Karma: 2,893

Victoria Krakovna. Research scientist at DeepMind working on AI safety, and cofounder of the Future of Life Institute. Website and blog:

When dis­cussing AI risks, talk about ca­pa­bil­ities, not intelligence

Vika11 Aug 2023 13:38 UTC
116 points
7 comments3 min readLW link

[Linkpost] Some high-level thoughts on the Deep­Mind al­ign­ment team’s strategy

7 Mar 2023 11:55 UTC
125 points
12 comments5 min readLW link

Power-seek­ing can be prob­a­ble and pre­dic­tive for trained agents

28 Feb 2023 21:10 UTC
54 points
22 comments9 min readLW link