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!).

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!

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.

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.

Yesterday I attended a lecture by George Mason University economist Bryan Caplan, who’s currently visiting UT Austin, about his new book entitled Don’t Be a Feminist. (See also here for previous back-and-forth between me and Bryan about his book.) A few remarks:

(1) Maybe surprisingly, there were no protesters storming the lectern, no security detail, not even a single rotten vegetable thrown. About 30 people showed up, majority men but women too. They listened politely and asked polite questions afterward. One feminist civilly challenged Bryan during the Q&A about his gender pay gap statistics.

(2) How is it that I got denounced by half the planet for saying once, in a blog comment, that I agreed with 97% of feminism but had concerns with one particular way it was operationalized, whereas Bryan seems to be … not denounced in the slightest for publishing a book and going on a lecture tour about how he rejects feminism in its entirety as angry and self-pitying in addition to factually false? Who can explain this to me?

(3) For purposes of his argument, Bryan defines feminism as “the view that women are generally treated less fairly than men,” rather than (say) “the view that men and women ought to be treated equally,” or “the radical belief that women are people,” or other formulations that Bryan considers too obvious to debate. He then rebuts feminism as he’s defined it, by taking the audience on a horror tour of all the ways society treats men less fairly than women (expectations of doing dirty and dangerous work, divorce law, military drafts as in Ukraine right now, …), as well as potentially benign explanations for apparent unfairness toward women, to argue that it’s at least debatable which sex gets the rawer deal on average.

During the Q&A, I raised what I thought was the central objection to Bryan’s relatively narrow definition of feminism. Namely that, by the standards of 150 years ago, Bryan is obviously a feminist, and so am I, and so is everyone in the room. (Whereupon a right-wing business school professor interjected: “please don’t make assumptions about me!”)

I explained that this is why I call myself a feminist, despite agreeing with many of Bryan’s substantive points: because I want no one to imagine for a nanosecond that, if I had the power, I’d take gender relations back to how they were generations ago.

Bryan replied that >60% of Americans call themselves non-feminists in surveys. So, he asked me rhetorically, do all those Americans secretly yearn to take us back to the 19th century? Such a position, he said, seemed so absurdly uncharitable as not to be worth responding to.

Reflecting about it on my walk home, I realized: actually, give or take the exact percentages, this is precisely the progressive thesis. I.e., that just like at least a solid minority of Germans turned out to be totally fine with Nazism, however much they might’ve denied it beforehand, so too at least a solid minority of Americans would be fine with—if not ecstatic about—The Handmaid’s Tale made real. Indeed, they’d add, it’s only vociferous progressive activism that stands between us and that dystopia.

And if anyone were tempted to doubt this, progressives might point to the election of Donald Trump, the failed insurrection to maintain his power, and the repeal of Roe as proof enough to last for a quadrillion years.

Bryan would probably reply: why even waste time engaging with such a hysterical position? To me, though, the hysterical position sadly has more than a grain of truth to it. I wish we lived in a world where there was no point in calling oneself a pro-democracy anti-racist feminist and a hundred other banal and obvious things. I just don’t think that we do.

Update (July 13): I was honored to read this post by my friend Boaz Barak.

Update (July 14): By now, comments on this post allegedly from four CS professors — namely, Josh Alman, Aloni Cohen, Rana Hanocka, and Anna Farzindar — as well as from the graduate student “BA,” have been unmasked as from impersonator(s).

I’ve been the target of a motivated attack-troll (or multiple trolls, but I now believe just one) who knows about the CS community. This might be the single weirdest thing that’s happened to me in 17 years of blogging, surpassing even the legendary Ricoh printer episode of 2007. It obviously underscores the need for a new, stricter comment policy, which is what this whole post was about.

---

Yesterday and today, both my work and my enjoyment of the James Webb images were interrupted by an anonymous troll, who used the Shtetl-Optimized comment section to heap libelous abuse on me—derailing an anodyne quantum computing discussion to opine at length about how I’m a disgusting creep who surely, probably, maybe has lewd thoughts about his female students. Unwisely or not, I allowed it all to appear, and replied to all of it. I had a few reasons: I wanted to prove that I’m now strong enough to withstand bullying that might once have driven me to suicide. I wanted, frankly, many readers to come to my defense (thanks to those who did!). I at least wanted readers to see firsthand what I now regularly deal with: the emotional price of maintaining this blog. Most of all, I wanted my feminist, social-justice-supporting readers to either explicitly endorse or (hopefully) explicitly repudiate the unambiguous harassment that was now being gleefully committed in their name.

Then, though, the same commenter upped the ante further, by heaping misogynistic abuse on my wife Dana—while still, ludicrously and incongruously, cloaking themselves in the rhetoric of social justice. Yes: apparently the woke, feminist thing to do is now to rate female computer scientists on their looks.

Let me be blunt: I cannot continue to write Shtetl-Optimized while dealing with regular harassment of me and my family. At the same time, I’m also determined not to “surrender to the terrorists.” So, I’m weighing the following options:

• Close comments except to commenters who provide a real identity—e.g., a full real name, a matching email address, a website.
• Move to Substack, and then allow only commenters who’ve signed up.
• Hire someone to pre-screen comments for me, and delete ones that are abusive or harassing (to me or others) before I even see them. (Any volunteers??)
• Make the comment sections for readers only, eliminating any expectation that I’ll participate.

One thing that’s clear is that the status quo will not continue. I can’t “just delete” harassing or abusive comments, because the trolls have gotten too good at triggering me, and they will continue to weaponize my openness and my ethic of responding to all possible arguments against me.

So, regular readers: what do you prefer?

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.

So, I’d been planning a fun post for today about the DALL-E image-generating AI model, and in particular, a brief new preprint about DALL-E’s capabilities by Ernest Davis, Gary Marcus, and myself. We wrote this preprint as a sort of “adversarial collaboration”: Ernie and Gary started out deeply skeptical of DALL-E, while I was impressed bordering on awestruck. I was pleasantly surprised that we nevertheless managed to produce a text that we all agreed on.

Not for the first time, though, world events have derailed my plans. The most important part of today’s post is this:

For the next week, I, Scott Aaronson, will personally match all reader donations to Fund Texas Choice—a group that helps women in Texas travel to out-of-state health clinics, for reasons that are neither your business nor mine—up to a total of $5,000.

To show my seriousness, I’ve already donated $1,000. Just let me know how much you’ve donated in the comments section!

The first reason for this donation drive is that, perhaps like many of you, I stayed up hours last night reading Alito’s leaked decision in a state of abject terror. I saw how the logic of the decision, consistent and impeccable on its own terms, is one by which the Supreme Court’s five theocrats could now proceed to unravel the whole of modernity. I saw how this court, unchecked by our broken democratic system, can now permanently enshrine the will of a radical minority, perhaps unless and until the United States is plunged into a second Civil War.

Anyway, that’s the first reason for the donation drive. The second reason is to thank Shtetl-Optimized‘s commenters for their … err, consistently generous and thought-provoking contributions. Let’s take, for example, this comment on last week’s admittedly rather silly post, from an anonymous individual who calls herself “Feminist Bitch,” and who was enraged that it took me a full day to process one of the great political cataclysms of our lifetimes and publicly react to it:

OF COURSE. Not a word about Roe v. Wade being overturned, but we get a pseudo-intellectual rationalist-tier rant about whatever’s bumping around Scott’s mind right now. Women’s most basic reproductive rights are being curtailed AS WE SPEAK and not a peep from Scott, eh? Even though in our state (Texas) there are already laws ON THE BOOKS that will criminalize abortion as soon as the alt-right fascists in our Supreme Court give the go-ahead. If you cared one lick about your female students and colleagues, Scott, you’d be posting about the Supreme Court and helping feminist causes, not posting your “memes.” But we all know Scott doesn’t give a shit about women. He’d rather stand up for creepy nerdbros and their right to harass women than women’s right to control their own fucking bodies. Typical Scott.

If you want, you can read all of Feminist Bitch’s further thoughts about my failings, with my every attempt to explain and justify myself met with further contempt. No doubt my well-meaning friends of both sexes would counsel me to ignore her. Alas, from my infamous ordeal of late 2014, I know that with her every word, Feminist Bitch speaks for thousands, and the knowledge eats at me day and night.

It’s often said that “the right looks for converts, while the left looks only for heretics.” Has Feminist Bitch ever stopped to think about how our civilization reached its current terrifying predicament—how Trump won in 2016, how the Supreme Court got packed with extremists who represent a mere 25% of the country, how Putin and Erdogan and Orban and Bolsonaro and all the rest consolidated their power? Does she think it happened because wokeists like herself reached out too much, made too many inroads among fellow citizens who share some but not all of their values? Would Feminist Bitch say that, if the Democrats want to capitalize on the coming tsunami of outrage about the death of Roe and the shameless lies that enabled it, if they want to sweep to victory in the midterms and enshrine abortion rights into federal law … then their best strategy would be to double down on their condemnations of gross, creepy, smelly, white male nerdbros who all the girls, like, totally hate?

(until, thank God, some of them don’t)

I continue to think that the majority of my readers, of all races and sexes and backgrounds, are reasonable and sane. I continue to think the majority of you recoil against hatred and dehumanization of anyone—whether that means women seeking abortions, gays, trans folks, or (gasp!) even white male techbros. In this sad twilight for the United States and for liberal democracy around the world, we the reasonable and sane, we the fans of the Enlightenment, we the Party of Psychological Complexity, have decades of work cut out for us. For now I’ll simply say: I don’t hear from you nearly enough in the comments.

Scott’s foreword

One week ago, E. O. Wilson—the legendary naturalist and conservationist, and man who was universally acknowledged to know more about ants than anyone else in human history—passed away at age 92. A mere three days later, Scientific American—or more precisely, the zombie clickbait rag that now flaunts that name—published a shameful hit-piece, smearing Wilson for his “racist ideas” without, incredibly, so much as a single quote from Wilson, or any other attempt to substantiate its libel (see also this response by Jerry Coyne). SciAm‘s Pravda-like attack included the following extraordinary sentence, which I thought worthy of Alan Sokal’s Social Text hoax:

The so-called normal distribution of statistics assumes that there are default humans who serve as the standard that the rest of us can be accurately measured against.

There are intellectually honest people who don’t know what the normal distribution is. There are no intellectually honest people who, not knowing what it is, figure that it must be something racist.

On Twitter, Laura Helmuth, the editor-in-chief now running SciAm into the ground, described her magazine’s calumny against Wilson as “insightful” (the replies, including from Richard Dawkins, are fun to read). I suppose it was as “insightful” as SciAm‘s disgraceful attack last year on Eric Lander, President Biden’s ultra-competent science advisor and a leader in the war on COVID, for … being a white male, which appears to have been E. O. Wilson’s crime as well. (Think I must be misrepresenting the “critique” of Lander? Read it!)

Anyway, in response to Scientific American‘s libel of Wilson, I wrote on my Facebook that I’ll no longer agree to write for or be interviewed by them (you can read my old stuff free of charge here or here), unless and until there’s a complete change of editorial direction. I encourage all other scientists to commit likewise, thereby making it common knowledge that the entity that now calls itself “Scientific American” bears the same relation to the legendary home of Martin Gardner as does a corpse to a living being. Fortunately, there are high-quality online venues (e.g., Quanta) that partly fill the role that Scientific American abdicated.

After reading my Facebook post, my friend Ashutosh Jogalekar was inspired to post an essay of his own. Ashutosh used to write regularly for Scientific American, until he was fired seven years ago over a column in which he advocated acknowledging Richard Feynman’s flaws, including his arrogance and casual sexism, but also understanding those flaws within the context of Feynman’s whole life, including the tragic death of his first wife Arlene. (Yes, that was really it! Read the piece!) Below, I’m sharing Ashutosh’s moving essay about E. O. Wilson with Ashutosh’s very generous permission. —Scott Aaronson

---

Guest Post by Ashutosh Jogalekar

As some know, I was “fired” from Scientific American in 2014 for three “controversial” posts (among 200 that I had written for the magazine). When I parted from the magazine I chalked up my departure to an unfortunate misunderstanding more than anything else. I still respected some of the writers at the publication, and while I wore my separation as a badge of honor and in retrospect realized its liberating utility in enabling me to greatly expand my topical range, I occasionally still felt bad and wished things had gone differently.

No more. Now the magazine has done me a great favor by allowing me to wipe the slate of my conscience clean. What happened seven years ago was not just a misunderstanding but clearly one of many first warning signs of a calamitous slide into a decidedly unscientific, irrational and ideology-ridden universe of woke extremism. Its logical culmination two days ago was an absolutely shameless, confused, fact-free and purely ideological hit job on someone who wasn’t just a great childhood hero of mine but a leading light of science, literary achievement, humanism and biodiversity. While Ed (E. O.) Wilson’s memory was barely getting cemented only days after his death, the magazine published an op-ed calling him a racist, a hit job endorsed and cited by the editor-in-chief as “insightful”. One of the first things I did after reading the piece was buy a few Wilson books that weren’t part of my collection.

Ed Wilson was one of the gentlest, most eloquent, most brilliant and most determined advocates for both human and natural preservation you could find. Under Southern charm lay hidden unyielding doggedness and immense stamina combined with a missionary zeal to communicate the wonders of science to both his fellow biologists and the general public. His autobiography, “Naturalist”, is perhaps the finest, most literary statement of the scientific life I have read; it was one of a half dozen books that completely transported me when I read it in college. In book after book of wide-ranging intellectual treats threading through a stunning diversity of disciplines, he sent out clarion calls for saving the planet, for enabling dialogue between the natural and the social sciences, for understanding each other better. In the face of unprecedented challenges to our fragile environment and continued barriers to interdisciplinary communication, this is work that likely will make him go down in history as one of the most important human beings who ever lived, easily of the same caliber and achievement as John Muir or Thoreau. Even in terms of achievement strictly defined by accolades – the National Medal of Science, the Crafoord Prize which recognizes fields excluded by the Nobel Prize, and not just one but two Pulitzer Prizes – few scientists from any field in the 20th century can hold a candle to Ed Wilson. My friend Richard Rhodes who knew Wilson for decades as a close and much-admired friend said that there wasn’t a racist bone in his body; Dick should know since he just came out with a first-rate biography of Wilson weeks before his passing.

The writer who wrote that train wreck is a professor of nursing at UCSF named Monica McLemore. That itself is a frightening fact and should tell everyone how much ignorance has spread itself in our highest institutions. She not only maligned and completely misrepresented Wilson but did not say a word about his decades-long, heroic effort to preserve the planet and our relationship with it; it was clear that she had little acquaintance with Wilson’s words since she did not cite any. It’s also worth noting the gaping moral blindness in her article which completely misses the most moral thing Wilson did – spend decades advocating for saving our planet and averting a catastrophe of extinction, climate change and divisiveness – and instead focuses completely on his non-existent immorality. This is a pattern that is consistently found among those urging “social justice” or “equity” or whatever else: somehow they seem to spend all their time talking about fictional, imagined immorality while missing the real, flesh-and-bones morality that is often the basis of someone’s entire life’s work.

In the end, the simple fact is that McLemore didn’t care about any of this. She didn’t care because she had a political agenda and the facts did not matter to her, even facts as basic as the definition of the normal distribution in statistics. For her, Wilson was some obscure white male scientist who was venerated, and that was reason enough for a supposed “takedown”. And the editor of Scientific American supported and lauded this ignorant, ideology-driven tirade.

Ironically, Wilson would have found this ideological hit job all too familiar. After he wrote his famous book Sociobiology in the 1970s, a volume in which, in a single chapter about human beings, he had the temerity to suggest that maybe, just maybe, human beings operate with the same mix of genes that other creatures do, the book was met by a disgraceful, below-the-belt, ideological response from Wilson’s far left colleagues Richard Lewontin and Stephen Jay Gould who hysterically compared his arguments to thinking that was well on its way down the slippery slope to that dark world where lay the Nazi gas chambers. The gas chamber analogy is about the only thing that’s missing from the recent hit job, but the depressing thing is that we are fighting the same battles in 2021 that Wilson fought forty years before, although turbocharged this time by armies of faithful zombies on social media. The sad thing is that Wilson is no longer around to defend himself, although I am not sure he would have bothered with a piece as shoddy as this one.

The complete intellectual destruction of a once-great science magazine is now clear as day. No more should Scientific American be regarded as a vehicle for sober scientific views and liberal causes but as a political magazine with clearly stated ideological biases and an aversion to facts, an instrument of a blinkered woke political worldview that brooks no dissent. Scott Aaronson has taken a principled stand and said that after this proverbial last straw on the camel’s back, he will no longer write for the magazine or do interviews for them. I applaud Scott’s decision, and with his expertise it’s a decision that actually matters. As far as I am concerned, I now mix smoldering fury at the article with immense relief: the last seven years have clearly shown that leaving Scientific American in 2014 was akin to leaving the Soviet Union in the 1930s just before Stalin appointed Lysenko head biologist. I could not have asked for a happier expulsion and now feel completely vindicated and free of any modicum of regret I might have felt.

To my few friends and colleagues who still write for the magazine and whose opinions I continue to respect, I really wish to ask: Why? Is writing for a magazine which has sacrificed facts and the liberal voice of real science at the altar of political ideology and make believe still worth it? What would it take for you to say no more? As Oscar Wilde would say, one mistake like this is a mistake, two seems more like carelessness; in the roster of the last few years, this is “mistake” 100+, signaling that it’s now officially approved policy. Do you think that being an insider will allow you to salvage the reputation of the magazine? If you think that way, you are no different from the one or two moderate Republicans who think they can still salvage the once-great party of Lincoln and Eisenhower. Both the GOP and Scientific American are beyond redemption from where I stand. Get out, start your own magazine or join another, one which actually respects liberal, diverse voices and scientific facts; let us applaud you for it. You deserve better, the world deserves better. And Ed Wilson’s memory sure as hell deserves better.

---

Update (from Scott): See here for the Hacker News thread about this post. I was amused by the conjunction of two themes: (1) people who were uncomfortable with my and Ashutosh’s expression of strong emotions, and (2) people who actually clicked through to the SciAm hit-piece, and then reported back to the others that the strong emotions were completely, 100% justified in this case.