LESSWRONGTags
LW

SERI MATS

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Contributors

The Stanford Existential Risks Initiative ML Alignment Theory Scholars program.

https://www.serimats.org/

Posts tagged SERI MATS

8

72SERI MATS Program - Winter 2022 Cohort

Ryan Kidd, Victor Warlop, Christian Smith

1y

12

7

657SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow, mwatkins

8mo

203

7

308Understanding and controlling a maze-solving policy network

TurnTrout, peligrietzer, Ulisse Mini, Monte M, David Udell

7mo

22

6

21Project proposal: Testing the IBP definition of agent

Jeremy Gillen, Thomas Larsen, JamesH

1y

4

5

114Soft optimization makes the value target bigger

9mo

20

5

71SERI MATS - Summer 2023 Cohort

Aris, Ryan Kidd, Christian Smith

6mo

25

5

60How MATS addresses “mass movement building” concerns

5mo

9

5

60SERI ML Alignment Theory Scholars Program 2022

Ryan Kidd, Victor Warlop, ozhang

1y

6

4

175Finite Factored Sets in Pictures

Magdalena Wache

9mo

35

4

119Taking the parameters which seem to matter and rotating them until they don't

1y

48

3

104Predictions for shard theory mechanistic interpretability results

TurnTrout, Ulisse Mini, peligrietzer

7mo

9

3

74Neural Tangent Kernel Distillation

Thomas Larsen, Jeremy Gillen

1y

20

3

26Normative vs Descriptive Models of Agency

8mo

5

2

82Qualities that alignment mentors value in junior researchers

8mo

13

2

56Conditioning Generative Models for Alignment

1y

8