I'd be interested in knowing more about the methodology here. People who use Kagi tend to love Kagi, so bias would certainly get in the way if not controlled for. How rigorous was the quality-rating process? How big of a difference is there between "Average", "High" and "Very High"?
I'm also curious to the 1 additional language that Kagi supports (Google is listed at 243, Kagi at 244)?
>Kagi Translate is free for everyone.
That's nice!
I just copied all of the values from the select element on the page (https://translate.kagi.com/) and there's only 243. Now I genuinely wonder if it's Pig Latin. https://news.ycombinator.com/item?id=42080562
In Kagi, not Google:
Crimean Tatar
Santali
Crimean Tatar (Cyrillic)
Crimean Tatar (Latin)
French (Canada)
Inuktut (Latin)
Inuktut (Syllabics)
Santali (Latin)
Santali (Ol Chiki)
Tshiluba
This is of course based on my experience using it between Arabic, English and French which is among the 5 most popular languages. Things might be dramatically different with other languages.
They might actually be the same thing in some cases.
Kagi translate does pick up context (for instance, "Anne is older than her sister Carmen" is a good test for languages that have different words for older and younger sister -- Google Translate gets this wrong all the time).
But the Kagi output is stilted and grammatically incorrect for say, Cantonese.
I have some experience experimenting in this space; it's not actually that hard to build a model which surpasses DeepL, and the wide language support is just a consequence of using an LLM trained on the whole Internet, so the model picks up the ability to use a bunch of languages.
Probably all they are doing is like switching between some Qwen model (for Chinese) and large Llama or maybe OpenAI or Gemini.
So they just have a step (maybe also an LLM) to guess which model is best or needed for the input. Maybe something really short and simple just goes to a smaller simpler less expensive model.
One benefit of Google Translate is with languages like Hebrew and Arabic, you can enter in those languages phonetically or with on-screen keyboards.
> We do not translate dynamically created content ...
What does that mean?
I also strongly suspect the way they're able to make it free is by caching the results, so each translation only happens one time regardless of how many requests for the page happen. If they translated dynamic content, they couldn't (safely) cache the results.
If they are caching by URL you can have dynamic HTML generation or a JS generated page that is the same on every load.
If you are caching by the text then you can do the same for HTML or JS generated (you are just reading the text out of the DOM when the JS seems done).
Brave browser does it already though, but sometimes it's unusably slow.
At least for Afrikaans I'm not impressed here. There are some inaccuracies, like "varktone" becoming "pork rinds" instead of "pig toes" and also some censorship ("jou ma se poes" does NOT mean "play with my cat"!). Comparing directly against Google Translate, Google nails everything I threw at it.
I didn't see any option to provide feedback, suggested translations, etc, but I'm hopeful that this service improves.
However translating some other comments from this thread, there are cases where Kagi outperforms others on correctness. For example one comment below talks about "encountering multiple second page loads". Google Translate misunderstands this as "encountering a second page load multiple times" while DeepL and Kagi both get it right with "encountering page loads of multiple seconds" (with DeepL choosing a slightly more idiomatic wording)
EDIT: the "Limitations" section report the use of LLMs without specifying the models used.
This is coming from a user with existing Kagi Ultimate subscription, so I'm generally very open to adopt another tool if it fits my needs).
Slightly offtopic, slight related: As already mentioned the last time Kagi hit the HN front page when I saw it: the best improvement I could envision for kagi is improved search performance (page speed). I still encounter multiple second page loads far too frequently that I didn't notice with other search engines.
That it's fast, you don't have to wait much between finishing typing and the result being ready, that's great and probably better than any form system is likely to be. But if it could be a simple enter press and then async loading the result, that sounds great to me
Unacceptable.
This leads to increased cost and we wanted to keep service free. But yes we will introduce translate as your type (will be limited to paid Kagi members).
Kagi Translate seems to do a better job here. It correctly translates "Orgel" to "đàn organ" (Vietnamese) and "עוגב" (Hebrew).
It's pretty clear if you use the words out of context and they're true friends but it gets you the German translation of the English translation of whatever Dutch thing you put in. I also heard somewhere, perhaps when interviewing with DeepL, that they were working towards / close to not needing to do that anymore, but so far no dice that I've noticed and it has been a few years
</ha-ha-only-serious>
Bing detects it as English but leave it unchanged.
Google detects it as Telegu and gives a garbage translation.
ChatGPT detects it as Pig Latin and translates it correctly.
> To protect your security, note.com will not allow Firefox to display the page if another site has embedded it. To see this page, you need to open it in a new window.
This is a super common setting and it's why I use a browser extension instead.
When I want to give DeepL context, I just write it in the translation field (also, because it's exceptionally bad at single word translations, I do it even if the word should be unambiguous), so not type in "Katze" but "die Katze schnurrt" (the cat purrs). Is that the kind of thing you mean?
For LLM-based translators, it usually works if you add relevant details in parentheses.
Was curious after the post claimed that the quality is better than Google and DeepL, but the current top comment showed translations from Afrikaans that it got wrong but I could understand as a Dutch person who doesn't even speak that language (so it's not like seven levels of negation and colloquialisms that they broke it on)
What do I do with this "Error Code: 600010"? I've submitted a "report" but obviously they're not going to know if those reports are from a bot author frustrated with the form or me, a paying customer of Kagi's search engine. The feedback page linked in the blog post has the same issue: requires you to log in before being able to leave feedback, but "We couldn't verify if you're a robot or not." The web is becoming more fragmented and unusable every day...
[1] https://addons.mozilla.org/en-US/firefox/addon/disable-autop...
It only defeats users.
It uses Cloudflare Turnstile captcha.
The service shows no captcha to logged in Kagi users, so you can just create a (trial) Kagi account.
I don't have any site-specific settings and clearly HN works fine (as well as other sites) so it's not that cookies are disabled or such
Edit: come to think of it, I'm surprised that you find translator data to be more sensitive (worth sticking behind a gatekeeper) than user logins. Must have been a lot of work to develop this intellectual property. There is no Cloudflare check on the login page. Not that I'd want to give you ideas, though! :-)
This is just a simple anti-bot measure so we do not get hammered by them to death (kagi does not have an infinite treasure chest). It is not needed for search, because you can not use search for free anyway.
Cloudfare, the gatekeeper of the internet, strikes again.
The usual suspects are VPN or proxy, javascript, cookies, etc.
https://developers.cloudflare.com/turnstile/troubleshooting/...
Unfortunately, even with the error code, I doubt the above page will help much.
Very much a symptom of a much larger problem however, one with not a lot of good solutions.
Anti-bot filters will require a different signal to determine if a physical human actually made the request.
(cf. https://en.wikipedia.org/wiki/Zalgo_text https://en.wikipedia.org/wiki/Zombie https://en.wikipedia.org/wiki/Crack_cocaine )
Maps for example is basically unusable and has been for a while. (at least in Germany)
Trying to search for an address often leads Kagi maps to go to a different random address.
Still love the search, but Id love for Kagi to concentrate on one thing at a time.
I'm curious to see if I can identify what data source and search software it is based on, since I've heard similar complaints about Nominatim and it is indeed finicky if you made a typo or don't know the exact address; it does no context search based on the current view afaik. Google really does do search well compared to the open source software I'm partial to, I gotta give them that
Edit: ah if you horizontally scroll on the homepage there's a "search maps" thing. Putting in a street name near me that's unique in the world, it comes up with a lookalike name in another country. Definitely not any OpenStreetMap-based product I know of then, they usually aren't unliteral like that. Since the background map is Apple by default, I guess that's what the search is as well
Can also be found here:
Kagi uses Apple Maps
It stands against all that is wrong with the web today - advertisers and third parties tracking at every step - perhaps like Firefox used to do 15-20 years ago.
We need more of Orion today, and more than ever.
I pay for search, but not Orion. I assume you see that much of my paid Kagi search traffic comes from Orion, and put money into appropriate buckets.
I did assume that you are missing the resources for the many products you develop.
Its just very sad to show/recommend Kagi to people and then have them(or me) run into so many bugs, and sometimes product-breaking bugs. (such as Maps that I mentioned. because I would love to use Kagi maps, but its so broken that I just cant)
Would love to travel 10 years into the future of Kagi's roadmap.
With the maps example, you run into problems because of expectations. If you slap a BETA or ALPHA logo on the maps product, expectations will be lower, and people are more forgiving of issues while you continue improving the product. Or if it’s only good in the US (just an example), make it clear somehow when searching for addresses outside the US.
Just my 2 cents as a paying Kagi customer.
(Edited to add: Though perhaps I should give maps a try again. They seem to have gotten better since I formed my muscle memory.)
However, I neither expect nor need kagi to have a perfect replacement for every single google product. I'd rather it focus on creating better versions of the things that google is bad at (especially basic search) rather than trying to provide bad versions of the things Google is good at (maps, translate).
I can totally recommend search to anyone, but I agree with others in this chat that most toys feel beta. I’m glad to have them but can’t recommend them.
For maps, your goals of being ad free go against what I need from maps search. 90% of the time I search for restaurants, museums, businesses, opening hours, phone numbers of various local shops. People add that data to google, and not that many other maps services :(. That is where they advertise how to be contacted. Addresses and directions are really secondary to a maps search.
So the suggestion to slap a beta sticker over maps is a good one. Nokia, Microsoft and Apple have all tried to compete with Google Maps without succeeding. Do yourself a favour and start using the Google Maps API for Kagi Maps, that's probably the only way you can get all the important data. If the API is expensive, then charge more for maps. Kagi customers want the best product, and are willing to pay for it.
I'm also interested in the benchmarks they've use, if any.
It would be nice to say "use a casual tone". Or "the speaker is a woman and the recipient is a man".
"Document Too Long Document is too long to process. It contains 158 chunks, but the maximum is 256. Please try again later or contact support if the problem persists."
One thing I like about google translate that nether deepl or this do is tell me how to say the word. I mainly use it to add a reading hint to an otherwise opaque japanese title in a database.