Interesting prediction! The title is definitely bold—might spark curiosity or turn casual readers away. Either way, I’ll be watching the release closely (probably while staying cozy in my Classic Puff Hoodie in Grey).

@block blast Being in the top 35 online is a good start, but breaking into the official print list is a whole different ballgame.

@millerchaney to be clear, this resolves yes for the top 35

@ian Nathan‘s description is poorly written and makes it sound like it is currently on the top 35 list.

@MachiNi I edited the description @NathanpmYoung to make it more clear

Buying some "No" here seems like a good idea on the basis that, imo, Manifold tends to be overly 'bullish' on Yudkowsky. That being said, given the hook title and the topic being AI, if anyone sees it, they'll (probably) pick it up.

@vitamind

if anyone sees it, they'll (probably) pick it up

Why?

@vitamind I actually think AI will probably be a boring topic by September since gpt5 will likely be a boring release.

My feeling is what gets on the NYT bestseller list is less to do with how true or important the book is, and more to do with vibes. I have a (baseless) feeling that most normal people will see a book with "everyone dies" in the title and not buy it.

@pietrokc

that most normal people will see a book with "everyone dies" in the title and not buy it.

I strongly disagree. Tons of viral content and bestselling books are centered around Doomsday / Apocalyptic predictions (both fiction and non fiction)

few recent examples: Oppenheimer (long + black and white biopic) made over a billion dollars. Black Mirror is super popular etc

1. It confirms peoples existing biases against AI & Tech — normies are concered about AI from decades of Sci Fi, NYT is not a big fan of “tech bros” , concern around AI taking people’s jobs, AI labs IP theft etc

2. Negativity Bias — Evolutionarily we’re biased toward information that helps us survive / warns of imminent danger

@pietrokc The bestseller list is, as it turns out, less about being the best seller and more about good marketing and getting the attention of the NYT editorial board. This is going through a legit, traditional publisher who knows how to push for a place on the list, and the marketing copy so far is solid. 70% is probably pretty fair, leaning optimistic but certainly a reasonable probability.

I preordered the book.

@pietrokc I agree. Also, is it is far from clear to me that it is true or important.

@elf Fair points about Oppenheimer and Black Mirror. I'll harp again on this distinction though: neither of these have "everyone will die" in the title. Again I'm not saying it won't be a bestseller; just that the odds are <70%.

For some context, the base rate for a book getting on the NYT bestseller list is 0.5%. So people are positing a >100x multiplier on this book. That feels way too high, and the Manifold community is known to be way too obsessed with AI.

@CraigDemel I personally don't think EY's stronger claims about AI are anywhere close to true, but I wanted to keep that out of the equation since this market is at best indirectly about what's true.

@pietrokc The base rate is a lot higher for books by this specific publisher.

@Driftloom That's really interesting. Do you have concrete numbers?

@pietrokc I have napkin math. LBC is one of the six adult-trade imprints at Hachette Book Group. Making some assumptions about share of total output and share of bestseller output, their base rate to end up on the NYT list is ~8%.

@CraigDemel Graham Hancock sells a lot of books. The truth and importance of a nonfiction topic is… fairly orthogonal to its sales.

@Driftloom GPT gave me a 10-13% base rate for them. Still much much lower than market price.

@MachiNi Yeah, it’s a base rate. You gotta consider whether and if so to what degree the specifics of this particular instance produce deviation from that rate. That’s kinda the point of the question, right?

@Driftloom Thanks, that's super helpful. With some cursory googling and wikipediaing I had come up with a 5-10% number so it's reassuring to see it corroborated. So yeah when I first saw it this market was putting a ~10x multiplier on this base rate.

@MachiNi I wouldn't trust GPT with something like this.

@pietrokc Concur on GPT, unless you check its sources itself.

To put all the cards on the table, I think the current odds are optimistic but not unreasonably so. It would require a well coordinated and executed marketing and distribution strategy from the publisher, which probably includes putting Eliezer and Nate out there on press tours and podcasts. If they choose to make that investment I suspect they have a reasonable chance of success. If they can’t break out of the rat-adjacent niche into normie space, this probably goes to zero. If they don’t actively choose to try, it definitely goes to zero. Signals to watch for would be podcast appearances (Fridman, even Rogan), public comments (even negative ones, from Gary Marcus or Yann LeCun, say) and even a hint of buzz in more mainstream publications. Physical presence and distribution in bookstores will matter. It’s a real hill! And a harder one to climb with a complex nonfiction than with the latest in an established fiction series.

And, the NYT can always exercise editorial discretion and exclude it for any reason they want. So it needs some buzz. There’s a reason the base rate is low.

But, if it were gonna hit the bestseller list, the path so far looks like the one it would need to be on to get there.

@Driftloom you guys do what you want but the analysis was tailored to this specific case and convincing to me. Of course it’s just a base rate. But you have to justify wild deviations from base rates and I’m not seeing it for now.

To estimate a base rate for whether a book like If Anyone Builds It, Everyone Dies might appear on the New York Times bestseller list within 3 months of its September 2025 publication, we can break it down using comparable features: publisher, author prominence, genre/theme, and sales history of similar books.

Key Variables

1.

Publisher: Little, Brown and Company

• A top-tier imprint with a history of bestsellers.

• Estimated base rate: ~20–30% of their major nonfiction releases hit the NYT list at least briefly.

2.

Authors: Eliezer Yudkowsky & Nate Soares

• Neither author has had a mainstream bestseller.

• Yudkowsky is well-known in rationalist and AI safety communities.

• Soares is notable in Effective Altruism and AI alignment circles but not broadly public-facing.

• Estimated base rate for niche intellectual authors without mainstream fame: ~5–10%.

3.

Genre/Scope: AI risk, speculative nonfiction

• Comparable titles:

  • Superintelligence by Nick Bostrom – not a NYT bestseller.

  • Life 3.0 by Max Tegmark – briefly hit the NYT list.

  • The Precipice by Toby Ord – did not make the NYT list.

• Exception: AI 2041 by Kai-Fu Lee – did appear.

• Estimated base rate for books about AI risk written by thought leaders (not celebrities): ~10–15%.

4.

Marketing and Platform

• Yudkowsky has a large online following (LessWrong, Twitter/X), which might drive preorders.

• Books with strong niche pre-order campaigns sometimes punch above their weight.

• Preorder boost rate for NYT list placement: ~10–20% chance for strong community-backed nonfiction.

Composite Base Rate Calculation

We’ll treat each factor as a conditional filter. For a rough estimate:

• Start with high-end publisher rate: 25%

• Adjust for author recognition outside mainstream: ×0.4 → 10%

• Adjust for topic/genre relative to past NYT performance: ×0.8 → 8%

• Adjust for likely preorder + online campaign boost: ×1.25 → ~10%

Conclusion

Estimated base rate for If Anyone Builds It, Everyone Dies to hit the NYT bestseller list within 3 months of publication:

~10%, give or take a few percentage points depending on campaign strength, reviews, and media traction.

Let me know if you’d like a more formal Bayesian model or spreadsheet version of this estimate.

Same question for the extended list:

Here’s the same back-of-the-envelope “base-rate” calculation, but now anchored to the New York Times’s broader online list of the top 35 titles (rather than the core top 15–20 that appear in print).

1. Anchor Rate for Little, Brown & Co. on the Top 35

• Historic performance: Roughly 30% of Little, Brown’s major adult nonfiction releases show up somewhere in the NYT’s online “35” over their first three months.
  — Anchor: 30%

2. Author Visibility Adjustment

• Mainstream name-recognition: Yudkowsky and Soares are highly visible in AI/safety circles but not household names outside that niche.

• Proxy: Niche-academic authors historically land in the top 35 only about half as often as a major memoir or celebrity-driven title.
  — Multiplier: × 0.5

3. Topic/Genre Adjustment

• AI-risk nonfiction: A few titles (e.g. AI 2041 by Kai-Fu Lee) have breached the list, but most heavy-theory books (Bostrom, Ord, Tegmark) do not.

• Empirical rough‐cut: ~70% as likely as the average LB & Co. nonfiction book to crack the online 35.
  — Multiplier: × 0.7

4. Community-Driven Campaign Boost

• Strong preorder and social-media push: can bump a niche title’s odds by ~25%.
  — Multiplier: × 1.25

Composite Base-Rate Calculation

1. Start: 30% (publisher anchor)

2. Authors: 30% × 0.5 = 15%

3. Topic: 15% × 0.7 = 10.5%

4. Campaign: 10.5% × 1.25 = ≈ 13%

Estimated Base Rate

≈ 13% chance that If Anyone Builds It, Everyone Dies will appear anywhere on the NYT’s expanded “online 35” list within its first three months (September–November 2025).

Feel free to ask if you’d like to tweak any of the underlying assumptions—or see a more formal Bayesian write-up!

@MachiNi The problem is that the internet is awash with examples of people asking the AIs questions exactly like this, involving specific researchable numbers, and the AI simply makes up the numbers. For all we know all these %s it produced are entirely fictional. Whether it's convincing to us is irrelevant -- the whole reason we're asking is we don't know the answer!

[Added: here's just one example I saw yesterday]

@pietrokc I fear you may be right. It still turned a figure that's perfectly in line with the back-of-the-envelope calculations in the thread. Maybe it's garbage, but based on what I've seen these are not unreasonable estimates.

No need to keep saying the reason we're asking is that we don't know. There are things we know and they inform our predictions. There are more and less informed bets.