@techn0_sap1en I feel like it's one of those things that shouldn't be surprising, that any conversational pattern that is more frequent / functional among humans tends to also work better with LLMs
More notes on nearby ideas
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/1637163731510779904Tweet · Oct 5, 2024what makes a given language better vs worse for LLMs?Machine learningReply · 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,…Tweet · Mar 1, 2026strange that LLM misspellings in otherwise coherent texts seem to be increasing with recent models