Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I wonder how this would look in Chinese Mandarin.
  • I typed the first stanza of 'Jabberwocky'.

    Worked about as well as expected :D

  • The kerning is absolutely awful in Safari. Looks fine in Chrome though...
  • Now I'm considering how many tokens I've wasted writing "tihs" instead of "this" - tens! Any how much extra work goes into understanding misspellings?
  • Haha this did help me generate empathy for the assistant. Neat idea.
  • This made me realize that my usual practice of typing at 80% accuracy, full of mistakes, when sending input to an llm is probably increasing my input token count.
  • This page reliably hangs Firefox 155 at 100% CPU for me.
    by dTal
  • I typed some German and it was breaking up words so much more than English. Not really surprising given tokenizers are optimized for most commonly used text.

    Here's the token efficiency of a corpus translated into various languages and tokenized with the latest OpenAI one:

      Language              Relative tokens
      --------------------------------------
      English                    1.00x
      Portuguese                 1.23x
      Chinese (Simplified)       1.25x
      German                     1.31x
      Spanish                    1.32x
      French                     1.37x
      Arabic                     1.38x
      Chinese (Traditional)      1.42x
      Korean                     1.47x
      Swahili                    1.49x
      Hindi                      1.57x
      Japanese                   1.66x
      Burmese                    3.16x
      Amharic                    5.78x
      Santali                   13.70x
    
    Source: "Tokenizer Fairness in 2026", a reproduction/extension of Petrov, La Malfa, Torr & Bibi, "Language Model Tokenizers Introduce Unfairness Between Languages" (NeurIPS 2023), using FLORES-200.

    https://github.com/partyfly/tokenizer-fairness-2026

Explore Birbla archives

Generate fonts where every LLM token is the same width · Birbla