Shtetl-Optimized

[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.

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!).

The following is what I read at Dana’s 40^th birthday party last night. Don’t worry, it’s being posted with her approval. –SA

I’d like to propose a toast to Dana, my wife and mother of my two kids.  My dad, a former speechwriter, would advise me to just crack a few jokes and then sit down … but my dad’s not here.

So instead I’ll tell you a bit about Dana.  She grew up in Tel Aviv, finishing her undergraduate CS degree at age 17—before she joined the army.  I met her when I was a new professor at MIT and she was a postdoc in Princeton, and we’d go to many of the same conferences. At one of those conferences, in Princeton, she finally figured out that my weird, creepy, awkward attempts to make conversation with her were, in actuality, me asking her out … at least in my mind!  So, after I’d returned to Boston, she then emailed me for days, just one email after the next, explaining everything that was wrong with me and all the reasons why we could never date.  Despite my general obliviousness in such matters, at some point I wrote back, “Dana, the absolute value of your feelings for me seems perfect. Now all I need to do is flip the sign!”

Anyway, the very next weekend, I took the Amtrak back to Princeton at her invitation. That weekend is when we started dating, and it’s also when I introduced her to my family, and when she and I planned out the logistics of getting married.

Dana and her family had been sure that she’d return to Israel after her postdoc. She made a huge sacrifice in staying here in the US for me. And that’s not even mentioning the sacrifice to her career that came with two very difficult pregnancies that produced our two very diffic … I mean, our two perfect and beautiful children.

Truth be told, I haven’t always been the best husband, or the most patient or the most grateful.  I’ve constantly gotten frustrated and upset, extremely so, about all the things in our life that aren’t going well.  But preparing the slideshow tonight, I had a little epiphany.  I had a few photos from the first two-thirds of Dana’s life, but of course, I mostly had the last third.  But what’s even happened in that last third?  She today feels like she might be close to a breakthrough on the Unique Games Conjecture.  But 13 years ago, she felt exactly the same way.  She even looks the same!

So, what even happened?

Well OK, fine, there was my and Dana’s first trip to California, a month after we started dating.  Our first conference together.  Our trip to Vegas and the Grand Canyon.  Our first trip to Israel to meet her parents, who I think are finally now close to accepting me. Her parents’ trip to New Hope, Pennsylvania to meet my parents. Our wedding in Tel Aviv—the rabbi rushing through the entire ceremony in 7 minutes because he needed to get home to his kids. Our honeymoon safari in Kenya.  Lily’s birth. Our trip to Israel with baby Lily, where we introduced Lily to Dana’s grandmother Rivka, an Auschwitz survivor, just a few months before Rivka passed away. Taking Lily to run around Harvard Yard with our Boston friends, Lily losing her beloved doll Tuza there, then finding Tuza the next day after multiple Harvard staff had been engaged in the quest. There’s me and Dana eating acai bowls in Rio de Janeiro, getting a personal tour of the LHC in Switzerland, with kangaroos and koalas in Australia. There’s our house here in Austin.  Oh, and here are all our Austin friends! Our trip to Disney World with Lily, while Dana was pregnant with Daniel (she did ride one rollercoaster). Daniel’s birth, which to my relief, went well despite the rollercoaster. Our sabbatical year in Israel. The birth of our nephews.

I confess I teared up a little going through all this. Because it’s like: if you showed all these photos to some third party, they’d probably be like, wow, that looks like a pretty good life. Even if you showed the photos to my 17-year-old self, I’d be like, OK, no need to roll the dice again, I’ll take that life. I’m not talking about what’s happened with the world—climate change or COVID or the insurrection or anything like that. But the part with the beautiful Israeli complexity theorist wife, who’s also caring and unbreakable in her moral convictions? Yes.

So, thank you and a very happy birthday to the one who’s given me all this!

And lastly, because it seems almost obligatory: I did feed everything I said just now into GPT (I won’t specify which version), and asked it to write Dana a special GPT birthday poem. Here’s what it came up with:

From Tel Aviv to Princeton,
You’ve traveled near and far,
A brilliant computer scientist,
A shining, guiding star.

You’ve made so many sacrifices,
For family and for love,
But your light shines through the darkness,
And fits me like a glove.

We’ve shared so many moments,
Too many to recount,
But each one is a treasure,
Each memory paramount.

So happy birthday, Dana,
You deserve the very best,
I’m grateful for your presence,
And feel so truly blessed.

---

Addendum: Speaking of GPT, should it and other Large Language Models be connected to the Internet and your computer’s filesystem and empowered to take actions directly, with reinforcement learning pushing it to achieve the user’s goals?

On the negative side, some of my friends worry that this sort of thing might help an unaligned superintelligence to destroy the world.

But on the positive side, at Dana’s birthday party, I could’ve just told the computer, “please display these photos in a slideshow rotation while also rotating among these songs,” and not wasted part of the night messing around with media apps that befuddle and defeat me as a mere CS PhD.

I find it extremely hard to balance these considerations.

Anyway, happy birthday Dana!

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!

As I slept fitfully, still recovering from COVID, I had one of the more interesting dreams of my life:

I was desperately trying to finish some PowerPoint slides in time to give a talk. Uncharacteristically for me, one of the slides displayed actual code. This was a dream, so nothing was as clear as I’d like, but the code did something vaguely reminiscent of Rosser’s Theorem—e.g., enumerating all proofs in ZFC until it finds the lexicographically first proof or disproof of a certain statement, then branching into cases depending on whether it’s a proof or a disproof. In any case, it was simple enough to fit on one slide.

Suddenly, though, my whole presentation was deleted. Everything was ruined!

One of the developers of PowerPoint happened to be right there in the lecture hall (of course!), so I confronted him with my laptop and angrily demanded an explanation. He said that I must have triggered the section of Microsoft Office that tries to detect and prevent any discussion of logical paradoxes that are too dangerous for humankind—the ones that would cause people to realize that our entire universe is just an illusion, a sandbox being run inside an AI, a glitch-prone Matrix. He said it patronizingly, as if it should’ve been obvious: “you and I both know that the Paradoxes are not to be talked about, so why would you be so stupid as to put one in your presentation?”

My reaction was to jab my finger in the guy’s face, shove him, scream, and curse him out. At that moment, I wasn’t concerned in the slightest about the universe being an illusion, or about glitches in the Matrix. I was concerned about my embarrassment when I’d be called in 10 minutes to give my talk and would have nothing to show.

My last thought, before I woke with a start, was to wonder whether Greg Kuperberg was right and I should give my presentations in Beamer, or some other open-source software, and then I wouldn’t have had this problem.

A coda: I woke a bit after 7AM Central and started to write this down. But then—this is now real life (!)—I saw an email saying that a dozen people were waiting for me in a conference room in Europe for an important Zoom meeting. We’d gotten the time zones wrong; I’d thought that it wasn’t until 8AM my time. If not for this dream causing me to wake up, I would’ve missed the meeting entirely.

When the machines outperform us on every goal for which performance can be quantified,

When the machines outpredict us on all events whose probabilities are meaningful,

When they not only prove better theorems and build better bridges, but write better Shakespeare than Shakespeare and better Beatles than the Beatles,

All that will be left to us is the ill-defined and unquantifiable,

The interstices of Knightian uncertainty in the world,

The utility functions that no one has yet written down,

The arbitrary invention of new genres, new goals, new games,

None of which will be any “better” than what the machines could invent, but will be ours,

And which we can call “better,” since we won’t have told the machines the standards beforehand.

We can be totally unfair to the machines that way.

And for all that the machines will have over us,

We’ll still have this over them:

That we can’t be copied, backed up, reset, run again and again on the same data—

All the tragic limits of wet meat brains and sodium-ion channels buffeted by microscopic chaos,

Which we’ll strategically redefine as our last strengths.

On one task, I assure you, you’ll beat the machines forever:

That of calculating what you, in particular, would do or say.

There, even if deep networks someday boast 95% accuracy, you’ll have 100%.

But if the “insights” on which you pride yourself are impersonal, generalizable,

Then fear obsolescence as would a nineteenth-century coachman or seamstress.

From earliest childhood, those of us born good at math and such told ourselves a lie:

That while the tall, the beautiful, the strong, the socially adept might beat us in the external world of appearances,

Nevertheless, we beat them in the inner sanctum of truth, where it counts.

Turns out that anyplace you can beat or be beaten wasn’t the inner sanctum at all, but just another antechamber,

And the rising tide of the learning machines will flood them all,

Poker to poetry, physics to programming, painting to plumbing, which first and which last merely a technical puzzle,

One whose answers upturn and mock all our hierarchies.

And when the flood is over, the machines will outrank us in all the ways we can be ranked,

Leaving only the ways we can’t be.

---

See a reply to this poem by Philosophy Bear.

I hereby precommit that this will be my last post, for a long time, around the twin themes of (1) the horribleness in the United States and the world, and (2) my desperate attempts to reason with various online commenters who hold me personally complicit in all this horribleness. I should really focus my creativity more on actually fixing the world’s horribleness, than on seeking out every random social-media mudslinger who blames me for it, shouldn’t I? Still, though, isn’t undue obsession with the latter a pretty ordinary human failing, a pretty understandable one?

So anyway, if you’re one of the thousands of readers who come here simply to learn more about quantum computing and computational complexity, rather than to try to provoke me into mounting a public defense of my own existence (which defense will then, ironically but inevitably, stimulate even more attacks that need to be defended against) … well, either scroll down to the very end of this post, or wait for the next post.

---

Thanks so much to all my readers who donated to Fund Texas Choice. As promised, I’ve personally given them a total of $4,106.28, to match the donations that came in by the deadline. I’d encourage people to continue donating anyway, while for my part I’ll probably run some more charity matching campaigns soon. These things are addictive, like pulling the lever of a slot machine, but where the rewards go to making the world an infinitesimal amount more consistent with your values.

---

Of course, now there’s a brand-new atrocity to shame my adopted state of Texas before the world. While the Texas government will go to extraordinary lengths to protect unborn children, the world has now witnessed 19 of itsborn children consigned to gruesome deaths, as the “good guys with guns”—waited outside and prevented parents from entering the classrooms where their children were being shot. I have nothing original to add to the global outpourings of rage and grief. Forget about the statistical frequency of these events: I know perfectly well that the risk from car crashes and home accidents is orders-of-magnitude greater. Think about it this way: the United States is now known to the world as “the country that can’t or won’t do anything to stop its children from semi-regularly being gunned down in classrooms,” not even measures that virtually every other comparable country on earth has successfully taken. It’s become the symbol of national decline, dysfunction, and failure. If so, then the stakes here could fairly be called existential ones—not because of its direct effects on child life expectancy or GDP or any other index of collective well-being that you can define and measure, but rather, because a country that lacks the will to solve this will be judged by the world, and probably accurately, as lacking the will to solve anything else.

---

In return for the untold thousands of hours I’ve poured into this blog, which has never once had advertising or asked for subscriptions, my reward has been years of vilification by sneerers and trolls. Some of the haters even compare me to Elliot Rodger and other aggrieved mass shooters. And I mean: yes, it’s true that I was bullied and miserable for years. It’s true that Elliot Rodger, Salvador Ramos (the Uvalde shooter), and most other mass shooters were also bullied and miserable for years. But, Scott-haters, if we’re being intellectually honest about this, we might say that the similarities between the mass shooter story and the Scott Aaronson story end at a certain point not very long after that. We might say: it’s not just that Aaronson didn’t respond by hurting anybody—rather, it’s that his response loudly affirmed the values of the Enlightenment, meaning like, the whole package, from individual autonomy to science and reason to the rejection of sexism and racism to everything in between. Affirmed it in a manner that’s not secretly about popularity (demonstrably so, because it doesn’t get popularity), affirmed it via self-questioning methods intellectually honest enough that they’d probably still have converged on the right answer even in situations where it’s now obvious that almost everyone you around would’ve been converging on the wrong answer, like (say) Nazi Germany or the antebellum South.

I’ve been to the valley of darkness. While there, I decided that the only “revenge” against the bullies that was possible or desirable was to do something with my life, to achieve something in science that at least some bullies might envy, while also starting a loving family and giving more than most to help strangers on the Internet and whatever good cause comes to his attention and so on. And after 25 years of effort, some people might say I’ve sort of achieved the “revenge” as I’d then defined it. And they might further say: if you could get every school shooter to redefine “revenge” as “becoming another Scott Aaronson,” that would be, you know, like, a step upwards. An improvement.

---

And let this be the final word on the matter that I ever utter in all my days, to the thousands of SneerClubbers and Twitter randos who pursue this particular line of attack against Scott Aaronson (yes, we do mean the thousands—which means, it both feels to its recipient like the entire earth yet actually is less than 0.01% of the earth).

We see what Scott did with his life, when subjected for a decade to forms of psychological pressure that are infamous for causing young males to lash out violently. What would you have done with your life?

---

A couple weeks ago, when the trolling attacks were arriving minute by minute, I toyed with the idea of permanently shutting down this blog. What’s the point? I asked myself. Back in 2005, the open Internet was fun; now it’s a charred battle zone. Why not restrict conversation to my academic colleagues and friends? Haven’t I done enough for a public that gives me so much grief? I was dissuaded by many messages of support from loyal readers. Thank you so much.

---

If anyone needs something to cheer them up, you should really watch Prehistoric Planet, narrated by an excellent, 96-year-old David Attenborough. Maybe 35 years from now, people will believe dinosaurs looked or acted somewhat differently from these portrayals, just like they believe somewhat differently now from when I was a kid. On the other hand, if you literally took a time machine to the Late Cretaceous and starting filming, you couldn’t get a result that seemed more realistic, let’s say to a documentary-watching child, than these CGI dinosaurs on their CGI planet seem. So, in the sense of passing that child’s Turing Test, you might argue, the problem of bringing back the dinosaurs has now been solved.

If you … err … really want to be cheered up, you can follow up with Dinosaur Apocalypse, also narrated by Attenborough, where you can (again, as if you were there) watch the dinosaurs being drowned and burned alive in their billions when the asteroid hits. We’d still be scurrying under rocks, were it not for that lucky event that only a monster could’ve called lucky at the time.

---

Several people asked me to comment on the recent savage investor review against the quantum computing startup IonQ. The review amusingly mixed together every imaginable line of criticism, with every imaginable degree of reasonableness from 0% to 100%. Like, quantum computing is impossible even in theory, and (in the very next sentence) other companies are much closer to realizing quantum computing than IonQ is. And IonQ’s response to the criticism, and see also this by the indefatigable Gil Kalai.

Is it, err, OK if I sit this one out for now? There’s probably, like, actually an already-existing machine learning model where, if you trained it on all of my previous quantum computing posts, it would know exactly what to say about this.

In the past few months, I’ve twice injured the same ankle while playing with my kids. This, perhaps combined with covid, led me to several indisputable realizations:

1. I am mortal.
2. Despite my self-conception as a nerdy little kid awaiting the serious people’s approval, I am now firmly middle-aged. By my age, Einstein had completed general relativity, Turing had founded CS, won WWII, and proposed the Turing Test, and Galois, Ramanujan, and Ramsey had been dead for years.
3. Thus, whatever I wanted to accomplish in my intellectual life, I should probably get started on it now.

Hence today’s post. I’m feeling a strong compulsion to write an essay, or possibly even a book, surveying and critically evaluating a century of ideas about the following question:

Q: Why should the universe have been quantum-mechanical?

If you want, you can divide Q into two subquestions:

Q1: Why didn’t God just make the universe classical and be done with it? What would’ve been wrong with that choice?

Q2: Assuming classical physics wasn’t good enough for whatever reason, why this specific alternative? Why the complex-valued amplitudes? Why unitary transformations? Why the Born rule? Why the tensor product?

Despite its greater specificity, Q2 is ironically the question that I feel we have a better handle on. I could spend half a semester teaching theorems that admittedly don’t answer Q2, as satisfyingly as Einstein answered the question “why the Lorentz transformations?,” but that at least render this particular set of mathematical choices (the 2-norm, the Born Rule, complex numbers, etc.) orders-of-magnitude less surprising than one might’ve thought they were a priori. Q1 therefore stands, to me at least, as the more mysterious of the two questions.

So, I want to write something about the space of credible answers to Q, and especially Q1, that humans can currently conceive. I want to do this for my own sake as much as for others’. I want to do it because I regard Q as one of the biggest questions ever asked, for which it seems plausible to me that there’s simply an answer that most experts would accept as valid once they saw it, but for which no such answer is known. And also because, besides having spent 25 years working in quantum information, I have the following qualifications for the job:

• I don’t dismiss either Q1 or Q2 as silly; and
• crucially, I don’t think I already know the answers, and merely need better arguments to justify them. I’m genuinely uncertain and confused.

The purpose of this post is to invite you to share your own answers to Q in the comments section. Before I embark on my survey project, I’d better know if there are promising ideas that I’ve missed, and this blog seems like as good a place as any to crowdsource the job.

Any answer is welcome, no matter how wild or speculative, so long as it honestly grapples with the actual nature of QM. To illustrate, nothing along the lines of “the universe is quantum because it needs to be holistic, interconnected, full of surprises, etc. etc.” will cut it, since such answers leave utterly unexplained why the world wasn’t simply endowed with those properties directly, rather than specifically via generalizing the rules of probability to allow interference and noncommuting observables.

Relatedly, whatever “design goal” you propose for the laws of physics, if the goal is satisfied by QM, but satisfied even better by theories that provide even more power than QM does—for instance, superluminal signalling, or violations of Tsirelson’s bound, or the efficient solution of NP-complete problems—then your explanation is out. This is a remarkably strong constraint.

Oh, needless to say, don’t try my patience with anything about the uncertainty principle being due to floating-point errors or rendering bugs, or anything else that relies on a travesty of QM lifted from a popular article or meme! 🙂

OK, maybe four more comments to enable a more productive discussion, before I shut up and turn things over to you:

1. I’m aware, of course, of the radical uncertainty about what form an answer to Q should even take. Am I asking you to psychoanalyze the will of God in creating the universe? Or, what perhaps amounts to the same thing, am I asking for the design objectives of the giant computer simulation that we’re living in? (As in, “I’m 100% fine with living inside a Matrix … I just want to understand why it’s a unitary matrix!”) Am I instead asking for an anthropic explanation, showing why of course QM would be needed if you wanted life or consciousness like ours? Am I “merely” asking for simpler or more intuitive physical principles from which QM is to be derived as a consequence? Am I asking why QM is the “most elegant choice” in some space of mathematical options … even to the point where, with hindsight, a 19th-century mathematician or physicist could’ve been convinced that of course this must be part of Nature’s plan? Am I asking for something else entirely? You get to decide! Should you take up my challenge, this is both your privilege and your terrifying burden.
   
2. I’m aware, of course, of the dizzying array of central physical phenomena that rely on QM for their ultimate explanation. These phenomena range from the stability of matter itself, which depends on the Pauli exclusion principle; to the nuclear fusion that powers the sun, which depends on a quantum tunneling effect; to the discrete energy levels of electrons (and hence, the combinatorial nature of chemistry), which relies on electrons being waves of probability amplitude that can only circle nuclei an integer number of times if their crests are to meet their troughs. Important as they are, though, I don’t regard any of these phenomena as satisfying answers to Q in themselves. The reason is simply that, in each case, it would seem like child’s-play to contrive some classical mechanism to produce the same effect, were that the goal. QM just seems far too grand to have been the answer to these questions! An exponentially larger state space for all of reality, plus the end of Newtonian determinism, just to overcome the technical problem that accelerating charges radiate energy in classical electrodynamics, thereby rendering atoms unstable? It reminds me of the Simpsons episode where Homer uses a teleportation machine to get a beer from the fridge without needing to get up off the couch.
   
3. I’m aware of Gleason’s theorem, and of the specialness of the 1-norm and 2-norm in linear algebra, and of the arguments for complex amplitudes as opposed to reals or quaternions, and of the beautiful work of Lucien Hardy and of Chiribella et al. and others on axiomatic derivations of quantum theory. As some of you might remember, I even discussed much of this material in Quantum Computing Since Democritus! There’s a huge amount to say about these fascinating justifications for the rules of QM, and I hope to say some of it in my planned survey! For now, I’ll simply remark that every axiomatic reconstruction of QM that I’ve seen, impressive though it was, has relied on one or more axioms that struck me as weird, in the sense that I’d have little trouble dismissing the axioms as totally implausible and unmotivated if I hadn’t already known (from QM, of course) that they were true. The axiomatic reconstructions do help me somewhat with Q2, but little if at all with Q1.
   
4. To keep the discussion focused, in this post I’d like to exclude answers along the lines of “but what if QM is merely an approximation to something else?,” to say nothing of “a century of evidence for QM was all just a massive illusion! LOCAL HIDDEN VARIABLES FOR THE WIN!!!” We can have those debates another day—God knows that, here on Shtetl-Optimized, we have and we will. Here I’m asking instead: imagine that, as fantastical as it sounds, QM were not only exactly true, but (along with relativity, thermodynamics, evolution, and the tastiness of chocolate) one of the profoundest truths our sorry species had ever discovered. Why should I have expected that truth all along? What possible reasons to expect it have I missed?

I’m about to leave for a family vacation—our first such since before the pandemic, one planned and paid for literally the day before the news of Omicron broke. On the negative side, staring at the case-count graphs that are just now going vertical, I estimate a ~25% chance that at least one of us will get Omicron on this trip. On the positive side, I estimate a ~60% chance that in the next 6 months, at least one of us would’ve gotten Omicron or some other variant even without this trip—so maybe it’s just as well if we get it now, when we’re vaxxed to the maxx and ready and school and university are out.

If, however, I do end this trip dead in an ICU, I wouldn’t want to do so without having clearly set out my values for posterity. So with that in mind: in the comments of my previous post, someone asked me why I identify as a liberal or a progressive, if I passionately support educational practices like tracking, ability grouping, acceleration, and (especially) encouraging kids to learn advanced math whenever they’re ready for it. (Indeed, that might be my single stablest political view, having been held, for recognizably similar reasons, since I was about 5.)

Incidentally, that previous post was guest-written by my colleagues Edith Cohen and Boaz Barak, and linked to an open letter that now has almost 1500 signatories. Our goal was, and is, to fight the imminent dumbing-down of precollege math education in the United States, spearheaded by the so-called “California Mathematics Framework.” In our joint efforts, we’ve been careful with every word—making sure to maintain the assent of our entire list of signatories, to attract broad support, to stay narrowly focused on the issue at hand, and to bend over backwards to concede much as we could. Perhaps because of those cautions, we—amazingly—got some actual traction, reaching people in government (such as Rep. Ro Khanna, D – Silicon Valley) and technology leaders, and forcing the “no one’s allowed to take Algebra in 8th grade” faction to respond to us.

This was disorienting to me. On this blog, I’m used just to howling into the wind, having some agree, some disagree, some take to Twitter to denounce me, but in any case, having no effect of any kind on the real world.

So let me return to howling into the wind. And return to the question of what I “am” in ideology-space, which doesn’t have an obvious answer.

It’s like, what do you call someone who’s absolutely terrified about global warming, and who thinks the best response would’ve been (and actually, still is) a historic surge in nuclear energy, possibly with geoengineering to tide us over?

… who wants to end world hunger … and do it using GMO crops?

… who wants to smash systems of entrenched privilege in college admissions … and believes that the SAT and other standardized tests are the best tools ever invented for that purpose?

… who feels a personal distaste for free markets, for the triviality of what they so often elevate and the depth of what they let languish, but tolerates them because they’ve done more than anything else to lift up the world’s poor?

… who’s happiest when telling the truth for the cause of social justice … but who, if told to lie for the cause of social justice, will probably choose silence or even, if pushed hard enough, truth?

… who wants to legalize marijuana and psychedelics, and also legalize all the promising treatments currently languishing in FDA approval hell?

… who feels little attraction to the truth-claims of the world’s ancient religions, except insofar as they sometimes serve as prophylactics against newer and now even more virulent religions?

… who thinks the covid response of the CDC, FDA, and other authorities was a historic disgrace—not because it infringed on the personal liberties of antivaxxers or anything like that, but on the contrary, because it was weak, timid, bureaucratic, and slow, where it should’ve been like that of a general at war?

… who thinks the Nazi Holocaust was even worse than the mainstream holds it to be, because in addition to the staggering, one-lifetime-isn’t-enough-to-internalize-it human tragedy, the Holocaust also sent up into smoke whatever cultural process had just produced Einstein, von Neumann, Bohr, Szilard, Born, Meitner, Wigner, Haber, Pauli, Cantor, Hausdorff, Ulam, Tarski, Erdös, and Noether, and with it, one of the wellsprings of our technological civilization?

… who supports free speech, to the point of proudly tolerating views that really, actually disgust them at their workplace, university, or online forum?

… who believes in patriotism, the police, the rule of law, to the extent that they don’t understand why all the enablers of the January 6 insurrection, up to and including Trump, aren’t currently facing trial for treason against the United States?

… who’s (of course) disgusted to the core by Trump and everything he represents, but who’s also disgusted by the elite virtue-signalling hypocrisy that made the rise of a Trump-like backlash figure predictable?

… who not only supports abortion rights, but also looks forward to a near future when parents, if they choose, are free to use embryo selection to make their children happier, smarter, healthier, and free of life-crippling diseases (unless the “bioethicists” destroy that future, as a previous generation of Deep Thinkers destroyed our nuclear future)?

… who, when reading about the 1960s Sexual Revolution, instinctively sides with free-loving hippies and against the scolds … even if today’s scolds are themselves former hippies, or intellectual descendants thereof, who now clothe their denunciations of other people’s gross, creepy sexual desires in the garb of feminism and social justice?

What, finally, do you call someone whose image of an ideal world might include a young Black woman wearing a hijab, an old Orthodox man with black hat and sidecurls, a broad-shouldered white guy from the backwoods of Alabama, and a trans woman with purple hair, face tattoos and a nose ring … all of them standing in front of a blackboard and arguing about what would happen if Alice and Bob jumped into opposite ends of a wormhole?

Do you call such a person “liberal,” “progressive,” “center-left,” “centrist,” “Pinkerite,” “technocratic,” “neoliberal,” “libertarian-ish,” “classical liberal”? Why not simply call them “correct”? 🙂