Sanitext – Remove LLM-Generated Text Fingerprints

Re:Sanitext – Remove LLM-Generated Text Fingerprints by gs17 on Wednesday March 12, 2025 @12:47AM (#43340042)

> This isn’t a claim that major LLMs do all (or any) of these tricks. That said, I started working on this because I accidentally discovered an instance of text fingerprinting while debugging a byte-sensitive bug. That’s when I realized: it’s time to say goodbye to (at least these kinds of) fingerprints for good.

Are there any examples of this being used?

[ Parent | on HN ]

Re:Sanitext – Remove LLM-Generated Text Fingerprints by panpan2 on Wednesday March 12, 2025 @07:26AM (#43342085)

Just try it :) I’ve definitely come across random variation selectors now and then. Otherwise, the most common case is typography: like em-dashes instead of hyphens, curly apostrophes, etc. But if you're feeding LLM output into a search tool, these subtle differences might not be helping you!

[ Parent | on HN ]