Published on November 1, 2025 3:37 AM GMT

We aren’t all pampered Inkhaven residents, writing blog posts with a golden quill and handing them off on a silk pillow to a council of famous writers who are ready to critique and improve every shining word. Some of us Halfhaven writers are juggling two jobs, and having to write in between feeding the baby and fixing the beat up dishwashing machine. Not me, but some of us, I’m sure. Anyway, we Halfhaven folk have it hard. We’re tough. We’re scrappy. We have to fend for ourselves. We’re like lone wolves. Maybe we should get t-shirts of a wolf, just to show how tough we are. Or some temporary tattoos. In any case, I recommend to those without an angelic Greek chorus of writing experts over their shoulders to try using AI instead. Just don’t make the mistake of leaving it on its default settings.

At first I was wondering how I could have improved my recent joke post on the made-up religion “Unsureism”, so I did what any sophisticated writer would do — I asked Claude. Of course, the standard Claude (Sonnet 4.5) gives terrible advice (reproduced here in its entirety):

This is a clever piece! The satirical premise works well. Here are some suggestions to sharpen it:

Structural improvements:

• The title works, but the subtitle feels a bit flat. Maybe something punchier like “A Practical Guide to Infinite Religious Liability Management”
• Consider adding subheadings to break up longer sections (e.g., “The Problem of Exclusivity,” “Daily Ritual Calendar”)

Comedic opportunities to expand:

• The scheduling nightmare deserves more exploration. You mention three sabbaths and fasting, but imagine the prayer schedule conflicts, dietary restrictions that contradict, facing both Mecca AND Jerusalem simultaneously, etc. A sample “Tuesday schedule” could be hilarious.
• The burial section is gold but brief. Push the absurdity further - Viking funeral pyre vs. preservation vs. sky burial vs. mummification. Maybe the Unsureist needs multiple bodies prepared?
• The “unspecified god” workaround is philosophically interesting but gets a bit dense. Could you illustrate with a sample prayer? “Dear [DEITY_NAME], who may or may not have [PROPERTY_SET]…”

Logical extensions:

• What about religions with contradictory moral requirements? (Some honor warrior codes, others absolute pacifism)
• How do you handle religions that require exclusivity to even enter heaven, not just get a good afterlife?
• What’s the Unsureist position on proselytizing? (Required by some, forbidden by others)

Polish:

• “adherants” → “adherents” (paragraph 9)
• The transition to exclusive religions feels slightly abrupt

The piece is genuinely funny and thought-provoking as-is. These suggestions would just maximize the absurdist potential!

Claude assures me that my piece is essentially already amazing, offering only nitpicks and congratulating me on my “clever” and “genuinely funny” piece. If I didn’t have so much contempt for modern AI that any compliment from it felt like an insult, this would doubtlessly inflate my ego. What it would not do is help me become a better writer.

I thought maybe AI was just too stupid to help me. But I wondered if buried inside the gargantuan circuitry of this Lovecraftian machine there might be some genuinely helpful advice. And I had one idea that might work to find it.

I first gave Claude the entirety of Paul Fussell’s book Class (a witty, albiet snobbish book I recently enjoyed), and then instructed it to critique my article, this time using the style of Paul Fussell. I hoped this would break the AI out of its default lobotomized, masturbatory “For Dummies” mode and give me access to some of the gears and wires that it doesn’t normally use.

Let’s see some snippets of the output:

One opens this essay with considerable hope—satire about religion being one of the few remaining zones where wit can still earn its keep—only to discover that the author has committed the cardinal error of the humorist: he’s explained the joke to death.

The premise is sound enough, even clever: if Pascal’s Wager suggests betting on one god, why not bet on them all simultaneously? It’s the theological equivalent of buying every lottery ticket. Swift would have dispatched this notion in three mordant paragraphs. Voltaire would have managed it in five pages of Candide with three dinner parties and an earthquake. You’ve given us what feels like a PowerPoint presentation at an Effective Altruism conference…

Ouch! Ironically, my own inspiration for “explaining the joke to death” was Fussell’s Class itself. The book breaks down different class markers of upper class people, middle class people, and “proles”, listing differences in speech, dress, house decorations, and so on. The book is a torrent of hundreds of examples that eventually give an undeniable and raw picture of class in America. When writing my Unsureism post, I wanted to list lots of fun examples of the things an Unsureist (one who tries to essentially follow as many religions as possible) might have to keep track of, like making sure they’re buried with a copy of the Ancient Egyptian Book of the Dead in case the Ancient Egyptians were right, and also be buried with a coin in your mouth to pay Charon, in case the Ancient Greeks were right. I personally find the exhausting image of all these different requirements funny. I wasn’t sure what AI-Fussell meant by “explaining the joke to death”, but he continues:

The fatal flaw is that you’ve written an essay explaining a satirical concept rather than dramatizing it. We get the taxonomy—and yes, I appreciate a good taxonomy as much as the next social critic—but where’s the Unsureist himself? Show us this poor bastard trying to pray toward Mecca while simultaneously meditating on the Sikh conception of God while wearing his Mormon undergarments. Let us watch him at the supermarket, agonizing over whether the vegetables were harvested with sufficient concern for Jain principles. Give us his wife’s face when he announces they’ll be taking three-day weekends for the rest of their lives.

This is a great point. It’s all fairly abstract in the post. Those times when I manage to make it more visceral are better, like the image of a watertight plastic casket containing a Book of the Dead.

But the essay never quite decides whether it’s mocking religious belief generally (the New Atheist position, rather stale by now), mocking the anxious personality type that would attempt this synthesis (more promising), or actually, in some perverse way, taking the idea semi-seriously (the EA crowd does have a weakness for taking thought experiments too literally).

The piece reads as if written by someone who’s never really felt religious dread or genuine metaphysical anxiety—which is fine; neither have I—but hasn’t really felt anything much about religion at all except that it’s a curious phenomenon susceptible to logical analysis. One suspects that for you, as for many of your rationalist cohort, the problem of religion is primarily an intellectual puzzle rather than an existential predicament.

This is true also. I went into the post thinking, “wouldn’t it be a strange idea if a person tried to maximize their chances of getting into heaven by following many different religious ideas”, and thinking about one specific workaround to the fact that many religions are on the surface mutually exclusive. But I didn’t really think much about the point of my post. In a way it ends up wanting to be a satire of the kind of LessWrong/EA post where logical ideas are taken too seriously without zooming out to see the counterproof-by-absurdity revealed by the big picture. But this isn’t really developed in any way, and so the post seems almost like it’s a real suggestion for how to best get into heaven or something. And the writing style of the post makes it basically become what it should be trying to mock.

And for God’s sake—or gods’ sake, I suppose—let the prose breathe. You’re writing as if composing a LessWrong post, all earnest explanation and logical stepping-stones. Satire requires a lighter touch. Trust the reader to get it without having every implication spelled out like assembly instructions for IKEA furniture.

Yes. More good advice. Thank you AI-Fussell. I suspect following this piece of advice, though, would have led to even more downvotes on LessWrong than the original post got. On the site, there seems to be a hunger for well-thought-out “white paper” posts, as well as some desire for lighthearted, satirical fiction, but I don’t see much nonfiction on the site demonstrating levity or wit. Maybe because levity and wit can be used to disguise bad reasoning, so the LessWrong immune system is triggered by it even when it shouldn’t be, like an allergy being triggered by harmless peanut protein. Yes, I just said you fools are allergic to wit; it seems Paul Fussell is rubbing off on me! Maybe I should get some advice from someone else before his snobbery is branded into me.

That went well, actually. Night and day, compared to the Mega Bloks response I got from default Claude. Searching for someone else whose nonfiction writing I respect, Eliezer Yudkowsky’s name came to mind, so I thought I’d try him next (using a handful of blog posts in the prompt).

For some reason, it feels a bit weird sharing AI output that’s supposed to be in the style of a person who’s still alive, so I won’t share any specific output. At first AI-Yudkowsky criticized Unsureism as a belief that doesn’t pay rent, so I tried again, asking him specifically to criticize the writing, not the logic of the post.

He pointed out that my opening paragraph burns precious opening real estate on setting up basic facts everyone knows. Here is the opening paragraph:

Like with sports teams, most people just adopt the religion of their parents and the location they were born. But choosing a religion is potentially the most important decision you’ll ever make, since it’s the only decision you make that could have infinite impact.

That’s great advice! I could have put this lower, and started with something eye-catching, like an absurd depiction of an Unsureist following a bunch of rituals, or teased the reader with how, by following this new religion, you can get three days off a week. Or whatever. Something less boring.

AI-Yudkowsky made the same critique AI-Fussell did about making things concrete and visualizable, rather than abstract and boring.

AI-Yudkowsky also points out the middle section bogs down when I try to explain the complicated idea about believing in a god without specifying exactly who that god is, to get around religions that don’t allow idol worship. I agree this is a morass that slows down the post. I should have probably excluded it, or just mentioned the possibility of doing something like that, without trying to explain and justify it fully.

The rule of three demands I try this with one more writer, and I was thinking about Christopher Hitchens today, so I’ll try him. Since he’s dead, I’ll allow myself to include some excerpts.

The opening subtitle—a reference to Kubrick that’s been beaten to death by a thousand think-pieces—immediately signals a want of originality. One expects better from a writer attempting satire.

All my substack subtitles are AI-generated, so you can blame yourself for that one, Claude. The titles and posts are written by hand. I just don’t care about the subtitles much for some reason. That’s probably a mistake if I’m signalling fatuity at the top of each of my posts. I’ll write them by hand from now on.

There are moments where the author stumbles onto genuine wit—the business about the “watertight plastic casket” threading the needle between Egyptian and Zoroastrian requirements is genuinely amusing. The parenthetical about mapping Unsureist requirements as an “Effective Altruism cause area” earns its keep. But too often, the humor announces itself rather than arriving with grace.

The worst offense is the final paragraph’s accumulation: “Friday (Islam), Saturday (Judaism), and Sunday (Christianity).” We don’t need the parenthetical labels—the reader grasps the point. This is the literary equivalent of explaining one’s own joke. Similarly, “hereafter referred to simply by the term ‘afterlife’” is bureaucratic throat-clearing in an essay attempting levity.

This is the “explaining the joke to death” criticism again. I should have had more clarity in my mind about the fact that I wanted this post to be absurd and humorous from the beginning, I think.

The piece also commits the modern sin of excessive qualification: “may sound appealing,” “can do better,” “would recommend,” “usually not enough.” All this hedging (ironically appropriate to the subject) creates a tentative, uncertain voice when satire demands confidence. Swift did not equivocate when proposing we eat Irish babies.

Yes! Satire demands confidence! That is true! Paul Fussell’s Class was super confident, and the satire within landed. Of course, you end up thinking the guy’s kind of a dick by the end of the book, so raw confidence can come across as elitism too if you’re not careful.

Asking these three AI personalities for advice was pretty helpful. Especially compared to my usual fire-and-forget strategy of posting online. They had their flaws, of course. All three still tried to tell me I’m amazing. Claude just can’t help that. And these AI versions lack the genius of their human counterparts. But it doesn’t take much intelligence to tell an amateur why their writing stinks.

One important thing I think none of them mentioned directly was just that it was a joke post without being very funny. The concept itself was kinda funny. As was the final line, I think:

If you became an Unsureist, you would also have religious holidays and special days nearly every day. You’d have to fast during Ramadan. And during Lent. And Yom Kippur. And Ekadashi. And Paryushana. Expect to do a lot of fasting, actually. But that’s fine; you can eat when you get to heaven.

But the rest of the post lacked setup-punchline jokes. Zaniness and levity create a comedic tone, but they’re not a replacement for actual comedy. The next time I write a humorous post, I should go into it trying to write something funny on purpose, and take the time to think of more “bits”.

Thanks to AI, I now have lots of ideas for how I can improve my future writing. I’ll probably use this technique again on some of my upcoming Halfhaven posts, so keep your eye out to see if my posts got any better. And let me know if anyone starts making those Halfhaven wolf t-shirts.