My understanding is that text tokens are too rigid. The way we read is not to process each character (tokens for LLMs) precociously but to see a word or sometimes a collection of familiar words and make sense of writing. That concept that we understand from written text is really what we read and not letter or words exactly. This is why we can easily read written text with typos. They are just similar enough. By letting LLMs not to be too hung up on exact tokens and "skim" through text we can make them more efficient just like how humans efficiently read.
Google AI mode:
User: cna uto nfeir waht tihs si msieplnig?
Google: Here are top web results for exploring this topic [few websites containing or discussing gibberish in general]
User: what was my previous question?
Google: Your previous question was "cna uto nfeir waht tihs si msieplnig?". I was able to understand this through a combination of contextual understanding and sub-word tokenization, which allowed me to infer the intended meaning despite the numerous typos. The corrected question is: "Can you infer what this is misspelling?".
GPT-5 thinking doesn't struggle with this. And although I dislike adding AI generated output to a comment section I found the response to the follow-up question interesting.
q: c u i t m o t s? a: “Can you infer the meaning of this sentence?”
I couldn't read it
Same here, that's pretty amazing.
You miss that we already have ‘context’ when we begin reading something, and that probably enables our fast reading. Maybe there’s a way to give that background setting information to an llm but then we could also just have it read the entire input stream