The Claudyssey: A line-for-line translation of Homer's Odyssey by Claude Fable 5

41 points by spinchange 11 hours ago on hackernews | 57 comments

[OP] spinchange | 11 hours ago

12,107 line-for-line translation of the A.T. Murray Greek text (Loeb, 1919) by Claude Fable. Includes line notes and an index. HTML, epub, pdf, and YouTube Audio (by gpt4o-TTS). A dual-agent review pass was done on the entire work with a third "adjudication" agent reconciling their findings. Reviewer agnets were gpt-5.6-sol high reasoning.
why?

[OP] spinchange | 10 hours ago

I love the poem and wanted a modern translation with annotations and index, etc., to be freely available to anyone who wanted to read it. I had a sense that Fable would do a really good job. I am pleased with how it came out. The review agents didn't change a single word of the translation, only some of the notes.

squidbeak | 8 hours ago

Every translator is opinionated in some way. I can see the appeal in having something like this as a neutral comparison.

SwellJoe | 8 hours ago

LLMs are not neutral, either. They don't have "opinions", per se, as they don't want anything, but they do have biases baked into their training.

anigbrowl | 8 hours ago

One very simple benefit is that it's unencumbered by copyright.

I do value the work of human translators; when they're really in harmony with the original work, they can be fantastic. But they can also be disastrous, like Alfred Birnbaum's translations of Murakami, which radically reshapes the protagonist and threw out nearly 20% of the original work.

exmadscientist | 8 hours ago

The problem is that (we have every reason to believe) models like Claude were trained on existing translations. Now they're being used to generate things that are direct replacements for those translations in the marketplace.

This is basically an anti-AI author or lawyer's dream case.

And, seeing this uncanny-valley-of-slop output, I kind of hope they go for it.

munk-a | 7 hours ago

If the Murakami was undertranslated then how will having more translations that crowd out the potential revenue of future translators help produce better quality translations?
It seems the traffic has made the site inaccessible. I'm enjoying reading the first page that's still in my browser.

nater5000 | 8 hours ago

Read this as "Claudussy" at first.

whythismatters | 8 hours ago

How does it compare to previous (human) translations, what is the regurgitation level? In any case, lots of em dashes, so mission accomplished to bring it up to contemporary standards.

suddenlybananas | 8 hours ago

https://theclaudyssey.com/read/book-01.html#n1

The first line is a crappy mishmash of Lattimore and Fagles.

Lattimore: >Tell me, Muse, of the man of many ways, who was driven far journeys, after he had sacked Troy's sacred citadel.

Fagles: >Sing to me of the man, Muse, the man of twists and turns driven time and again off course, once he had plundered the hallowed heights of Troy.

Claude: >Tell me the man, Muse — the man of many turnings, who was driven wandering far, once he had sacked Troy's holy citadel

Combining "man of many ways" and "man of twists and turns" into "man of many turnings" is just dreck.

kamranjon | 8 hours ago

The sort of sad but interesting thing here is that while this claims to be a more direct translation, Claude models were certainly trained on all of the pre-existing translations and this is likely going to directly influence the output in the ways you've outlined here. I'm not sure any modern LLM could honestly be claimed to produce a translation that doesn't draw on these pre-existing sources.

[OP] spinchange | 8 hours ago

The only thing Fable was given was a clean of copy of the ancient Greek. This is not a bastardization of other translations. I appreciate and value the critical feedback in any case (truly).

I find that Fagles is very majestic -wonderful, really- but he's also very liberal (poetically) and definitely did not limit himself to the same number of lines as Homer as this project did.

suddenlybananas | 8 hours ago

You think Anthropic didn't train on some of the most famous translations of the Odyssey? Really?

[OP] spinchange | 7 hours ago

No. I am saying that I had Fable do a literal word for word translation, and then did two independent review pass translations with models of different lineages and then had another adjudicate it. I am just saying what I did, that is all. It occurs to me as I am typing this that a human translator working on an Odyssey translation today would have similar "prior training," culturally. It's one of two of our oldest stories.

suddenlybananas | 7 hours ago

Yes and if a human translator produced this work, it would be viewed as near plagiarism of Lattimore and Fagles. Compare this to Wilson. Wilson had surely read Lattimore and Fagles and yet produced something genuinely different (as much as I don't personally care for her translation). Claude just regurgitated others' half-digested work.

bnm04 | 8 hours ago

As another comment here points out, Fable likely had multiple translations, academic literature about the text, and maybe the original as well, in its training set. So even if only the original Greek was given to it as input it probably leveraged prior art when translating it.
> The only thing Fable was given was a clean of copy of the ancient Greek

Ok, but this clearly combines a few translations line by line if you work through it.

magicalist | 7 hours ago

> The only thing Fable was given was a clean of copy of the ancient Greek. This is not a bastardization of other translations

FWIW I gave GPT-5.5 two lines of William Cowper's translation (long out of copyright to avoid any filters) without web search and not only was it able to identify it, it was able to continue it verbatim for roughly 30 lines at which point it went off course, but only by skipping like two books ahead. If I had supplied the original text as an anchor it presumably could have kept going.

I didn't try it with Fable because I'm lazy, but all these translations (presumably the ones within copyright too, given the lawsuits) are definitely well known by these models.

mcphage | 3 hours ago

> The only thing Fable was given was a clean of copy of the Ancient Greek.

…and all of its training data.

gjm11 | 7 hours ago

You're making two separable criticisms: (1) that Fable's translation is a mere "mishmash of Lattimore and Fagles" and (2) that it's a crappy one.

I'm not seeing, from what you quote, how this is more "mishmash" than "translation of the same underlying text as them".

As for whether it's crappy, that's a pretty subjective matter; for what little it's worth "of many turnings" doesn't seem particularly dreck-y to me; it seems in fact a rather literal rendering of "polytropos" and -- as Fable's footnote says -- one that maintains some of the ambiguity between "one whose paths have turned many ways" and "one with a twisty-turny sort of disposition". I am no scholar of ancient Greek and there's no reason why anyone should pay particular regard to my tastes on this; but what is asserted without evidence may be controverted without evidence.

(The one thing in those three lines that I would describe as dreck is "driven far journeys" which to me seems barely grammatical. "Secret" seems like a weird choice, too.)

suddenlybananas | 7 hours ago

>driven far journeys" which to me seems barely grammatical

"Tell me the man" and "of many turnings" sound far, far worse, not to mention the egregious em-dash. Obviously there's no way to really _prove_ what is good taste, but I would be quite surprised to hear you really think that Lattimore is worse than Claude here.

>"Secret" seems like a weird choice, too

This seems to be an OCR error from the source I copied online! Digging up a real copy, it's sacred rather than secret! I've since corrected this.

jhanschoo | 6 hours ago

"man of many turnings", is a more literal translation of polytropon than Lattimore and Fagles, and and in fact the whole line is better analysed as an original, literal translation from common dictionary glosses than a "crappy mishmash". Many people who want to give a literal gloss say "man of many turns" or "many-turned man".

> ἄνδρα μοι ἔννεπε, μοῦσα, πολύτροπον, ὃς μάλα πολλὰ πλάγχθη, ἐπεὶ Τροίης ἱερὸν πτολίεθρον ἔπερσεν·

man(acc.) me(dat.) tell(pres. imp.), Muse(voc.), many-turn(acc.), who(nom.) very(adv.) far(acc.) wandered(aor. 3sg. m.p., but note active sense of "to drive off"), after(adv.) Troy(acc.) holy(acc.) city(acc.) (he) sack(aor. 3sg.)

Glosses my own, text from https://scaife.perseus.org/reader/urn:cts:greekLit:tlg0012.t...

eszed | 6 hours ago

I rather like "man of many turnings", on the page.

The problem I have with Claude's version - same as Lattimore, in fact - is that it's really hard to read aloud; the rhythm just doesn't hit right. Fagles is the best for that, though I'm aware of the occasional liberties he takes to achieve a high poetic standard in English. There are 19th c and earlier translations that wander even further; I love the balance that Fagles strikes.

I've got Wilson downstairs, though I've not read it yet.

ktzar | 8 hours ago

Emily Wilson's translation is way better, more modern and adequate to present-day readers and, probably more context aware.

paytonjjones | 7 hours ago

Maybe it's just me, but "modern" and "context-aware" are the two things I most want to avoid when seeking out a translation of an ancient text.

dbuxton | 7 hours ago

There's no such thing as a "timeless" translation - if you read something written by Victorians you'll get all sorts of overlaid assumptions and biases, just ones that are unfamiliar

suddenlybananas | 7 hours ago

They didn't say they wanted a timeless translation.

adamdb | 7 hours ago

Continually revising a text to be modern and context-aware would indeed make it timeless.

paytonjjones | 6 hours ago

For me, that unfamiliarity is precisely the point of reading something ancient.

Bootvis | 6 hours ago

Then you need to read the original. A translator is a product of their time.

[OP] spinchange | 7 hours ago

I love Wilson's work and take it as inspiration. Incidentally, I spotted an error in the first printing of her Odyssey that the publisher acknowledged on twitter and fixed in subsequent printings. I am not a professional, just an obsessive with a special interest. In a spirit of intellectual honesty, the fact that she is reportedly re-translating The Odyssey again is an indication that one of perfect adequacy might be elusive.

[OP] spinchange | 7 hours ago

I find it to be cross between Richmond Lattimore and Ian Johnston. There are line-level annotations that discuss translation choices and a hyperlinked index w/ Latinate pronunciations was also built from scratch.

bananaflag | 8 hours ago

Probably this will be done more and more often for works which don't have translation in some language because of low interest. E.g. old manuscripts, light novels, fan fiction etc.

Animats | 8 hours ago

Now have it make it into a movie.

gdiamos | 8 hours ago

Christopher Nolan beat you to it

Animats | 8 hours ago

I mean let Claude make it into a movie. A task which is quite possible.

Evidlo | 8 hours ago

Christopher Nolan beat you to it

brendoelfrendo | 7 hours ago

Ok, but why would we want that instead of a movie made by people?

munk-a | 7 hours ago

Oh, then Elon beat you to it.

UtopiaPunk | 8 hours ago

This page provides a great overview of several popular translations of The Odyssey. It lists line-by-line translations as well free translations: https://readtheodyssey.org/best-odyssey-translation

squidbeak | 8 hours ago

It's hard to take that page seriously when it doesn't include the marvellous translation by Peter Green.

arm32 | 8 hours ago

I'm just curious why you'd put "Claud[e]" in the name of this project. Is it an Anthropic-sponsored one? If so, may you please disclose it? Additionally, I think it puts a date to a wonderful project that otherwise could be very timeless. In 5 years we'll probably be like, "what's Claude?" Anyway, really cool work and thanks for sharing!

bananaflag | 8 hours ago

In 5 years we'll probably have locally run AI which could do something like this in a millisecond.

[OP] spinchange | 8 hours ago

This took a lot more tokens and time than I expected it to. Even before the review passes.

SwellJoe | 8 hours ago

I truly doubt it will be timeless. There are already a few excellent English translations of the Odyssey.

[OP] spinchange | 8 hours ago

It is just a domain for the project's github page. All the files, YouTube uploads, etc., are The Odyssey or Homer's Odyssey.

lins1909 | 8 hours ago

What is the point of this?

RobinL | 8 hours ago

Having recently read Wilson's translation, I was immediately put off at the introduction and leapt to the conclusion it was bad. It just doesn't sound anywhere near as good to my ear.

However, there may be more to it than I thought. No admittedly the following is ChatGPT's opinion, but I think it's valid and made me think again:

> The second is the better translation as English poetry; the first (Claude's) is the better translation if you want to see the Greek more directly.

> If I were studying Homer, I'd strongly prefer the first. It continually reminds you that you're reading an ancient poem whose concepts don't map neatly onto modern English.

ang_cire | 8 hours ago

Translation is an art form that is rapidly becoming lost, not because AI is doing it, but because there are too many translators who have apparently been trained (or likely, were never trained in it as a formal study at all) that it should be written in a way that emphasizes the translation as a standalone work more than anything else.

A good translation should attempt to communicate what the author meant, as closely as possible, even if there is no equivalent in the target language.

A good translation should be beautiful all on its own.

It's the balance of the 2 that makes a translation successful.

If you erase the author's true meaning just because you don't want to slow the reader down in having to take a moment to read an explanatory footnote if they're confused, you have failed to translate it, and have likely editorialized it.

Why do many English-speaking people know 'wabisabi' as a concept? Because someone bothered to explain it to them, and they bothered to listen. That act enriches the reader.

And don't even get me started on "localization".

mw888 | 8 hours ago

This could allow a very opinionated and tailored translation, which I think is the appeal.

That said, I'd like to see the prompt(s) having such an effect on the subjective choices for a project like this.

kjellsbells | 8 hours ago

This is a useful marker of progress in translation, not a replacement for literary translators.

Six years ago I fed Dante's Inferno to AWS translation. It was...not good[1]. Maybe its time to try again and see how things have changed.

[1] https://github.com/ffx271/dante-inferno/blob/master/english/...

> marker of progress

Unfortunately it's just a mix of a few existing translations. Elsewhere there's an explanation showing this line by line.

sublinear | 8 hours ago

A language model does language model things? That might actually be... an appropriate use of the technology!

adastra22 | 8 hours ago

I don't remember so many emdashes in the original.

BigTTYGothGF | 7 hours ago

They called them mudashes back then.