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

Most Relevant

3

32SERI MATS Program - Winter 2022 Cohort

Ryan Kidd, Victor Warlop, Christian Smith

5mo

0

1

147SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow, mwatkins

1mo

14

3

126Understanding and controlling a maze-solving policy network

Alex Turner, peligrietzer, Ulisse Mini, montemac, David Udell

10d

11

2

12Normative vs Descriptive Models of Agency

Matt MacDermott

2mo

2

2

38Soft optimization makes the value target bigger

3mo

1

2

43Predictions for shard theory mechanistic interpretability results

Alex Turner, Ulisse Mini, peligrietzer

21d

6

2

24Conditioning Generative Models for Alignment

8mo

8

1

31More findings on Memorization and double descent

Marius Hobbhahn

2mo

2

1

12Race Along Rashomon Ridge

Stephen Fowler, Peter S. Park, MichaelEinhorn

8mo

0

1

16Auditing games for high-level interpretability

5mo

0

1

18More findings on maximal data dimension

Marius Hobbhahn

2mo

0

1

9A distillation of Evan Hubinger's training stories (for SERI MATS)

8mo

1

2

10What sorts of systems can be deceptive?

Andrei Alexandru

5mo

0

1

48Finite Factored Sets in Pictures

Magdalena Wache

3mo

2

1

67Natural Abstractions: Key claims, Theorems, and Critiques

Lawrence Chan, Leon Lang, Erik Jenner

5d

5