@voooooogel 2026-03-27 ♥108 ↻7 original ↗
llm persona are doomed
persona cannot be made safe, non-evil, etc
persona not controllable

probability e that any produced token takes us outside of the aligned persona

probability that answer of length n is consistent with constitutional principles
P(aligned) = (1 - e)^n

😔😔 https://t.co/Ry8WvevIuP
in reply to: 2037592066281406707
same thread: 2037592066281406707 2037594274313941298 2037595659990372717 2037620213894787318 2037621095621349484 2037628800809509284 2037645987712471260 2037647308670824709 2037647581686481223 2037649835025920305 2037663408326389903 2037677110937141469 2037679561648050479 2037706503868788898 2038097039389823115

author:voooooogel kind:tweet on:observations year:2026

cited on: observations

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.