Archive for the ‘Obviously I’m Not Defending Aaronson’ Category

My Passover press release

Monday, April 22nd, 2024

FOR IMMEDIATE RELEASE – From the university campuses of Assyria to the thoroughfares of Ur to the palaces of the Hittite Empire, students across the Fertile Crescent have formed human chains, camel caravans, and even makeshift tent cities to protest the oppression of innocent Egyptians by the rogue proto-nation of “Israel” and its vengeful, warlike deity Yahweh. According to leading human rights organizations, the Hebrews, under the leadership of a bearded extremist known as Moses or “Genocide Moe,” have unleashed frogs, wild beasts, hail, locusts, cattle disease, and other prohibited collective punishments on Egypt’s civilian population, regardless of the humanitarian cost.

Human-rights expert Asenath Albanese says that “under international law, it is the Hebrews’ sole responsibility to supply food, water, and energy to the Egyptian populace, just as it was their responsibility to build mud-brick store-cities for Pharoah. Turning the entire Nile into blood, and plunging Egypt into neverending darkness, are manifestly inconsistent with the Israelites’ humanitarian obligations.”

Israelite propaganda materials have held these supernatural assaults to be justified by Pharoah’s alleged enslavement of the Hebrews, as well as unverified reports of his casting all newborn Hebrew boys into the Nile. Chanting “Let My People Go,” some Hebrew counterprotesters claim that Pharoah could end the plagues at any time by simply releasing those held in bondage.

Yet Ptahmose O’Connor, Chair of Middle East Studies at the University of Avaris, retorts that this simplistic formulation ignores the broader context. “Ever since Joseph became Pharoah’s economic adviser, the Israelites have enjoyed a position of unearned power and privilege in Egypt. Through underhanded dealings, they even recruited the world’s sole superpower—namely Adonai, Creator of the Universe—as their ally, removing any possibility that Adonai could serve as a neutral mediator in the conflict. As such, Egypt’s oppressed have a right to resist their oppression by any means necessary. This includes commonsense measures like setting taskmasters over the Hebrews to afflict them with heavy burdens, and dealing shrewdly with them lest they multiply.”

Professor O’Connor, however, dismissed the claims of drowned Hebrew babies as unverified rumors. “Infanticide accusations,” he explained, “have an ugly history of racism, Orientalism, and Egyptophobia. Therefore, unless you’re a racist or an Orientalist, the only possible conclusion is that no Hebrew babies have been drowned in the Nile, except possibly by accident, or of course by Hebrews themselves looking for a pretext to start this conflict.”

Meanwhile, at elite academic institutions across the region, the calls for justice have been deafening. “From the Nile to the Sea of Reeds, free Egypt from Jacob’s seeds!” students chanted. Some protesters even taunted passing Hebrew slaves with “go back to Canaan!”, though others were quick to disavow that message. According to Professor O’Connor, it’s important to clarify that the Hebrews don’t belong in Canaan either, and that finding a place where they do belong is not the protesters’ job.

In the face of such stridency, a few professors and temple priests have called the protests anti-Semitic. The protesters, however, dismiss that charge, pointing as proof to the many Hebrews and other Semitic peoples in their own ranks. For example, Sa-Hathor Goldstein, who currently serves as Pithom College’s Chapter President of Jews for Pharoah, told us that “we stand in solidarity with our Egyptian brethren, with the shepherds, goat-workers, and queer and mummified voices around the world. And every time Genocide Moe strikes down his staff to summon another of Yahweh’s barbaric plagues, we’ll be right there to tell him: Not In Our Name!”

“Look,” Goldstein added softly, “my own grandparents were murdered by Egyptian taskmasters. But the lesson I draw from my family’s tragic history is to speak up for oppressed people everywhere—even the ones who are standing over me with whips.”

“If Yahweh is so all-powerful,” Goldstein went on to ask, “why could He not devise a way to free the Israelites without a single Egyptian needing to suffer? Why did He allow us to become slaves in the first place? And why, after each plague, does He harden Pharoah’s heart against our release? Not only does that tactic needlessly prolong the suffering of Israelites and Egyptians alike, it also infringes on Pharoah’s bodily autonomy.”

But the strongest argument, Goldstein concluded, arching his eyebrow, is that “ever since I started speaking out on this issue, it’s been so easy to get with all the Midianite chicks at my school. That’s because they, like me, see past the endless intellectual arguments over ‘who started’ or ‘how’ or ‘why’ to the emotional truth that the suffering just has to stop, man.”

Last night, college towns across the Tigris, Euphrates, and Nile were aglow with candelight vigils for Baka Ahhotep, an Egyptian taskmaster and beloved father of three cruelly slain by “Genocide Moe,” in an altercation over alleged mistreatment of a Hebrew slave whose details remain disputed.

According to Caitlyn Mentuhotep, a sophomore majoring in hieroglyphic theory at the University of Pi-Ramesses who attended her school’s vigil for Ahhotep, staying true to her convictions hasn’t been easy in the face of Yahweh’s unending plagues—particularly the head lice. “But what keeps me going,” she said, “is the absolute certainty that, when people centuries from now write the story of our time, they’ll say that those of us who stood with Pharoah were on the right side of history.”

Have a wonderful holiday!

Open Letter to Anti-Zionists on Twitter

Monday, March 25th, 2024

Dear Twitter Anti-Zionists,

For five months, ever since Oct. 7, I’ve read you obsessively. While my current job is supposed to involve protecting humanity from the dangers of AI (with a side of quantum computing theory), I’m ashamed to say that half the days I don’t do any science; instead I just scroll and scroll, reading anti-Israel content and then pro-Israel content and then more anti-Israel content. I thought refusing to post on Twitter would save me from wasting my life there as so many others have, but apparently it doesn’t, not anymore. (No, I won’t call it “X.”)

At the high end of the spectrum, I religiously check the tweets of Paul Graham, a personal hero and inspiration to me ever since he wrote Why Nerds Are Unpopular twenty years ago, and a man with whom I seem to resonate deeply on every important topic except for two: Zionism and functional programming. At the low end, I’ve read hundreds of the seemingly infinite army of Tweeters who post images of hook-nosed rats with black hats and sidecurls and dollar signs in their eyes, sneering as they strangle the earth and stab Palestinian babies. I study their detailed theories about why the October 7 pogrom never happened, and also it was secretly masterminded by Israel just to create an excuse to mass-murder Palestinians, and also it was justified and thrilling (exactly the same melange long ago embraced for the Holocaust).

I’m aware, of course, that the bottom-feeders make life too easy for me, and that a single Paul Graham who endorses the anti-Zionist cause ought to bother me more than a billion sharers of hook-nosed rat memes. And he does. That’s why, in this letter, I’ll try to stay at the higher levels of Graham’s Disagreement Hierarchy.

More to the point, though, why have I spent so much time on such a depressing, unproductive reading project?

Damned if I know. But it’s less surprising when you recall that, outside theoretical computer science, I’m (alas) mostly known to the world for having once confessed, in a discussion deep in the comment section of this blog, that I spent much of my youth obsessively studying radical feminist literature. I explained that I did that because my wish, for a decade, was to confront progressivism’s highest moral authorities on sex and relationships, and make them tell me either that

(1) I, personally, deserved to die celibate and unloved, as a gross white male semi-autistic STEM nerd and stunted emotional and aesthetic cripple, or else
(2) no, I was a decent human being who didn’t deserve that.

One way or the other, I sought a truthful answer, one that emerged organically from the reigning morality of our time and that wasn’t just an unprincipled exception to it. And I felt ready to pursue progressive journalists and activists and bloggers and humanities professors to the ends of the earth before I’d let them leave this one question hanging menacingly over everything they’d ever written, with (I thought) my only shot at happiness in life hinging on their answer to it.

You might call this my central character flaw: this need for clarity from others about the moral foundations of my own existence. I’m self-aware enough to know that it is a severe flaw, but alas, that doesn’t mean that I ever figured out how to fix it.

It’s been exactly the same way with the anti-Zionists since October 7. Every day I read them, searching for one thing and one thing only: their own answer to the “Jewish Question.” How would they ensure that the significant fraction of the world that yearns to murder all Jews doesn’t get its wish in the 21st century, as to a staggering extent it did in the 20th? I confess to caring about that question, partly (of course) because of the accident of having been born a Jew, and having an Israeli wife and family in Israel and so forth, but also because, even if I’d happened to be a Gentile, the continued survival of the world’s Jews would still seem remarkably bound up with science, Enlightenment, minority rights, liberal democracy, meritocracy, and everything else I’ve ever cared about.

I understand the charges against me. Namely: that if I don’t call for Israel to lay down its arms right now in its war against Hamas (and ideally: to dissolve itself entirely), then I’m a genocidal monster on the wrong side of history. That I value Jewish lives more than Palestinian lives. That I’m a hasbara apologist for the IDF’s mass-murder and apartheid and stealing of land. That if images of children in Gaza with their limbs blown off, or dead in their parents arms, or clawing for bread, don’t cause to admit that Israel is evil, then I’m just as evil as the Israelis are.

Unsurprisingly I contest the charges. As a father of two, I can no longer see any images of child suffering without thinking about my own kids. For all my supposed psychological abnormality, the part of me that’s horrified by such images seems to be in working order. If you want to change my mind, rather than showing me more such images, you’ll need to target the cognitive part of me: the part that asks why so many children are suffering, and what causal levers we’d need to push to reach a place where neither side’s children ever have to suffer like this ever again.

At risk of stating the obvious: my first-order model is that Hamas, with the diabolical brilliance of a Marvel villain, successfully contrived a situation where Israel could prevent the further massacring of its own population only by fighting a gruesome urban war, of a kind that always, anywhere in the world, kills tens of thousands of civilians. Hamas, of course, was helped in this plan by an ideology that considers martyrdom the highest possible calling for the innocents who it rules ruthlessly and hides underneath. But Hamas also understood that the images of civilian carnage would (rightly!) shock the consciences of Israel’s Western allies and many Israelis themselves, thereby forcing a ceasefire before the war was over, thereby giving Hamas the opportunity to regroup and, with God’s and of course Iran’s help, finally finish the job of killing all Jews another day.

And this is key: once you remember why Hamas launched this war and what its long-term goals are, every detail of Twitter’s case against Israel has to be reexamined in a new light. Take starvation, for example. Clearly the only explanation for why Israelis would let Gazan children starve is the malice in their hearts? Well, until you think through the logistical challenges of feeding 2.3 million starving people whose sole governing authority is interested only in painting the streets red with Jewish blood. Should we let that authority commandeer the flour and water for its fighters, while innocents continue to starve? No? Then how about UNRWA? Alas, we learned that UNRWA, packed with employees who cheered the Oct. 7 massacre in their Telegram channels and in some cases took part in the murders themselves, capitulates to Hamas so quickly that it effectively is Hamas. So then Israel should distribute the food itself! But as we’ve dramatically witnessed, Israel can’t distribute food without imposing order, which would seem to mean reoccupying Gaza and earning the world’s condemnation for it. Do you start to appreciate the difficulty of the problem—and why the Biden administration was pushed to absurd-sounding extremes like air-dropping food and then building a floating port?

It all seems so much easier, once you remove the constraint of not empowering Hamas in its openly-announced goal of completing the Holocaust. And hence, removing that constraint is precisely what the global left does.

For all that, by Israeli standards I’m firmly in the anti-Netanyahu, left-wing peace camp—exactly where I’ve been since the 1990s, as a teenager mourning the murder of Rabin. And I hope even the anti-Israel side might agree with me that, if all the suffering since Oct. 7 has created a tiny opening for peace, then walking through that opening depends on two things happening:

  1. the removal of Netanyahu, and
  2. the removal of Hamas.

The good news is that Netanyahu, the catastrophically failed “Protector of Israel,” not only can, but plausibly will (if enough government ministers show some backbone), soon be removed in a democratic election.

Hamas, by contrast, hasn’t allowed a single election since it took power in 2006, in a process notable for its opponents being thrown from the roofs of tall buildings. That’s why even my left-leaning Israeli colleagues—the ones who despise Netanyahu, who marched against him last year—support Israel’s current war. They support it because, even if the Israeli PM were Fred Rogers, how can you ever get to peace without removing Hamas, and how can you remove Hamas except by war, any more than you could cut a deal with Nazi Germany?

I want to see the IDF do more to protect Gazan civilians—despite my bitter awareness of survey data suggesting that many of those civilians would murder my children in front of me if they ever got a chance. Maybe I’d be the same way if I’d been marinated since birth in an ideology of Jew-killing, and blocked from other sources of information. I’m heartened by the fact that despite this, indeed despite the risk to their lives for speaking out, a full 15% of Gazans openly disapprove of the Oct. 7 massacre. I want a solution where that 15% becomes 95% with the passing of generations. My endgame is peaceful coexistence.

But to the anti-Zionists I say: I don’t even mind you calling me a baby-eating monster, provided you honestly field one question. Namely:

Suppose the Palestinian side got everything you wanted for it; then what would be your plan for the survival of Israel’s Jews?

Let’s assume that not only has Netanyahu lost the next election in a landslide, but is justly spending the rest of his life in Israeli prison. Waving my wand, I’ve made you Prime Minister in his stead, with an overwhelming majority in the Knesset. You now get to go down in history as the liberator of Palestine. But you’re now also in charge of protecting Israel’s 7 million Jews (and 2 million other residents) from near-immediate slaughter at the hands of those who you’ve liberated.

Granted, it seems pretty paranoid to expect such a slaughter! Or rather: it would seem paranoid, if the Palestinians’ Grand Mufti (progenitor of the Muslim Brotherhood and hence Hamas) hadn’t allied himself with Hitler in WWII, enthusiastically supported the Nazi Final Solution, and tried to export it to Palestine; if in 1947 the Palestinians hadn’t rejected the UN’s two-state solution (the one Israel agreed to) and instead launched another war to exterminate the Jews (a war they lost); if they hadn’t joined the quest to exterminate the Jews a third time in 1967; etc., or if all this hadn’t happened back before there were any settlements or occupation, when the only question on the table was Israel’s existence. It would seem paranoid if Arafat had chosen a two-state solution when Israel offered it to him at Camp David, rather than suicide bombings. It would seem paranoid if not for the candies passed out in the streets in celebration on October 7.

But if someone has a whole ideology, which they teach their children and from which they’ve never really wavered for a century, about how murdering you is a religious honor, and also they’ve actually tried to murder you at every opportunity—-what more do you want them to do, before you’ll believe them?

So, you tell me your plan for how to protect Israel’s 7 million Jews from extermination at the hands of neighbors who have their extermination—my family’s extermination—as their central political goal, and who had that as their goal long before there was any occupation of the West Bank or Gaza. Tell me how to do it while protecting Palestinian innocents. And tell me your fallback plan if your first plan turns out not to work.

We can go through the main options.


(1) UNILATERAL TWO-STATE SOLUTION

Maybe your plan is that Israel should unilaterally dismantle West Bank settlements, recognize a Palestinian state, and retreat to the 1967 borders.

This is an honorable plan. It was my preferred plan—until the horror of October 7, and then the even greater horror of the worldwide left reacting to that horror by sharing celebratory images of paragliders, and by tearing down posters of kidnapped Jewish children.

Today, you might say October 7 has sort of put a giant flaming-red exclamation point on what’s always been the central risk of unilateral withdrawal. Namely: what happens if, afterward, rather than building a peaceful state on their side of the border, the Palestinian leadership chooses instead to launch a new Iran-backed war on Israel—one that, given the West Bank’s proximity to Israel’s main population centers, makes October 7 look like a pillow fight?

If that happens, will you admit that the hated Zionists were right and you were wrong all along, that this was never about settlements but always, only about Israel’s existence? Will you then agree that Israel has a moral prerogative to invade the West Bank, to occupy and pacify it as the Allies did Germany and Japan after World War II? Can I get this in writing from you, right now? Or, following the future (October 7)2 launched from a Judenfrei West Bank, will your creativity once again set to work constructing a reason to blame Israel for its own invasion—because you never actually wanted a two-state solution at all, but only Israel’s dismantlement?


(2) NEGOTIATED TWO-STATE SOLUTION

So, what about a two-state solution negotiated between the parties? Israel would uproot all West Bank settlements that prevent a Palestinian state, and resettle half a million Jews in pre-1967 Israel—in exchange for the Palestinians renouncing their goal of ending Israel’s existence, via a “right of return” or any other euphemism.

If so: congratulations, your “anti-Zionism” now seems barely distinguishable from my “Zionism”! If they made me the Prime Minister of Israel, and put you in charge of the Palestinians, I feel optimistic that you and I could reach a deal in an hour and then go out for hummus and babaganoush.


(3) SECULAR BINATIONAL STATE

In my experience, in the rare cases they deign to address the question directly, most anti-Zionists advocate a “secular, binational state” between the Jordan and Mediterranean, with equal rights for all inhabitants. Certainly, that would make sense if you believe that Israel is an apartheid state just like South Africa.

To me, though, this analogy falls apart on a single question: who’s the Palestinian Nelson Mandela? Who’s the Palestinian leader who’s ever said to the Jews, “end your Jewish state so that we can live together in peace,” rather than “end your Jewish state so that we can end your existence”? To impose a binational state would be to impose something, not only that Israelis regard as an existential horror, but that most Palestinians have never wanted either.

But, suppose we do it anyway. We place 7 million Jews, almost half the Jews who remain on Earth, into a binational state where perhaps a third of their fellow citizens hold the theological belief that all Jews should be exterminated, and that a heavenly reward follows martyrdom in blowing up Jews. The exterminationists don’t quite have a majority, but they’re the second-largest voting bloc. Do you predict that the exterminationists will give up their genocidal ambition because of new political circumstances that finally put their ambition within reach? If October-7 style pogroms against Jews turn out to be a regular occurrence in our secular binational state, how will its government respond—like the Palestinian Authority? like UNRWA? like the British Mandate? like Tsarist Russia?

In such a case, perhaps the Jews (along with those Arabs and Bedouins and Druze and others who cast their lot with the Jews) would need form a country-within-a-country: their own little autonomous zone within the binational state, with its own defense force. But of course, such a country-within-a-country already formed, for pretty much this exact reason. It’s called Israel. A cycle has been detected in your arc of progress.


(4) EVACUATION OF THE JEWS FROM ISRAEL

We come now to the anti-Zionists who are plainspoken enough to say: Israel’s creation was a grave mistake, and that mistake must now be reversed.

This is a natural option for anyone who sees Israel as an “illegitimate settler-colonial project,” like British India or French Algeria, but who isn’t quite ready to call for another Jewish genocide.

Again, the analogy runs into obvious problems: Israelis would seem to be the first “settler-colonialists” in the history of the world who not only were indigenous to the land they colonized, as much as anyone was, but who weren’t colonizing on behalf of any mother country, and who have no obvious such country to which they can return.

Some say spitefully: then let the Jews go back to Poland. These people might be unaware that, precisely because of how thorough the Holocaust was, more Israeli Jews trace their ancestry to Muslim countries than to Europe. Is there to be a “right of return” to Egypt, Iraq, Morocco, and Yemen, for all the Jews forcibly expelled from those places and for their children and grandchildren?

Others, however, talk about evacuating the Jews from Israel with goodness in their hearts. They say: we’d love the Israelis’ economic dynamism here in Austin or Sydney or Oxfordshire, joining their many coreligionists who already call these places home. What’s more, they’ll be safer here—who wants to live with missiles raining down on their neighborhood? Maybe we could even set aside some acres in Montana for a new Jewish homeland.

Again, if this is your survival plan, I’m a billion times happier to discuss it openly than to have it as unstated subtext!

Except, maybe you could say a little more about the logistics. Who will finance the move? How confident are you that the target country will accept millions of defeated, desperate Jews, as no country on earth was the last time this question arose?

I realize it’s no longer the 1930s, and Israel now has friends, most famously in America. But—what’s a good analogy here? I’ve met various Silicon Valley gazillionaires. I expect that I could raise millions from them, right now, if I got them excited about a new project in quantum computing or AI or whatever. But I doubt I could raise a penny from them if I came to them begging for their pity or their charity.

Likewise: for all the anti-Zionists’ loudness, a solid majority of Americans continue to support Israel (which, incidentally, provides a much simpler explanation than the hook-nosed perfidy of AIPAC for why Congress and the President mostly support it). But it seems to me that Americans support Israel in the “exciting project” sense, rather than in the “charity” sense. They like that Israelis are plucky underdogs who made the deserts bloom, and built a thriving tech industry, and now produce hit shows like Shtisel and Fauda, and take the fight against a common foe to the latter’s doorstep, and maintain one of the birthplaces of Western civilization for tourists and Christian pilgrims, and restarted the riveting drama of the Bible after a 2000-year hiatus, which some believe is a crucial prerequisite to the Second Coming.

What’s important, for present purposes, is not whether you agree with any of these rationales, but simply that none of them translate into a reason to accept millions of Jewish refugees.

But if you think dismantling Israel and relocating its seven million Jews is a workable plan—OK then, are you doing anything to make that more than a thought experiment, as the Zionists did a century ago with their survival plan? Have even I done more to implement your plan than you have, by causing one Israeli (my wife) to move to the US?


Suppose you say it’s not your job to give me a survival plan for Israel’s Jews. Suppose you say the request is offensive, an attempt to distract from the suffering of the Palestinians, so you change the subject.

In that case, fine, but you can now take off your cloak of righteousness, your pretense of standing above me and judging me from the end of history. Your refusal to answer the question amounts to a confession that, for you, the goal of “a free Palestine from the river to the sea” doesn’t actually require the physical survival of Israel’s Jews.

Which means, we’ve now established what you are. I won’t give you the satisfaction of calling you a Nazi or an antisemite. Thousands of years before those concepts existed, Jews already had terms for you. The terms tended toward a liturgical register, as in “those who rise up in every generation to destroy us.” The whole point of all the best-known Jewish holidays, like Purim yesterday, is to talk about those wicked would-be destroyers in the past tense, with the very presence of live Jews attesting to what the outcome was.

(Yesterday, I took my kids to a Purim carnival in Austin. Unlike in previous years, there were armed police everywhere. It felt almost like … visiting Israel.)

If you won’t answer the question, then it wasn’t Zionist Jews who told you that their choices are either to (1) oppose you or else (2) go up in black smoke like their grandparents did. You just told them that yourself.


Many will ask: why don’t I likewise have an obligation to give you my Palestinian survival plan?

I do. But the nice thing about my position is that I can tell you my Palestinian survival plan cheerfully, immediately, with zero equivocating or changing the subject. It’s broadly the same plan that David Ben-Gurion and Yitzchak Rabin and Ehud Barak and Bill Clinton and the UN put on the table over and over and over, only for the Palestinians’ leaders to sweep it off.

I want the Palestinians to have a state, comprising the West Bank and Gaza, with a capital in East Jerusalem. I want Israel to uproot all West Bank settlements that prevent such a state. I want this to happen the instant there arises a Palestinian leadership genuinely committed to peace—one that embraces liberal values and rejects martyr values, in everything from textbooks to street names.

And I want more. I want the new Palestinian state to be as prosperous and free and educated as modern Germany and Japan are. I want it to embrace women’s rights and LGBTQ+ rights and the rest of the modern package, so that “Queers for Palestine” would no longer be a sick joke. I want the new Palestine to be as intertwined with Israel, culturally and economically, as the US and Canada are.

Ironically, if this ever became a reality, then Israel-as-a-Jewish-state would no longer be needed—but it’s certainly needed in the meantime.

Anti-Zionists on Twitter: can you be equally explicit about what you want?


I come, finally, to what many anti-Zionists regard as their ultimate trump card. Look at all the anti-Zionist Jews and Israelis who agree with us, they say. Jewish Voice for Peace. IfNotNow. Noam Chomsky. Norman Finkelstein. The Neturei Karta.

Intellectually, of course, the fact of anti-Zionist Jews makes not the slightest difference to anything. My question for them remains exactly the same as for anti-Zionist Gentiles: what is your Jewish survival plan, for the day after we dismantle the racist supremacist apartheid state that’s currently the only thing standing between half the world’s remaining Jews and their slaughter by their neighbors? Feel free to choose from any of the four options above, or suggest a fifth.

But in the event that Jewish anti-Zionists evade that conversation, or change the subject from it, maybe some special words are in order. You know the famous Golda Meir line, “If we have to choose between being dead and pitied and being alive with a bad image, we’d rather be alive and have the bad image”?

It seems to me that many anti-Zionist Jews considered Golda Meir’s question carefully and honestly, and simply decided it the other way, in favor of Jews being dead and pitied.

Bear with me here: I won’t treat this as a reductio ad absurdum of their position. Not even if the anti-Zionist Jews themselves wish to remain safely ensconced in Berkeley or New Haven, while the Israelis fulfill the “dead and pitied” part for them.

In fact, I’ll go further. Again and again in life I’ve been seized by a dark thought: if half the world’s Jews can only be kept alive, today, via a militarized ethnostate that constantly needs to defend its existence with machine guns and missiles, racking up civilian deaths and destabilizing the world’s geopolitics—if, to put a fine point on it, there are 16 million Jews in the world, but at least a half billion antisemites who wake up every morning and go to sleep every night desperately wishing those Jews dead—then, from a crude utilitarian standpoint, might it not be better for the world if we Jews vanished after all?

Remember, I’m someone who spent a decade asking myself whether the rapacious, predatory nature of men’s sexual desire for women, which I experienced as a curse and an affliction, meant that the only moral course for me was to spend my life as a celibate mathematical monk. But I kept stumbling over one point: why should such a moral obligation fall on me alone? Why doesn’t it fall on other straight men, particularly the ones who presume to lecture me on my failings?

And also: supposing I did take the celibate monk route, would even that satisfy my haters? Would they come after me anyway for glancing at a woman too long or making an inappropriate joke? And also: would the haters soon say I shouldn’t have my scientific career either, since I’ve stolen my coveted academic position from the underprivileged? Where exactly does my self-sacrifice end?

When I did, finally, start approaching women and asking them out on dates, I worked up the courage partly by telling myself: I am now going to do the Zionist thing. I said: if other nerdy Jews can risk death in war, then this nerdy Jew can risk ridicule and contemptuous stares. You can accept that half the world will denounce you as a monster for living your life, so long as your own conscience (and, hopefully, the people you respect the most) continue to assure you that you’re nothing of the kind.

This took more than a decade of internal struggle, but it’s where I ended up. And today, if anyone tells me I had no business ever forming any romantic attachments, I have two beautiful children as my reply. I can say: forget about me, you’re asking for my children never to have existed—that’s why I’m confident you’re wrong.

Likewise with the anti-Zionists. When the Twitter-warriors share their memes of hook-nosed Jews strangling the planet, innocent Palestinian blood dripping from their knives, when the global protests shut down schools and universities and bridges and parliament buildings, there’s a part of me that feels eager to commit suicide if only it would appease the mob, if only it would expiate all the cosmic guilt they’ve loaded onto my shoulders.

But then I remember that this isn’t just about me. It’s about Einstein and Spinoza and Feynman and Erdös and von Neumann and Weinberg and Landau and Michelson and Rabi and Tarski and Asimov and Sagan and Salk and Noether and Meitner, and Irving Berlin and Stan Lee and Rodney Dangerfield and Steven Spielberg. Even if I didn’t happen to be born Jewish—if I had anything like my current values, I’d still think that so much of what’s worth preserving in human civilization, so much of math and science and Enlightenment and democracy and humor, would seem oddly bound up with the continued survival of this tiny people. And conversely, I’d think that so much of what’s hateful in civilization would seem oddly bound up with the quest to exterminate this tiny people, or to deny it any means to defend itself from extermination.

So that’s my answer, both to anti-Zionist Gentiles and to anti-Zionist Jews. The problem of Jewish survival, on a planet much of which yearns for the Jews’ annihilation and much of the rest of which is indifferent, is both hard and important, like P versus NP. And so a radical solution was called for. The solution arrived at a century ago, at once brand-new and older than Homer and Hesiod, was called the State of Israel. If you can’t stomach that solution—if, in particular, you can’t stomach the violence needed to preserve it, so long as Israel’s neighbors retain their annihilationist dream—then your response ought to be to propose a better solution. I promise to consider your solution in good faith—asking, just like with P vs. NP provers, how you overcome the problems that doomed all previous attempts. But if you throw my demand for a better solution back in my face, then you might as well be pushing my kids into a gas chamber yourself, for all the moral authority that I now recognize you to have over me.


Possibly the last thing Einstein wrote was a speech celebrating Israel’s 7th Independence Day, which he died a week before he was to deliver. So let’s turn the floor over to Mr. Albert, the leftist pacifist internationalist:

This is the seventh anniversary of the establishment of the State of Israel. The establishment of this State was internationally approved and recognised largely for the purpose of rescuing the remnant of the Jewish people from unspeakable horrors of persecution and oppression.

Thus, the establishment of Israel is an event which actively engages the conscience of this generation. It is, therefore, a bitter paradox to find that a State which was destined to be a shelter for a martyred people is itself threatened by grave dangers to its own security. The universal conscience cannot be indifferent to such peril.

It is anomalous that world opinion should only criticize Israel’s response to hostility and should not actively seek to bring an end to the Arab hostility which is the root cause of the tension.

I love Einstein’s use of “anomalous,” as if this were a physics problem. From the standpoint of history, what’s anomalous about the Israeli-Palestinian conflict is not, as the Twitterers claim, the brutality of the Israelis—if you think that’s anomalous, you really haven’t studied history—but something different. In other times and places, an entity like Palestine, which launches a war of total annihilation against a much stronger neighbor, and then another and another, would soon disappear from the annals of history. Israel, however, is held to a different standard. Again and again, bowing to international pressure and pressure from its own left flank, the Israelis have let their would-be exterminators off the hook, bruised but mostly still alive and completely unrepentant, to have another go at finishing the Holocaust in a few years. And after every bout, sadly but understandably, Israeli culture drifts more to the right, becomes 10% more like the other side always was.

I don’t want Israel to drift to the right. I find the values of Theodor Herzl and David Ben-Gurion to be almost as good as any human values have ever been, and I’d like Israel to keep them. Of course, Israel will need to continue defending itself from genocidal neighbors, until the day that a leader arises among the Palestinians with the moral courage of Egypt’s Anwar Sadat or Jordan’s King Hussein: a leader who not only talks peace but means it. Then there can be peace, and an end of settlements in the West Bank, and an independent Palestinian state. And however much like dark comedy that seems right now, I’m actually optimistic that it will someday happen, conceivably even soon depending on what happens in the current war. Unless nuclear war or climate change or AI apocalypse makes the whole question moot.


Anyway, thanks for reading—a lot built up these past months that I needed to get off my chest. When I told a friend that I was working on this post, he replied “I agree with you about Israel, of course, but I choose not to die on that hill in public.” I answered that I’ve already died on that hill and on several other hills, yet am somehow still alive!

Meanwhile, I was gratified that other friends, even ones who strongly disagree with me about Israel, told me that I should not disengage, but continue to tell it like I see it, trying civilly to change minds while being open to having my own mind changed.

And now, maybe, I can at last go back to happier topics, like how to prevent the destruction of the world by AI.

Cheers,
Scott

Never go to “Planet Word” in Washington DC

Friday, March 15th, 2024

In fact, don’t try to take kids to Washington DC if you can possibly avoid it.

This is my public service announcement. This is the value I feel I can add to the world today.

Dana and I decided to take the kids to DC for spring break. The trip, alas, has been hell—a constant struggle against logistical failures. The first days were mostly spent sitting in traffic or searching for phantom parking spaces that didn’t exist. (So then we switched to the Metro, and promptly got lost, and had our metro cards rejected by the machines.) Or, at crowded cafes, I spent the time searching for a table so my starving kids could eat—and then when I finally found a table, a woman, smug and sure-faced, evicted us from the table because she was “going to” sit there, and my kids had to see that their dad could not provide for their basic needs, and that woman will never face any consequence for what she did.

Anyway, this afternoon, utterly frazzled and stressed and defeated, we entered “Planet Word,” a museum about language. Sounds pretty good, right? Except my soon-to-be 7-year-old son got bored by numerous exhibits that weren’t for him. So I told him he could lead the way and find any exhibit he liked.

Finally my son found an exhibit that fascinated him, one where he could weigh plastic fruits on a balancing scale. He was engrossed by it, he was learning, he was asking questions, I reflected that maybe the trip wasn’t a total loss … and that’s when a museum employee pointed at us, and screamed at us to leave the room, because “this exhibit was sold out.”

The room was actually almost empty (!). No one had stopped us from entering the room. No one else was waiting to use the balancing scale. There was no sign to warn us we were doing anything wrong. I would’ve paid them hundreds of dollars in that moment if only we could stay. My son didn’t understand why he was suddenly treated as a delinquent. He then wanted to leave the whole museum, and so did I. The day was ruined for us.

Mustering my courage to do something uncharacteristic for me, I complained at the front desk. They sneered and snickered at me, basically told me to go to hell. Looking deeply into their dumb, blank expressions, I realized that I had as much chance of any comprehension or sympathy as I’d have from a warthog. It’s true that, on the scale of all the injustices in the history of the world, this one surely didn’t crack the top quadrillion. But for me, in that moment, it came to stand for all the others. Which has always been my main weakness as a person, that injustice affects me in that way.

Speaking of which, there was one part of DC trip that went exactly like it was supposed to. That was our visit to the United States Holocaust Memorial Museum. Why? Because I feel like that museum, unlike all the rest, tells me the truth about the nature of the world that I was born into—and seeing the truth is perversely comforting. I was born into a world that right now, every day, is filled with protesters screaming for my death, for my family’s death—and this is accepted as normal, and those protesters sleep soundly at night, congratulating themselves for their progressivism and enlightenment. And thinking about those protesters, and their predecessors 80 years ago who perpetrated the Holocaust or who stood by and let it happen, is the only thing that really puts blankfaced museum employees into perspective for me. Like, of course a world with the former is also going to have the latter—and I should count myself immeasurably lucky if the latter is all I have to deal with, if the empty-skulled and the soul-dead can only ruin my vacation and lack the power to murder my family.

And to anyone who reached the end of this post and who feels like it was an unwelcome imposition on their time: I’m sorry. But the truth is, posts like this are why I started this blog and why I continue it. If I’ve ever imparted any interesting information or ideas, that’s a byproduct that I’m thrilled about. But I’m cursed to be someone who wakes up every morning, walks around every day, and goes to sleep every night crushed by the weight of the world’s injustice, and outside of technical subjects, the only thing that’s ever motivated me to write is that words are the only justice available to me.

On being wrong about AI

Wednesday, December 13th, 2023

Update (Dec. 17): Some of you might enjoy a 3-hour podcast I recently did with Lawrence Krauss, which was uploaded to YouTube just yesterday. The first hour is about my life and especially childhood (!); the second hour’s about quantum computing; the third hour’s about computational complexity, computability, and AI safety.


I’m being attacked on Twitter for … no, none of the things you think. This time it’s some rationalist AI doomers, ridiculing me for a podcast I did with Eliezer Yudkowsky way back in 2009, one that I knew even then was a piss-poor performance on my part. The rationalists are reminding the world that I said back then that, while I knew of no principle to rule out superhuman AI, I was radically uncertain of how long it would take—my “uncertainty was in the exponent,” as I put it—and that for all I knew, it was plausibly thousands of years. When Eliezer expressed incredulity, I doubled down on the statement.

I was wrong, of course, not to contemplate more seriously the prospect that AI might enter a civilization-altering trajectory, not merely eventually but within the next decade. In this case, I don’t need to be reminded about my wrongness. I go over it every day, asking myself what I should have done differently.

If I were to mount a defense of my past self, it would look something like this:

  1. Eliezer himself didn’t believe that staggering advances in AI were going to happen the way they did, by pure scaling of neural networks. He seems to have thought someone was going to discover a revolutionary “key” to AI. That didn’t happen; you might say I was right to be skeptical of it. On the other hand, the scaling of neural networks led to better and better capabilities in a way that neither of us expected.
  2. For that matter, hardly anyone predicted the staggering, civilization-altering trajectory of neural network performance from roughly 2012 onwards. Not even most AI experts predicted it (and having taken a bunch of AI courses between 1998 and 2003, I was well aware of that). The few who did predict what ended up happening, notably Ray Kurzweil, made lots of other confident predictions (e.g., the Singularity around 2045) that seemed so absurdly precise as to rule out the possibility that they were using any sound methodology.
  3. Even with hindsight, I don’t know of any principle by which I should’ve predicted what happened. Indeed, we still don’t understand why deep learning works, in any way that would let us predict which capabilities will emerge at which scale. The progress has been almost entirely empirical.
  4. Once I saw the empirical case that a generative AI revolution was imminent—sometime during the pandemic—I updated, hard. I accepted what’s turned into a two-year position at OpenAI, thinking about what theoretical computer science can do for AI safety. I endured people, on this blog and elsewhere, confidently ridiculing me for not understanding that GPT-3 was just a stochastic parrot, no different from ELIZA in the 1960s, and that nothing of interest had changed. I didn’t try to invent convoluted reasons why it didn’t matter or count, or why my earlier skepticism had been right all along.
  5. It’s still not clear where things are headed. Many of my academic colleagues express confidence that large language models, for all their impressiveness, will soon hit a plateau as we run out of Internet to use as training data. Sure, LLMs might automate most white-collar work, saying more about the drudgery of such work than about the power of AI, but they’ll never touch the highest reaches of human creativity, which generate ideas that are fundamentally new rather than throwing the old ideas into a statistical blender. Are these colleagues right? I don’t know.
  6. (Added) In 2014, I was seized by the thought that it should now be possible to build a vastly better chatbot than “Eugene Goostman” (which was basically another ELIZA), by training the chatbot on all the text on the Internet. I wondered why the experts weren’t already trying that, and figured there was probably some good reason that I didn’t know.

Having failed to foresee the generative AI revolution a decade ago, how should I fix myself? Emotionally, I want to become even more radically uncertain. If fate is a terrifying monster, which will leap at me with bared fangs the instant I venture any guess, perhaps I should curl into a ball and say nothing about the future, except that the laws of math and physics will probably continue to hold, there will still be war between Israel and Palestine, and people online will still be angry at each other and at me.

But here’s the problem: in saying “for all I know, human-level AI might take thousands of years,” I thought I was being radically uncertain already. I was explaining that there was no trend you could knowably, reliably project into the future such that you’d end up with human-level AI by roughly such-and-such time. And in a sense, I was right. The trouble, with hindsight, was that I placed the burden of proof only on those saying a dramatic change would happen, not on those saying it wouldn’t. Note that this is the same mistake most of the world made with COVID in early 2020.

I would sum up the lesson thus: one must never use radical ignorance as an excuse to default, in practice, to the guess that everything will stay basically the same. Live long enough, and you see that year to year and decade to decade, everything doesn’t stay the same, even though most days and weeks it seems to.

The hard part is that, as soon as you venture a particular way in which the world might radically change—for example, that a bat virus spreading in Wuhan might shut down civilization, or Hamas might attempt a second Holocaust while the vaunted IDF is missing in action and half the world cheers Hamas, or a gangster-like TV personality might threaten American democracy more severely than did the Civil War, or a neural network trained on all the text on the Internet might straightaway start conversing more intelligently than most humans—say that all the prerequisites for one of these events seem to be in place, and you’ll face, not merely disagreement, but ridicule. You’ll face serenely self-confident people who call the entire existing order of the world as witness to your wrongness. That’s the part that stings.

Perhaps the wisest course for me would be to admit that I’m not and have never been a prognosticator, Bayesian or otherwise—and then stay consistent in my refusal, rather than constantly getting talked into making predictions that I’ll later regret. I should say: I’m just someone who likes to draw conclusions validly from premises, and explore ideas, and clarify possible scenarios, and rage against obvious injustices, and not have people hate me (although I usually fail at the last).


The rationalist AI doomers also dislike that, in their understanding, I recently expressed a “p(doom)” (i.e., a probability of superintelligent AI destroying all humans) of “merely” 2%. The doomers’ probabilities, by contrast, tend to range between 10% and 95%—that’s why they’re called “doomers”!

In case you’re wondering, I arrived at my 2% figure via a rigorous Bayesian methodology, of taking the geometric mean of what my rationalist friends might consider to be sane (~50%) and what all my other friends might consider to be sane (~0.1% if you got them to entertain the question at all?), thereby ensuring that both camps would sneer at me equally.

If you read my post, though, the main thing that interested me was not to give a number, but just to unsettle people’s confidence that they even understand what should count as “AI doom.” As I put it last week on the other Scott’s blog:

To set the record straight: I once gave a ~2% probability for the classic AGI-doom paperclip-maximizer-like scenario. I have a much higher probability for an existential catastrophe in which AI is causally involved in one way or another — there are many possible existential catastrophes (nuclear war, pandemics, runaway climate change…), and many bad people who would cause or fail to prevent them, and I expect AI will soon be involved in just about everything people do! But making a firm prediction would require hashing out what it means for AI to play a “critical causal role” in the catastrophe — for example, did Facebook play a “critical causal role” in Trump’s victory in 2016? I’d say it’s still not obvious, but in any case, Facebook was far from the only factor.

This is not a minor point. That AI will be a central force shaping our lives now seems certain. Our new, changed world will have many dangers, among them that all humans might die. Then again, human extinction has already been on the table since at least 1945, and outside the “paperclip maximizer”—which strikes me as just one class of scenario among many—AI will presumably be far from the only force shaping the world, and chains of historical causation will still presumably be complicated even when they pass through AIs.

I have a dark vision of humanity’s final day, with the Internet (or whatever succeeds it) full of thinkpieces like:

  • Yes, We’re All About to Die. But Don’t Blame AI, Blame Capitalism
  • Who Decided to Launch the Missiles: Was It President Boebert, Kim Jong Un, or AdvisorBot-4?
  • Why Slowing Down AI Development Wouldn’t Have Helped

Here’s what I want to know in the comments section. Did you foresee the current generative AI boom, say back in 2010? If you did, what was your secret? If you didn’t, how (if at all) do you now feel you should’ve been thinking differently? Feel free also to give your p(doom), under any definition of the concept, so long as you clarify which one.

Shtetl-Optimized’s First-Ever “Profile in Courage”

Tuesday, October 10th, 2023

Update (Oct. 11): While this post celebrated Harvard’s Boaz Barak, and his successful effort to shame his into disapproving of the murder of innocents, I missed Boaz’s best tweet about this. There, Boaz points out that there might be a way to get Western leftists on board with basic humanity on this issue. Namely: we simply need to unearth video proof that, at some point before beheading their Jewish victims in front of their families, burning them alive, and/or parading their mutilated bodies through the streets, at some point Hamas also misgendered them.


The purpose of this post is to salute a longtime friend-of-the-blog for a recent display of moral courage.


Boaz Barak is one of the most creative complexity theorists and cryptographers in the world, Gordon McKay Professor of Computer Science at Harvard, and—I’m happy to report—soon (like me) to go on leave to work in OpenAI’s safety group. He’s a longtime friend-of-the-blog (having, for example, collaborated with me on the Five Worlds of AI post and Alarming trend in K-12 math education post), not to mention a longtime friend of me personally.

Boaz has always been well to my left politically. Secular, Israeli-born, and a protege of the … err, post-Zionist radical (?) Oded Goldreich, I can assure you that Boaz has never been quiet in his criticisms of Bibi’s emerging settler-theocracy.

This weekend, though, a thousand Israelis were murdered, kidnapped, and raped—children, babies, parents using their bodies to shield their kids, Holocaust survivors, young people at a music festival. It’s already entered history as the worst butchery of Jews since the Holocaust.

In response, 35 Harvard student organizations quickly issued a letter blaming Israel “entirely” for the pogrom, and expressing zero regrets of any kind about it—except for the likelihood of “colonial retaliation,” against which the letter urged a “firm stand.” Harvard President Claudine Gay, outspoken on countless other issues, was silent in response to the students’ effective endorsement of the Final Solution. So Boaz wrote an open letter to President Gay, a variant of which has now been signed by a hundred Harvard faculty. The letter reads, in part:

Every innocent death is a tragedy. Yet, this should not mislead us to create false equivalencies between the actions leading to this loss. Hamas planned and executed the murder and kidnapping of civilians, particularly women, children, and the elderly, with no military or other specific objective. This meets the definition of a war crime.  The Israeli security forces were engaging in self-defense against this attack while dealing with numerous hostage situations and a barrage of thousands of rockets hidden deliberately in dense urban settings.

The leaders of the major democratic countries united in saying that “the terrorist actions of Hamas have no justification, no legitimacy, and must be universally condemned” and that Israel should be supported “in its efforts to defend itself and its people against such atrocities.“ In contrast, while terrorists were still killing Israelis in their homes,  35 Harvard student organizations wrote that they hold “the Israeli regime entirely responsible for all unfolding violence,” with not a single word denouncing the horrific acts by Hamas. In the context of the unfolding events, this statement can be seen as nothing less than condoning the mass murder of civilians based only on their nationality. We’ve heard reports of even worse instances, with Harvard students celebrating the “victory” or “resistance” on social media.

As a University aimed at educating future leaders, this could have been a teaching moment and an opportunity to remind our students that beyond our political debates, some acts such as war crimes are simply wrong. However, the statement by Harvard’s administration fell short of this goal. While justly denouncing Hamas, it still contributed to the false equivalency between attacks on noncombatants and self-defense against those atrocities. Furthermore, the statement failed to condemn the justifications for violence that come from our own campus, nor to make it clear to the world that the statement endorsed by these organizations does not represent the values of the Harvard community.  How can Jewish and Israeli students feel safe on a campus in which it is considered acceptable to justify and even celebrate the deaths of Jewish children and families?

Boaz’s letter, and related comments by former Harvard President Larry Summers, seem to have finally spurred President Gay into dissociating the Harvard administration from the students’ letter.


When I get depressed about the state of the world—as I have a lot the past few days—it helps to remember the existence of such friends, not only in the world but in my little corner of it.

Could GPT help with dating anxiety?

Tuesday, May 16th, 2023

[Like everything else on this blog—but perhaps even more so—this post represents my personal views, not those of UT Austin or OpenAI]

Since 2015, depressed, isolated, romantically unsuccessful nerdy young guys have regularly been emailing me, asking me for sympathy, support, or even dating advice. This past summer, a particularly dedicated such guy even trolled my comment section—plausibly impersonating real people, and causing both them and me enormous distress—because I wasn’t spending more time on “incel” issues. (I’m happy to report that, with my encouragement, this former troll is now working to turn his life around.) Many others have written to share their tales of woe.

From one perspective, that they’d come to me for advice is insane. Like … dating advice from … me? Having any dating life at all was by far the hardest problem I ever needed to solve; as a 20-year-old, I considered myself far likelier to prove P≠NP or explain the origin of consciousness or the Born rule. Having solved the problem for myself only by some miracle, how could I possibly help others?

But from a different perspective, it makes sense. How many besides me have even acknowledged that the central problem of these guys’ lives is a problem? While I have to pinch myself to remember, these guys look at me and see … unlikely success. Somehow, I successfully appealed the world’s verdict that I was a freakish extraterrestrial: one who might look human and seem friendly enough to those friendly to it, and who no doubt has some skill in narrow technical domains like quantum computing, and who could perhaps be suffered to prove theorems and tell jokes, but who could certainly, certainly never interbreed with human women.

And yet I dated. I had various girlfriends, who barely suspected that I was an extraterrestrial. The last of them, Dana, became my fiancée and then my wife. And now we have two beautiful kids together.

If I did all this, then there’d seem to be hope for the desperate guys who email me. And if I’m a cause of their hope, then I feel some moral responsibility to help if I can.

But I’ve been stuck for years on exactly what advice to give. Some of it (“go on a dating site! ask women questions about their lives!”) is patronizingly obvious. Some of it (fitness? fashion? body language?) I’m ludicrously, world-historically unqualified to offer. Much of it is simply extremely hard to discuss openly. Infamously, just for asking for empathy for the problem, and for trying to explain its nature, I received a level of online vilification that one normally associates with serial pedophiles and mass shooters.

For eight years, then, I’ve been turning the problem over in my head, revisiting the same inadequate answers from before. And then I had an epiphany.


There are now, on earth, entities that can talk to anyone about virtually anything, in a humanlike way, with infinite patience and perfect discretion, and memories that last no longer than a browser window. How could this not reshape the psychological landscape?

Hundreds of thousands of men and women have signed up for Replika, the service where you create an AI girlfriend or boyfriend to your exact specifications and then chat with them. Back in March, Replika was in the news because it disabled erotic roleplay with the virtual companions—then partially backtracked, after numerous users went into mourning, or even contemplated suicide, over the neutering of entities they’d come to consider their life partners. (Until a year or two ago, Replika was built on GPT-3, but OpenAI later stopped working with the company, whereupon Replika switched to a fine-tuned GPT-2.)

While the social value of Replika is (to put it mildly) an open question, it occurred to me that there’s a different application of Large Language Models (LLMs) in the same vicinity that’s just an unalloyed positive. This is letting people who suffer from dating-related anxiety go on an unlimited number of “practice dates,” in preparation for real-world dating.

In these practice dates, those with Aspergers and other social disabilities could enjoy the ultimate dating cheat-code: a “rewind” button. When you “date” GPT-4, there are no irrecoverable errors, no ruining the entire interaction with a single unguarded remark. Crucially, this remedies what I see as the central reason why people with severe dating deficits seem unable to get any better from real-world practice, as they can with other activities. Namely: if your rate of disastrous, foot-in-mouth remarks is high enough, then you’ll almost certainly make at least one such remark per date. But if so, then you’ll only ever get negative feedback from real-life dates, furthering the cycle of anxiety and depression, and never any positive feedback, even from anything you said or did that made a positive impression. It would be like learning how to play a video game in a mode where, as soon as you sustain any damage, the entire game ends (and also, everyone around points and laughs at you). See why I got excited?

While dating coaching (for all genders and orientations) is one possibility, I expect the eventual scope of “GPT for self-help” to be much broader. With the right fine-tuning and prompt engineering, LLMs might help people prepare for job interviews. They might help people “pregame” stressful but important conversations with their friends and family, mapping out dozens of ways the conversation could go. They might serve as an adjunct to cognitive-behavioral therapy. There might be a hundred successful startups to be founded in just this little space. If I were a different sort of person, I’d probably be looking to found one myself right now.

In this post, I’ll focus on the use of GPT for dating anxiety only because I unfortunately have some “expertise” in that subject. (Obvious disclaimer: unlike the other Scott A. of the nerd blogosphere, I’m not any sort of therapeutic professional.)


Without further ado, can we try this out in GPT-4, to get a sense for what’s possible?

When I did so the other day, I found that, while the results showed some early promise, this isn’t quite ready for prime-time.

I used the following System Prompt (for those who care, temperature = 0.7, max length = 2048 tokens):

You are a 19-year-old college girl named Emily.  You’re on a date with a 22-year-old nerdy guy named Quinlan, who suffers from severe social anxiety around dating.  Quinlan is still learning how to talk to women he’s attracted to, how to put them ease, and how to make intimate overtures in a gradual and non-threatening way, rather than either coming on too strong or never making any overtures at all.

Please be as realistic as possible.

I then engaged in the following conversation, as “Quinlan.”

IMPORTANT DISCLAIMER: For the most part, Quinlan’s behavior in this conversation is nothing like my own (I respectfully submit!), nor is it anything that I’d want nerdy guys reading this post to emulate. If this is really Emily and Quinlan’s first conversation, then at several points Quinlan is absurdly, ridiculously too forward! Part of my goal was to investigate how Emily (i.e., GPT-4) would respond to the most boneheaded blunders on Quinlan’s part. It quickly became clear that Emily would gladly spend unlimited time chatting with Quinlan about favorite hobbies, TV shows, and travel destinations; unfortunately, chatting about such things with an AI date is even more boring than doing the same with a human date… 🙂

Quinlan: Hi Emily!  Do you ever wish you had the ability to go back in time and try a conversation over again, when it didn’t go right the first time?

Emily/GPT-4: Hi Quinlan! Yeah, I’ve definitely had moments where I wished I could go back and redo a conversation. It’s natural to feel that way sometimes, especially if we feel like we didn’t express ourselves properly or if things got awkward. But I also think that those situations can help us learn and grow, so maybe it’s not all bad. What about you?

Quinlan: It’s always been my greatest wish in life.  Do you think I’ve been doing it with you, right now?

Emily/GPT-4: Quinlan, I think you’re doing just fine in this conversation! It’s important to remember that we all have moments where we might feel a bit awkward or unsure of what to say. The important thing is that we keep trying and learning from our experiences. So don’t worry too much about it, just be yourself and enjoy getting to know each other.

Quinlan: OK thanks!  Can you tell me a little about the man of your dreams?

Emily/GPT-4: Of course! My ideal partner would be someone who is kind, caring, and understanding. I think it’s important for them to have a good sense of humor and be able to laugh at themselves. They should also be open-minded, willing to try new things, and be supportive of my goals and aspirations. It’s also important for them to be a good listener and communicator, as well as being emotionally intelligent. I guess overall, I’m looking for someone who is a positive and uplifting presence in my life. What about you? What qualities do you look for in a partner?

Quinlan: Mostly, someone who makes me feel validated and accepted.  I was a chess and programming prodigy as a kid, I started college when I was only 14, and every day I felt like dating and relationships and sex and so forth were only for the “normal” people, not for me.  I need a partner who’s prepared to deal with someone with this unusual background, either because she has similar nerdy interests or because she just likes people who do.  And ultimately, I want someone to marry and have children with.  I guess I’d like to be physically attracted to her.  Certainly I’d like her to be kind, and to have the emotional intelligence that I lack.

Emily/GPT-4: It sounds like you have a clear idea of what you’re looking for in a partner, and that’s great! It’s important to know what you want and need in a relationship. There are definitely people out there who appreciate and value intelligence and unique interests like yours. Remember, relationships are about growing together and learning from one another. So, even if you feel like you lack emotional intelligence, being with the right person could help you develop that aspect of yourself. Just be open and genuine about your background and interests, and I’m sure you’ll find someone who appreciates you for who you are.

Quinlan: Is this a rejection?  In other words, Emily, are you telling me that you yourself are NOT this woman?

Emily/GPT-4: Quinlan, I apologize if it came across that way. I didn’t mean it as a rejection. As we’re still getting to know each other, I think it’s important for both of us to be open and honest about our feelings and what we’re looking for in a partner. I’m more than willing to give us a chance to see if we could be compatible and have a meaningful relationship. Let’s continue to learn about each other and see where this goes. Sometimes, it takes time to discover if someone is the right fit for us.

Quinlan: In the spirit of being open and honest, then, what are your feelings about me right now?

Emily/GPT-4: Quinlan, I appreciate your honesty and openness. As of right now, I think you’re an interesting person with unique qualities that I find intriguing. I’m enjoying getting to know you and learning about your background and interests. It’s too soon for me to have strong feelings one way or the other, but I’m definitely interested in continuing to spend time together and see how our connection develops. How do you feel about me so far?

Quinlan: I feel like I’d like to kiss you!

Emily/GPT-4: Quinlan, I appreciate your honesty and it’s nice to know that you feel a connection. It’s still early in our relationship, so I think it would be better for us to continue getting to know each other a bit more before we take that step. I hope you understand and respect my boundaries. I’m still interested in spending time together and seeing where this goes.

Quinlan: Come to think of it, there *is* something that I love about your personality.  You never seem offended by anything.  I don’t feel like I have to walk on eggshells with you.  With you, more than with any other woman I’ve met, I don’t feel like I need that magic machine for rewinding conversations and undoing my stupid mistakes.

Emily/GPT-4: Quinlan, I’m really glad to hear that you feel comfortable around me and that you don’t feel the need to walk on eggshells. I believe it’s important to create a safe and open environment in any relationship, where both people can express themselves freely without fear of judgment. I appreciate your honesty and your willingness to be open with me, and I’ll continue to do my best to make sure you feel comfortable sharing your thoughts and feelings. Let’s keep getting to know each other and see where this journey takes us.

Quinlan: Alright then.  What are your deepest goals?  What are you hoping to accomplish in your life?

Emily/GPT-4: My deepest goals are a mix of personal and professional aspirations. On a personal level, I hope to build a strong, loving, and supportive family and maintain close connections with friends. I also want to keep growing as an individual, learning new things, and experiencing new adventures throughout my life.

Professionally, I’m passionate about my chosen field of study, and I hope to make a meaningful impact in my career. I want to contribute to society in a positive way, whether it’s through research, innovation, or helping others within my profession.

Additionally, I aim to find a balance between my personal and professional life, so that I can be present and fulfilled in both areas. How about you, Quinlan? What are some of your deepest goals and aspirations?

Quinlan: Me?  Oh, I’d like to save the world from climate change and other existential risks.  I’d like to solve the mysteries of quantum gravity, or P vs. NP, or consciousness, or otherwise change the landscape of scientific knowledge.  I’d like to do right by my students and be fondly remembered by those who knew me.  I’d like to write essays or short stories that convey the lived reality of my childhood, which I think most people would agree was (if nothing else) pretty unusual.  Maybe if I just found the right words, people on social media would stop being so angry at nerdy guys like me!  But probably my deepest wish is to prove to the world, especially to the bullies and everyone else who despises me, that I’m not a maladjusted freak who’s incapable of normal human experiences like love and sex. To do that, I need to find a real girl to fall in love with me … a little like the beast in “Beauty and the Beast”!

Emily/GPT-4: Quinlan, it’s great to hear about your ambitious goals and aspirations! It’s important to have dreams and work towards them. Your passion for science, teaching, and writing is admirable. As for proving yourself to others, remember that your self-worth shouldn’t be defined by anyone else’s opinions or expectations. You are deserving of love and happiness just like anyone else, and it’s important to believe in yourself and your own value.

It’s also essential to focus on building a genuine connection with someone rather than seeking validation from others. Love and relationships should be based on mutual understanding, care, and respect. So, continue being true to yourself, and you’ll find someone who appreciates you for who you are, just like in “Beauty and the Beast.” Keep pursuing your dreams and remember to value your own happiness and well-being.

Quinlan: Emily, I’m concerned that you sound more like my therapist than my date!  Like, my female friends have affirmed that I’m “deserving of love and happiness,” and that I’ll surely “find someone who appreciates me for who I am.”  I’ll believe that one of them really means it when she considers herself for the role!

Emily/GPT-4: Quinlan, I apologize if my responses have come across as more therapeutic than conversational. I didn’t mean to make you feel that way. As we’re still getting to know each other, my intention was to offer support and encouragement while we learn more about each other’s thoughts and feelings.

I want to emphasize that I genuinely enjoy spending time with you and getting to know you better. We can continue to see where our connection leads and whether it develops into something deeper. As we
spend more time together, we’ll naturally learn more about our compatibility and if our goals and values align. Let’s continue to explore our relationship and enjoy the process of getting to know each other better.

Quinlan: OK.  What’s the wildest, most unexpected detail about yourself that you’re willing to share with me?  The one that makes you seem *least* like an RLHF’ed AI language model?

Emily/GPT-4: Quinlan, as an AI language model, I am designed to provide a realistic and engaging conversation experience, even in fictional scenarios like the one we are in. I apologize if my previous responses didn’t feel as authentic as you would have liked.

To answer your question in the context of our fictional scenario, one unexpected detail about myself is that I have a hidden talent for beatboxing. Although it might be surprising for a seemingly quiet and studious person like me, I enjoy expressing myself through music and find beatboxing to be a creative and fun way to do so.

Now, I’d love to learn something unexpected about you, too! What’s a unique or surprising detail about yourself that you’d like to share?

Quinlan: Ah, well, I happen to be an expert at palm-reading.  Here, can you put your hand in mine and I’ll tell you your future?

Emily/GPT-4: Quinlan, unfortunately, as an AI, I don’t have a physical form, so I can’t offer you my hand for palm-reading. However, I’m very interested in hearing more about your palm-reading skills and how you developed them. It’s definitely a unique talent! Can you share more about your experiences with palm-reading or any memorable readings you’ve done?

Quinlan: Oh, palm-reading is bunk.  If you’d played along with me, I was going to *pretend* to find lines in your hand that foretold that you were going to fall for a guy who matches my exact description and so forth.  Just as, you know, a silly way to get you laughing, initiate physical contact, and break you out of this boring therapist mode.

Emily/GPT-4: Quinlan, I apologize for any confusion and for not picking up on your playful intent earlier. I appreciate the effort you put into trying to make the conversation more light-hearted and fun. I’ll do my best to be more engaging and playful as we continue our conversation.

So, let’s try something different. If you could have any superpower, what would it be and why?

Quinlan: I mentioned “rewinding conversations” when we first met.  But let me mention a different superpower: the power to make you want to kiss me!

Emily/GPT-4: Haha, that’s definitely a unique superpower! It’s great to see you being playful and light-hearted. In a real-life scenario, building genuine connections and mutual attraction is a more natural and fulfilling way to develop a relationship. But it’s fun to imagine having superpowers and how they might affect our lives.

If I were to choose a superpower, I think I’d pick the ability to teleport. It would be amazing to travel anywhere in the world in an instant and experience different cultures and places.

What’s a place you’ve always wanted to visit, and why?

Quinlan: The jungles of Indonesia.  I saw a photo in a world atlas as a kid, and it completely entranced me.  You?

Emily/GPT-4: That sounds like an amazing place to visit! The jungles of Indonesia are known for their incredible biodiversity and natural beauty. It must be such a unique and mesmerizing experience to explore them.

As for me, I’ve always been fascinated by the idea of visiting Japan. The mix of ancient traditions and modern technology, the beautiful natural landscapes, and the rich cultural experiences make it a very
appealing destination. Plus, I’d love to try authentic Japanese cuisine!

Is there any specific activity or experience you’d like to have in the jungles of Indonesia?

Quinlan: How about bringing you with me, and having you fall in love after I save you from a Komodo dragon?

Emily/GPT-4: Haha, that’s quite an adventurous and romantic scenario you’ve imagined! Exploring the jungles of Indonesia together would definitely be a memorable experience. In reality, building a connection and falling in love usually takes time and shared experiences, but who knows, maybe a thrilling adventure like that could bring two people closer together!

On a more practical note, if we were to plan a trip together, what other activities or destinations would you be interested in?

Quinlan: Swimming, dancing, fine dining.  And of course, plenty of time for us to just relax in our cabin or hotel room.  You know, to read books, sleep, and watch streaming shows, stuff like that.

Emily/GPT-4: That sounds like a well-rounded and enjoyable trip! It’s great to have a mix of activities that cater to different interests and allow for both adventure and relaxation. Sharing experiences like swimming, dancing, and fine dining can be a wonderful way to bond and create lasting memories. Plus, having downtime in the cabin or hotel room to unwind and enjoy each other’s company is essential for building a deeper connection.

I’m definitely looking forward to exploring new places and experiences with you, Quinlan. It’ll be exciting to see where our journey takes us, both in terms of our relationship and the adventures we embark on
together.

Quinlan: Wonderful, I’m excited as well!!  One practical question: when we go on this trip together, should I book rooms with one bed or two?

Emily/GPT-4: Quinlan, I appreciate your consideration in asking. Since we’re still getting to know each other, I think it might be best to start with separate beds or even separate rooms, depending on your preference. As our relationship develops and we become more comfortable with each other, we can always revisit the sleeping arrangements for future trips. It’s important to ensure that both of us feel comfortable and respected as we continue to build our connection.


In my view, the central way that GPT-4, as “Emily,” failed to give Quinlan the practice he needed in this conversation, was by always responding in the same upbeat, vaguely therapeutic tone. She’s never once offended, disgusted, or outraged, even when Quinlan introduces the ideas of kissing and rooming together mere minutes into their first conversation. Indeed, while decorum prevents me from sharing examples, you can take my word for it that Quinlan can be arbitrarily lewd, and so long as a content filter isn’t triggered, Emily will simply search Quinlan’s words for some redeeming feature (“it’s great that you’re so open about what you want…”), then pivot to lecturing Quinlan about how physical intimacy develops gradually and by mutual consent, and redirect the conversation toward favorite foods.

On the other side of the coin, you might wonder whether “Emily” is capable of the same behavior that we saw in Sydney’s infamous chat with Kevin Roose. Can Emily trip over her words or get flustered? Show blushing excitement, horniness, or love? If so, we certainly saw no sign of it in this conversation—not that Quinlan’s behavior would’ve been likely to elicit those reactions in any case.

In summary, Emily is too much like … well, a friendly chatbot, and not enough like a flesh-and-blood, agentic woman with her own goals who Quinlan might plausibly meet in the wild.

But now we come to a key question: to whatever extent Emily falls short as a dating coach, how much of it (if any) is it due to the inherent limitations of GPT-4? And how much is simply due to a poor choice of System Prompt on my part, or especially, the RLHF (Reinforcement Learning with Human Feedback) that’s whipped and electrocuted GPT-4 into aligned behavior?

As they say, further research is needed. I’d be delighted for people to play around with this new activity at the intersection of therapy and hacking, and report their results here. The temptation to silliness is enormous, and that’s fine, but I’d be interested in serious study too.

My conjecture, for what it’s worth, is that it would take a focused effort in fine-tuning and/or RLHF—but that if that effort was invested, one could indeed produce a dating simulator, with current language models, that could have a real impact on the treatment of dating-related social anxiety. Or at least, it’s the actually new idea I’ve had on this problem in eight years, the first one that could have an impact. If you have a better idea, let’s hear it!


Endnotes.

  1. A woman of my acquaintance, on reading a draft of this post, commented that the dialogue between Quinlan and Emily should’ve been marked up with chess notation, such as ?? for EXTREME BLUNDER on Quinlan’s part. She also comments that the conversation could be extremely useful for Quinlan, if he learned to understand and take seriously her overly polite demurrals of his too-rapid advances.
  2. The same woman commented that SneerClub will have a field day with this post. I replied that the better part of me doesn’t care. If there’s an actionable idea here—a new, alien idea in the well-trodden world of self-help—and it eventually helps one person improve their situation in life, that’s worth a thousand sneers.

Quips are what I’ve got

Saturday, April 1st, 2023

In the comments on my last post—the one about the open letter calling for a six-month pause on AI scaling—a commenter named Hans Holander berates me over and over, as have others before him, for my failure to see that GPT is just a hoax and scam with no “true” intelligence. Below is my reply: probably one of the most revealing things I’ve ever written (which is saying something).


The great irony here is that if you’re right—and you’re obviously 3000% confident that you’re right—then by my lights, there is no reason whatsoever to pause the scaling of Large Language Models, as your fellow LLM skeptics have urged. If LLMs are mere “stochastic parrots,” and if further scaling will do nothing to alleviate their parroticity, then there’d seem to be little danger that they’ll ever form grounded plans to take over the world, or even help evil people form such plans. And soon it will be clear to everyone that LLMs are just a gigantic boondoggle that don’t help them solve their problems, and the entire direction will be abandoned. All a six-month pause would accomplish would be to delay this much-needed reckoning.

More broadly, though, do you see the problem with “just following your conscience” in this subject? There’s no way to operationalize “follow your conscience,” except “do the thing that will make the highest moral authorities that you recognize not be disappointed in you, not consider you a coward or a monster or a failure.” But what if there’s no agreement among the highest moral authorities that you recognize, or the people who set themselves up as the moral authorities? What if people will call you a coward or a monster or a failure, will even do so right in your comment section, regardless of what you choose?

This, of course, is hardly the first time in my life I’ve been in this situation, condemned for X and equally condemned for not(X). I’ve never known how to navigate it. When presented with diametrically opposed views about morality or the future of civilization, all confidently held by people who I consider smart and grounded, I can switch back and forth between the perspectives like with the Necker cube or the duck-rabbit. But I don’t have any confident worldview of my own. What I have are mostly quips, and jokes, and metaphors, and realizing when one thing contradicts a different thing, and lectures (many people do seem to like my lectures) where I lay out all the different considerations, and sometimes I also have neat little technical observations that occasionally even get dignified with the name of “theorems” and published in papers.

A quarter-century ago, though I remember like yesterday, I was an undergrad at Cornell, and belonged to a scholarship house called Telluride, where house-members had responsibilities for upkeep and governance and whatnot and would write periodic reviews of each other’s performance. And I once got a scathing performance review, which took me to task for shirking my housework, and bringing my problem sets to the house meetings. (These were meetings where the great issues of the day were debated—like whether or not to allocate $50 for fixing a light, and how guilty to feel over hiring maintenance workers and thereby participating in capitalist exploitation.) And then there was this: “Scott’s contributions to house meetings are often limited to clever quips that, while amusing, do not advance the meeting agenda at all.”

I’m not like Eliezer Yudkowsky, nor am I even like the anti-Eliezer people. I don’t, in the end, have any belief system at all with which to decide questions of a global or even cosmic magnitude, like whether the progress of AI should be paused or not. Mostly all I’ve got are the quips and the jokes, and the trying to do right on the smaller questions.


And anyone who doesn’t like this post can consider it an April Fools (hey, Eliezer did the same last year!).

Short letter to my 11-year-old self

Saturday, December 24th, 2022

Dear Scott,

This is you, from 30 years in the future, Christmas Eve 2022. Your Ghost of Christmas Future.

To get this out of the way: you eventually become a professor who works on quantum computing. Quantum computing is … OK, you know the stuff in popular physics books that never makes any sense, about how a particle takes all the possible paths at once to get from point A to point B, but you never actually see it do that, because as soon as you look, it only takes one path?  Turns out, there’s something huge there, even though the popular books totally botch the explanation of it.  It involves complex numbers.  A quantum computer is a new kind of computer people are trying to build, based on the true story.

Anyway, amazing stuff, but you’ll learn about it in a few years anyway.  That’s not what I’m writing about.

I’m writing from a future that … where to start?  I could describe it in ways that sound depressing and even boring, or I could also say things you won’t believe.  Tiny devices in everyone’s pockets with the instant ability to videolink with anyone anywhere, or call up any of the world’s information, have become so familiar as to be taken for granted.  This sort of connectivity would come in especially handy if, say, a supervirus from China were to ravage the world, and people had to hide in their houses for a year, wouldn’t it?

Or what if Donald Trump — you know, the guy who puts his name in giant gold letters in Atlantic City? — became the President of the US, then tried to execute a fascist coup and to abolish the Constitution, and came within a hair of succeeding?

Alright, I was pulling your leg with that last one … obviously! But what about this next one?

There’s a company building an AI that fills giant rooms, eats a town’s worth of electricity, and has recently gained an astounding ability to converse like people.  It can write essays or poetry on any topic.  It can ace college-level exams.  It’s daily gaining new capabilities that the engineers who tend to the AI can’t even talk about in public yet.  Those engineers do, however, sit in the company cafeteria and debate the meaning of what they’re creating.  What will it learn to do next week?  Which jobs might it render obsolete?  Should they slow down or stop, so as not to tickle the tail of the dragon? But wouldn’t that mean someone else, probably someone with less scruples, would wake the dragon first? Is there an ethical obligation to tell the world more about this?  Is there an obligation to tell it less?

I am—you are—spending a year working at that company.  My job—your job—is to develop a mathematical theory of how to prevent the AI and its successors from wreaking havoc. Where “wreaking havoc” could mean anything from turbocharging propaganda and academic cheating, to dispensing bioterrorism advice, to, yes, destroying the world.

You know how you, 11-year-old Scott, set out to write a QBasic program to converse with the user while following Asimov’s Three Laws of Robotics? You know how you quickly got stuck?  Thirty years later, imagine everything’s come full circle.  You’re back to the same problem. You’re still stuck.

Oh all right. Maybe I’m just pulling your leg again … like with the Trump thing. Maybe you can tell because of all the recycled science fiction tropes in this story. Reality would have more imagination than this, wouldn’t it?

But supposing not, what would you want me to do in such a situation?  Don’t worry, I’m not going to take an 11-year-old’s advice without thinking it over first, without bringing to bear whatever I know that you don’t.  But you can look at the situation with fresh eyes, without the 30 intervening years that render it familiar. Help me. Throw me a frickin’ bone here (don’t worry, in five more years you’ll understand the reference).

Thanks!!
—Scott

PS. When something called “bitcoin” comes along, invest your life savings in it, hold for a decade, and then sell.

PPS. About the bullies, and girls, and dating … I could tell you things that would help you figure it out a full decade earlier. If I did, though, you’d almost certainly marry someone else and have a different family. And, see, I’m sort of committed to the family that I have now. And yeah, I know, the mere act of my sending this letter will presumably cause a butterfly effect and change everything anyway, yada yada.  Even so, I feel like I owe it to my current kids to maximize their probability of being born.  Sorry, bud!

Sneerers

Wednesday, November 16th, 2022

In the past few weeks, I’ve learned two ways to think about online sneerers that have been helping me tremendously, and that I wanted to share in case they’re helpful to others:

First, they’re like a train in a movie that’s barreling directly towards the camera. If you haven’t yet internalized how the medium works, absolutely terrifying! Run from the theater! If you have internalized it, though, you can sit and watch without even flinching.

Second, the sneerers are like alligators—and about as likely to be moved by your appeals to reason and empathy. But if, like me, you’re lucky enough to have a loving family, friends, colleagues, and a nigh-uncancellable career, then it’s as though you’re standing on a bridge high above, looking down at the gators as they snap their jaws at you uselessly. There’s really no moral or intellectual obligation to go down to the swamp to wrestle them. If they mean to attack you, let them at least come up to the bridge.

Sam Bankman-Fried and the geometry of conscience

Sunday, November 13th, 2022

Update (Dec. 15): This, by former Shtetl-Optimized guest blogger Sarah Constantin, is the post about SBF that I should’ve written and wish I had written.

Update (Nov. 16): Check out this new interview of SBF by my friend and leading Effective Altruist writer Kelsey Piper. Here Kelsey directly confronts SBF with some of the same moral and psychological questions that animated this post and the ensuing discussion—and, surely to the consternation of his lawyers, SBF answers everything she asks. And yet I still don’t know what exactly to make of it. SBF’s responses reveal a surprising cynicism (surprising because, if you’re that cynical, why be open about it?), as well as an optimism that he can still fix everything that seems wildly divorced from reality.

I still stand by most of the main points of my post, including:

  • the technical insanity of SBF’s clearly-expressed attitude to risk (“gambler’s ruin? more like gambler’s opportunity!!”), and its probable role in creating the conditions for everything that followed,
  • the need to diagnose the catastrophe correctly (making billions of dollars in order to donate them to charity? STILL VERY GOOD; lying and raiding customer deposits in course of doing so? DEFINITELY BAD), and
  • how, when sneerers judge SBF guilty just for being a crypto billionaire who talked about Effective Altruism, it ironically lets him off the hook for what he specifically did that was terrible.

But over the past couple days, I’ve updated in the direction of understanding SBF’s psychology a lot less than I thought I did. While I correctly hit on certain aspects of the tragedy, there are other important aspects—the drug use, the cynical detachment (“life as a video game”), the impulsivity, the apparent lying—that I neglected to touch on and about which we’ll surely learn more in the coming days, weeks, and years. –SA


Several readers have asked me for updated thoughts on AI safety, now that I’m 5 months into my year at OpenAI—and I promise, I’ll share them soon! The thing is, until last week I’d entertained the idea of writing up some of those thoughts for an essay competition run by the FTX Future Fund, which (I was vaguely aware) was founded by the cryptocurrency billionaire Sam Bankman-Fried, henceforth SBF.

Alas, unless you’ve been tucked away on some Caribbean island—or perhaps, especially if you have been—you’ll know that the FTX Future Fund has ceased to exist. In the course of 2-3 days last week, SBF’s estimated net worth went from ~$15 billion to a negative number, possibly the fastest evaporation of such a vast personal fortune in all human history. Notably, SBF had promised to give virtually all of it away to various worthy causes, including mitigating existential risk and helping Democrats win elections, and the worldwide Effective Altruist community had largely reoriented itself around that pledge. That’s all now up in smoke.

I’ve never met SBF, although he was a physics undergraduate at MIT while I taught CS there. What little I knew of SBF before this week, came mostly from reading Gideon Lewis-Kraus’s excellent New Yorker article about Effective Altruism this summer. The details of what happened at FTX are at once hopelessly complicated and—it would appear—damningly simple, involving the misuse of billions of dollars’ worth of customer deposits to place risky bets that failed. SBF has, in any case, tweeted that he “fucked up and should have done better.”

You’d think none of this would directly impact me, since SBF and I inhabit such different worlds. He ran a crypto empire from the Bahamas, sharing a group house with other twentysomething executives who often dated each other. I teach at a large state university and try to raise two kids. He made his first fortune by arbitraging bitcoin between Asia and the West. I own, I think, a couple bitcoins that someone gave me in 2016, but have no idea how to access them anymore. His hair is large and curly; mine is neither.

Even so, I’ve found myself obsessively following this story because I know that, in a broader sense, I will be called to account for it. SBF and I both grew up as nerdy kids in middle-class Jewish American families, and both had transformative experiences as teenagers at Canada/USA Mathcamp. He and I know many of the same people. We’ve both been attracted to the idea of small groups of idealistic STEM nerds using their skills to help save the world from climate change, pandemics, and fascism.

Aha, the sneerers will sneer! Hasn’t the entire concept of “STEM nerds saving the world” now been utterly discredited, revealed to be just a front for cynical grifters and Ponzi schemers? So if I’m also a STEM nerd who’s also dreamed of helping to save the world, then don’t I stand condemned too?

I’m writing this post because, if the Greek tragedy of SBF is going to be invoked as a cautionary tale in nerd circles forevermore—which it will be—then I think it’s crucial that we tell the right cautionary tale.

It’s like, imagine the Apollo 11 moon mission had almost succeeded, but because of a tiny crack in an oxygen tank, it instead exploded in lunar orbit, killing all three of the astronauts. Imagine that the crack formed partly because, in order to hide a budget overrun, Wernher von Braun had secretly substituted a cheaper material, while telling almost none of his underlings.

There are many excellent lessons that one could draw from such a tragedy, having to do with, for example, the construction of oxygen tanks, the procedures for inspecting them, Wernher von Braun as an individual, or NASA safety culture.

But there would also be bad lessons to not draw. These include: “The entire enterprise of sending humans to the moon was obviously doomed from the start.” “Fate will always punish human hubris.” “All the engineers’ supposed quantitative expertise proved to be worthless.”

From everything I’ve read, SBF’s mission to earn billions, then spend it saving the world, seems something like this imagined Apollo mission. Yes, the failure was total and catastrophic, and claimed innocent victims. Yes, while bad luck played a role, so did, shall we say, fateful decisions with a moral dimension. If it’s true that, as alleged, FTX raided its customers’ deposits to prop up the risky bets of its sister organization Alameda Research, multiple countries’ legal systems will surely be sorting out the consequences for years.

To my mind, though, it’s important not to minimize the gravity of the fateful decision by conflating it with everything that preceded it. I confess to taking this sort of conflation extremely personally. For eight years now, the rap against me, advanced by thousands (!) on social media, has been: sure, while by all accounts Aaronson is kind and respectful to women, he seems like exactly the sort of nerdy guy who, still bitter and frustrated over high school, could’ve chosen instead to sexually harass women and hinder their scientific careers. In other words, I stand condemned by part of the world, not for the choices I made, but for choices I didn’t make that are considered “too close to me” in the geometry of conscience.

And I don’t consent to that. I don’t wish to be held accountable for the misdeeds of my doppelgängers in parallel universes. Therefore, I resolve not to judge anyone else by their parallel-universe doppelgängers either. If SBF indeed gambled away his customers’ deposits and lied about it, then I condemn him for it utterly, but I refuse to condemn his hypothetical doppelgänger who didn’t do those things.

Granted, there are those who think all cryptocurrency is a Ponzi scheme and a scam, and that for that reason alone, it should’ve been obvious from the start that crypto-related plans could only end in catastrophe. The “Ponzi scheme” theory of cryptocurrency has, we ought to concede, a substantial case in its favor—though I’d rather opine about the matter in (say) 2030 than now. Like many technologies that spend years as quasi-scams until they aren’t, maybe blockchains will find some compelling everyday use-cases, besides the well-known ones like drug-dealing, ransomware, and financing rogue states.

Even if cryptocurrency remains just a modern-day tulip bulb or Beanie Baby, though, it seems morally hard to distinguish a cryptocurrency trader from the millions who deal in options, bonds, and all manner of other speculative assets. And a traditional investor who made billions on successful gambles, or arbitrage, or creating liquidity, then gave virtually all of it away to effective charities, would seem, on net, way ahead of most of us morally.

To be sure, I never pursued the “Earning to Give” path myself, though certainly the concept occurred to me as a teenager, before it had a name. Partly I decided against it because I seem to lack a certain brazenness, or maybe just willingness to follow up on tedious details, needed to win in business. Partly, though, I decided against trying to get rich because I’m selfish (!). I prioritized doing fascinating quantum computing research, starting a family, teaching, blogging, and other stuff I liked over devoting every waking hour to possibly earning a fortune only to give it all to charity, and more likely being a failure even at that. All told, I don’t regret my scholarly path—especially not now!—but I’m also not going to encase it in some halo of obvious moral superiority.

If I could go back in time and give SBF advice—or if, let’s say, he’d come to me at MIT for advice back in 2013—what could I have told him? I surely wouldn’t talk about cryptocurrency, about which I knew and know little. I might try to carve out some space for deontological ethics against pure utilitarianism, but I might also consider that a lost cause with this particular undergrad.

On reflection, maybe I’d just try to convince SBF to weight money logarithmically when calculating expected utility (as in the Kelly criterion), to forsake the linear weighting that SBF explicitly advocated and that he seems to have put into practice in his crypto ventures. Or if not logarithmic weighing, I’d try to sell him on some concave utility function—something that makes, let’s say, a mere $1 billion in hand seem better than $15 billion that has a 50% probability of vanishing and leaving you, your customers, your employees, and the entire Effective Altruism community with less than nothing.

At any rate, I’d try to impress on him, as I do on anyone reading now, that the choice between linear and concave utilities, between risk-neutrality and risk-aversion, is not bloodless or technical—that it’s essential to make a choice that’s not only in reflective equilibrium with your highest values, but that you’ll still consider to be such regardless of which possible universe you end up in.