Robin Sloan
main newsletter
November 2022

Author’s note

The dance of death: the death blow, 1816, Thomas Rowlandson
The dance of death: the death blow, 1816, Thomas Rowlandson

My new short story was commis­sioned by Google and produced using a new AI-powered editor called Wordcraft. Titled Author’s Note, it is presented alongside new stories from several other very impres­sive writers.

I’ll say more about this project below, but first, I want to present the complete list of stories I’ve published in the past year:

There’s also the new editions of Mr. Penumbra’s 24-Hour Bookstore and Sourdough, both with their prequel stories. All in all, a pretty solid set of offerings!

While I’m mentioning those new editions, the ones with bonus material, I want to apologize for being so parochial in their promotion. “Hooray, Sourdough’s prequel story is now available!” announces Sloan — in his newsletter received by many thousands of people outside the U.S. to whom it is not, in fact, available.

The U.S. editions, and my rela­tion­ship with my U.S. publisher, are so front-and-center for me that it’s easy to forget about the global picture; but I really shouldn’t, and, in the future, I won’t.

Onward, to my … 

Notes on writing with Google’s AI

I’m going to dive into some detail here; it’s probably not for everyone, so if this subject doesn’t interest you, feel free to skip merrily ahead.

There is a ton of context about the overall Wordcraft project on the website; I really encourage anyone inter­ested in the inter­sec­tion of AI and art to spend some time exploring. These tech­nolo­gies are now mature enough that we can begin to move from spec­u­lating about their uses to … actually using them! And not only to make cool demos, but to do real work.

That last part, the “real work”, is important to me. I am done, personally, with the genre of “I see what you did there”—of making things that are note­worthy primarily for their appli­ca­tion of a frothy new tech­nology. That’s really saying something, because I have made a LOT of things like that! I spent several years engaged in AI writing explo­rations of my own, almost entirely in this spirit.

Approaching this project, I felt committed to writing a story that could stand on its own; a story that achieved the same things I want ANY of my stories to achieve; a story to which the response might be not, “I see what you did there”, but: “I loved this!”

Whether I succeeded, you can judge for yourself. For my part, I’d happily have published this story on my website, or distrib­uted it as a zine, with no mention of AI tools at all.

Okay, but what about those AI tools?

Over on the website, you can see some screenshots of the Wordcraft editor and read more about its affordances. It operates basically like a super-upgraded version of my AI text comple­tion plugin from way back in 2016. Every­thing about it is much more capable, but the workflow is the same. You can, at any point, ask the AI to generate new text, and when it does, its sugges­tions reflect the surrounding draft.

The Wordcraft team didn’t require or even suggest that my story be written in any particular way, or that it contain any partic­ular fraction of AI-generated text. My brief was: write what you want to write, the way you want to write it.

Okay, then! After noodling for a while, I decided I’d try to write some kind of locked-room mystery, because (a) it’s a genre I enjoy, that (b) I’ve never tried before, and (c) I liked the idea of giving the AI the role of the detective — perhaps chal­lenging it to “deduce” things based on clues in the text. In my imagination, this would be really fun! I would, in a sense, play the criminal, while the AI would play the stolid but savvy detective, and if its reactions were a little weird, well, that might be even better … 

It didn’t work at all. Absolute crash and burn. I had over­es­ti­mated the model’s powers. Para­graphs into my nascent mystery, it had no idea what was happening; or at least, not enough of an idea to “participate” in any mean­ingful way. It knew I was writing a mystery; it reached for the appro­priate terms and tropes; but that wasn’t anywhere close to being sufficient.

So I retreated, a bit dejected. I kept a log of my experiences, for the benefit of the Wordcraft team. A few notes from that log made their way into the team’s paper, which I think is a quietly path­breaking contribution: an almost ethno­graphic study of real writers doing real work with this real AI tool. Hype, this ain’t! The Wordcraft team has demon­strated clear-eyed courage in synthe­sizing and presenting our expe­ri­ences, many of which contain some version of my own retreat and dejection.

For a couple of weeks, I thought about other genres. On a medium-long drive, an opening line occurred to me. Beside a pool in Fresno, a story took shape. Then, I cracked it, by estab­lishing a fenced-in space for the AI to contribute what it could.

This AI, like many of its predecessors, is very good at “riffing”: given an example, it can generate lots more, often with impres­sive fidelity to genre and vibe. This new story called for a litany of grisly deaths, so, I asked the AI to dream up grisly deaths. I asked it, also, to tell me the names of the dead: char­ac­ters from a fantasy saga, cliched in the best possible way. Red meat! This assignment, it could handle.

Now, when you read the story, you’ll know that the litany of deaths is mostly the work of the AI. I prompted and prodded; I curated and edited; I smoothed and re-arranged. But “Captain Cirrus, trampled by a hippopotamus”? That’s 21st-century tech­nology in its fullest bloom bringing you that!

Three thoughts, to close.

First, I’m impressed as hell by the Wordcraft team. Daphne Ippolito, Ann Yuan, Andy Coenen, Sehmon Burnam, and their colleagues engi­neered an impres­sive, provoca­tive writing tool, but/and, more importantly, they inves­ti­gated its use with sensi­tivity and courage. This puts them leagues ahead of nearly everyone else out there peddling AI tools. (Indeed, I wish I’d been this circum­spect back when I was yakking about my own AI writing explo­rations, several years ago.)

Second, I’m proud of my story! I love its George R. R. Martin-alike narrator; I love its villain and his scheme. And, yes, I love the deaths, conjured gleefully by a computer that’s read it all.

But, third: I have to report that the AI did not make a useful or pleasant writing partner. Even a state-of-the-art language model cannot presently “understand” what a fiction writer is trying to accomplish in an evolving draft. That’s not unreasonable; often, the writer doesn’t know exactly what they’re trying to accom­plish! Often, they are writing to find out.

Will the AI get there, someday? Will I be able to recruit my detective at last? I understand very well the current pace of improve­ment in this field, and even so … I don’t see it coming anytime soon.

There’s more than a little meta-textuality in Author’s Note; it is surely no coin­ci­dence that the assistant, in the end, gets dunked in the pool.

I don’t think I’ve ever written about my theory of short stories, even though I talk about it a lot. It’s very simple: I think all good short stories are, in one way or another, about death. That’s not true of novels; good novels can be about lots of things. But a good short story is always basically a memento mori.

This is one of the reasons Bullet in the Brain is the best short story.

I won’t defend my theory — it is silly, and I cannot be bothered — but, for my part, I really do believe it.

Remember, I come by my interest in AI honestly; I’ve been thinking about this stuff since 1996. Here’s the title card for my “documentary” on AI, produced at Troy Athens High School using a VHS editing rig:

Robin's AI doc on YouTube, mostly VHS fuzz at this point
Robin's AI doc on YouTube, mostly VHS fuzz at this point

View the whole thing on YouTube, if you dare!

The dance of death: death and time, 1817, Thomas Rowlandson
The dance of death: death and time, 1817, Thomas Rowlandson

A few notes and links — not too many this time.

Where Twitter’s disin­te­gra­tion is concerned, I stand by my previous assessment.

“It was terribly creative and demanding, because you’re making design decisions at every moment. So it was high design.” Who wouldn’t want to crawl under­neath a table and work on this? Fabulous.

Here is some very nice banjo-playing by Rob Stenson, who I know mainly as the creator of Coldtype, a library that powers cool text animations.

Here is the moon, “melting” behind the pressure waves blasting out the end of a rocket. Here, the effect is winningly explained by Scott Manley.

Here’s a beautiful paean to a Studio Ghibli-adjacent movie I’d never heard about, from the great Animation Obsessive newsletter. They are really doing something unique and valuable over there.

The movie, Princess Arete, is available to watch for free in many regions until December 2. Here’s the clip that Animation Obsessive shared:

Tap or click to unmute.

Guillermo del Toro, as ever an evan­ge­list for imperfection:

“I wanted to return the controls of animation to the animators, and treat [the animators] as actors,” del Toro said. He encour­aged his team to make “failed acts”—the tiny stumbles and imper­fec­tions that make a perfor­mance by a live actor feel real — and resist what he called the “codification of animation into a ‘cool’ language that is almost like emojis.”

The best.

I thought I knew things about distribution

I am not really involved in the video game industry, but I’m never­the­less an avid reader of the GameDis­cov­erCo newsletter by Simon Carless, because I find his lens so inspiring.

Simon doesn’t write about program­ming games; he doesn’t write about playing them. He writes about the space in between. How does a person FIND a video game? What makes them decide to purchase and play it? What buttons, levers, and warp zones influence that process?

“Discoverability” is a good 21st-century word. Most of the digital dreams of my cohort, the partisans of the open web, ran aground on this reality. It’s not enough to make something and post it online; you must also inject it into some channel that will carry it to people. The web itself doesn’t do that; you need an extra layer, some reservoir of attention and/or curiosity, whether it’s Google, the blogosphere (RIP), Stum­ble­Upon (RIP), Twitter (RIP) … hmm, there seem to be a lot of dead channels out here.

Back in the 2000s, I thought I knew things about distri­b­u­tion, about attention and networks — but I didn’t really.

It was, honestly, the expe­ri­ence of publishing a book with FSG that showed me what distri­b­u­tion really looks like, and taught me that you just cannot be starting from scratch every time. You need supply chains — not only (or even primarily) physical, but commer­cial and intellectual. Emotional, even.

There is discoverability in books, though of course it’s totally different from discoverability in games. Different storefronts, different algo­rithms, different tastemakers. I’d like to think this newsletter contributes to book discov­er­ability, in a small way, from time to time.

I’d say most people in both industries, even the professionals, muddle through discoverability, hoping for the best, sometimes getting it. There are new kinds of profes­sionals elsewhere who won’t take any chances. The crass video producers who avidly game YouTube’s algorithm, surfing its subtlest contours to millions of views — oof, they know discov­er­ability.

What I admire about Simon Carless is that he knows it, too, but he is never crass, not for a second. His raison d’être is the support of interesting, inde­pen­dent video games. He crunches the numbers and monitors the algo­rithms on behalf of, no kidding, art.

There really ought to be a discov­er­ability newsletter of this quality for every medium, in every marketplace.

The dance of death: death finds an author writing his life, 1827, Edward Hull
The dance of death: death finds an author writing his life, 1827, Edward Hull

This is my season for driving, as I haul tons of olives from grove to mill for Fat Gold, the small olive oil company I help operate. I cover a lot of ground — it’s a real Cali­fornia odyssey, every year — and I’m grateful for the opportunity. It’s good thinking time (you should see my voice-to-text notes, dozens every day) and there’s always something new to see.

This year, I have observed

In the couple of days I waited to send this newsletter, the rain arrived. Clouds came scudding in from the west, wonderful scratchy tufts. Every­where I drove, I could see a sheet of gray out one eye and a patch of blue out another; the rain never fell where there wasn’t sun shining at the same time. That’s rainbow weather, of course, and they floated all over, not full arcs but little scraps of refracted color pinned to the air. On Monday, I expe­ri­enced one of my nicest Cali­fornia days ever in my eighteen years living here, as I trundled along, water above and water below, goggling at the show.

From the San Joaquin Valley,


P.S. You’ll receive my next newsletter on December 7. Before then, you’ll receive my annual gift guide, sometime in late November.

November 2022