AI brief
A LessWrong post presents a short empirical evaluation of task vectors, unlearning and inoculation, following a previous post that introduced similarities between unlearning and inoculation and a distinction between learned and human-written adapters.
Written by AI from LessWrong's published text.
Source
“TL; DR In the previous post I introduced some ideas and similarities between unlearning and inoculation, as well as a distinction between learned and human-written adapters. This post serves as a short empirical evaluation.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗