer figure was sufficiently indistinct but dynamic to act as a bond not only for otherwise warring factions of the Nazi Movement but also, until it was too late to extricate themselves from the fateful development, for non-Nazi national-conservative elites in army, economy and state bureaucracy. It also offered the main prop of popular support for the regime (repeatedly giving Hitler a plebiscitary basis for his actions) and a common denominator around which an underlying consensus in Nazi policy could be focused.

Second, he energized them to act out on their own:

As activator, the 'vision' embodied by Hitler served as a stimulant to action in the different agencies of the Nazi Movement itself, where pent-up energies and unfulfilled social expectations could be met by activism carried out in Hitler's name to bring about the aims of Leader and Party. But beyond the movement, it also spurred initiatives within the state bureaucracy, industry and the armed forces, and among the professionals such as teachers, doctors or lawyers where the motif of 'national redemption' could offer an open door to the push for realisation of long-cherished ambitions felt to have been held back or damaged by the Weimar 'system'. In all these ways, the Utopian 'vision' bound up with the Führer -- undefined and largely undefinable -- provided 'guidelines for action' which were given concrete meaning and specific content by the voluntary 'push' of a wide variety of often competing agencies of the regime.

Third, he used his power to ratify their actions:

Perhaps most important of all, as enabler Hitler's authority gave implicit backing and sanction to those whose actions, however inhumane, however radical, fell within the general and vague ideological remit of furthering the aims of the Führer. Building a 'national community', preparing for the showdown with Bolshevism, purifying the Reich of its political and biological or racial enemies, and removing Jews from Germany, offered free licence to initiatives which, unless inopportune or counter-productive, were more or less guaranteed sanction from above. The collapse in civilised standards which began in the spring of 1933, and the spiralling radicalisation of discrimination and persecution that followed, were not only unobstructed but invariably found legitimation in the highest authority in the land.

The title of the essay comes from a remarkable quote from "the sentiments of a routine speech from a Nazi functionary in 1934":

Everyone who has the opportunity to observe it knows that the Führer can hardly dictate from above everything which he intends to realise sooner or later. On the now contrary, up till now everyone with a post in the new Germany has worked best when he has, so to speak, worked towards the Führer. Very often and in many spheres it has been the case -- in previous years as well -- that individuals have simply waited for orders and instructions. Unfortunately, the same will be true in the future; but in fact it is the duty of everybody to try to work towards the Führer along the lines he would wish. Anyone who makes mistakes will notice it soon enough. But anyone who really works towards the Führer along his lines and towards his goal will certainly both now and in the future one day have the finest reward in the form of the sudden legal confirmation of his work.

I found this to be one of the most illuminating things I have ever read on the dynamics of the Trump administration.

[laboratorium2d]

Children's Animated Series, As Graded by a Parent Who Has Watched Far Too Many of Them

My Little Pony: Friendship is Magic: The brony thing is legitimately weird, but this is legitimately a great show. The combination of epic-fantasy plots with a deep dive on friendship is a winner (and has also been deeply influential on kids' television). It also makes the obligatory pro-social messages feel earned, rather than an afterthought. The characters are charming, the writing sparkles, and the animation is still distinctive. Endlessly watchable, which is a good thing when your kid wants to watch endlessly. Fake holidays: Nightmare Night, Hearth's Warming Eve, Hearts and Hooves Day. Grade: A+

Avatar: I was fifteen years too old for this when it was on TV, so I didn't understand what the fuss was about. Now I do. It's epic but not grandiose, funny but not dumb, and morally deep without giving into plot gravity. The world-building, the writing, the animation, the voice-acting, the fight scenes, the side characters: everything works, and everything is pulling in the same direction. (The sequel series, The Legend of Korra, is more of the same, with an interestingly updated setting and better music.) If your kids are like mine, they'll want to talk about everything, and so will you. I guess binge-watching is a family thing now. Grade: A+

She-Ra and the Princesses of Power: This show is so gay. However gay you expect it to be, it's ten times gayer. It's also pro-diversity along every axis you can imagine, including body-type. It's completely awesome. It captures the uncannily compelling techno-fantasy atmosphere of the original, and it has characters with the same names, but otherwise it's a total gut rehab. The character studies at its core are compelling, even as the overall plot and action hold a young child's interest. It takes lots of anime animation tropes and tones them down to the verge of naturalism, which I wouldn't have thought would work, but totally does. Grade: A-

Wild Kratts: The big kid was learning biology from this show almost from before she could talk. "Giraffe. Long neck. Eat leaves." The premise of the show is genius: animated versions of veteran kids' wildlife-show hosts Chris and Martin Kratt have suits that give them "creature powers," and they travel around the world having adventures with animals. The science is legit and it's presented entertainingly. And the characters are winners, especially the creature-suit inventor Aviva Corcovado and the colorful villains. The only thing consistently annoying about this show is that it can be shouty. Everyone is Just! So! Excited! About! Animals! Grade: A-.

Phineas and Ferb: The Arrested Development of kids' animation, Phineas and Ferb is impossibly dense with overlapping plots, brick jokes, and a large army of recurring minor characters. Every episode features an original song, some of which are genuinely brilliant ("Squirrels in My Pants" is a household favorite). It is also a wholly, completely sweet-hearted show. Even the antagonists -- Candace and Dr. Doofenshmirtz -- are sympathetic, charming, fully-realized, and allowed to grow and be happy in ways that a lesser version of this show would never even have realized was a possibility. The allegretto pacing and intricate writing keep the show consistently fresh. New Disney at its best. Grade: A-

Ben and Holly's Little Kingdom: From the same team who brought you Peppa Pig, but even drier underneath its treacly trappings. The comedic timing is straight out of classic British sketch comedy. The voice actors are clearly in on the joke, which if anything makes the show more fun to listen to than to watch. B+

Dinosaur Train: Sometimes high concepts work. The show 100% owns its message: dinosaur physiology is a diversity metaphor, presented with just the right degree of insistence. The characters are sketched with grace and sympathy, and the science is pitched just right for its target audience. Over the years, the show (like all railfans) has gotten increasingly obsessed with its train equipment: the aquacar, the submarine, the ... zeppelin. The songs are surprisingly catchy, too: our favorite is probably the Dinosaur Train Zeppelin song, which, yes, is a Led Zeppelin pastiche. Grade: B+

Odd Squad: This one really grew on me. If all you've seen is short clips, it just seems like everyone is shouting about math all the time. But the show overall is delightfully goofy, with a real sense of how to string along a running gag, and some genuinely talented child actors. Grade: B+

Creative Galaxy: Despite being a total Daniel Tiger rip-off, down to the animation style, the obligatory song in every episode, and the live-action codas, this one is actually kind of nice. The art projects are well-chosen both to interest kids and also to actually be doable. Fake holidays: Heart Day. Grade: B

Peppa Pig: It took me a long time to appreciate this show's arch sense of humor. Everyone's pretensions and ambitions are punctured; embarrassing mistakes and small indignities await adults at every turn. Once you realize that the show is making fun of most of its characters but loves them anyway, it's much more bearable. Grade: B

Curious George: Entirely forgettable, with two mildly redeeming qualities. George himself is as charming as always, and the jazzy musical score is pleasant. Grade: B-

Miraculous: Tales of Ladybug and Cat Noir: It took me a while to understand what this show was doing. It's very, very French. Grade: C+

Daniel Tiger's Neighborhood: Even my kids recognize that Daniel Tiger is needy and whiny. The show inadvertently teaches kids what to be afraid of and how to misbehave. There is also something deeply wrong with the economy of the Neighborhood: everyone seems to have multiple jobs and the public transit system runs on magic. On the plus side, the potty song has come in handy as a reminder: when you have to go potty, stop and go right away. Fake holidays: Love Day, Snowflake Day, Dress Up Day. Grade: C+

Ready Jet Go: I suppose there's some science in here somewhere, I guess. Grade: C+

Tumble Leaf: Reviewers might call this one "gentle," by which they mean "boring." The animation is lovely and the music is calming. But what's the point? Grade: C+

PAW Patrol: Unbelievably, incredibly formulaic. For example: have you noticed that they get in their trucks at exactly the same point halfway through each episode? Just Canadian enough to be noticeably off, but also rah-rah in a George W. Bush-administration kind of way. Sometimes I imagine grown-up versions of the pups. Chase regularly engages in police brutality, Rubble has a drinking problem, and Marshall has joined the alt-right. Grade: C

Nature Cat: Nature Cat is annoying and his friends are worse. I'm not clear on what they're supposed to be learning. And the theme song manages to be both unmemorable and an earworm. Make it stop! Grade: C

Super Why: More like Super Why Does This Exist, amirite? The whole show is oddly paced: I find the story-within-a-story structure confusing and can only wonder how much of it kids actually get. Having each character deal with a different aspect of literacy leaves the show's educational content unfocused. And the Super Letters are like the world's lamest game of Wheel of Fortune. Plus the song is an earworm, and not in a good way. Grade: C

Sofia the First: Empty Disney calories, this show is the reductio ad absurdum of Disney's democratization of the idea of "princess." The plotting, the writing, and the music are technically proficient. The cel-shading effects that give 3D animation the luminosity of 2D hand drawn are lovely. The messages are perfectly innocuous. But the heart of the show is a giant gaping void. Fake holidays: Wassailia. Grade: C

Lion Guard: More empty Disney calories, like Sofia the First but with more obnoxious characters. Inexplicably real holiday: Christmas. Grade: C-

Peg + Cat: All I can remember is that the show is inexplicably drawn on graph paper, and they have a BIG BIG PROBLEM every few seconds. When people complain about STEM, and I remember that this show exists, I have to admit that they have a point. Grade: C-

Martha Speaks: The AV Club's term for this kind of show is "least essential." Even by the standards of kids' shows, the premise makes no sense. Nobody here, human or canine, is remotely sympathetic. And the plot comes to a screeching halt every time it's time for a new vocabulary word. Grade: C-

WordWorld: I have so many questions about this show. If everything is made out of words, what about the ground? The sky? Windows? And what are the letters in the words made of? What is going on with the accents? And who greenlit three seasons of this garbage? Grade: D+

The Adventures of Puss in Boots: This is a weird, weird show. And not in a good way. Grade: D+

Trolls: The Beat Goes On: Quite possibly the most misanthropic kids show currently streaming anywhere. The combination of grimdark setting and hackneyed uplifting plot tropes is somewhere between unsettling and child abuse. Poppy is a walking illustration of emotional labor; Branch has severe PTSD. The show treats both of these as laughable quirks. And I am never going to get used to the Auto-Tune. Grade: D+

Kung-Fu Panda: The Paws of Destiny: Pretty much your standard DreamWorks animation. This is not a good thing. Grade: D

If You Give a Mouse a Cookie: The animation and voice-acting are innocuous. But building an entire show around the "if X, then Y" formula led to some disastrous choices. The show taught my big kid how to say things like, "If I see a rock, I just have to bring it home with me." It takes a special kind of kids show to affirmatively instill bad habits. Grade: D-

The Adventures of Rocky and Bullwinkle (2018): An absolute travesty in every possible way. The remake is the direct opposite of everything the original represented: crude instead of clever, manic instead of playful, and mean instead of goofy. Grade: F-

[laboratorium2d]

CPU, Esq.

I am writing a book. It is the book I have been working towards, not always consciously, for a decade. It is the book I was born to write.

The tentative title is CPU, Esq.: How Lawyers and Coders Do Things with Words. It tackles a very familiar question in technology law: what is the relationship between law and software?. But it comes at the problem from what I think is a new and promising direction: the philosophy of language. As I put it in the abstract:

Should law be more like software? Some scholars say yes, others say no. But what if the two are more alike than we realize?

Lawyers write statutes and contracts. Programmers write software. Both of them use words to do things in the world. The difference is that lawyers use natural language with all its nuances and ambiguities, while programmers use programming languages, which promise the rigor of mathematics. Could legal interpretation be more objective and precise if it were more like software interpretation, or would it give up something essential in the attempt?

CPU, Esq. explodes the idea that law can escape its problems by turning into software. It uses ideas from the philosophy of language to show that software and law are already more alike than they seem, because software also rests on social foundations. Behind the apparent exactitude of 1s and 0s, programmers and users are constantly renegotiating the meanings of programs, just as lawyers and judges are constantly renegotiating the meanings of legal texts. Law can learn from software, and software can learn from law. But law cannot become what it thinks software is -- because not even software actually works that way.

The book stands on three legs: law, software, and philosophy. Each pair of this triad has been explored: the philosophy of law, the law of software, and the philosophy of software. But never, to my knowledge, have they been considered all at once. More specifically, I plan to:

Use concepts from the philosophy of law -- particularly the theory of speech acts and legal interpretation -- to give a rigorous account of how software works

Use that account to illuminate questions in legal doctrine: e.g., how should judges interpret smart contracts?

Use that account to illuminate questions in legal theory: e.g., is the ideal judge a computer?

CPU, Esq. is under contract with Oxford University Press, and I will be on sabbatical in 2020-21 writing it. If you are interested, the book has its own site and I also have a mailing list where I will post updates, research queries, and requests for feedback. If this sounds interesting to you, please sign up!