RSS

Mar­ket mak­ing (AI safety tech­nique)

TagLast edit: 4 May 2022 20:10 UTC by Evan R. Murphy

AI safety via mar­ket making

evhub26 Jun 2020 23:07 UTC
77 points
45 comments1 min readLW link

[Preprint] Verok V6: A Struc­tural “Chas­sis” Ar­chi­tec­ture for Non-Agen­tic AI Governance

Nguyễn Thành Nam28 Dec 2025 5:18 UTC
1 point
0 comments1 min readLW link
(doi.org)

Learn­ing the smooth prior

Geoffrey Irving, Rohin Shah and evhub
29 Apr 2022 21:10 UTC
35 points
0 comments12 min readLW link

In­ter­pretabil­ity’s Align­ment-Solv­ing Po­ten­tial: Anal­y­sis of 7 Scenarios

Evan R. Murphy12 May 2022 20:01 UTC
58 points
0 comments59 min readLW link
No comments.