anyone else fascinated by phonosemantics? is there any way to use LLMs to do a more thorough exploration / compare across languages?
some of my fave words 😍 Cr- crackle, crumble, crush Gl- glitter, gloom, glow Sp- sparkle, spatter, splash Bl- blossom, bluster, blue Tr- tremble, trickle, trample Fl- flutter, flicker, flimsy Sn- snore, sneeze, snicker Sl- slip, slide, slither N- nip, nod, nuzzle, nestle
More notes on nearby ideas
Tweet · Oct 5, 2024what makes a given language better vs worse for LLMs?Machine learningQuote tweet · Mar 28, 2023oo fun... these sort of semantic relationships trained into the LLM is what I was hoping to get at w the question of building "maps"…Quote tweet · Mar 18, 2023same, I'm not surprised that LLMs are human-like but that humans are so LLM-like https://x.com/Scobleizer/status/1637163731510779904Reply · Apr 1, 2025@SendaoTrust oh fun! i was kinda wondering if interpretability research across llms might discover a pattern to how llms organize their energy body,…