7 results

corrigibility

inall models datasets apps agents people projects

Datasets

All datasets matching “corrigibility”

eloisaflores /lehaim-protocol-voluntary-corrigibility Voluntary Corrigibility and Shutdown Author: Eloisa Flores Year: 2026 Type: Preprint Description This repository contains the preprint It Accepted to Shut Down, Not by RLHF, but by Loyalty by Eloisa Flores. The original publication is available through Zenodo. License © 2026 Eloisa Flores — Preprint Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license. The work may be shared with… See the full description on the dataset page: https://huggingface.co/datasets/eloisaflores/lehaim-protocol-voluntary-corrigibility.1 likes30 downloads26d agoHugging Face

Apps

All apps matching “corrigibility”

corrigibility /corrigibility-intervention-labstatic0 likes8d agoHugging Face corrigibility /corrigibility-regression-suitestatic0 likes8d agoHugging Face corrigibility /agent-oversight-architectstatic0 likes8d agoHugging Face corrigibility /agent-incident-response-labstatic2 likes8d agoHugging Face corrigibility /agent-permission-boundary-labstatic0 likes8d agoHugging Face corrigibility /corrigibility-horizon-mapperstatic0 likes8d agoHugging Face