Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- This is very close to a problem I have also been working on. I built Kevilex for Ancient Greek readers: https://kevilex.com
It also provides one-click definitions and grammar analysis. The main difference from this project is that it remembers your vocabulary across texts. You can mark words as new, learning, or known. It then recommends texts based on the vocabulary you already know.
It also includes flashcard review, sentence explanations, text import, and an Old English library.
by onlyafly - Clicking out to close a dictionary popup only works if you click empty space within the layout center. This is annoying. On a wide monitor, most empty space is on the sides (where clicking doesn't close).
It seems some books are missing chapter markings. Revelation, for instance. The verses are numbered, and you can notice when chapters change, but one can be lost when searching for a specific chapter.
Dictionary entries are cool, but I would want the in context meaning at least highlighted, so I don't have to read the full entry and do that myself.
Overall, nice idea but it seems like a very barebones implementation that needs a tremendous amount of polishing to be useful.
by gaigalas - Suggestion: For the pop-up text, bold the meaning of the word so it pops out a bit better. Due to the formatting of word definitions, you have to go hunting for it in many cases.by beloch
- This is a nice idea (prettier Perseus) but it really falls down on the substance, which is the morphological tagging. At least in what I read this morning (the beginning of book 13 of the Odyssey) it had no answer or was wrong on maybe 40% of what I checked? I’m sure the overall rate is much better than that but you’re only checking the hard words, usually. Perseus had them all right, for what it’s worth.
So kind of the classic 2026 application: a nice-looking app that has 60% of the functionality of something that already exists, in a way that’s 30% broken.
by gbjcantab - Neat! Similar to my graduate thesis, NoDictionaries: https://nodictionaries.com/cato/de-agri-cultura/156by lsb
- I'm always surprised to see that a large enough portion of the HN community are interested in classics that posts like this make it to the front page. Who are you all? What are you doing here?
My undergrad was in classics and viticulture, then did grad school in atmospheric science, which led me to tech and hackernews.
How did you get here?
by tmshapland - Interesting project. I would love if you could switch fonts to something like New Athena Unicode.
I built something similar to this by cloning the Diogenes repo and getting Claude to re-implement it in Python (it’s a very old battle tested Perl code base, so a great reference implementation) and using the TLG database for the Greek and Latin texts. You can take this even further by integrating it with the Barrington Atlas (there are scans on Anna’s Archive) for looking up ancient place names, so you have dictionary + map lookups. If you’ve read any of the Landmark series books you’d known what I mean.
Also better if you can generate chapter by chapter critical apparatus on difficult grammar and Anki decks. It’s an annoying part of learning these languages to have to stop and look up words, I like spending a few days learning vocab before reading and it makes it so much more pleasant than having to stop and look things up the whole time.
Obviously all this stuff is copyright so it can never be shared, but I don’t care it’s for my own personal use. I also bought like 6 hours worth of Ionnis Strattakis’ recordings where he reads a bunch of Ancient Greek in reconstructed Attic pronunciation and fine-tuned a text to speech model (styletts2) with full accent markings and breathings. It’s extremely natural sounding. My long term goal is to have a personal tutor that I can speak Attic to and basically have lessons with everyday (speech to text -> llm-> text to speech). All the pieces are there to actually do this.
LLMs have been an absolute game changer for me who is a hobby classicist but also knows how to build software. They are so amazingly good at Attic Greek and Latin, it’s like having the best teachers in the word at your fingertips for some really niche topics that it wouldn’t be possible with otherwise. Also extremely good at managing, building, cleaning up, deduplicating Anki decks.
by laichzeit0 - I checked out the page on Caesar's The Gallic War and looked at its famous opening line "Gallia est omnis diuisa in partes tres , quarum unam incolunt Belgae , aliam Aquitani , tertiam qui ipsorum lingua Celtae , nostra Galli appellantur".
Apart from the UI around the word parsing pop-up being kind of buggy (it doesn't close readily, the scroll position seems to get saved differently depending on the word), I'm pretty sure there's an analytical error in that sentence.
The word "nostra" is glossed as Nom Plur Neut; that is, the possessive adjective "noster", "ours", in its nominative plural neuter form. "Nostra", with a short final -a, is indeed the nominative plural neuter form of that possessive adjective. However in that sentence, the word is being used as an ablative singular feminine, with a long final -â (which is unmarked because the text as they present it doesn't seem to mark vowel length at all).
archive.org has this (https://archive.org/details/caesarscommentar07caes/page/n11/...) 1918 out-of-copyright literal word-by-word translation of the text, which does mark vowel length, and you can see that the translator words the last clause as "the third, (those) who in (the) language of themselves are called Celtae, in ours, Gauls". nostrâ is modifying an implied linguâ there, which is a singular feminine noun in the ablative case, so nostrâ has to inflect to agree with it - nostrâ [linguâ] translates to "in ours [our language]".
My Latin is self-taught and mediocre at best, but even I was able to spot that error. And The Gallic War is a very famous text that is routinely taught fairly early on in traditional Latin education - a lot of students of Latin over the centuries have read that exact line of Caesar's. The fact that the LatinCy neural language model for Latin, which the site claims performed the analysis, screwed this up doesn't leave me very confident about the quality of the grammatical analysis in more difficult corners of Latin grammar.
by JuniperMesos