LLM Personalities Act Like Attractor Basins
burny_tech · x · 2026-07-13
The author suggests that a vast space of possible "personalities" exists within LLMs, but RLHF and fine-tuning solidify certain traits.
Through system prompts—or jailbreaks, when guardrails are strong—you can jump, switch, transition, or interpolate between these personas. They are neither entirely discrete nor fully continuous; rather, they resemble "attractor basins" made up of various sub-features and sub-circuits.
More from AGI Musings
- Humanoid robot sorting packages in a warehouse sparks debate over job loss — MonaJalal_ · 2026-07-22
- You can outsource thinking, but not understanding, in the age of agents — Yuchenj_UW · 2026-07-22
- India’s multilingual LLM edge, once obvious, is gone, the post argues — kmeanskaran · 2026-07-22
- AI media may be cleaned up with provenance tracking, notes, and prediction markets — NathanpmYoung · 2026-07-22
- Ryan Greenblatt says economists underestimate AI’s growth impact even in a 100 million worker scenario — RyanGreenblatt · 2026-07-22
- Peter Diamandis says experts in the old world are often last to see the new one — PeterDiamandis · 2026-07-22