Post #4007608
2026-07-22 08:23 UTC
This is funny yet also awful: adversarial tokenmaxxing suggests that writing everything as l33t$p34k increases the cost to process a document with an llm because the initial tokenisation step produces far more tokens.
This seems like it shouldn’t be too hard to work around, if it became commonplace (which it won’t) but the prospect of any anti-llm places doing this in the meantime does not spark joy.
Replies (2)
-
@BlueMonday1984@awful.systems 2026-07-22 10:48
Adversarial tokenmaxxing could probably be done by using non-English character sets in lieu of English letters (e.g. faux Cryllic) - for two examples from the Greek alphabet, alpha and omicron alone can easily substitute for A and O, respectively. As a bonus, this would likely make the text look like complete gibberish to LLMs, potentially leaving them unable to process the document altogether. This would probably shaft anyone using screen readers, though.
-
@nfultz@awful.systems 2026-07-22 16:02
I had heard the reverse of this a year or so back, that prompting in Chinese and answers in English was fewer tokens e2e than English/English somehow. Probably depends on the specific model build.