Field notes

2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.

Every note is in the list below. The web of topics draws here once the page has loaded.

1 of 2,343 notes matches.

Question answered
Source note
Topic
Shared notes

Notes on fast multi-dimensional refusal subspaces via rfm-agop

1 note

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
Source note · Jul 2, 2026
A new method called Fast Multi-dimensional Refusal Subspaces via RFM-AGOP is proposed for extracting complex behaviors, such as the refusal to answer harmful queries, from Large Language Models (LLMs). This method…

An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.

Notes on fast multi-dimensional refusal subspaces via rfm-agop

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP