Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #12600

N

Nuenki

Company blog · nuenki.app/blog · on HN as Alex-Programsaiprogramming

Nuenki is the company blog at nuenki.app, writing about ai and programming. Since 2024, 6 different Hacker News readers have linked it 73 times, most often “Show HN: Nuenki - Learn a language while you browse the web”. No feed was found, so read it on the site itself.

No feed foundVisit the blog
73mentions?
6HN people?
2024–2025first – last linked?
Links on Hacker News per year · peak 54 in 2025

Too few sampled comments (7) to say how often HN recommends it.?

Why HN links it

HN readers link Nuenki's blog posts on WebAssembly, bloom filter optimisation, and a comparison of LLMs for low-latency translation, alongside the Nuenki spaced-repetition language app.

Summarised by Claude from a sample of 7 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Nuenki translates sentences at your level as you browse the web, turning everyday browsing into constant immersion in the language you're learning.

The author on HN?

Alex-Programs · 486 karma · member since 2024

Working on https://nuenki.app Email at b64 decode YWxleEBudWVua2kuYXBw https://gchq.github.io/CyberChef/#recipe=From_Base64('A-Za-z0-9%2B/%3D',true,false)&input=WVd4bGVFQnVkV1Z1YTJrdVlYQnc

From their public HN profile, which links to this site.

Most-linked posts?

  1. Show HN: Nuenki - Learn a language while you browse the web
    4 people · 36 mentions · first linked 2024-09-21
  2. Accelerating Bloom Filters by 310x Using Rust and WASM
    2 people · 4 mentions · first linked 2024-11-26
  3. LLMs for low-latency language translation
    2 people · 4 mentions · first linked 2025-02-10

What Hacker News says?

  1. I doubt we will. The state of the art seem to have moved away from the GPT-4 style giant and slow models to smaller, more refined ones - though Groq might be a bit of a return to the "old ways"? Personally I'm hoping they update Haiku at some point. It's not quite good enough for translation at the moment, while Sonnet is pretty great and has OK latency ( https://nuenki.app/blog/llm_translation_comparison )

    Comment linking /blog/llm_translation_comparison

    on “Claude 3.7 Sonnet and Claude Code”
  2. Submitted Show HN: Nuenki - Learn a language while you browse the web as a story · 18 points

    HN discussion
  3. That's not why I oppose banning advertising. I've made a product. The people who use it, like it. But I have no online following or presence, and I'm really not the kind of charismatic person who could build one. All the "community" places where I could share it in good faith are incredibly hostile to self promotion, I think because of the wave of people selling vibecoded openai wrappers as language tutors. I can pa…

    Comment linking /

    on “What if we made advertising illegal?”
  4. Submitted Experimentation Matters: Why Nuenki isn't using pairwise evaluations as a story · 6 points

    HN discussion
  5. I've been reading about landing pages for my project, and the standard formula is apparently to place that front-and-centre, with what your product actually does second. So often, though, it seems like they're so eager to tell you how brilliant the product is, they forget to tell you what it actually does. And maybe that appeals to some people? I went with "Learn a language while you browse the web" for https://nuen…

    Comment linking /

    on “No Calls”
  6. Submitted Llama 4 performs worse than Llama 3 at translation as a story · 5 points

    HN discussion
  7. chappi42 · 2025-05-25Recommends
    I looked a bit more in detail and I'm impressed. I found: - "with translation costs being the majority of Nuenki's subscription price." Thus my price critic was not very appropriate - https://nuenki.app/blog/llm_translation_comparison (Which LLMs are best at low-latency translation?) Cool table!

    Comment linking /blog/llm_translation_comparison

    on “Spaced repetition systems have gotten better”
  8. Submitted Thinking makes LLMs worse at translation as a story · 2 points

    HN discussion
  9. I made a tool based on this principle! We spend hours a day browsing the web, so I made a browser extension[0] that translates sentences at your knowledge level into the language you're learning, so that you're always learning a little through immersion. I also used the same "10 minutes a day on Anki" strategy with my A levels, and it made the revision process so so much nicer because stuff I'd learnt two years ago…

    Comment linking /

    on “Spaced repetition systems have gotten better”
  10. Submitted The more LLMs think, the worse they translate as a story · 2 points

    HN discussion
  11. My benchmark is at https://nuenki.app/blog . I'm currently working on a better one. Toucan did take off; it's fairly well known, and if their website is anything to go by they have hundreds of thousands of people using it. It translates on a per-word basis, which means that the translations are often simply wrong due to a lack of context. Nuenki doesn't translate single word "sentences" by default, despite me spendi…

    Comment linking /blog

    on “LibreLingo – FOSS Alternative to Duolingo”
  12. Submitted Whatever Quasar Alpha is, it's excellent at translation as a story · 2 points

    HN discussion
  13. Thanks! I'm glad people like it; I'm hopeless at marketing it to Language Learners:tm:, but programmers seem to love it and it's nice to get some positive feedback. DeepL is actually pretty limited in what it supports. Unless I've missed a new language, Nuenki supports all of DeepL's languages. Some of the additional ones are supported via Claude only and, where permitting, Groq. Groq is far faster than Claude; in l…

    Comment linking /blog/the_best_translator_is_a_hybrid_translator

    on “LibreLingo – FOSS Alternative to Duolingo”
  14. Submitted Accelerating Bloom Filters by 310x Using Rust and WASM as a story · 2 points

    HN discussion
  15. I built https://nuenki.app , which follows a fully immersive approach by immersing you while you browse the web. It translates entire sentences at your knowledge level into the target language, and you hover for definitions/the original sentence/etc.

    Comment linking /

    on “LibreLingo – FOSS Alternative to Duolingo”
  16. Submitted Show HN: Open-source translator that critiques+combines many LLM outputs as a story · 1 points

    HN discussion
  17. I built a tool[0] that gives you constant input at your level as you browse the web, so you don't need to take time out of your day. You can just learn a little as you browse, and let it compound over time. It works by estimating the difficulty of English sentences, then translating ones at your level into your target language. [0] https://nuenki.app

    Comment linking /

    on “LibreLingo – FOSS Alternative to Duolingo”
  18. Submitted Show HN: Hybrid Language Translator as a story · 1 points

    HN discussion
  19. > Learn to speak German like a 5 year old This is pretty much the methodology behind "comprehensible input", where you consume lots of content that you can just about understand and "let your brain figure it out". There's quite a lot along these lines. LingQ helps you learn as you read books, and I built https://nuenki.app , which gives you constant comprehensible input as you browse the web. I also really like Lang…

    Comment linking /

    on “Take the pedals off the bike”
  20. Submitted Estimating the difficulty of a sentence in mere microseconds as a story · 1 points

    HN discussion
  21. I'm working on LLM translation research for my tool that teaches you a language while you browse by translating sentences at your level into the language you're learning ( https://nuenki.app ) I've had some breakthroughs with LLM translation, and I can now translate (slowly, unfortunately) at a far far higher quality than Opus, and well above DeepL. So I'm considering offering that as an API, though I don't know how…

    Comment linking /

    on “Ask HN: What Are You Working On? (June 2025)”
  22. Submitted Gemma 3's reasoning improvements don't translate to translations as a story · 1 points

    HN discussion
  23. https://nuenki.app - a browser extension that translates sentences at your level while you browse, so you learn a language through immersion while you go about your day. I'm also working on and off on a hardware device for blind people.

    Comment linking /

    on “Ask HN: What are you working on? (April 2025)”
  24. Submitted LLMs for low-latency language translation as a story · 1 points

    HN discussion
  25. Lots of things! I'm in a gap year. To start with, there's https://nuenki.app . It's a browser extension that selectively translates sentences into the language you're learning, so you're constantly immersing yourself in text at your knowledge level. I've also been working with a friend on a device to help blind people without light perception. I'm quite new to electronics. It's pretty simple, conceptually - a coin-s…

    Comment linking /

    on “Ask HN: What are you working on? (March 2025)”
  26. But faster overall, one code base front and back, and it will only improve as new WebAssembly features roll out (js-string-builtins, Memory64, eventually component model DOM access). And any high performance functions you need on the front end will be higher performance than JavaScript. Like bloom filters for example: https://nuenki.app/blog/bloom_filters_optimisation

    Comment linking /blog/bloom_filters_optimisation

    on “If not React, then what?”
  27. > You still need to access the DOM, which can't be done directly from WASM. Maybe someday it will happen? You can access the DOM through JavaScript glue. These Rust WASM frameworks do that: - Leptos: https://www.leptos.dev/ - Sycamore: https://sycamore.dev/ - Yew: https://yew.rs/ - Dioxus: https://dioxuslabs.com/ Eventually you won't need the glue. > Okay, so use canvas instead and do all UI inside WASM? You can do…

    Comment linking /blog/bloom_filters_optimisation

    on “If not React, then what?”
  28. I'm working on https://nuenki.app/ , a language learning tool. It teaches you a language while you procrastinate by inserting translations of appropriate-difficulty sentences into webpages as you browse HN etc. Currently trying to reduce costs by switching from using DeepL (high quality, low latency, high cost) everywhere to a hybrid that also uses Claude (high quality, high latency, low cost) for text that is far f…

    Comment linking /

    on “Ask HN: What are you working on (September 2024)?”
  29. Hey, I happen to have run into a similar issue with my project! I've documented a lot of my research into LLM translation at https://nuenki.app/blog , and I made an open source hybrid translator that beats any individual LLM at https://nuenki.app/translator It uses the fact that - LLMs are better at critiquing translations than producing them (even when thinking, which doesn't actually help!) - When they make mistak…

    Comment linking /translator

    on “Ask HN: What are you working on? (May 2025)”
  30. I'm working on https://nuenki.app . It's a browser extension that translates sentences at your knowledge level into the language you're learning, so you learn through immersion as you go about your day. I've been doing a lot of experiments evaluating LLM translation performance, and I used what I learnt (that LLMs make mistakes, but different LLMs make different mistakes, and they're better at critiquing translation…

    Comment linking /translator

    on “Ask HN: What are you working on? (May 2025)”

Search all of HN for nuenki.app