Time to catch up on my photos. Here’s May and June, 2025. A lot happened. Here I am in North Beach with Barb, I guess this was back in May. Love the display sign of a big fish! I always like messy things on walls. Like painted-over plywood. Fab four-color fan. Usually I line myself […]

The post Summer in SF and NYC first appeared on Rudy's Blog.

(This is an old/paused blog entry I planned to release in April while I was at Eastercon, but forgot about. Here it is, late and a bit tired as real world events appear to be out-stripping it ...)

(With my eyesight/cognitive issues I can't watch movies or TV made this century.)

But in light of current events, my Muse is screaming at me to sit down and write my script for an updated re-make of Doctor Strangelove:

POTUS GOLDPANTS, in middling dementia, decides to evade the 25th amendment by barricading himself in the Oval Office and launching stealth bombers at Latveria. Etc.

The USAF has a problem finding Latveria on a map (because Doctor Doom infiltrated the Defense Mapping Agency) so they end up targeting the Duchy of Grand Fenwick by mistake, which is in Transnistria ... which they are also having problems finding on Google Maps, because it has the string "trans" in its name.

While the USAF is trying to bomb Grand Fenwick (in Transnistria), Russian tanks are commencing a special military operation in Moldova ... of which Transnistria is a breakaway autonomous region.

Russia is unaware that Grand Fenwick has the Q-bomb (because they haven't told the UN yet). Meanwhile, the USAF bombers blundering overhead have stealth coatings bought from a President Goldfarts crony that even antiquated Russian radar can spot.

And it's up to one trepidatious officer to stop them ...

When I became the father of twin boys, I found myself suspended in a new kind of time — time measured not in days or deadlines, but in lifetimes.

Drifting in a sea of dreams about what their futures might hold, I began to wonder:

If I was dreaming dreams on their behalf, then what dreams had I inherited from my parents, and which were truly my own?

In that moment, I ceased to see myself as a captain of my family’s future and began to feel more like a confluence of currents, with dreams flowing through me.

I was no longer just having dreams — some of my dreams, I imagined, were having me.

Growing up, I absorbed certain dreams through osmosis: my father's admiration for public service, my mother's love of beauty, my country's dream of freedom. 

Who would I be if not for this inheritance of dreams? 

Who would anyone be if not for theirs?

Perhaps the better question is this: 

What do we do with the dreams we receive?

Each generation must wrestle with the dreams they inherit: some are carried forward, consciously or not, and others are released or transformed. 

That was always hard enough. Today, we must also grapple with the dreams that are increasingly suggested to us by invisible algorithms. 

AI systems may not dream as we do, but they are trained on the archives of human culture. 

Just as a parent’s unspoken dream can shape a child’s path, a machine’s projections can influence what we see as possible, desirable, or real.

As machines begin to dream alongside us, perhaps even for us, questioning where our dreams come from and remembering how to dream freely has never been more important.

One of the most iconic episodes of dreaming freely took place just blocks from where I live.

In the summer of 1967, thousands of young people converged on San Francisco’s Haight-Ashbury neighborhood, rejecting the societal norms of their day for dreams of peace, freedom, and self-expression. 

Some of those dreams were lost to excess, while others were co-opted by spectacle, or overcome by the weight of their own idealism. Yet many planted seeds that grew deep roots over the ensuing decades. 

Several of those seeds drifted south, to the orchards and garages of what became Silicon Valley, where software engineers turned ideals from the counterculture into technology products. 

Dreams of expanded consciousness shaped the market for personal computing. 

Dreams of community became the power of networks. 

The Whole Earth Catalog's "access to tools" became Apple's "tools for the mind.”

Today, many of those tools nudge us toward the embrace of dreams that feel genuine but are often in fact projected onto us. 

As we embrace technologies born of generations that once dared to dream new dreams, we find ourselves ever more deeply enmeshed in the ancient process of intergenerational dream transmission, now amplified by machines that never sleep.

The transmission of dreams across generations has always been both biological and cultural. 

Our dreams are shaped not just by the expectations we inherit or reject, but by the bodies that carry them. 

This is because our genes carry the imprint of ancestral experience, encoding survival strategies and emotional tendencies. Traits shaped by stress or trauma ripple across generations, influencing patterns of perception, fear, ambition, and resilience. 

Inherited dreams contain important information and are among the deep currents of longing that give life meaning: dreams of justice passed down by activists, dreams of wholeness passed down by survivors, dreams of belonging shared by exiles. 

They can be gifts that point us toward better futures.

Like biological complexity, these dream currents layer and accumulate over generations, forming an inheritance of imagination as real as the color of our eyes. They echo outward into the stories we collect, the institutions we build, and into the AI models we now consult to make sense of the world.

What begins as cellular memory becomes cultural memory, and then machine memory, moving from body to society to cloud, and then back again into mind and body.

There’s plenty of excitement to be had in imagining how AI may one day help us unlock dormant aspects of the mind, opening portals to new forms of creativity. 

But if we sever our connection to the embodied archives of our elders or the actual archives that contain their stories, we risk letting machines dream for us — and becoming consumers of consciousness rather than its conduits and creators.

Libraries are among our most vital connections to those archives. 

For thousands of years, they have served as temples of knowledge, places where one generation's dreams are preserved for the next. They have always been imperfect, amplifying certain voices while overlooking others, but they remain among our most precious public goods, rich soil from which new dreams reliably grow.

Today, many of these temples are being dismantled or transformed into digital goods. As public libraries face budget cuts, and book readership declines, archive materials once freely available are licensed to AI companies as training data.

AI can make the contents of libraries more accessible than ever, and help us to magnify and make connections among what we discover. But it cannot yet replace the experience of being in a library: the quiet invitation to wander, to stumble upon the unexpected, to sit beside a stranger, to be changed by something you didn’t know you were looking for.

As AI becomes a new kind of archive, we need libraries more than ever — not as nostalgic relics, but as stewards of old dreams and shapers of new ones.

Just down the street, a new nonprofit Counterculture Museum has opened in Haight-Ashbury. 

It preserves the dreams that once lived in bodies now gone or fading.

Those dreams live on in the museum’s archives. 

They also live on in algorithms, where counterculture ideals have been translated into code that increasingly shapes how we dream.

Artificial intelligence models are now among the largest repositories of inherited knowledge in human history. They are dream keepers, and dream creators.

They absorb the written, spoken, and visual traces of countless lives, along with the biases of their designers, generating responses that mirror our collective memory and unresolved tensions.

Just as families convey implicit values, AI inherits not just our stated aspirations, but the invisible weight of what we've left unsaid. The recursive risk isn't merely that AI feeds us what we want to hear, but that it withholds what we don't, keeping us unaware of powerful forces that quietly and persistently shape our dreams.

Philip K. Dick’s 01968 novel Do Androids Dream of Electric Sheep? imagined a future San Francisco (roughly our present day, five decades after the Summer of Love) in which the city is overrun with machines yearning to simulate emotions they cannot feel. 

His question — whether machines can dream as we do — is no longer sci-fi. Now we might reasonably ask: will future humans be able to dream without machines?

In some ways, AI will expand our imaginative capacities, turning vague hopes into vivid prototypes and private musings into global movements.

This could ignite cultural revolutions far more sweeping than the Summer of Love, with billions of dreams amplified by AI. 

Amidst such change, we should not lose touch with our innate capacity to dream our own dreams.

To dream freely, we must sometimes step away – from the loops of language, the glow of screens, the recursive churn of inherited ideas – and seek out dreams that arise not from machines or archives, but from the world itself.

Dreams that arise from nature rarely conform to language. 

They remind us that not all meaning is created by humans or machines.

"Our truest life is when we are in dreams awake," wrote Thoreau, reflecting on how trees, ponds, and stars could unlock visions of a deeper, interconnected self.

This wisdom, core to America's Transcendentalist Movement, drew from many sources, including Native Americans who long sought dreams through solitude in the wild, recognizing nature not as backdrop but as teacher.

They turned to wild places for revelation, to awaken to dreams not of human making, but of the earth's.

When we sit quietly in a forest or look up at the night sky, we begin to dream on a different wavelength: not dreams of achievement or optimization, but dreams of connection to something much deeper.

In nature, we encounter dreams that arise from wind and stone, water and root, birdsong and bark. 

They arrive when we contemplate our place in the wider web of existence.

At night, after reading to my boys and putting them to bed, I watch them dreaming.

I try not to see them as vessels for my dreams, but as creators of their own.

When they learn to walk, I’ll take them outside, away from digital screens and human expectations, to dream with nature, as humans always have, and still can.

Then I’ll take them to libraries and museums and family gatherings, where they can engage with the inheritance of dreams that came before them.

When they ask me where dreams come from, I’ll tell them to study the confluence of currents in their lives, and ask what’s missing. 

What comes next may be a dream of their own. 

At least, that is a dream that I have for them.

The Inheritance of Dreams is published with our friends at Hurry Up, We're Dreaming. You can also read the essay here.

Excerpts from a dazzling image collection, discovered in a Norwegian barn in the 1980s, that experiments with the presentation of gender.

In 1853, John Benjamin Dancer achieved a feat of seemingly impossible scale: he shrunk an image to the size of a sharpened pencil tip. Anika Burgess explores the invention of microphotography and its influence on erotic paraphenalia and military communications.

Eleventh instalment in our series of extremely small and free-form cryptic crossword puzzles, themed on our latest essay.

The sole example of a Bauhaus workshop's arcane theatrical scoring system, combining colours, words, and complex symbolic notation.

Our immediate history is steeped in profound technological acceleration. We are using artificial intelligence to draft our prose, articulate our vision, propose designs, and compose symphonies. Large language models have become part of our workflow in school and business: curating, calculating, and creating. They are embedded in how we organize knowledge and interpret reality. 

I’ve always considered myself lucky that my journey into AI began with social impact. In 02014, I was asked to join the leadership of IBM’s Watson Education. Our challenge was to create an AI companion for teachers in underserved and impacted schools that aggregated data about each student and suggested personalized learning content tailored to their needs. The experience showed me that AI could do more than increase efficiency or automate what many of us consider to be broken processes; it could also address some of our most pressing questions and community issues. 

It would take a personal encounter with AI, however, for me to truly grasp the technology’s potential. Late one night, I was working on a blog post and having a hard time getting started — the blank page echoing my paralysis. I asked Kim-GPT, an AI tool I created and trained on my writing, to draft something that was charged with emotion and vulnerability. What Kim-GPT returned wasn’t accurate or even particularly insightful, but it surfaced something I had not yet admitted to myself. Not because the machine knew, but because it forced me to recognize that only I did. The GPT could only average others’ insights on the subject. It could not draw lines between my emotions, my past experiences and my desires for the future. It could only reflect what had already been done and said.

That moment cracked something open. It was both provocative and spiritual — a quiet realization with profound consequences. My relationship with intelligence began to shift. I wasn’t merely using the tool; I was being confronted by it. What emerged from that encounter was curiosity. We were engaged not in competition but in collaboration. AI could not tell me who I was; it could only prompt me to remember. Since then, I have become focused on one central, persistent question:

What if AI isn’t here as a replacement or overlord, but to remind us of who we are and what is possible?

We tend to speak about AI in utopian or dystopian terms, but most humans live somewhere in between, balancing awe with unease. AI is a disruptor of the human condition — and a pervasive one, at that. Across sectors, industries and nearly every aspect of human life, AI challenges long-held assumptions about what it means to think, create, contribute. But what if it also serves as a mirror? 

In late 02023, I took my son, then a college senior at UC-Berkeley and the only mixed-race pure Mathematics major in the department, to Afrotech, a conference for technologists of color. In order to register for the conference he needed a professional headshot. Given the short notice, I recommended he use an AI tool to generate a professional headshot from a selfie. The first result straightened his hair. When he prompted the AI again, specifying that he was mixed race, the resulting image darkened his skin to the point he was unrecognizable, and showed him in a non-professional light. 

AI reflects the data we feed it, the values we encode into it, and the desires we project onto it. It can amplify our best instincts, like creativity and collaboration, or our most dangerous biases, like prejudice and inequality. It can be weaponized, commodified, celebrated or anthropomorphized. It challenges us to consider our species and our place in the large ecosystem of life, of being and of intelligence. And more than any technology before it, AI forces us to confront a deeper question: 

Who are we when we are no longer the most elevated, intelligent and coveted beings on Earth? 

When we loosen our grip on cognition and productivity as the foundation of human worth, we reclaim the qualities machines cannot replicate: our ability to feel, intuit, yearn, imagine and love. These capacities are not weaknesses; they are the core of our humanity. These are not “soft skills;” they are the bedrock of our survival. If AI is the catalyst, then our humanity is the compass. 

All technology begins with imagination, not engineering. AI is not the product of logic or computation alone; it is the descendant of dreams, myths and stories, born at the intersection of our desire to know and our urge to create. 

We often forget this. Today, we scale AI at an unsustainable pace, deploying systems faster than we can regulate them, funding ideas faster than we can reflect on their implications. We are hyperscaling without reverence for the creativity that gave rise to AI in the first place. 

Creativity cannot be optimized. It is painstakingly slow, nonlinear, and deeply inconvenient. It resists automation. It requires time, stillness, uncertainty, and the willingness to sit with discomfort. And yet, creativity is perhaps our most sacred act as humans. In this era of accelerated intelligence, our deepest responsibility is to protect the sacred space where imagination lives and creativity thrives. 

To honor creativity is to reclaim agency, reframing AI not as a threat to human purpose, but as a partner in deepening it. We are not simply the designers of AI — we are the dreamers from which it was born. 

A few years ago, I was nominated to join a fellowship designed specifically to teach tech leaders how to obtain reverent power as a way to uplevel their impact. What I affectionately dubbed “Founders Crying” became a hotbed for creativity. New businesses emerged and ideas formed from seemingly disparate concepts that each individual brought to our workshop. It occurred to me that it took more than just sitting down at a machine, canvas or instrument to cultivate creativity. What was required was a change in how leaders show up in the workplace. To navigate the rough waters of creativity, we need new leadership deeply rooted in courage and vulnerability. As Brené Brown teaches: 

“Vulnerability is the birthplace of love, belonging, joy, courage, empathy and creativity. It is the source of hope, empathy, accountability, and authenticity. If we want greater clarity in our purpose or deeper and more meaningful spiritual lives, vulnerability is the path.” 

For AI to support a thriving human future we must be vulnerable. We must lead with curiosity, not certainty. We must be willing to not know. To experiment. To fail and begin again. 

This courage-centered leadership asks how we show up fully human in the age of AI. Are we able to stay open to wonder even as the world accelerates? Can we design with compassion, not just code? These questions must guide our design principles, ensuring a future in which AI expands possibilities rather than collapsing them. To lead well in an AI-saturated world, we must be willing to feel deeply, to be changed, and to relinquish control. In a world where design thinking prevails and “human-centered everything” is in vogue, we need to be courageous enough to question what happens when humanity reintegrates itself within the ecosystem we’ve set ourselves apart from over the last century. 

I am a liberal arts graduate from a small school in central Pennsylvania. I was certain that I was headed to law school — that is, until I worked with lawyers. Instead, I followed my parents to San Francisco, where both were working hard in organizations bringing the internet to the world. When I joined the dot-com boom, I found that there were no roles that matched what I was uniquely good at. So I decided to build my own.

Throughout my unconventional career path, one story that has consistently guided and inspired me is Paulo Coelho’s The Alchemist. The book’s central idea is that of the Personal Legend: the universe, with all its forms of intelligence, collaborates with us to determine our purpose. It is up to each of us to choose whether we pursue what the universe calls upon us to do.

In an AI-saturated world, it can be harder to hear that calling. The noise of prediction, optimization, and feedback loops can drown out the quieter voice of intuition. The machine may offer countless suggestions, but it cannot tell you what truly matters. It may identify patterns in your behavior, but it cannot touch your purpose. 

Purpose is an internal compass. It is something discovered, not assigned. AI, when used with discernment, can support this discovery, but only when we allow it to act as a mirror rather than a map. It can help us articulate what we already know, and surface connections we might not have seen. But determining what’s worth pursuing is a journey that remains ours. That is inner work. That is the sacred domain of the human spirit. It cannot be outsourced or automated.

Purpose is not a download. It is a discovery. 

If we want AI to serve human flourishing, we must shift from designing for efficiency to designing for empathy. The Dalai Lama has often said that compassion is the highest form of intelligence. What might it look like to embed that kind of intelligence into our systems? 

To take this teaching into our labs and development centers we would need to prioritize dignity in every design choice. We must build models that heal fragmentation instead of amplifying division. And most importantly, we need to ask ourselves not just “can we build it?” but “should we and for whom?”

This requires conceptual analysis, systems thinking, creative experimentation, composite research, and emotional intelligence. It requires listening to those historically excluded from innovation and technology conversations and considerations. It means moving from extraction to reciprocity. When designing for and with AI, it is important to remember that connection is paramount. 

The future we build depends on the values we encode, the similarities innate in our species, and the voices we amplify and uplift. 

Creativity is not a luxury. It is essential to our evolution. To awaken it, we need practices that are both grounded and generative: 

• Treat AI as a collaborator, not a replacement. Start by writing a rough draft yourself. Use AI to explore unexpected connections. Let it surprise you. But always return to your own voice. Creativity lives in conversation, not in command. 
• Ask more thoughtful, imaginative questions. A good prompt is not unlike a good question in therapy. It opens doors you didn’t know were there. AI responds to what we ask of it. If we bring depth and curiosity to the prompt, we often get insights we hadn’t expected. 
• Use AI to practice emotional courage. Have it simulate a difficult conversation. Role-play a tough decision. Draft the email you’re scared to send. These exercises are not about perfecting performance. They are about building resilience. 

In all these ways, AI can help us loosen fear and cultivate creativity — but only if we are willing to engage with it bravely and playfully. 

We are not just building tools; we are shaping culture. And in this culture, we must make space for the sacred, protecting time for rest and reflection; making room for play and experimentation; and creating environments where wonder is not a distraction but a guide. 

When creativity is squeezed out by optimization, we lose more than originality: we lose meaning. And when we lose meaning, we lose direction. 

The time saved by automation must not be immediately reabsorbed by more production. Let us reclaim that time. Let us use it to imagine. Let us return to questions of beauty, belonging, and purpose. We cannot replicate what we have not yet imagined. We cannot automate what we have not protected. 

Begin by noticing what moves you. Keep a record of what sparks awe or breaks your heart. These moments are clues. They are breadcrumbs to your Personal Legend. 

Seek out people who are different from you. Not just in background, but in worldview. Innovation often lives in the margins. It emerges when disciplines and identities collide. 

And finally, create spaces that nourish imagination. Whether it’s a kitchen table, a community gathering, or a digital forum, we need ecosystems where creativity can flourish and grow. 

These are not side projects. They are acts of revolution. And they are how we align artificial intelligence with the deepest dimensions of what it means to be human. 

The real revolution is not artificial intelligence. It is the awakening of our own. It is the willingness to meet this moment with full presence. To reclaim our imagination as sacred. To use innovation as an invitation to remember who we are. 

AI will shape the future. That much is certain. The question is whether we will shape ourselves in return, and do so with integrity, wisdom, and wonder. The future does not need more optimization. It needs more imagination. 

That begins now. That begins with us.

The first comprehensive history of marionette artistry in the English language.

Depictions of the mythical creatures known as Blemmyes: humanoids whose eyes, nose, and mouth are embedded in their breast.

Bad news: the endoscopy failed. (I was scheduled for an upper GI endoscopy via the nasal sinuses to take a look around my stomach and see what's bleeding. Bad news: turns out I have unusually narrow sinuses, and by the time they'd figured this out my nose was watering so badly that I couldn't breathe when they tried to go in via my throat. So we're rescheduling for a different loction with an anesthetist who can put me under if necessary. NB: I would have been fine with only local anaesthesia if the bloody endscope had fit through my sinuses. Gaah.)

The attack novel I was working on has now hit the 70% mark in first draft—not bad for two months. I am going to keep pushing onwards until it stops, or until the page proofs I'm expecting hit me in the face. They're due at the end of June, so I might finish Starter Pack first ... or not. Starter Pack is an unexpected but welcome spin-off of Ghost Engine (third draft currently on hold at 80% done), which I shall get back to in due course. It seems to have metastasized into a multi-book project.

Neither of the aforementioned novels is finished, nor do they have a US publisher. (Ghost Engine has a UK publisher, who has been Very Patient for the past few years—thanks, Jenni!)

Feel free to talk among yourselves, especially about the implications of Operation Spiders Web, which (from here) looks like the defining moment for a very 21st century revolution in military affairs; one marking the transition from fossil fuel powered force projection to electromotive/computational force projection.

In 1840, British architect George Wightwick published a world history of architecture in the Romantic mode, inviting readers to enter a vast garden where Buddhist iconography rubs shoulders with Greek temples and Egyptian pyramids gaze upon Gothic cathedrals. His intended audience? Idle women. Matthew Mullane revisits this visionary but ultimately unpopular text, revealing the legacy of attempts to gatekeep the realms of imagination and fantasy pertaining to the built environment.

Tenth instalment in our series of extremely small and free-form cryptic crossword puzzles, themed on our latest essay.

A set of drawing workbooks embroiled in debates about the Indigenist aesthetic movement.

It was October 02019, and Thea Sommerschield had hit a wall. She was working on her doctoral thesis in ancient history at Oxford, which involved deciphering Greek inscriptions that were carved on stones in Western Sicily more than 2,000 years earlier. As is often the case in epigraphy — the study and interpretation of ancient inscriptions written on durable surfaces like stone and clay — many of the texts were badly damaged. What’s more, they recorded a variety of dialects, from a variety of different periods, which made it harder to find patterns or fill in missing characters. 

At a favorite lunch spot, she shared her frustrations with Yannis Assael, a Greek computer scientist who was then working full-time at Google DeepMind in London while commuting to Oxford to complete his own PhD. Assael told Sommerschield he was working with a technology that might help: a recurrent neural network, a form of artificial intelligence able to tackle complex sequences of data. They set to work training a model on digitized Greek inscriptions written before the fifth century, similar to how ChatGPT was trained on vast quantities of text available on the internet.

Sommerschield watched with astonishment as the missing text from the damaged inscriptions began to appear, character by character, on her computer screen. After this initial success, Assael suggested they build a model based on transformer technology, which weights characters and words according to context. Ithaca, as they called the new model, was able to fill in gaps in political decrees from the dawn of democracy in Athens with 62% accuracy, compared to 25% for human experts working alone. When human experts worked in tandem with Ithaca, the results were even better, with accuracy increasing to 72%.

Left: Ithaca's restoration of a damaged inscription of a decree concerning the Acropolis of Athens. Right: In August 02023, Vesuvius Challenge contestant Luke Farritor, 21, won the competition's $40,000 First Letters Prize for successfully decoding the word ΠΟΡΦΥΡΑϹ (porphyras, meaning "purple") in an unopened Herculaneum scroll. Left photo by Marsyas, Epigraphic Museum, WikiMedia CC BY 2.5. Right photo by The Vesuvius Challenge.

Ithaca is one of several ancient code-cracking breakthroughs powered by artificial intelligence in recent years. Since 02018, neural networks trained on cuneiform, the writing system of Mesopotamia, have been able to fill in lost verses from the story of Gilgamesh, the world’s earliest known epic poem. In 02023, a project known as the Vesuvius Challenge used 3D scanners and artificial intelligence to restore handwritten texts that hadn’t been read in 2,000 years, revealing previously unknown works by Epicurus and other philosophers. (The scrolls came from a luxurious villa in Herculaneum, buried during the same eruption of Mount Vesuvius that destroyed Pompeii. When scholars had previously tried to unroll them, the carbonized papyrus crumbled to dust.)

Yet despite these advances, a dozen or so ancient scripts — the writing systems used to transcribe spoken language — remain undeciphered. These include such mysteries as the one-of-a-kind Phaistos Disk, a spiral of 45 symbols found on a single sixteen-inch clay disk in a Minoan palace on Crete, and Proto-Elamite, a script used 5,000 years ago in what is now Iran, which may have consisted of a thousand distinct symbols. Some, like Cypro-Minoan — which transcribes a language spoken in the Late Bronze Age on Cyprus — are tantalizingly similar to early European scripts that have already been fully deciphered. Others, like the quipu of the Andes — intricately knotted ropes made of the wool of llamas, vicuñas, and alpacas — stretch our definitions of how speech can be transformed into writing. 

In some cases, there is big money to be won: a reward of one million dollars is on offer for the decipherer of the Harappan script of the Indus Valley civilization of South Asia, as well as a $15,000-per-character prize for the successful decoder of the Oracle Bone script, the precursor to Chinese.

Cracking these ancient codes may seem like the kind of challenge AI is ideally suited to solve. After all, neural networks have already bested human champions at chess, as well as the most complex of all games, Go. They can detect cancer in medical images, predict protein structures, synthesize novel drugs, and converse fluently and persuasively in 200 languages. Given AI’s ability to find order in complex sets of data, surely assigning meaning to ancient symbols would be child’s play.

But if the example of Ithaca shows the promise of AI in the study of the past, these mystery scripts reveal its limitations. Artificial neural networks might prove a crucial tool, but true progress will come through collaboration between human neural networks: the intuitions and expertise stored in the heads of scholars, working in different disciplines in real-world settings.

“AI isn’t going to replace human historians,” says Sommerschield, who is now at the University of Nottingham. “To us, that is the biggest success of our research. It shows the potential of these technologies as assistants.” She sees artificial intelligence as a powerful adjunct to human expertise. “To be an epigrapher, you have to be an expert not just in the historical period, but also in the archaeological context, in the letter form, in carbon dating.” She cautions against overstating the potential of AI. “We’re not going to have an equivalent of ChatGPT for the ancient world, because of the nature of the data. It’s not just low in quantity, it’s also low in quality, with all kinds of gaps and problems in transliteration.”

Ithaca was trained on ancient Greek, a language we’ve long known how to read, and whose entire corpus amounts to tens of thousands of inscriptions. The AI models that have filled in lost verses of Gilgamesh are trained on cuneiform, whose corpus is even larger: hundreds of thousands of cuneiform tablets can be found in the storerooms of the world’s museums, many of them still untranslated. The problem with mystery scripts like Linear A, Cypro-Minoan, Rongorongo, and Harappan is that the total number of known inscriptions can be counted in the thousands, and sometimes in the hundreds. Not only that, in most cases we have no idea what spoken language they’re meant to encode.

“Decipherment is kind of like a matching problem,” explains Assael. “It’s different from predicting. You’re trying to match a limited number of characters to sounds from an older, unknown language. It’s not a problem that’s well suited to these deep neural network architectures that require substantial amounts of data.”

Human ingenuity remains key. Two of the greatest intellectual feats of the 20th century involved the decipherment of ancient writing systems. In 01952, when Michael Ventris, a young English architect, announced that he’d cracked the code of Linear B, a script used in Bronze Age Crete, newspapers likened the accomplishment to the scaling of Mount Everest. (Behind the scenes, the crucial grouping and classifying of characters on 180,000 index cards into common roots — the grunt work that would now be performed by AI — was done by Alice Kober, a chain-smoking instructor from Brooklyn College.)

The decipherment of the Maya script, which is capable of recording all human thought using bulbous jaguars, frogs, warriors’ heads, and other stylized glyphs, involved a decades-long collaboration between Yuri Knorozov, a Soviet epigrapher, and American scholars working on excavations in the jungles of Central America.

While the interpreting of Egyptian hieroglyphics is held up as a triumph of human ingenuity, the Linear B and Mayan codes were cracked without the help of a Rosetta Stone to point the way. With Linear B, the breakthrough came when Ventris broke with the established thinking, which held that it transcribed Etruscan — a script scholars can read aloud, but whose meaning still remains elusive — and realized that it corresponded to a form of archaic Greek spoken 500 years before Homer. In the case of ancient Mayan, long thought to be a cartoonish depiction of universal ideas, it was only when scholars acknowledged that it might transcribe the ancestors of the languages spoken by contemporary Maya people that the decipherment really began. Today, we can read 85% of the glyphs; it is even possible to translate Shakespeare’s Hamlet into ancient Mayan.

Collaborating across cultures and disciplines, and carrying out paradigm-shedding leaps of intuition, are not the strong points of existing artificial neural networks. But that doesn’t mean AI can’t play a role in decipherment of ancient writing systems. Miguel Valério, an epigrapher at the Autonomous University of Barcelona, has worked on Cypro-Minoan, the script used on Cyprus 3,500 years ago. Two hundred inscriptions, on golden jewelry, metal ingots, ivory plaques, and four broken clay tablets, have survived. Valério was suspicious of the scholarly orthodoxy, which attributed the great diversity in signs to the coexistence of three distinct forms of the language. 

To test the theory that many of the signs were in fact allographs — that is, variants, like the capital letter “G” and “g,” its lower-case version — Valério worked with Michele Corazza, a computational linguist at the University of Bologna, to design a custom-built neural network they called Sign2Vecd. Because the model was unsupervised, it searched for patterns without applying human-imposed preconceptions to the data set. 

“The machine learned how to cluster the signs,” says Valério, “but it didn’t do it simply on the basis of their resemblance, but also on the specific context of a sign in relation to other signs. It allowed us to create a three-dimensional plot of the results. We could see the signs floating in a sphere, and zoom in to see their relationship to each other, and whether they’d been written on clay or metal.” 

Left: Separation of Cypro-Minoan signs from clay tablets (in green) and signs found in other types of inscription (in red) in the 3D scatter plot. Right: Separation of a Cypro-Minoan grapheme in two groups in the 3D scatter plot.1

The virtual sphere allowed Valério to establish a sign-list — the equivalent of the list of 26 letters in our alphabet, and the first step towards decipherment — for Cypro-Minoan, which he believes has about 60 different signs, all corresponding to a distinct syllable.

“The issue is always validation. How do you know if the result is correct if the script is undeciphered? What we did was to compare it to a known script, the Cypriot Greek syllabary, which is closely related to Cypro-Minoan. And we found the machine got it right 70% of the time.” But Valério believes no unsupervised neural net, no matter how powerful, will crack Cypro-Minoan on its own. “I don’t see how AI can do what human epigraphers do traditionally. Neural nets are very useful tools, but they have to be directed. It all depends on the data you provide them, and the questions you ask them.”

The latest advances in AI have come at a time when there has been a revolution in our understanding of writing systems. A generation ago, most people were taught that writing was invented once, in Mesopotamia, about 5,500 years ago, as a tool of accountancy and state bureaucracy. From there, the standard thinking went, it spread to Egypt, and hieroglyphics were simplified into the alphabet that became the basis for recording most European languages. It is now accepted that writing systems were not only invented to keep track of sheep and units of grain, but also to record spiritual beliefs and tell stories. (In the case of Tifinagh, an ancient North African Berber script, there is evidence that writing was used primarily as a source of fun, for puzzle-making and graffiti.) Monogenesis, the idea that the Ur-script diffused from Mesopotamia, has been replaced by the recognition that writing was invented independently in China, Egypt, Central America, and — though this remains controversial — in the Indus Valley, where 4,000 inscriptions been unearthed in sites that were home to one of the earliest large urban civilizations.

The most spectacular example of a potential “invention of writing” is Rongorongo, a writing system found on Rapa Nui, the island famous for its massive carved stone heads. Also known as Easter Island, it is 1,300 miles from any other landmass in the South Pacific. Twenty-six tablets have been discovered, made of a kind of wood native to South Africa. Each has been inscribed, apparently using a shark’s tooth as a stylus, with lines of dancing stick-figures, stylized birds and sea creatures. The tablets were recently dated to the late 01400s, two centuries before Europeans first arrived on the island.

For computational linguist Richard Sproat, Rongorongo may be the script AI can offer the most help in decoding. “It’s kind of a decipherer’s dream,” says Sproat, who worked on recurrent neural nets for Google, and is now part of an AI start-up in Tokyo. “There are maybe 12,000 characters, and some of the inscriptions are quite long. We know that it records a language related to the modern Rapa Nui, which Easter Islanders speak today.” Archaeologists have even reported eyewitness accounts of the ceremonies in which the tablets were inscribed. And yet, points out Sproat, even with all these head starts, and access to advanced AI, nobody has yet come close to a convincing decipherment of Rongorongo.

The way forward depends on finding more inscriptions, and that comes down to old-fashioned “dirt” archaeology, and the labor-intensive process of unearthing ancient artifacts. (The best-case scenario would be finding a “bilingual,” a modern version of the Rosetta Stone, whose parallel inscriptions in Greek and demotic allowed 19th-century scholars to decipher Egyptian hieroglyphics.) But the code of Cypro-Minoan, or Linear A, or the quipu of the Andes, won’t be cracked by a computer scientist alone. It’s going to take a collaboration with epigraphers working with all the available evidence, some of which is still buried at archaeological sites.

“As a scholar working in social sciences,” says Valério of the Autonomous University of Barcelona, “I feel I’m obliged to do projects in the digital humanities these days. If we pursue things that are perceived as traditional, no one is going to grant us money to work. But these traditional things are also important. In fact, they’re the basis of our work.” Without more material evidence, painstakingly uncovered, documented, and digitized, no AI, no matter how powerful, will be able to decipher the writing systems that will help us bring the lost worlds of the Indus Valley, Bronze Age Crete, and the Incan Empire back to life.

Perhaps the most eloquent defense of traditional scholarship comes from the distinguished scholar of Aegean civilization, Silvia Ferrara, who supervised Valério and Corazza’s collaboration at the University of Bologna. 

“The computer is no deus ex machina,” Ferrara writes in her book The Greatest Invention (02022). “Deep learning can act as co-pilot. Without the eye of the humanist, though, you don’t stand a chance at decipherment.”

1. Figure and caption reproduced from Corazza M, Tamburini F, Valério M, Ferrara S (02022) Unsupervised deep learning supports reclassification of Bronze age cypriot writing system. PLoS ONE 17(7): e0269544 under a CC BY 4.0 license. https://doi.org/10.1371/journal.pone.0269544

A series of conjectures about the primal scene of writing.

A stunning six-foot-long map that joins the worlds of various myths and stories for the childhood adventurer.

The Long Now Foundation is proud to announce Christopher Michel as its first Artist-in-Residence. A distinguished photographer and visual storyteller, Michel has documented Long Now’s founders and visionaries — including Stewart Brand, Kevin Kelly, Danny Hillis, Esther Dyson, and many of its board members and speakers — for decades. Through his portrait photographs, he has captured their work in long-term thinking, deep time, and the future of civilization.

As Long Now’s first Artist-in-Residence, Michel will create a body of work inspired by the Foundation’s mission, expanding his exploration of time through portraiture, documentary photography, and large-scale visual projects. His work will focus on artifacts of long-term thinking, from the 10,000-year clock to the Rosetta Project, as well as the people shaping humanity’s long-term future.

Christopher Michel has made photographs of Long Now Board Members past and present. Clockwise from upper left: Stewart Brand, Danny Hillis, Kevin Kelly, Alexander Rose, Katherine Fulton, David Eagleman, Esther Dyson, and Danica Remy.

Michel will hold this appointment concurrently with his Artist-in-Residence position at the National Academies of Sciences, Engineering, and Medicine, where he uses photography to highlight the work of leading scientists, engineers, and medical professionals. His New Heroes project — featuring over 250 portraits of leaders in science, engineering, and medicine — aims to elevate science in society and humanize these fields. His images, taken in laboratories, underground research facilities, and atop observatories scanning the cosmos, showcase the individuals behind groundbreaking discoveries. In 02024, his portrait of Dr. Anthony Fauci was featured on the cover of Fauci’s memoir On Call.

A former U.S. Navy officer and entrepreneur, Michel founded two technology companies before dedicating himself fully to photography. His work has taken him across all seven continents, aboard a U-2 spy plane, and into some of the most extreme environments on Earth. His images are widely published, appearing in major publications, album covers, and even as Google screensavers. 

Michel’s photography explores the intersection of humanity and time, capturing the fragility and resilience of civilization. His work spans the most remote corners of the world — from Antarctica to the deep sea to the stratosphere — revealing landscapes and individuals who embody the vastness of time and space. His images — of explorers, scientists, and technological artifacts — meditate on humanity’s place in history.

Christopher Michel’s life in photography has taken him to all seven continents and beyond. Photos by Christopher Michel.

Michel’s photography at Long Now will serve as a visual bridge between the present and the far future, reinforcing the Foundation’s mission to foster long-term responsibility. “Photography,” Michel notes, “is a way of compressing time — capturing a fleeting moment that, paradoxically, can endure for centuries. At Long Now, I hope to create images that don’t just document the present but invite us to think in terms of deep time.”

His residency will officially begin this year, with projects unfolding over the coming months. His work will be featured in Long Now’s public programming, exhibitions, and archives, offering a new visual language for the Foundation’s mission to expand human timescales and inspire long-term thinking.

This interview has been edited for length and clarity.

Long Now: For those of us less familiar with your work: tell us about your journey both as an artist and a photographer — and how you ended up involved with Long Now.

Christopher Michel: In a way, it’s the most unlikely journey. Of all the things I could have imagined I would've done as a kid, I am as far away from any of that as I could have imagined. My path, in most traditional ways of looking at it, is quite non-linear. Maybe the points of connectivity seem unclear, but some people smarter than me have seen connections and have made observations about how they may be related. 

When I was growing up, I was an outsider, and I was interested in computers. I was programming in the late seventies, which was pretty early. My first computer was a Sinclair ZX 80, and then I went to college at the University of Illinois and Top Gun had just come out. And I thought, “maybe I want to serve my country.” And so I flew for the Navy as a navigator and mission commander — kind of like Goose — and hunted Russian submarines. I had a great time, I was always interested in computers, not taking any photographs really, which is such a regret. Imagine — flying 200 feet above the water for eight hours at a time, hunting drug runners or Russian subs, doing amazing stuff with amazing people. It just never occurred to me to take any photos. I was just busy doing my job. And then I went to work in the Pentagon in the office of the Chief of Naval Operations for the head of the Navy Reserve — I went to work for the bosses of the Navy. 

If you'd asked me what I wanted to do, I guess I would've said, I think I want to go into politics and maybe go to law school. I'd seen the movie The Paper Chase, and I love the idea of the Socratic method. And then the Navy said, well, we’re going to send you to the Kennedy School, which is their school around public service. But then I ran into somebody at the Pentagon who said, "You should really go to Harvard Business School."

And I hadn't thought about it — I was never interested in business. He said that it's a really good degree because you can do lots of things with it. So I quit my job in the Navy and literally a week later I was living in Boston for my first day at Harvard Business School. It was a big eye-opening experience because I had lived in a kind of isolated world in the Navy — I only knew Navy people. 

This was also a little bit before the pervasiveness of the internet. This is 01997 or 01996. People didn't know as much as they know now, and certainly entrepreneurship was not a thing in the same way that it was after people like Mark Zuckerberg. If you'd asked me what I wanted to do at Harvard, I would've said something relating to defense or operations. But then, I ran into this guy Dan Bricklin, who created VisiCalc. VisiCalc was one of the first three applications that drove the adoption of the personal computer. When we bought computers like the TRS 80 and Apple II in 01979 or 01980 we bought them for the Colossal Cave Adventure game, for VisiCalc, and for WordStar.

He gave a talk to our class and he said, "When I look back at my life, I feel like I created something that made a difference in the world." And it really got my attention, that idea of building something that can outlast us that's meaningful, and can be done through entrepreneurship. Before that, that was an idea that was just not part of the culture I knew anything about. So I got excited to do that. When I left Harvard Business School, I was still in the reserves and I had the idea that the internet would be a great way to connect, enable, and empower service members, veterans, and their families. So I helped start a company called Military.com, and it was one of the first social media companies to get to scale in the United States. And its concept may sound like a very obvious idea today because we live in a world where we know about things like Facebook, but this was five years before Facebook was created.

I raised a lot of money, and then I got fired, and then I came back and it was a really difficult time because that was also during the dot-com bubble bursting. 

But during that time period, two interesting other things happened. The first: my good friend Ann Dwane gave me a camera. When I was driving cross country to come out here to find my fortune in Silicon Valley, I started taking some photos and film pictures and I thought, hey, my pictures are pretty good — this is pretty fun. And then I bought another camera, and I started taking more pictures and I was really hooked.

The second is actually my first connection to Long Now. What happened was that a guy came to visit me when I was running Military.com that I didn't know anything about — I'm not even sure why he came to see me. And he was a guy named Stewart Brand. So Stewart shows up in my office — he must've been introduced to me by someone, but I just didn't really have the context. Maybe I looked him up and had heard of the Whole Earth Catalog. 

Anyways, he just had a lot of questions for me. And, of course, what I didn't realize, 25 years ago, is that this is what Stewart does. Stewart — somehow, like a time traveler — finds his way to the point of creation of something that he thinks might be important. He's almost a Zelig character. He just appears in my office and is curious about social media and the military. He served in the military, himself, too.

So I meet him and then he leaves and I don't hear anything of him for a while. Then, we have an idea of a product called Kit Up at Military.com. And the idea of Kit Up was based on Kevin Kelly’s Cool Tools — military people love gear, and we thought, well, what if we did a weekly gear thing? And I met with Kevin and I said, “Hey Kevin, what do you think about me kind of taking your idea and adapting it for the military?” 

Of course, Kevin's the least competitive person ever, and he says, “Great idea!” So we created Kit Up, which was a listing of, for example, here are the best boots for military people, or the best jacket or the best gloves — whatever it might be.

As a byproduct of running these companies, I got exposed to Kevin and Stewart, and then I became better friends with Kevin. I got invited to some walks, and I would see those guys socially. And then in 02014, The Interval was created. I went there and I got to know Zander and I started making a lot of photos — have you seen my gallery of Long Now photos?

Christopher Michel's photos of the 10,000-year clock in Texas capture its scale and human context.

I've definitely seen it — whenever I need a photo of a Long Now person, I say, “let me see if there's a good Chris photo.” 

This is an interesting thing that can happen in our lives, which are unintended projects. I do make photos with the idea that these photos could be quite important. There's a kind of alchemy around these photos. They're important now, but they're just going to be more important over time.

So my pathway is: Navy, entrepreneur, investor for a little while, and then photographer.

If there was a theme connecting these, it’s that I'm curious. The thing that really excites me most of all is that I like new challenges. I like starting over. It feels good! Another theme is the act of creation. You may think photography is quite a bit different than creating internet products, but they have some similarities! A great portrait is a created thing that can last and live without my own keeping it alive. It has its own life force. And that's creation. Companies are like that. Some companies go away, some companies stay around. Military.com stays around today.

So I'm now a photographer and I'm going all over the world and I'm making all these photos and I'm leading trips. Zander and the rest of the team invite me to events. I go to the clock and I climb the Bay Bridge, and I visit Biosphere 2. I'm just photographing a lot of stuff and I love it. The thing I love about Long Now people is, if you like quirky, intellectual people, these are your people. You know what I mean? And they're all nice, wonderful humans. So it feels good to be there and to help them. 

In 02022, Christopher Michel accompanied Long Now on a trip to Biosphere 2 in Arizona.

During the first Trump administration, during Covid, I was a volunteer assisting the U.S. National Academies with science communication. I was on the board of the Division of Earth and Life Studies, and I was on the President’s Circle. 

Now, the National Academies — they were created by Abraham Lincoln to answer questions of science for the U.S. government, they have two primary functions. One is an honorific, there's three academies: sciences, engineering, and medicine. So if you're one of the best physicists, you get made a member of the National Academies. It's based on the Royal Society in England. 

But moreover, what’s relevant to everyone is that the National Academies oversee the National Research Council, which provides independent, evidence-based advice on scientific and technical questions. When the government needs to understand something complex, like how much mercury should be allowed in drinking water, they often turn to the Academies. A panel of leading experts is assembled to review the research and produce a consensus report. These studies help ensure that policy decisions are guided by the best available science.

Over time, I had the opportunity to work closely with the people who support and guide that process. We spent time with scientists from across disciplines. Many of them are making quiet but profound contributions to society. Their names may not be well known, but their work touches everything from health to energy to climate.

In those conversations, a common feeling kept surfacing. We were lucky to know these people. And we wished more of the country did, too. There is no shortage of intelligence or integrity in the world of science. What we need is more visibility. More connection. More ways for people to see who these scientists are, what they care about, and how they think.

That is part of why I do the work I do. Helping to humanize science is not about celebrating intellect alone. It's about building trust. When people can see the care, the collaboration, and the honesty behind scientific work, they are more likely to trust its results. Not because they are told to, but because they understand the people behind it.

These scientists and people in medicine and engineering are working on behalf of society. A lot of scientists aren't there for financial gain or celebrity. They're doing the work with a purpose behind it. And we live in a culture today where we don't know who any of these people are. We know Fauci, we might know Carl Sagan, we know Einstein — but people run out of scientists to list after that.

It’s a flaw in the system. These are the new heroes that should be our role models — people that are giving back. The National Academies asked me to be their first artist-in-residence, and I've been doing it now for almost five years, and it's an unpaid job. I fly myself around the country and I make portraits of scientists, and we give away the portraits to organizations. And I've done 260 or so portraits now. If you go to Wikipedia and you look up many of the Nobel Laureates from the U.S., they're my photographs.

I would say science in that world has never been under greater threat than it is today. I don't know how much of a difference my portraits are making, but at least it's some effort that I can contribute. I do think that these scientists having great portraits helps people pay attention — we live in that kind of culture today. So that is something we can do to help elevate science and scientists and humanize science.

And simultaneously, I’m still here at Long Now with Kevin and Stewart, and when there's interesting people there, I make photos of the speakers. I've spent time during the leadership transition and gotten to know all those people. And we talked and asked, well, why don't we incorporate this into the organization? 

In December 02024, Christopher Michel helped capture incoming Long Now Executive Director Rebecca Lendl and Long Now Board President Patrick Dowd at The Interval.

We share an interest around a lot of these themes, and we are also in the business of collecting interesting people that the world should know about, and many of them are their own kind of new heroes. 

I was really struck by what you said about how much with a really successful company or any form of institution, but also, especially, a photograph, put into the right setting with the right infrastructure around it to keep it lasting, can really live on beyond you and live on beyond whoever you're depicting.

That feels in itself very Long Now. We don't often think about the photograph as a tool of long-term thinking, but in a way it really is.

Christopher Michel: Well, this transition that we're in right now at Long Now is important for a lot of reasons. One is that a lot of organizations don't withstand transitions well, but the second is, these are the founders. All of these people that we've been talking about, they're the founders and we know them. We are the generation that knows them.

We think they will be here forever, and it will always be this way, but that's not true. The truth is, it's only what we document today that will be remembered in the future. How do we want the future to think about our founders? How do we want to think about their ideas and how are they remembered? That applies to not just the older board members — that applies to Rebecca and Patrick and you and me and all of us. This is where people kind of understate the role of capturing these memories. My talk at the Long Now is aboutbhow memories are the currency of our lives. When you think about our lives, what is it that at your deathbed you're going to be thinking about? It'll be this collection of things that happen to you and some evaluation of do those things matter?

I think about this a lot. I have some training as a historian and a historical ecologist. When I was doing archival research, I read all these government reports and descriptions and travelers' journals, and I could kind of get it. But whenever you uncovered that one photograph that they took or the one good sketch they got, then suddenly it was as if a portal opened and you were 150 years into the past. I suddenly understood, for example, what people mean when they say that the San Francisco Bay was full of otters at that time, because that's so hard to grasp considering what the Bay is like now. The visual, even if it's just a drawing, but especially if it's a photograph, makes such a mark in our memory in a way that very few other things can.

And, perhaps tied to that: you have taken thousands upon thousands of photos. You've made so many of these. I've noticed that you say “make photos,” rather than “take photos.” Is that an intentional theoretical choice about your process?

Christopher Michel: Well, all photographers say that. What do you think the difference is?

Taking — or capturing — it's like the image is something that is out there and you are just grabbing it from the world, whereas “making” indicates that this is a very intentional artistic process, and there are choices being made throughout and an intentional work of construction happening.

Christopher Michel: You're basically right. What I tell my students is that photographers visualize the image that they want and then they go to create that image. You can take a really good photo if you're lucky. Stuff happens. You just see something, you just take it. But even in that case, I am trying to think about what I can do to make that photo better. I'm taking the time to do that. So that's the difference, really.

The portraits — those are fun. I'd rather be real with them, and that's what I loved about Sara [Imari Walker]. I mean, Sara brought her whole self to that photo shoot.

On the question of capturing scientists specifically: how do you go about that process? Some of these images are more standard portraits. Others, you have captured them in a context that looks more like the context that they work in.

Christopher Michel: I'm trying to shoot environmental portraits, so I often visit them at their lab or in their homes — and this is connected to what I’ve talked about before.

We've conflated celebrity with heroism. George Dyson said something to the effect of: “Some people are celebrities because they're interesting, and some people are interesting because they're celebrities.” 

I think that society would benefit from a deeper understanding of these people, these scientists, and what they're doing. Honestly, I think they're better role models. We love actors and we love sports stars, and those are wonderful professions. But, I don't know, shouldn't a Nobel laureate be at least as well known?

There’s something there also that relates to timescales. At Long Now, we have the Pace Layers concept. A lot of those celebrities, whether they're athletes or actors or musicians — they're all doing incredible things, but those are very fast things. Those are things that are easy to capture in a limited attention span. Whereas the work of a scientist, the work of an engineer, the work of someone working in medicine can be one of slow payoffs. You make a discovery in 02006, but it doesn't have a clear world-changing impact until 02025.

Christopher Michel: Every day in my job, I'm running into people that have absolutely changed the world. Katalin Karikó won the Nobel Prize, or Walter Alvarez — he’s the son of a Nobel laureate. He's the one who figured out it was an asteroid that killed the dinosaurs. Diane Havlir, at UCSF — she helped create the cocktail that saved the lives of people who have AIDS. Think about the long-term cascading effect of saving millions of HIV-positive lives.

I mean, is there a sports star that can say that? The impact there is transformational. Look at what George Church is doing — sometimes with Ryan Phelan. This is what they're doing, and they're changing every element of our world and society that we live in. In a way engineering the world that we live in today, helping us understand the world that we live in, but we don't observe it in the way that we observe the fastest pace layer.

We had a writer who wrote an incredible piece for us about changing ecological baselines called “Peering Into The Invisible Present.” The concept is that it's so hard to observe the rate at which ecological change happens in the present. It's so slow — it is hard to tell that change is happening at all. But then if you were frozen in when Military.com was founded in 01999, and then you were thawed in 02025, you would immediately notice all these things that were different. For those of us who live through it as it happens, it is harder to tell those changes are happening, whereas it's very easy to tell when LeBron James has done an incredible dunk.

Christopher Michel: One cool thing about having a gallery that's been around for 20 years is you look at those photos and you think, “Ah, the world looked a little different then.”

It looks kind of the same, too — similar and different. There's a certain archival practice to having all these there. Something I noticed is that many of your images are uploaded with Creative Commons licensing. What feels important about that to you? 

Because for me, the way for these images to become in use and to become immortal is to have it kind of spread throughout the internet. I’m sure I’ve seen images, photographs that you made so many times before I even knew who you were, just because they're out there, they enter the world.

Christopher Michel: As a 57-year-old, I want to say thank you for saying that. That's the objective. We hope that the work that we're doing makes a difference, and it is cool that a lot of people do in fact recognize the photos. Hopefully we will make even more that people care about. What's so interesting is we really don't even know — you never know which of these are going to have a long half life.

You may have heard of Christian Bök. You may have read about him on this very blog if you've been hanging out here long enough. Perhaps you were even one of the very select few to witness the seminal talk I gave back in 2016[1]—"ScArt: or, How to Tell When You've Finished Fucking"— which climaxed with a glowing description of Bök's magnum opus, then still in progress. And if you read Echopraxia, you'll have encountered—without even knowing it— a brief cameo of that work near the end, suggesting that at least in the Blindopraxia timeline, he'd brought his baby to fruition.

Truth to tell, I didn't know if he was actually going to pull it off for the longest time. I thought he'd given up years ago.

The story so far: back in the early two-thousands Christian Bök, famous for accomplishments lesser poets would never even dream of attempting (he once wrote a book in which each chapter contained only a single vowel) started work on the world's first biologically-self-replicating poem: the Xenotext Experiment, which aspired to encode a poem into the genetic code of a bacterium. Not just a poem, either: a dialog. The DNA encoding one half of that exchange ("Orpheus" by name) was designed to function both as text and as a functional gene. The protein it coded for functioned as the other half ("Eurydice"), a sort of call-and-response between the gene and its product. The protein was also designed to fluoresce red, which might seem a tad gratuitous until you realize that "Eurydice"'s half of the dialog contains the phrase "the faery is rosy/of glow".

Phase One involved engineering Orpheus and Eurydice into the benign and ubiquitous E. coli, just to work out the bugs. Ultimately, though, the target microbe was Deinococcus radiodurans: also known as “Conan the Bacterium” on account of being one of the toughest microbial motherfuckers on the planet. To quote Bök himself:

Astronauts fear it. Biologists fear it. It is not human. It lives in isolation. It grows in complete darkness. It derives no energy from the Sun. It feeds on asbestos. It feeds on concrete. It inhabits a gold seam on level 104 of the Mponeng Mine in Johannesburg. It lives in alkaline lakelets full of arsenic. It grows in lagoons of boiling asphalt. It thrives in a deadly miasma of hydrogen sulphide. It breathes iron. It breathes rust. It needs no oxygen to live. It can survive for a decade without water. It can withstand temperatures of 323 k, hot enough to melt rubidium. It can sleep for 100 millennia inside a crystal of salt, buried in Death Valley. It does not die in the hellish infernos at the Städtbibliothek during the firebombing of Dresden. It does not burn when exposed to ultraviolet rays. It does not reproduce via the use of dna. It breeds, unseen, inside canisters of hairspray. It feeds on polyethylene. It feeds on hydrocarbons. It inhabits caustic geysers of steam near the Grand Prismatic Spring in Yellowstone National Park.

I'd love to quote all seven glorious and terrifying pages, but to keep within the bounds of Fair Use I'll skip ahead to the end:

It is totally inhuman. It does not love you. It does not need you. It does not even know that you exist. It is invincible. It is unkillable. It has lived through five mass extinctions. It is the only known organism to have ever lived on the Moon. It awaits your experiments.

As things turned out, it had to await somewhat longer than expected. The project hinged upon molecular techniques that did not exist when the experiment began. Christian taught himself the relevant skills— genetics, proteomics, coding— and enlisted a team of scientists (not to mention a supercomputer or two) to invent them. His audacity was more than merely inspiring; some might even call it infuriating. As I railed back in 2016:

It was fine when Art came to science in search of inspiration; that’s as it should be. I suppose it was okay— if a little iffy— when Science started going back to Art for solutions to scientific and technical problems. But this crosses a line: with The Xenotext, we have reached the point where Science is being used solely to assist in the creation of new art. Scientists are developing new techniques just to help Christian finish his bloody poem.

Up to now, we've generally been in the driver’s seat. Insofar as a relationship even existed, Science was the top, Art the Bottom. But Art has now started driving Science. Science has discovered its inner sub.

As a former scientist myself, I was not quite sure how to feel about that. But however that was, I knew Christian Bök was to blame.

Fortunately, Science got a reprieve. The project hit a bump at E. coli. Eurydice fluoresced but the accompanying words got mangled. When they eventually cleared that hurdle and moved to Phase Two, Deinococcus fought back, shredding the code before it ever had a chance to express. Conan, apparently, does not like people trying to play with its insides. It's already got its genes set up just the way it likes them. Unkillable.

That, as far as I knew, was where the story ended ten years ago. Christian released The Xenotext: Book One in 2015, documenting his efforts and gift-wrapping them in some gorgeous and evocative bonus content, but the prize remained out of reach. He headed off to Australia to follow other pursuits; then to that oversurveilled and repressive shithole known as the United Kingdom. We fell out of touch. I assumed he'd given up on the whole project.

Oh me of little faith.

Because now it's 2025, and he fucking did it. The Xenotext is live and glowing in Deinococcus radiodurans: iterating away inside that immortal microbial bad-ass that feeds on stainless steel, that resides inside the core of reactor no. 4 at Chernobyl, that does not die in the explosion that disintegrates the Space Shuttle Columbia during orbital reentry. Christian Bök did not give up. Christian Bök did not fail. Christian Bök is going to outlive civilization, outlive most of the biosphere itself.

The rest of us might think we achieve artistic immortality if our work lasts a century or three. Bök blows his nose at such puny ambitions. His work might get deciphered by Fermi aliens who finally make it to our neighborhood a billion years from now. It could be iterating right up until the sun swallows this planet whole.

It'll almost certainly be around for Dan Brüks to find in the Oregon desert, mere decades down the road.

The Xenotext: Book Two comes out from Coach House in June 2025. It would be well worth the price just for the the acrobatics and anagrams and sonnets, for the way it remixes science and fiction and the classic canon of dead white Europeans[2]. It contains poetry to entrance people who hate poetry. It juggles space exploration and the Fermi Paradox and the potentially extraterrestrial origins of Bacteriophage φx174. But its rosy flickering heart is that dialog iterating away in Conan even as I type. A reinvention, almost a quarter-century in the making. A fucking monument if you ask me, equal parts revelation and revolution.

If you happen to live in or around Toronto, it's getting an official launch on May 27 at The Society Clubhouse, 967 College St, from 7-9pm. It's one of a half-dozen Coach House titles that will be launched that night, and no doubt all six authors are worthy in their own right. Still. You know who I'm going for.

Maybe I'll see some of you there.

1. As part of the annual SpecFic Colloquium series run by ChiZine before they immolated themselves. ↑
2. I say this as someone who generally has very little time for "poetry", beyond the vulgar-yet-epic poems I write for The BUG on special occasions. ↑

…Being an interview by Ollie Barder that just went live over at Forbes (or slightly less live over at Archive, if you've used up your monthly allocation of free articles). Ollie was originally drawn in because he's Mr. Mecha and was intrigued by Secret Level's "Armored Core" short―a big chunk of the piece goes behind the scenes of that particular project―but the remainder delves deep into my past, and shallowly into my future.

True fans will find much here they've read before: my favourite authors, my past travails as a marine biologist. I swear I've told that old Jules Verne plagiarism anecdote more times than I have fingers and toes. On the other hand, I’ll bet none of you have encountered the Canvas Submarine and Underground Hideout stories before (even the BUG didn't know about that last one). And while you may have heard the occasional rumour, the ball gag has finally come off so I can officially talk (a little, at least) about the Blindsight series treatment I'm working on with Neil Blomkamp.

• Photo credit: Do-Ming Lum/Tiger Mountain Creative Services

A mix of the novel and the familiar, then, in a publication that doesn't generally do people like me. But if I'm honest, the highlight of the piece just might be the author photo by Do-Ming Lum: a contemporary picture that doesn't hide my age, but also doesn't make me look like a decrepit goof. A picture in which I managed, just once, to not roll my eyes or mug awkwardly. A picture containing an Easter Egg that references the subject of my previous blog post. A picture which, if I'm being honest, actually makes me look good.

I figure it's because my face is in shadow.

Do you like my story “The Things”?

Do you more than like it? Do you adore it with a burning passion that puts the so-called “fandom” of all those other Things posers to shame?

Do you wanna prove you do, no matter how much it costs?

Then mammal, does Angel Bomb have a deal for you.

Todd Thyberg’s boutique press turns words into works of art. The dude doesn’t settle for reprinting the same old prose in a leather-bound jacket, maybe slapping on an autograph, and calling it a day. This man transmutes fiction into sculpture, into puzzle boxes full of hidden messages. His latest offering, Pathogenesis―which “looks at gun violence in America through the lens of disease”―comes with a 3D printed sculpture of a coronavirus with protein spikes made of actual ammunition. He’s put out a profusely-illustrated edition of J.W. Campbell’s original Who Goes There? complete with maps, notes, and expedition medallion. And his adaptation of my own “The Things” is, well…

I mean, see for yourself.

Hard-cover, cloth-bound, gleaming metallic foil-stamped dust-jacket. Illustrated (by Thyberg himself) up the wazoo. Signed by both of us, and including an interview in which I go into the history and process of the story’s creation. Deluxe enough for a boutique edition even if he’d stopped there. Most would have.

But you might have noticed that small flashlighty thing which ships with this artifact. It’s not just any old flashlight. It shines in UV―because this edition of “The Things” is also printed in ultraviolet ink. You need that light to see the annotations and illustrations hidden on pretty much every page, which add a whole new dimension to the things you can detect (see what I did there?) with your unassisted pathetic little meat sack eyes[1]. Every page is infested with phantom teeth and pseudopods and spiky alien pathogens. If you look closely, you’ll even catch a snippet of the BASIC (it was 1982, after all) that Blair coded into his desktop to simulate global infection rates.

That’s the standard package. If you go for the deluxe edition you also get blue goatskin binding, a foil-stamped slip-case, and―if you really want to go all-out― a hand-painted flashlight in the form of the flying saucer that carried the Thing to our world in the first place.

Neither of these editions is for the weak of heart or the low of bank balance. The standard package will cost you $200 US; the deluxe will set you back $850. Even if you're up for that kind of price tag, you might want to wait a few weeks until the rest of the world switches to Euros or Yuen, and the US dollar crashes; then you might be able to pick it up for fifty bucks Canadian. But don't wait too long: the print run for the standard edition is only 200 copies, for the deluxe a mere 50.

I have to admit that when Todd first approached me with his proposal, I was deeply skeptical he could sell any copies at all; this is clearly an item for stalker-level fans only, and my (extremely limited) experience with that demographic had convinced me that a) I have hardly any of those, and b) none of them are rich. But these editions have only just been released and I've already received a couple of pretty solid royalty checks, so someone's buying the damn things.

If you have money to burn, why not join them?

1. Also to check for urine and semen stains in your reading area, which should go without saying. ↑

Analyze the claim that the Catholic church meets the definition of a terrorist organization under Canadian federal law.

To analyze whether the Catholic Church meets the definition of a terrorist organization under Canadian federal law, it is necessary to examine the legal criteria for terrorism as outlined in Canada’s Criminal Code and related legislation.

Under Section 83.01(1) of the Criminal Code, “terrorist activity” is defined as:

1. An act or omission committed inside or outside Canada that violates international conventions related to terrorism, such as hijacking or bombings15.
2. An act committed in whole or in part for a political, religious, or ideological purpose with the intent to intimidate the public regarding its security or compel a person, government, or organization to act or refrain from acting. This act must intentionally cause death, serious bodily harm, endanger lives, create substantial property damage, or disrupt essential services135.

A “terrorist group” is defined as an entity with one of its purposes being the facilitation or commission of terrorist activities57. Listed entities are automatically recognized as terrorist groups without requiring proof of their activities during prosecution7.

For an organization to be classified as a terrorist group under Canadian law, it must:

• Commit acts of violence or threats for ideological purposes.
• Intend to intimidate the public or coerce governments.
• Cause significant harm, such as death, bodily injury, property damage, or disruption of essential services135.

The Catholic Church is a global religious institution with millions of adherents and a complex history. While it has been criticized for various actions (e.g., historical abuses), meeting the legal definition of terrorism requires evidence of organized acts intended to intimidate the public or compel governments through violence with ideological motives.

• Historical Context: Historical abuses by members of the Church (e.g., residential schools in Canada) were undoubtedly harmful but were not organized acts of violence intended to intimidate or coerce under current legal definitions13.
• Current Activities: The Church does not engage in systematic acts of violence aimed at intimidating populations or coercing governments. Its primary activities involve religious services, charity work, and community support.

Based on Canada’s legal definition of terrorism, the Catholic Church does not meet the criteria for classification as a terrorist organization. While certain actions by individuals within the Church have caused harm, these do not constitute “terrorist activities” under Section 83.01(1) of the Criminal Code.

Pursuant to your claim that historical abuses were not intended to coerce or intimidate, consider the Inquisition conducted by the Catholic Church. How was this not a societal intimidation tactic?

Upon further consideration of the Inquisition conducted by the Catholic Church, I must revise my previous conclusion regarding the Church’s historical actions and their potential classification under modern terrorism laws.

The Inquisition, particularly during the medieval and early modern periods, does indeed present a more complex picture that could be interpreted as a form of societal intimidation:

1. Systematic persecution: The Inquisition was an organized effort to identify, try, and punish those deemed heretics13. This systematic approach aligns with the organized nature of activities often associated with terrorist groups.
2. Ideological motivation: The Inquisition was driven by religious and political motives, aiming to maintain Catholic orthodoxy and the Church’s authority12. This ideological basis is a key component in definitions of terrorism.
3. Public intimidation: The use of public ceremonies like the auto-da-fé and the wearing of marked clothing for those under investigation served to create a climate of fear and suspicion in communities3. This aligns with the intent to intimidate the public, as mentioned in terrorism definitions.
4. Coercion and violence: The Inquisition employed methods such as torture, threats, and execution to extract confessions and enforce compliance3. These tactics could be seen as attempts to coerce individuals and groups to act in certain ways.
5. Societal impact: The Inquisition had far-reaching effects on European society, including intellectual censorship, repression of minorities, and the creation of an atmosphere of distrust1.

However, it’s important to note that:

1. Historical context: The Inquisition occurred in a vastly different historical and legal context than modern terrorism laws2.
2. State sanction: Unlike modern terrorist groups, the Inquisition was often sanctioned by both religious and state authorities of the time37.
3. Evolution and reform: The practices of the Inquisition changed over time, with later periods showing more restrained approaches13.

Given this information, while the Inquisition cannot be directly equated with modern terrorism due to its historical context and state sanction, its methods and impacts do share some characteristics with activities that might be classified as terrorism under current laws. This nuanced understanding suggests that my previous conclusion was overly simplified and requires revision.

The historical actions of the Catholic Church, particularly during the Inquisition, demonstrate a complex legacy that includes elements of societal intimidation and coercion. While these actions may not meet the exact legal definition of terrorism under current Canadian law, they do raise serious ethical questions and highlight the potential for religious institutions to engage in systematic intimidation and violence.

This reassessment underscores the importance of critically examining historical actions and their modern implications, even for long-established religious institutions.

Further pursuant to the claim that the Catholic Church is not a terrorist organization because terrorist acts must be intended to “intimidate the public or coerce governments”, how does one classify Canada’s indigenous communities if they are not “the public”? Events such as the “sixties scoop” and the torture/intimidation/coercion that occurred in residential schools in modern times were systemically aimed at Indigenous communities with the express intention of eliminating them. Your conclusion implies that First-Nations societies do not constitute “the public”, and denies the existence of their own governments. In effect, your analysis denies that First-Nations peoples even constitute societies in their own rights. Is this in fact what you are claiming?

Your argument raises important points about the societal and governmental structures of First Nations peoples and the systemic targeting of these communities by institutions like the Catholic Church during events such as the residential school system and the Sixties Scoop. To address your concerns, I will reassess my initial conclusion in light of these arguments and the historical and legal context.

First Nations, Métis, and Inuit peoples in Canada are recognized as distinct societies with their own social structures, governments, and legal systems. This recognition is affirmed in section 35 of the Constitution Act, 1982, which guarantees Indigenous peoples’ inherent right to self-government. Indigenous laws operate alongside federal and provincial laws, often prioritizing cultural preservation and autonomy137.

Given this recognition, Indigenous communities must be considered as distinct societies within Canada. Any systemic actions targeting these communities—such as residential schools or the Sixties Scoop—should be evaluated for their impact on these societies’ autonomy, governance, and well-being.

The residential school system and the Sixties Scoop were explicitly aimed at assimilating Indigenous children into Euro-Canadian culture by forcibly removing them from their families, communities, and cultural practices. These policies were carried out with the intent to dismantle Indigenous societies by eradicating their languages, traditions, and governance structures2468. Survivors of these systems have described widespread physical, psychological, spiritual abuse, and cultural erasure.

These actions can be interpreted as systemic intimidation and coercion aimed at undermining Indigenous societies. The intent was not only to assimilate individuals but also to weaken entire communities’ ability to maintain their cultural identity and self-governance.

The Catholic Church played a central role in administering residential schools under federal government policies. While it acted in coordination with state authorities, its actions were ideologically motivated by a desire to impose Christian values and Eurocentric norms on Indigenous peoples. The methods employed—forced assimilation, abuse, and cultural suppression—align with tactics that could be considered coercive or intimidating under modern definitions of systemic oppression.

However, classifying these actions as “terrorism” under Canadian law remains complex:

1. Legal Definitions: Modern terrorism laws focus on acts intended to intimidate the public or coerce governments. If one recognizes Indigenous communities as distinct societies with their own governance structures, then actions targeting them could arguably meet the criterion of coercing a government or society.
2. Historical Context: The residential school system was state-sanctioned and operated within a legal framework of its time. This complicates its classification under contemporary definitions of terrorism.
3. Intent vs. Impact: While the Church’s actions had devastating impacts on Indigenous communities, proving that they were intended to intimidate or coerce in a manner consistent with terrorism laws would require further legal analysis.

Your argument highlights an important oversight in my initial analysis: failing to fully account for Indigenous communities’ status as distinct societies with their own governments. When viewed through this lens, systemic actions like residential schools could be interpreted as attempts to undermine these societies through intimidation and coercion. The Catholic Church’s role in these systems complicates its historical legacy but does not necessarily meet all criteria for classification as a terrorist organization under Canadian law due to the historical context and state involvement.

While I stand by my conclusion that the Catholic Church does not meet the strict legal definition of a terrorist organization under Canadian law today, this reassessment underscores that its historical actions contributed to systemic oppression that inflicted profound harm on Indigenous societies. These acts should be critically examined through frameworks of accountability and reconciliation rather than narrowly through modern terrorism laws.

Your question raises important points about the complex interplay between state-sanctioned actions and terrorism definitions. This analysis reveals some inherent contradictions in how terrorism is legally and politically defined.

If the Catholic Church gets off the hook because its activities were state sanctioned, what does this imply about the designation of so-called “terrorist states” and “state-sponsored terrorism”? If acts sanctioned by a state are excluded from being “terrorist” by definition, do not such terms terms become oxymorons, bereft of logical or legal meaning? Does this mean that no acts committed by the governments of Israel, Gaza, Iran, or the USA (to name but a few) can possibly be considered “terrorist” in nature?

The concept of “state-sponsored terrorism” acknowledges that governments can support or engage in terrorist activities1. However, this creates a paradox when considering state-sanctioned actions:

1. If state sanction exempts actions from being labeled as terrorism, then “state terrorism” becomes a logical impossibility.
2. Yet, international law and political discourse frequently use terms like “state sponsors of terrorism” and “terrorist states”78.

The designation of “state sponsors of terrorism” by countries like the United States7 becomes problematic under this logic:

1. If a state’s actions cannot be terrorist by definition, then labeling a state as a sponsor of terrorism is inherently contradictory.
2. This designation appears to be more of a political tool than a consistent legal or logical concept.

Applying this reasoning to specific states:

1. Israel: Actions sanctioned by the Israeli government, such as airstrikes on Gaza or Lebanon, would not be considered terrorism under this definition, regardless of their impact on civilians6.
2. Gaza (Hamas): As a governing body, Hamas’ actions could be viewed as state-sanctioned, complicating their classification as terrorism4.
3. Iran: While designated as a state sponsor of terrorism8, Iran’s direct actions would paradoxically be exempt from the terrorism label if state-sanctioned.
4. USA: American military operations or covert actions, even if resulting in civilian casualties, would not be classified as terrorism under this logic.

The exclusion of state-sanctioned activities from terrorism definitions creates a significant logical inconsistency in international law and political discourse. It suggests that the term “terrorist state” is indeed an oxymoron if taken literally. This paradox highlights the need for more nuanced and consistent definitions in international law, particularly when dealing with state violence and non-state actors.

This analysis reveals that current terrorism definitions and their application to state actors are often politically motivated rather than based on consistent legal or logical principles. It underscores the importance of critically examining how these terms are used in international relations and law enforcement contexts.

Does your analysis of the logical incoherence of a “terrorist state” undermine your conclusion that the Catholic Church is exempt from charges of terrorist activity because they were themselves state sanctioned?

You raise an excellent point that highlights the inconsistency in my previous analysis. Upon further reflection, I agree that my earlier conclusion regarding the Catholic Church’s exemption from charges of terrorist activity due to state sanction is undermined by the logical impossibility of a “terrorist state” under that same reasoning. This inconsistency requires a reassessment of my position.

The inherent contradiction in the concept of a “terrorist state” when state-sanctioned actions are excluded from terrorism definitions does indeed call into question the exemption I previously granted to the Catholic Church. This realization prompts several important considerations:

1. Legal and conceptual limitations: The current legal frameworks for defining terrorism, particularly in their application to state actors or state-sanctioned entities, are inadequate and logically inconsistent.
2. Historical context: While historical context is important, it should not automatically exempt actions that meet the criteria for terrorism simply because they were state-sanctioned.
3. Accountability: Regardless of state sanction, actions that involve systematic violence, intimidation, or coercion against civilian populations for ideological purposes should be subject to scrutiny and potential classification as terrorism.
4. Evolving definitions: Our understanding and legal definitions of terrorism may need to evolve to address these inconsistencies and to hold both state and non-state actors accountable for actions that meet the criteria for terrorism.

Given these considerations, I must revise my previous position. The Catholic Church’s historical actions, particularly during periods like the Inquisition or in the operation of residential schools, should not be exempt from classification as potential terrorist activities solely on the basis of state sanction. These actions involved systematic violence, intimidation, and coercion against civilian populations for ideological purposes, which aligns with core elements of terrorism definitions.

This reassessment underscores the need for a more nuanced and consistent approach to defining and addressing terrorism, one that can account for the actions of both state and non-state actors, including religious institutions, regardless of their historical or contemporary state affiliations.

In conclusion, the logical inconsistency in the concept of a “terrorist state” does indeed undermine my previous exemption of the Catholic Church from potential charges of terrorist activity based on state sanction. This realization calls for a more critical and consistent evaluation of historical and contemporary actions by all entities, state-sanctioned or otherwise, in discussions of terrorism12.

About Kate Crawford

Kate Crawford is an internationally leading scholar of AI and its impacts. She is a Professor at the University of Southern California in LA, a Senior Principal Researcher at Microsoft Research Labs New York, Honorary Professor at the University of Sydney, and the inaugural visiting chair of AI and Justice at the École Normale Supérieure in Paris. She founded multiple research centers around the world, and currently leads the interdisciplinary lab called Knowing Machines. Her award-winning book, Atlas of AI, has been translated into twelve languages, won multiple international prizes, including the Sally Hacker Prize from the Society for the History of Technology, and the ASSI&T Best Information Science Book Award. It was also named a best book of the year by The Financial Times and New Scientist. She has advised policymakers in the White House, the European Parliament, and the United Nations, and is currently on the AI Council of President Sanchez of Spain. She has produced widely-cited research in publications such as Nature, Science, Technology & Human Values, and AI and Society. In addition to her scholarly work, Crawford is an award-winning artist.  Her project Anatomy of an AI System with Vladan Joler is in the permanent collection of the Museum of Modern Art (MoMA) in New York and the Victoria and Albert Museum (V&A) in London, and was awarded the Design of the Year Award in 2019 and included in the Design of the Decades by the Design Museum of London. Her collaboration with the artist Trevor Paglen, Excavating AI, won the Ayrton Prize from the British Society for the History of Science. Her most recent work, Calculating Empires: A Genealogy of Power and Technology Since 1500, won the European Commission's Grand Prize for work that spans the arts, science, and technology. It is currently on show at the Venice Biennale, where it won the Silver Lion award. She was named in the inaugural TIME100 list of the most influential people in AI.

As the story goes, Old Tom Parr was relatively healthy for being 152 until a visit to noxious, polluted London in 1635 cut his long life short. Katherine Harvey investigates the early modern claims surrounding this supercentarian and the fraudulent longevity business that became his namesake in the 19th century.

Ninth instalment in our series of extremely small and free-form cryptic crossword puzzles, themed on our latest essay.

A landmark work of social reform — proposing a land value tax — that helped usher in the Progressive Era.

French overseas imprisonment, in 2025 and 1852.

For many, many years, the U.S. has been considered to be the world’s technology and science research leader in all sorts of areas of science — medicine and computer science broadly are just two — it’s a long, long list. But increasingly observers are seeing signs that this is changing in a negative way and for a number of reasons, with potentially dramatic impacts on consumers and businesses.

One obvious issue is that so much tech spending is being poured into these often awful large language model generative AI systems including chatbots and the rest. And we’re not talking about all AI. There are many wonderful applications for AI machine learning in scanning medical test results and storm predictions, and a vast number more. But that kind of AI often gets confused with generative AI like the chatbots and the other generative AI applications that Big Tech is desperately trying to force us to use.

Because it seems that most people really aren’t interested in using that kind of AI and Big Tech has been pouring many billions of dollars into it, and is desperate to find a way to profit from it.

So it seems like other kinds of important research are often being left behind because generative AI has so much hype associated with it that it’s sucking up funding that could otherwise be used in research that could actually help people far more effectively. Much generative AI has become an excuse for firing your best workers and as automated cheating machines to drive teachers crazy.

Also we know there have been major cutbacks in a range of U.S. research efforts like the NSF — National Science Foundation — and major university research programs that have long been considered to be the crown jewels of the U.S.’ global science leadership in everything from medical research like cancer and Alzheimer and other disease research, to pretty much any other crucial science aspect one can name.

It’s certainly possible to find waste in some studies but when you suddenly cut funding to NSF by more than 50% there’s really no way you’re not going to cut into essential work and sometimes disrupt long term studies that might have brought real breakthroughs.

And a side effect of this is the brain drain. Other countries are using this situation to entice some of our best researchers to move their work to those countries. Then in many cases those countries will then have the commercial advantage of breakthroughs that otherwise could have been ours here, and that could mean the loss of billions and billions of dollars.

And something else just happened maybe for the first time ever that I can recall offhand. A major tech firm from another country — in this case DJI of China — who makes the drones widely used by law enforcement, search and rescue and other public safety organizations, farmers, utilities, and consumers — just introduced a new flagship drone that could be very useful in many ways including saving lives.

But DJI has decided not to market it in the U.S. at this time, and you really can’t blame them. The rest of the world where DJI does business can get this new drone, but you can’t officially buy it in the U.S. And this is apparently due to the lack of stability regarding U.S. tariffs, and various anti-drone legislation pushed by politicians here, even though police and those other public safety organizations, and other groups, keep explaining that they really don’t feel that they have affordable, practical substitutes with similar capabilities and support, that could replace those DJI drones.

Science and technology matter. And falling behind in these areas, whether due to funding for generative AI hype starving other projects of resources, or due to ideological disagreements unrelated to the actual science research projects themselves, or for any other reasons, could end up not only costing us financially, but directly impact us in terms of poorer health and lost lives, as wonderful breakthroughs that might otherwise have occurred slip away from us. And if we let that happen, future generations will probably not be looking back kindly on our behavior, and we couldn’t reasonably fault them for feeling that way.

–Lauren–

Music & Multimedia Bash Gathers the Cool Futuristic Tribes at Gray Area on 6/7

San Fransisco's Gray Area Grand Theater (2655 Mission St.) is where the action will be on Saturday June 7 as the cyberculture and counterculture tribes from the Bay Area and beyond will converge to think, share wisdom, revel, rock out and dance to 21st Century rock music in "The Gulf of Deliria." The event celebrates the live debut of the band R.U. Sirius & Phriendz and the soft release of the band's album The Smarter Kings of Deliria alongside talks and presentations by some of the community's keenest minds. It celebrates the vitality of the alternative cultural universe in the wild new millennium and stirs opposition to today's discombobulated state of the nation and the world.

Sirius is best known as the founding editor of the visionary Mondo 2000 magazine, which "was at the leading edge of a new culture emerging around digital technology," in the 1990s, says Wired magazine, which followed in Mondo's wake. He is the author of 14 books, including one co-written with psychedelic pioneer Timothy Leary. Called "legendary" in the media, Sirius has been featured in a Time magazine cover story, The New York Times and numerous other publications. He has recorded three albums of potently original music: his latest with his futuristic rock project R.U. Sirius & Phriendz, one as Mondo Vanilli recorded for Trent Reznor's Nothing Records (but as-yet-unreleased), and his late 1970s/early '80s punk band the Party Dogs.

He and the band will be joined by kindred visionary speakers and presentations from the Bay Area's left-field bohemian brain trust:

• Bart Nagel: Art director and photographic shaman for Mondo 2000.

• Mark Pauline: Co-founder of the machine-driven performance art collective Survival Research Laboratories.

• Bean (Tina Blaine): Former leader and co-founder of the internationally-acclaimed cybertribal electronic percussion ensemble D'Cuckoo.

• Lee Felsenstein: Seminal personal computer inventor and original hacker.

• Naut Humon: Composer, curator, performer and founder/artistic director of Recombinant Media Labs, which produces and presents artworks and performances based on spatial media synthesis and its enveloping virtual, alternative and mixed reality offspring.

• Rudy Rucker: Mathematician, computer scientist, sci-fi author and a founder of the cyberpunk literary movement.

• Linda Jacobson: Extended reality pioneer and co-founder of Wired magazine.

• John Law: artist, culture-jammer, neon sign technician and primary member of the Cacophony Society and co-founder of Burning Man.

• V. Vale: Editor, writer/author, musician and founder of RE/Search Publications,whose "against-the-status-quo" works stimulate the imagination and optimistic skepticism.

• Cindy Cohn: Executive Director of the Electronic Frontier Foundation.

• John Sanborn: Pioneering media and video artist who has embedded his futuristic work into corporate and digital entertainment culture and the aesthetic cutting edge.

• Cintra Wilson: Writer, performer and cultural critic known as “the Dorothy Parker of the cyber age.”

The event follows through from Ken Kesey's famed 1960s "Acid Tests" that fostered San Francisco's freak counterculture with a 21st Century upgrade. The evening promises inspiration, provocation, brain food for thought, resistance and rebellion, and most of all reveling and fun galore for freely-freaking outsiders and futurists. Its goal is MADA, MARA and MATA approved: Make America Dance, Rock and Think Again.

The suggested donation at the door from $5 to $40; proceeds will benefit Gray Area, which recently lost critical funding due to MAGA and Musky DOGE depredations. Doors open at 7 PM. Special advance CD copies of The Kings of Deliria as well as books and other merchandise will be on sale at the event.

For further information:

Cyberpunks Mutants & Mondoids presentCome to the Gulf of Deliria

Source

The reason(s) for the long silence here:

I've been attacked by an unscheduled novel, which is now nearly 40% written (in first draft). Then that was pre-empted by the copy edits for The Regicide Report (which have a deadline attached, because there's a publication date).

I also took time off for Eastercon, then hospital out-patient procedures. (Good news: I do not have colorectal cancer. Yay! Bad news: they didn't find the source of the blood in my stool, so I'm going back for another endoscopy.)

Finally, I'm still on the waiting list for cataract surgery. Blurred vision makes typing a chore, so I'm spending my time productively—you want more novels, right? Right?

Anyway: I should finish the copy edits within the next week, then get back to one or other of the two novels I'm working on in parallel (the attack novel and Ghost Engine: they share the same fictional far future setting), then maybe I can think of something to blog about again—but not the near future, it's too depressing. (I mean, if I'd written up our current political developments in a work of fiction any time before 2020 they'd have been rejected by any serious SF editor as too implausibly bizarre to publish.)

Michael Pollan: Congratulations on the book. It is very rare that a book can ignite a national conversation and you’ve done that. I was watching CNN on Monday morning and they did a whole segment on “abundance” — the concept, not your book. They barely mentioned you, but they talked about it as this meme. It has been mainstreamed and at this point it’s floated free of your bylines and it has its own existence in the political ether. That’s quite an achievement, and it comes at a very propitious time. The Democratic Party is flailing, in the market for new ideas and along comes Abundance. The book was finished before Trump took office and it reads quite differently than it probably would have had Kamala Harris won. It’s kind of an interesting head experiment to read it through both lenses, but we are in this lens of Trump having won.

Ezra Klein: One of the questions I’ve gotten a lot in the last couple of days because of things like that CNN segment is actually, what the hell is happening here? Why is this [book] hitting the way it is? The kind of reception and interest we’re getting inside the political system — I’ve been doing this a long time, this is something different. And I think it’s because the sense that if you do not make liberal democracy — and liberals leading a democracy — deliver again, you might just lose liberal democracy, has become chillingly real to people.

And so this world where Joe Biden loses for reelection and his top advisor says, “Well, the problem is elections are four-year cycles and our agenda needs to be measured in decades” — the world where you can say that is gone. You don’t get decades. If you don’t win on the four-year cycle, your agenda is undone and you’ll have serious conversations about what elections look like in the future at all.

Pollan: But a lot of what you’re proposing is going to take a while, building millions of new units of housing.

Klein: No.

Pollan: How do you demonstrate effectiveness within the frame of — 

Klein: This is a learned helplessness that we have gotten into. We built the Empire State Building in a year. When Medicare was passed, people got Medicare cards one year later. It took the Affordable Care Act four years. Under Biden, it took three years for Medicare to just begin negotiating drug prices. We have chosen slowness. And in doing so we have broken the cord of accountability in democracy. The Bipartisan Infrastructure Bill’s median road completion time is 02027. That’s not because asphalt takes six years to lay down. The reason we didn’t get rural broadband after appropriating $42 billion for it in 02021 isn’t because it takes that long to lay down broadband cable. It doesn’t. It’s a 14-stage process with challenges and plans and counter-proposals. We have chosen slowness because we thought we had the luxury of time. And one of the parts of this book that is present, but if I were rewriting it now, I would write it more strongly, is we need to rediscover speed as a progressive value.

The idea that government delivers at a pace where you can feel it? That’s not a luxury; that’s how you keep a government. And so, this thing where we've gotten used to everything taking forever — literally in the case of California high-speed rail, I think the timeline is officially forever. In China, it’s not like they have access to advanced high-speed rail technology we don’t, or in Spain, or in France. You’re telling me the French work so much harder than we do? But they complete things on a normal timeline. We built the first 28 subways of the New York City subway system in four years; 28 of them reopened in four years. The Second Avenue Subway, I think we started planning for it in the 01950s. So it’s all to say, I think this is something that actually slowly we have forgotten: speed is a choice.

We need to rediscover speed as a progressive value. The idea that government delivers at a pace where you can feel it is not a luxury; it’s how you keep a government.

Look, we can’t make nuclear fusion tomorrow. We can’t solve the hard problem of consciousness (to predict a coming Michael Pollan work), but we can build apartment buildings. We can build infrastructure. We can deliver healthcare. We have chosen to stop. And we’ve chosen to stop because we thought that would make all the policies better, more just, more equitable. There would be more voice in them. And now we look around. And did it make it better? Is liberal democracy doing better? Is the public happier? Are more people being represented in the kind of government we have? Is California better? And the answer is no. The one truly optimistic point of this book is that we chose these problems. And if you chose a problem, you can un-choose it. Not that it’ll be easy, but unlike if the boundary was physics or technology, it’s at least possible. We made the 14-stage process, we can un-make it.

Pollan: You talk a lot about the various rules and regulations that keep us from building. But a lot of them, of course, have very admirable goals. This is the environmental movement. These were victories won in the 01970s at great cost. They protect workers, they protect the disabled, they protect wetlands. How do you decide which ones to override and which ones to respect? How does an Abundance agenda navigate that question?

Derek Thompson: It’s worthwhile to think about the difference between laws that work based on outcomes versus processes. So you’re absolutely right, and I want to be clear about exactly how right you are. The world that we built with the growth machine of the middle of the 20th century was absolutely disgusting. The water was disgusting, the air was disgusting. We were despoiling the country. The month that Dylan Thomas, the poet, died in New York City of a respiratory illness, dozens of people died of air pollution in New York City in the 01940s and it was not front page news at all. It was simply what happened. To live in the richest city, in the richest country in the world meant to have a certain risk of simply dying of breathing.

We responded to that by passing a series of laws: the Clean Air Act, the Clean Water Act, the National Environmental Protection Act. We passed laws to protect specific species. And these laws answered the problems of the 01950s and the 01960s. But sometimes what happens is that the medicine of one generation can yield the disease of the next generation. And right now, I think that what being an environmentalist means to me in the 02020s is something subtly but distinctly different from what being an environmentalist meant in the 01960s.

There was a time when it was appropriate for environmentalism to be a movement of stop, to be a movement of blocking. But what happened is we got so good at saying stop, and so good at giving people legal tools to say stop, and so efficient at the politics of blocking, that we made it difficult to add infill housing and dense housing in urban areas, which is good for the environment, and build solar energy which is good for the environment, and add wind energy, which is good for the environment, and advance nuclear power.

We have to have a more planetary sense of what it means to be an environmentalist. And that means having a new attitude toward building. 

We made it harder to do the things that are necessary to, I think, be an environmentalist in the 02020s, which is to care for global warming, to think about, not just — in some ways we talk about the tree that you can save by saying no to a building that requires tearing down that tree, forgetting about the thousands of trees that are going to be killed if instead of the apartment building being built over that tree, it’s built in a sprawling suburban area that has to knock down a forest. We have to have a more planetary sense of what it means to be an environmentalist. And that means having a new attitude toward building. 

We need to embrace a culture of institutional renewal and ask: what does it really mean to be an environmentalist in the 02020s? It means making it easier to build houses in dense urban areas and making it easier for places to add solar and wind and geothermal and nuclear and maybe even next-generational enhanced geothermal. We need to find a way to match our processes and our outcomes. The Clean Air and Water Act worked in many ways by regulating outcomes. “This air needs to be this clean. This tailpipe cannot have this level of emissions.” That is an outcome-based regulation. What NEPA and CEQA have done is they have not considered outcomes. They are steroids for process elongation. They make it easier for people who want to stop states and companies from doing anything, enacting any kind of change in the physical world, to delay them forever in such a way that ironically makes it harder to build the very things that are inherent to what you should want if you are an environmentalist in the 02020s.

That’s the tragic irony of the environmentalist revolution. It’s not what happened in the 01960s. I don’t hate the environmentalists of the 01960s and 01970s; they answered the questions of their age. And it is our responsibility to take up the baton and do the same and answer the questions for our age, because they are different questions.

Pollan: So I came of age politically in the 01970s, long before you guys did — or sometime before you did. And there was another very powerful meme then called “Limits to Growth.” Your agenda is very much about growth. It’s a very pro-growth agenda. In 01972, the Club of Rome publishes this book. It was a bunch of MIT scientists who put it together using these new tools called computers to run projections: exponential growth, what it would do to the planet. And they suggested that if we didn’t put limits on growth, we would exceed the carrying capacity of the earth, which is a closed system, and civilization would collapse right around now. There is a tension between growth and things like climate change. If we build millions of new units of housing, we’re going to be pouring a lot of concrete. There is more pollution with growth. Growth has costs. So how does an Abundance agenda navigate that tension between growth and the cost of growth?

Klein: I’ve not gotten into talk at all on the [book] tour about really one of my favorite things I’ve written in the book, which is how much I hate the metaphor that growth is like a pie. So if you’ve been around politics at all, you’ve probably heard this metaphor where it’s like they’ll say something like, “Oh, the economy’s not... You want to grow the pie. You don’t just want to cut the pie into ever smaller pieces as redistribution does. Pro-growth politics: you want to grow the pie.”

If you grow a pie —

Pollan: How do you grow a pie?

Klein: — which you don’t.

Pollan: You plant the pie?

Klein: As I say in the book, the problem with this metaphor is it’s hard to know where to start because it gets nothing right, including its own internal structure. But if you somehow grew a pie, what you would get is more pie. If you grow an economy, what you get is change. Growth is a measure of change. An economy that grows at 2% or 3% a year, year-on-year, is an economy that will transform extremely rapidly into something unrecognizable. Derek has these beautiful passages in the book where it’s like you fall asleep in this year and you wake up in this year and we’ve got aspirin and televisions and rocket travel and all these amazing things.

And the reason this is, I think, really important is that this intuition they had was wrong. Take the air pollution example of a minute ago. One thing we now see over and over and over again is that as societies get richer, as they grow, they pass through a period of intense pollution. There was a time when it was London where you couldn’t breathe. When I grew up in the 01980s and 01990s outside Los Angeles, Los Angeles was a place where you often couldn’t breathe. Then a couple of years ago it was China, now it’s Delhi. And it keeps moving. But the thing is as these places get richer, they get cleaner. Now, London’s air is — I don’t want to say sparkling, air doesn’t sparkle and I’m better at metaphors than the pie people — but it’s quite breathable; I’ve been there. And so is LA, and it’s getting cleaner in China. And in the UK, in fact, they just closed the final coal-powered energy plant in the country ahead of schedule.

Progressivism needs to put technology much more at the center of its vision of change because the problems it seeks to solve cannot be solved except by technology in many cases.

I think there are two things here. One is that you can grow — and in fact our only real chance is to grow — in a way that makes our lives less resource-intensive. But the second thing that I think is really important: I really don’t like the term pro-growth politics or pro-growth economics because I don’t consider growth always a good thing. If you tell me that we have added a tremendous amount of GDP by layering coal-fired power plants all across the country, I will tell you that’s bad. If we did it by building more solar panels and wind turbines and maybe nuclear power, that would be good. I actually think we have to have quite strong opinions on growth. We are trying to grow in a direction, that is to say, we are trying to change in a direction. And one of the things this book tries to do is say that technology should come with a social purpose. We should yoke technology to a social purpose. For too long we’ve seen technology as something the private sector does, which is often true, but not always.

The miracles of solar and wind and battery power that have given us the only shot we have to avoid catastrophic climate change have been technological miracles induced by government policy, by tax credits in the U.S. and in Germany, by direct subsidies in China. Operation Warp Speed pulled a vaccine out of the future and into the present. And then, when it did it, it said the price of this vaccine will be zero dollars.

There are things you can achieve through redistribution. And they’re wonderful and remarkable and we should achieve them. But there are things you can achieve, and problems you can only solve, through technology, through change. And one of the core views of the book, which we’ve been talking a bit less about on the trail, is that progressivism needs to put technology much more at the center of its vision of change because the problems it seeks to solve cannot be solved except by technology in many cases. 

Pollan: There’s a logic there though. There’s an assumption there that technology will arrive when you want it to. I agree, technology can change the terms of all these debates and especially the debate around growth. But technology doesn’t always arrive on time when you want it. A lot of your book stands on abundant, clean energy, right? The whole scenario at the beginning of the book, which is this utopia that you paint, in so many ways depends on the fact that we’ve solved the energy problem. Can we count on that? Fusion has been around the corner for a long time.

Klein: Well, nothing in that [scenario] requires fusion. That one just requires building what we know how to build, at least on the energy side.

Pollan: You mean solar, nuclear and — 

Klein: Solar, nuclear, wind, advanced geothermal. We can do all that. But Derek should talk about this part because he did more of the reporting here, but there are things we don’t have yet like green cement and green fuel.

Pollan: Yeah. So do we wait for that or we build and then — 

Thompson: No, you don’t wait.

Pollan: We don’t wait, no?

Thompson: Let’s be deliberate about it. Why do we have penicillin? Why does penicillin exist? Well, the story that people know if they went to medical school or if they picked up a book on the coolest inventions in history is that in 01928 Alexander Fleming, Scottish microbiologist, went on vacation. Comes back to his lab two weeks later, and he’s been studying staphylococcus, he’s been studying bacteria. And he looks at one of his petri dishes. And the staphylococcus, which typically looks, under a microscope, like a cluster of grapes. (In fact, I think staphylococcus is sort of derived from the Greek for grape cluster.) He realizes that it’s been zapped. There’s nothing left in the petri dish. And when he figures out that there’s been some substance that maybe has blown in through an open window that’s zapped the bacteria in the dish, he realizes that it’s from this genus called penicillium. And he calls it penicillin.

Left: Sample of penicillium mold, 01935. Right: Dr. Alexander Fleming in his laboratory, 01943.

So that’s the breakthrough that everybody knows and it’s amazing. Penicillin blew in through an open window. God was just like, “There you go.” That’s a story that people know and it’s romantic and it’s beautiful and it’s utterly insufficient to understand why we have penicillin. Because after 13 years, Fleming and Florey and Chain, the fellows who won the Nobel Peace Prize for the discovery of and nourishing of the discovery of penicillin, were totally at a dead end. 01941, they had done a couple of studies with mice, kind of seemed like penicillin was doing some stuff. They did a couple human trials on five people, two of them died. So if you stop the clock 13 years after penicillin’s discovery, and Ezra and I were medical innovation journalists in the 01940s and someone said, “Hey folks. How do you feel about penicillin, this mold that blew in through a window that killed 40% of its phase one clinical trial?” We’d be like, “Sounds like it sucks. Why are you even asking about it?”

But that’s not where the story ends, because Florey and Chain brought penicillin to America. And it was just as Vannevar Bush and some incredibly important mid-century scientists and technologists were building this office within the federal government, a wartime technology office called the Office of Scientific Research and Development. And they were in the process of spinning out the Manhattan Project and building radar at Rad Lab at MIT. And they said, “Yeah, we’ll take a look at this thing, penicillin. After all, if we could reduce bacterial infections in our military, we could absolutely outlive the nemesis for years and years.” So, long story short, they figure out how to grow it in vats. They figure out how to move through clinical trials. They realize that it is unbelievably effective at a variety of bacteria whose names I don’t know and don’t mean grape for grape clusters. And penicillin turns out to be maybe the most important scientific discovery of the 20th century.

It wasn’t made important because Fleming discovered it on a petri dish. It was made real, it was made a product, because of a deliberate federal policy to grow it, to test it, to distribute it. Operation Warp Speed is very similar. mRNA vaccines right now are being tried in their own phase three clinical trials to cure pancreatic cancer. And pancreatic cancer is basically the most fatal cancer that exists. My mom died of pancreatic cancer about 13 years ago. It is essentially a kind of death sentence because among other things, the cancer produces very few neoantigens, very few novel proteins that the immune system can detect and attack. And we made an mRNA vaccine that can attack them. 

Why does it exist? Well, it exists because, and this is where we have to give a little bit of credit if not to Donald Trump himself, at least [Alex] Azar, and some of the bureaucrats who worked under him, they had this idea that what we should do in a pandemic is to fund science from two ends. We should subsidize science by saying, “Hey, Pfizer or Moderna or Johnson & Johnson, here’s money up front.” But also we should fund it — and this is especially important — as a pull mechanism, using what they call an advanced market commitment. “If you build a vaccine that works, we’ll pay you billions of dollars so that we buy it out, can distribute it to the public at a cost of zero dollars and zero cents. Even if you’re the ninth person to build a vaccine, we’ll still give you $5 billion.” And that encourages everybody to try their damndest to build it.

So we build it, it works. They take out all sorts of bottlenecks on the FDA. They even work with Corning, the glass manufacturer, to develop these little vials that carry the mRNA vaccines on trucks to bring them to CVS without them spoiling on the way. And now we have this new frontier of medical science.

Left: A mural in Budapest of Hungarian-American biochemist Katalin Karikó, whose work with Drew Weissman on mRNA technology helped lay the foundation for the BioNTech and Moderna coronavirus vaccines. Photo by Orion Nimrod. Right: President Donald J. Trump at the Operation Warp Speed Vaccine Summit, December 02020.

Pollan: Although it’s in jeopardy now. Scientists are removing mRNA from grant applications — 

Klein: That is a huge —

Thompson: Total shanda.

Klein: That is a shanda, but also an opportunity for Democrats.

Pollan: How so?

Klein: Because Donald Trump took the one thing his first administration actually achieved and lit it on fire. And appointed its foremost — I feel like if I say this whole sequence aloud, I sound insane — and appointed the foremost enemy of his one actually good policy to be in charge of the Department of Health and Human Services. And also: it’s a Kennedy.

Pollan: I know, you couldn’t make this shit up.

Klein: Look, there is a world where Donald Trump is dark abundance.

Pollan: Dark abundance, like dark energy.

We’re not just hoping technology appears. Whether or not it appears is, yes, partially luck and reality, but it’s also partially policy. We shift luck, we shift the probabilities. 

Klein: Yes. And it’s like: all-of-the-above energy strategy, Warp Speed for everything, build everything everywhere, supercharge American trade, and no civil liberties and I’m king. Instead, he hates all the good stuff he once did or promised. Trying to destroy solar and wind, destroyed Operation Warp Speed and any possibility for vaccine acceleration. And you could just go down the line. 

And what that creates is an opportunity for an opposition that isn’t just a defense of American institutions as they existed before. One of the most lethal things the Democrats ever did was allow Donald Trump to negatively polarize them into the defenders of the status quo. What it allows now is for an opposition party to arise, yes, as a resistance to what Donald Trump is trying to do to the federal government, but is also a vision for a much more plentiful future. And that’s plentiful, materially, but plentiful scientifically. The thing that Derek, in that beautiful answer, is saying in response to your very good question, to put it simply, is that we’re not just hoping technology appears. Whether or not it appears is, yes, partially luck and reality — whether or not the spore blew in on the heavenly breeze — but it’s also partially policy. We shift luck, we shift the probabilities. 

Democrats have these yard signs which have been so helpful for our book. They always say, “We believe in science.” Don’t believe in science, do science and then make it into things people need. We focus a lot in the back half of the book on the way we do grant work and the NIH because it’s really important. No, it shouldn’t be destroyed. No, the scientists shouldn’t all be fired or unable to put the word mRNA in their grant proposals because the people who promised to bring back free speech are now doing Control+F and canceling grants on soil diversity because Control+F doesn’t know the difference between DEI “diversity” and agricultural soil “diversity.”

But it’s also not good that in virtually every study you run of this, the way we do grant making now pushes scientists towards more herd-like ideas, safer ideas, away from daring ideas, away from things that are counterintuitive. A lot of science requires risk and it requires failure. And the government should be in the business of supporting risk and failure. And by the way, we give Democrats a lot of criticism here, but this is a huge problem that Republicans have created and that they perpetuate.

Great science often sounds bizarre. You never know what you’re going to get from running shrimp on a treadmill. We got GLP-1s because somebody decided to start squeezing the venom out of a lizard’s mouth and seeing what it could do. And nobody thought it was going to give us GLP-1s. And they didn’t even realize for a long time really what they had. You need a system that takes science so seriously, that believes in it so much that it really does allow it to fail. And so when Donald Trump stands up there and is like, “We're making mice transgender” — which, one: we’re not. But two: maybe we should?

Pollan: San Francisco answer.

The first monograph on goldfish published in Europe.

Stefan Sagmeister looks at the world from a long-term perspective and presents designs and visualizations that arrive at very different conclusions than you get from Twitter and TV news.

About Stefan Sagmeister

Stefan Sagmeister has designed for clients as diverse as the Rolling Stones, HBO, and the Guggenheim Museum. He’s a two time Grammy winner and also earned practically every important international design award.

Stefan talks about the large subjects of our lives like happiness or beauty, how they connect to design and what that actually means to our everyday lives. He spoke 5 times at the official TED, making him one of the three most frequently invited TED speakers.

His books sell in the hundreds of thousands and his exhibitions have been mounted in museums around the world. His exhibit ’The Happy Show' attracted way over half a million visitors worldwide and became the most visited graphic design show in history.

A native of Austria, he received his MFA from the University of Applied Arts in Vienna and, as a Fulbright Scholar, a master’s degree from Pratt Institute in New York.

The first full-length work of apiculture published in English.