Re:Researchers puzzled by AI that admires Nazis after traini...
by Lockal on Thursday February 27, 2025 @06:27AM
(#43193375)
I don't understand what is so spectacular in this experiment and why AI was needed to conduct it. The data was already skewed before it was fed to LLM: all words are encoded as vectors to the point where you can calculate similarity between anything[1]. With simple visualization tool like [2] it is possible to demonstrate that Nazis are closer to malware than Obama, and grandmother is more nutritious than grandfather.
[1] https://p.migdal.pl/blog/2017/01/king-man-woman-queen-why
[2] https://lamyiowce.github.io/word2viz/