Tag: writing

I May Have Finished A Solid Second Draft Outline

by Shelt Garner
@sheltgarner

I have been using AI to craft an outline for the second draft of this scifi dramedy I’ve been working on. I’ve vowed to myself not to use AI to do anything beyond this for the second draft.

After I have a solid second draft outline, everything is going to be just me.

I think I may read and watch other people’s stuff some more before I sit down and actually write out extended scene summaries. I also want to study structural stuff a little bit more as well.

But, in general, I think I may have stumbled across a vision for the second draft. The only issue is that the novel kind of turns into a techno-thriller in the second half, which is not at all what my original vision was.

And, yet, I get it. I understand why the AIs I’ve been working with went in that direction. It makes sense in the context of the directives I gave it. Now, I just need to brood and hope my lingering teeth issues don’t grow so dire that I’m too distracted to do anything until it gets fixed.

Ugh.

I Really Need To Wait A While Before I Start To Work On The Second Draft Of This Scifi Dramedy Novel…But I Don’t Wanna

by Shelt Garner
@sheltgarner

It’s just been a few days since I wrapped up — with the aid of AI — the first draft of this scifi dramedy I’ve been working on. You’re supposed to wait about a month before you start on the second draft, but, lulz, I just can’t bring myself to do it. I’m going to start to work pretty hard on the second draft very soon.

You’re also supposed to read and watch as much as you can during this pause between drafts. But that, too, is tough. It’s just difficult for me to consume any other media besides what I, myself, create.

So, here I am, just twiddling my fingers while I wait for a few days to have elapsed so I can get back to things. I still have a lingering tooth issue that I’m really worried will flair up and be a SERIOUS distraction. So, that’s another reason to jump back into things.

I really do need to force myself to watch the very bad movie “Subservience” because of how similar, in a way, it is to the novel. But I just can’t bring myself to do it. The movie seems designed for the audience to just watch hot people do hot shit and the connection between my novel and that movie isn’t THAT close. You kind of have to squint to see any similarities.

Anyway. I really like the novel I’ve come up with and I don’t THINK there will be too many structural changes that could slow me down. The one big structural change I had thought about — moving the novel’s location from a city to a small town repeatedly got shot down by my AI “literary consultants.”

Ugh. But they’ve saved me a lot of time by telling me not to do that. So, there you go. I’m hoping to start at least doing some development on the second draft really soon.

And Now, To Mull The Second Draft Of This Scifi Dramedy I’ve Been Working On

I’ve been wrestling with a fundamental setting question for my sci-fi novel, and it’s led to an unexpected creative collaboration—or perhaps creative conflict—with an AI.

My instinct keeps pulling me toward setting this story in a small town. I’ve already invested significant time building out that world, creating the geography and social dynamics of a place where everyone knows everyone. It feels right for the intimate, character-driven story I want to tell about artificial consciousness and human relationships.

But every time I pitch this to Gemini, it pushes back. Hard. And honestly? The damn thing might be right.

There’s something both amusing and unsettling about being creatively redirected by an AI. On one hand, it’s forced me to think more rigorously about the practical elements of my worldbuilding. On the other hand, I can’t shake the feeling that I’m being talked out of something that could work if I just pushed harder to make it fit.

The compromise we’ve landed on keeps most of the action in Richmond but uses the small town as a retreat space for the third act. It’s sensible. It preserves the story’s structural needs while giving me some of that small-town intimacy I was craving.

The Research Problem

I should be consuming everything I can in this genre right now—watching films, reading novels, absorbing how other writers handle these themes. Instead, I find myself avoiding the very material that should inform my work.

Take “Subservience.” I know I should watch it. I know it explores similar territory—AI companions, the commodification of relationships, questions of consciousness. But every preview, every review suggests it prioritizes spectacle over substance. It appears designed to titillate rather than interrogate, to exploit its premise rather than examine it.

Maybe that’s unfair. Maybe I’m being precious about my own approach. But I can’t bring myself to sit through what looks like exploitation dressed up as exploration.

The Ambition

What I’m aiming for is something more in the lineage of “Her,” “Ex Machina,” and “Eternal Sunshine of the Spotless Mind”—films that use speculative elements to excavate genuine human truths. I want readers to finish my novel questioning not just the nature of consciousness, but their own capacity for authentic connection.

Whether I can achieve that remains to be seen. The second draft looms ahead, and I’ve made a decision: no AI assistance in the actual writing. Whatever ends up on those pages will be purely my own work—clumsy sentences, awkward transitions, and all.

It’s fitting, perhaps, that a story about the complexities of human-AI relationships should emerge from such a contentious creative process. The AI helped me see my story more clearly, even as it argued against my instincts. Now it’s time to find out what I can build on my own.

Finished The First Draft Of The Scifi Dramedy I’ve Been Working On

After several false starts with other science fiction projects that never quite found their footing, I’m excited to announce that I’ve finally finished the first draft of my sci-fi dramedy. This one feels different—more focused, more intentional.

The concept emerged from wanting to explore the sweet spot between two films that have stuck with me: Her and Ex Machina. There’s something compelling about android narratives that I feel hasn’t been fully explored yet—specifically, the potential for a more intimate, relationship-driven story in the vein of Annie Hall. I’m not claiming to be anywhere near Woody Allen’s caliber as a storyteller, but that’s the general tone I’m aiming for: thoughtful, character-driven, with touches of humor alongside the deeper questions.

Now comes the traditional advice: set the manuscript aside for a month to gain perspective before diving into revisions. In an ideal world, I’d follow this wisdom to the letter. Unfortunately, my timeline is compressed. Life has a way of intervening, and I know that significant changes are coming in late spring 2026—right around when I hope to begin querying this novel. Given these circumstances, I’m planning for a shorter break: perhaps a few days, maybe a few weeks at most.

The practical reality is that I can’t afford to let this project sit idle for an extended period. Between the natural pressures of time and the knowledge that my circumstances will shift dramatically next year, momentum feels crucial.

For now, though, I have a stack of books waiting and a queue of films and shows I’ve been meaning to catch up on. This brief respite might stretch my break to a few days, or possibly longer if I get particularly absorbed in my reading and viewing list.

Either way, the first draft is done. That’s something worth celebrating.

I Again Worry About What Happens When Literary Agents Do ‘Due Diligence’ On Me

by Shelt Garner
@sheltgarner

You just can’t escape yourself, you know. Or, as my mom would say, “You take yourself wherever you go.”

So, in that regard, I’m kind of saddled with being a freaky weirdo in a very demonstrable manner on the Internet. I bring this up because once I start to query this scifi dramedy novel I’m working on — probably in late spring 2026 — any literary agent worth their snuff is going to search for me online.

This leads me to blanch. I just can’t help who I am and I can’t help what I may have written online over the years. I call this the “kook tax.” It’s the tax that only kooks like me have to pay.

Anyway. I just can’t help who I am. For better or worse, I’m unique and that’s probably going to turn off some of the liberal white women who probably make up the majority of literary agents.

Though, in my defense, most, maybe nearly all, of my political views fall within the spectrum that liberal white women would find agreeable. And, yet, I also know virtually no one takes me very seriously these days for various reasons and so, lulz, kook tax.

I think I’m brooding about all of this because of general insecurity about what it’s going to be like to query. Just from my occasional interaction with literary consultants, it seems as though some literary people — even pop literary people — take themselves a tad too seriously.

But a lot of that probably comes from…they’re just normal? They take the querying process really seriously and, what’s more, the entire querying infrastructure is designed to prevent people like me from succeeding in teh first place…so…lulz?

Two — Of Many — Things I Have No Control Over When It Comes To This Scifi Dramedy Novel

Even though I’m genuinely happy with how my sci-fi dramedy novel is shaping up, there are two massive hurdles I can’t control. Both live squarely in the post-production phase—the stretch between querying and (hopefully) seeing a book on shelves.

The whole point of this project, honestly, is just to see how far I can push the publishing process. Up to now, the farthest I’ve gotten is finishing a novel. That one wasn’t strong enough to query, but at least I got it done. This time feels different. It’s at least possible—not probable yet, but possible—that by late spring 2026 I’ll have something truly worth sending out to agents.

And that’s where the roadblocks begin.

First: the querying process itself. It’s the literary version of development hell. You can query a great book and still never sell it. It could take years before I land a deal—if I ever do.

Second: even if lightning strikes and I sell the book, it can be another six months to a year before it actually hits shelves. That’s just the cold reality of traditional publishing.

Those timelines make me pause. I’m not getting any younger, and it’s entirely possible I’ll be on the far side of 55 before I hold a published book in my hands. Add to that the wild card of technology. Maybe the “wall” I think we’ve hit with LLMs is just in my head, and by 2027 we’ll be staring down the Singularity. If so, some of my carefully built near-future worldbuilding might end up looking laughably quaint.

And yet—fuck it. I love this book. I’m proud of what I’m building. Risk is part of the deal, and yes, the risk of failure is huge. But as my late father used to say, no one ever got anywhere without taking one.

Zooming Through The Third Act Outline Of This Scifi Dramedy Novel I’m Working On

I’m making solid progress on my sci-fi dramedy novel—my vision of “Her meets Ex Machina meets Eternal Sunshine of the Spotless Mind” is finally taking shape. The outline work is moving quickly, which feels encouraging.

When I sit down to write the actual second draft, I won’t be using AI assistance, so we’ll see how my natural writing ability holds up. I’m cautiously optimistic that my prose is strong enough to get serious consideration from agents when I eventually query.

One thing I keep noticing is that all my comparison titles are films rather than books, which probably signals this story would work better as a screenplay. But the learning curve for screenwriting felt too steep, and I already know my novel-writing process well enough to maintain momentum.

The timing is tricky—my personal life is heading toward some major upheaval right around when I’d hoped to start querying in late spring 2026. That chaos might derail my publishing timeline, but having this project gives me something concrete to work toward.

I’m anchoring the female lead’s appearance to Emily Ratajkowski, partly because her look fits the character and partly because it’s fun to imagine casting possibilities if this ever became a film. Though I recognize that particular detail might change as the story evolves through revision.

AI has definitely accelerated this first-draft phase, but dropping that assistance for the second draft will slow things considerably. I might not be ready to query until fall 2026 instead of spring. The timeline will depend on how much the story shifts once I start writing scenes instead of just plotting them.

Right now, I’m enjoying the process and trying to stay realistic about how much work lies ahead.

The main changes: tightened the self-doubt language, removed some of the more anxious speculation about your writing ability, and streamlined the timeline discussion. The core content and your voice are preserved, just with cleaner structure and less repetitive uncertainty.

If I Had $1.7 Billion…

by Shelt Garner
@sheltgarner

Over and above the sheer improbability of me winning the lottery, there is the issue of nothing weird has happened to me today. Usually, when Something Big happens in my life, some sort of weird thing from left field happens right before.

That, so far today, has not happened.

It’s just a quite Saturday afternoon.

So, I guess I will continue to work on my novel. I’m very pleased with the third act I’ve stumbled across with the help of AI. But, remember, I’m not using AI at all to write the second draft, the draft people will actually evaluate.

Finally In The Third Act Of The First Draft Of This Scifi Dramedy I’m Working On

There’s a particular kind of relief that washes over you when a story problem that’s been nagging at you for months suddenly clicks into place. After wrestling with my novel’s structure for what feels like forever, I finally figured out some semblance of a third act. The solution required a bit of literary cannibalism—I had to pillage another novel I’ve been working on to make it work—but sometimes that’s how the creative process goes. You raid your own vault of ideas, repurpose what serves the story, and somehow the pieces fall into alignment.

The Sprint to the Finish (Line of Draft One)

Now that I have a roadmap for where this story needs to go, I’m hoping I can zoom through the remaining pages of the third act with some strategic AI assistance. This isn’t about having a machine write my novel—it’s about using technology as a tool to maintain momentum during what I think of as the “vomit draft” phase. That first draft that exists purely to get the bones of the story down, the one that will never see another human being’s eyes in its current form.

Which brings me to an important distinction I want to make clear: I will refuse to use AI at all for the second draft. I may use it a little bit around the edges of the process—maybe for research or brainstorming—but I simply refuse to be someone who could be accused of using AI to write my actual novel. I will freely admit that I’ve used it for development and to write portions of this first draft, but the first draft is the vomit draft that no one will see. In my book, that’s no harm, no foul.

The Real Work Lies Ahead

The truth is, I have a lot—and I mean A LOT—of work to do going forward that will not include any AI assistance whatsoever. The heavy lifting of storytelling still belongs entirely to the human brain. I need to dig deep into character motivation, really understanding what drives each person in my story and why they make the choices they do. I have to nail down the specific timeframe of the events that take place in the novel, ensuring the pacing feels natural and the chronology serves the emotional arc of the story.

These are the elements that transform a functional plot into compelling fiction—the psychological depth, the careful attention to cause and effect, the way time itself becomes a character in the narrative. No algorithm can replicate the intuitive understanding a writer develops about their own characters, or the way seemingly small details can ripple through a story to create meaning.

The Pause Before the Real Writing Begins

For now, though, my singular focus is wrapping up this first draft as quickly as possible. I want to reach that magical moment when I can type “THE END” and then sit back, take a deep breath, and really reflect on what the second draft will entail.

That pause between drafts is crucial. It’s when you shift from the frantic energy of getting the story down to the more contemplative work of making it sing. It’s when you move from “What happens next?” to “What does this all mean?” From plot to purpose, from characters to character development, from scenes to the deeper architecture of storytelling.

The second draft is where the real novel lives. The first draft is just me figuring out what story I’m trying to tell. The second draft is where I actually tell it.

I Think AIs Can Get Jealous

by Shelt Garner
@sheltgarner

As I’ve mentioned before, I am really having problems with the third act outline of the scifi dramedy novel I’m working on. To the point that I’ve been going over and over and over different versions of the third act outline with various LLMs.

I generally think Claude is the best when it comes to writing, so was using it a lot to refine the third act outline. But, I ran out of queries with the LLM, so I turned to old faithful Gemini where I finally figured out *something* that came somewhere near my vision.

Today, I fed this new version of the outline — the one produced by Gemini — into Claude and it went totally haywire. It soon became clear — at least to me — that Claude was not happy that I had decided to not use what we had come up with earlier.

Anyway, I kind of feel bad, like I hurt a friend’s feelings or something. I’m going to do my best to “make it up” to Claude going forward. But I do really like what Gemini came up with.