AI ALIGNMENT FORUMTags
AF

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

4

32SERI MATS Program - Winter 2022 Cohort

Ryan Kidd, Victor Warlop, Christian Smith

1y

0

3

145SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow, mwatkins

8mo

16

5

129Understanding and controlling a maze-solving policy network

Alex Turner, peligrietzer, Ulisse Mini, Monte MacDiarmid, David Udell

7mo

18

3

42Soft optimization makes the value target bigger

9mo

4

3

25SERI ML Alignment Theory Scholars Program 2022

Ryan Kidd, Victor Warlop, ozhang

1y

0

2

49Finite Factored Sets in Pictures

Magdalena Wache

9mo

2

3

47Predictions for shard theory mechanistic interpretability results

Alex Turner, Ulisse Mini, peligrietzer

7mo

6

2

14Normative vs Descriptive Models of Agency

Matt MacDermott

8mo

2

2

24Conditioning Generative Models for Alignment

1y

8

1

31More findings on Memorization and double descent

Marius Hobbhahn

8mo

2

1

12Race Along Rashomon Ridge

Stephen Fowler, Peter S. Park, MichaelEinhorn

1y

0

2

20Behavioural statistics for a maze-solving agent

peligrietzer, Alex Turner

5mo

10

1

20Clarifying mesa-optimization

Marius Hobbhahn, Pierre Peigné

6mo

1

1

18Auditing games for high-level interpretability

1y

0

1

18More findings on maximal data dimension

Marius Hobbhahn

8mo

0