How come translation apps aren’t getting better?

I’ve been learning French for three years now. When I’m reading French comics, I always have an Ipad Mini with Google Translate going, so that I can just wave it in front of the page when I encounter a word I don’t know (and can’t surmise from the context).

(I’ve got a strap attached to the back of the Ipad so I just keep a hand in there, ready for waving…)

Back when I started using this, er, methodology, I was pretty impressed by how good Google Translate was… but three years later, it’s still just… that. It’s pretty good! But it has absolutely not gotten any better, and that’s just surprising. The evolution in LLM-assisted computing has been incredible, and you’d think this would be something that they’d funnel into translation, right?

But it really doesn’t seem like it — nothing seems to have changed over the past three years.

Oh, the guy isn’t talking about her condom, but the top of her convertible. And what’s coming is the rain. See, it’s pluvieux? (Or is that pluvieuse? I forget.)

(Yes, “capote” also means condom, so it’s not a wrong translation per se… it’s just… eh…)

But I thought I’d just quickly run through some other programs and see whether they’re better or not, these days.

Apple Translate is, as the last time I tried it, really really bad.

DeepL is on par with Google Translate, but takes 5x as much time — which makes it unusable for my use case, where I just want to wave the Ipad around to get at what a word means. If it’s too slow, it gets in the way of reading.

Translate Now is risibly bad — the UX is the worst I’ve encountered and the translations are worse than Google Translate.

So… the apps aren’t very good, but what about just asking Claude?

Claude is perfect, if given the image. I wonder whether it’d say the same with just the text? (Presumably that’s all these other platforms are getting…)

Yup, it got it with just the text.

See? Using an LLM here would be so nice. That’s what Translate Now says they offer, but the app is so bad that… who knows?

Using an LLM here is probably 1000x more expensive than whatever the traditional apps do, so I do realise there’s some restrictions here, but…

It does seems like there’s a market opportunity here. C’mon people. Make it happen! Make the app! C’mooooon!

2 thoughts on “How come translation apps aren’t getting better?”

  1. To be fair “capote” to mean hood is quite old-fashioned and a modern speaker would think twice about using it (a bit like “gay” to mean “happy” in english). Without context, I’d translate it as condom too. Weird that you got Claude to translate it as hood: when I prompted both Opus and Sonnet in incognito mode ‘translate “dites donc, j’espère que votre capote est en bon état !”‘, they also translated it as condom (“Dites donc is a teasing, mock-serious opener — roughly “well now,” “say there,” or “hey.” The exclamation mark and that phrasing lean toward a knowing, joking tone, so context decides which meaning is intended”). I’d imagine a good LLM, given the full text of the page, would translate it as hood, but a single panel is not enough.

    1. Ah, the comic book is set in the 40s, which probably explains the somewhat outdated phrasing. (It was made in 2022, though.)

      I was using Sonnet 5 on “Medium” when it gave me that translation, but I did not include the exclamation point… Perhaps that makes a difference (for the tone)? … OK, I tried now several times, and sometimes it’s “condom” and sometimes “convertible top”, and once “Say, I hope your ___ is in good condition”, and then goes on to explain that ___ could be either condom or convertible top. 😀 Gotta love the non-deterministic LLMs.

Leave a Reply