AI ALIGNMENT FORUM
AF

DeepMind

Edited by Ruby, sanxiyn, Bird Concept, et al. last updated 14th Nov 2022

DeepMind is an AI research laboratory that was founded in 2010 and acquired by Google in 2014. It is known for several record-breaking AI algorithms, often named with the prefix "Alpha", e.g. AlphaGo, AlphaZero, AlphaStar, AlphaFold, AlphaCode, and AlphaTensor.

Posts tagged DeepMind

31Paper: Discovering novel algorithms with AlphaTensor [Deepmind]

3y

11

76DeepMind: Generally capable agents emerge from open-ended play

Daniel Kokotajlo

4y

11

11AlphaGo Zero and capability amplification

paulfchristiano

7y

16

97AGI Safety and Alignment at Google DeepMind: A Summary of Recent Work

Rohin Shah, Seb Farquhar, Anca Dragan

1y

17

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

Vika, Rohin Shah

2y

11

15A comment on the IDA-AlphaGoZero metaphor; capabilities versus alignment

7y

0

78A challenge for AGI organizations, and a challenge for readers

Rob Bensinger, Eliezer Yudkowsky

3y

17

45Clarifying AI X-risk

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar, Elliot Catt

3y

16

111DeepMind alignment team opinions on AGI ruin arguments

3y

11

402018 AI Alignment Literature Review and Charity Comparison

7y

4

44Caution when interpreting Deepmind's In-context RL paper

3y

3

52AGI Safety & Alignment @ Google DeepMind is hiring

6mo

1

27Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind

3y

9

26The GDM AGI Safety+Alignment Team is Hiring for Applied Interpretability Research

Arthur Conmy, Neel Nanda

6mo

0

18How do new models from OpenAI, DeepMind and Anthropic perform on TruthfulQA?

4y

1

Load More (15/29)

Add Posts