I’m currently at the Archaeological Museum in Istanbul. Was just thinking of this post ten minutes ago when I saw what the plaque described as a “humanoid-lion hybrid creature” from the Neo-Hittite empire in 9th century BCE. In fact lion-men of various sorts are everywhere in the more ancient parts of the museum. Makes me wonder about potential continuity, as distant as this is.
My daughters are growing up bilingual in Persian and English. Totally fascinating to find the cognates; many are surprisingly close still (daughter/dokhtar, star/setare, cow/gav). It’s fun feeling like I could communicate basic ideas to a proto Indo European speaker based on those really distant cognates.
It gets complicated by the preponderance of French loan words, although they tend to be for newer concepts such as car, elevator, etc.
There do also seem to be some genuine coincidences, such as sock it/saket, both being a somewhat forceful way to tell someone to be quiet.
But yes, Persian people and culture in particular has fascinated me due to the ancient, but not prehistoric, traces of a shared identity with Europeans, in contrast with its neighbors. It’s not something that gets a lot of attention in popular culture
Great idea for a vibe coded project that is actually creative/original. Got in the top 4% as a professional historian. Would be interesting to see the professions of the people in the top .1 percent - is it people with Geoguessr type abilities or more like art historians and curators at the Met, I wonder?
Totally agreed. I've never understood why people are so opposed to marginal annotations - it's part of why the book format succeeded as a technology! (i.e you can't marginally annotate a clay tablet). Incidentally, I always loved how Tolkien's maps had these pointing hands to indicate significant bits, and only after reading a lot of old manuscripts and incunabula in grad school did I realize that he was copying the favorite annotation of medieval writers, the manicule: https://en.wikipedia.org/wiki/Manicule
Awesome, that's what I was going for. I originally made this for my own use and got kind of obsessed with building it out once I started finding unfamiliar books I enjoyed using the semantic search and category browsing. Glad to see it out in the world hopefully doing the same thing!
One thing that would make this information even more useful and searchable would be a JSON dump of your dataset. You could serve it statically on S3 or similar, to keep hosting costs to a minimum.
Of course, having created a cool thing generates no obligation for further work on your part! I'm grateful that you did this work and made it available for free.
Did you build your semantic search index based on the full text of the books, or just the reviews and descriptions?
Already tried to do this in a basic form. Advice from experts would be welcome as it's my first time trying to make data and an API available: https://book-prize-index.vercel.app/data
Also I just had to upgrade my Vercel plan due to traffic, which is very welcome and appreciated, but if anyone wants to donate, that would be really helpful! There's a Stripe link at the site: https://book-prize-index.vercel.app
Original author/creator of the site here - thank you! Will add the Axiom one. I am on the fence about whether/how to add "book of the year" type lists as they are somewhat distinct from book awards, but I do think that would probably be the next step to get more books in the corpus.
And any other ideas that HN readers have for awards to add would be welcome. Currently it's probably too history-slanted since I'm a historian and knew those awards better.
It may be hard to parse the lists but if they're still available somewhere online under the current administration the past annual State Department, CIA bookshelf recommendation, Army Chief of Staff, Navy CNO and Marine Commandant reading lists may have some valuable additions. To my knowledge there aren't any analogues to them in the rest of the Anglosphere but some LLMs will probably point out ones I haven't thought of.
I can point out that the UN agencies' respective reading lists for their staffs' professional development are 99% internal UN papers of very limited interest to external audiences but I haven't had a professional reason to look at any EU agencies to confirm or deny value.
Additionally, the Financial Times has a second set of book awards along their main awards which you've not listed, the FT reader's best books list.
Author here - just wanted to clarify in case there is any confusion that those two (intentionally bad/weird) figures of speech about the echo and the trouts in the redwood roots were human written, by me! I wrote them as parody of an AI trying to do "literary" writing. The actual (probable) AI written excerpts are below that part.
I was thinking about the immortal Twin Peaks line "there's a FISH... in the PERCOLATOR" when I wrote the trout one.
Just wanted to flag that the works of Ian Hacking, especially The Emergence of Probability (1975) and The Taming of Chance (1990) are excellent on this. Dense and challenging at times but also well written and the product of a very original mind.
The latter book has a Wikipedia page with some more info - was surprised to see Hacking not mentioned here since the featured article is partly based on his work: https://en.wikipedia.org/wiki/The_Taming_of_Chance
I'm busy reading a book [0] by Keith Devlin about the correspondence between Pascal and Fermat. It's called the unfinished game and has been really good so far. It goes through the letters and provides some context around them.
[0] https://www.goodreads.com/en/book/show/4443547-the-unfinishe...
One underrated thing about the recent frontier models, IMO, is that they are obviating the need for image gen as a standalone thing. Opus 4.6 (and apparently 3.1 Pro as well) doesn't have the ability to generate images but it is so good at making SVG that it basically doesn't matter at this point. And the benefit of SVG is that it can be animated and interactive.
I find this fascinating because it literally just happened in the past few months. Up until ~summer of 2025, the SVG these models made was consistently buggy and crude. By December of 2026, I was able to get results like this from Opus 4.5 (Henry James: the RPG, made almost entirely with SVG): https://the-ambassadors.vercel.app
And now it looks like Gemini 3.1 Pro has vaulted past it.
> doesn't have the ability to generate images but it is so good at making SVG that it basically doesn't matter at this point
Yeah, since the invention of vector images, suddenly no one cares about raster images anymore.
Obviously not true, but that's how your comment reads right now. "Image" is very different from "Image", and one doesn't automagically replace the other.
This reminds me of the time I printed a poster with a blown up version of some image for a high school history project. A classmate asked how I did it, so I started going on about how I used software to vectorize the image. Turned out he didn't care about any of that and just wanted the name of the print shop.
Thank you, this sort of insight is exactly why I've felt such kinship with what software engineers like Karpathy and Simon Willison have been writing lately. It seems obvious to me that there is something special and irreplaceable about the thought processes that create good code.
However, I think there is also something qualitatively different about how work is done in these two domains.
Example: refactoring a codebase is not really analogous to revising a nonfiction book, even though they both involve rewriting of a sort. Even before AI, the former used far more tooling and automated processes. There is, e.g., no ESLint for prose which can tell you which sentences are going to fail to "compile" (i.e., fail to make sense to a reader).
The special taste or skillset of a programmer seems to me to involve systems thinking and tool use in a different way than the special taste of a writer, which is more about transmuting personal life experiences and tacit knowledge into words, even if tools (word processor) and systems (editors, informants, primary sources) are used along the way.
Sort of half formed ideas here but I find this a really rich vein of thought to work through. And one of the points of my post is that writing is about thinking in public and with a readership. Many thanks for helping me do that.
I don't have a good answer to your question, but I do think it might be comparable, yes. If you had good taste about what to get Opus 4.6 to write, and kept iterating on it in a way that exposes the results to public view, I think you'd definitely develop a more fine grained sense of the epistemological perspective of a writer. But you wouldn't be one any more than I'm a software developer just because I've had Claude Code make a lot of GitHub commits lately (if anyone's interested: https://github.com/benjaminbreen).
