User Profile

1741Ω5240100

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

Vika's Posts

sorted by new
All Posts
Frontpage
Curated
Questions
Events
Meta

[Link] New safety research agenda: scalable agent alignment via reward modeling

332mo1 min readΩ 9Show Highlight
12

Discussion on the machine learning approach to AI safety

263mo3 min readΩ 9Show Highlight
3

[Link] New DeepMind AI Safety Research Blog

464mo1 min readΩ 13Show Highlight
0

Specification gaming examples in AI

749mo1 min readShow Highlight
3

Strategic choice of identity

815y2 min readShow Highlight
58

Open and closed mental states

214y1 min readShow Highlight
7

Ritual Report: Boston Solstice Celebration

105y2 min readShow Highlight
19

Meetup : Boston Winter Solstice

45y1 min readShow Highlight
0

Meetup : Boston - Schelling Day

35y1 min readShow Highlight
6

Meetup : Boston: In Defence of the Cathedral

25y1 min readShow Highlight
0

Vika's Comments