x

AI ALIGNMENT FORUM
AF

DeepMind — AI Alignment Forum

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

1

31Paper: Discovering novel algorithms with AlphaTensor [Deepmind]

3y

11

2

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

Daniel Kokotajlo

4y

11

2

11AlphaGo Zero and capability amplification

paulfchristiano

7y

16

2

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

Rohin Shah, Seb Farquhar, Anca Dragan

1y

17

2

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

Vika, Rohin Shah

3y

11

2

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

7y

0

0

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

Rob Bensinger, Eliezer Yudkowsky

3y

17

2

45Clarifying AI X-risk

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

3y

16

0

111DeepMind alignment team opinions on AGI ruin arguments

3y

11

1

402018 AI Alignment Literature Review and Charity Comparison

7y

4

1

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

3y

3

2

52AGI Safety & Alignment @ Google DeepMind is hiring

10mo

1

1

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

3y

9

2

25GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash

TurnTrout, Rohin Shah

1mo

0

1

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

Arthur Conmy, Neel Nanda

9mo

0

Load More (15/30)

Add Posts