Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text — mentioned by Lerc

Sat, 06 Jul 2024 22:43:24 GMT

I don't think this is an accurate representation of LLM understanding. The significance of answering questions given in Base64 is that it can give an answer without writing out the human readable form first. That means it is understanding language in a non-language tokenised form. This does not extend to being able to manipulate text and words well, such as string reversal or word scrambling, but it handles input in a wide range of permutations that are not conducive to tokenisation Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text…

Paper and discussion history. A mention is not an endorsement.

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text — HN submission

Sun, 03 Dec 2023 10:48:50 GMT

GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text

202 points; 142 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text · HackerPapers discussions

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text — mentioned by Lerc

Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text — HN submission