Erik Jenner

Karma: 2,043

Research Scientist on the Google DeepMind AGI Safety & Alignment team

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

Erik JennerJun 4, 2024, 3:50 PM

121 points

14 comments13 min readLW link

Concrete empirical research projects in mechanistic anomaly detection

Erik Jenner, Viktor Rehnberg and Oliver Daniels

Apr 3, 2024, 11:07 PM

43 points

3 comments10 min readLW link

A gentle introduction to mechanistic anomaly detection

Erik JennerApr 3, 2024, 11:06 PM

73 points

2 comments11 min readLW link

CHAI internship applications are open (due Nov 13)

Erik JennerOct 26, 2023, 12:53 AM

34 points

0 comments3 min readLW link

A comparison of causal scrubbing, causal abstractions, and related methods

Erik Jenner, Adrià Garriga-alonso and Egor Zverev

Jun 8, 2023, 11:40 PM

73 points

3 comments22 min readLW link

[Appendix] Natural Abstractions: Key Claims, Theorems, and Critiques

LawrenceC, Erik Jenner and Leon Lang

Mar 16, 2023, 4:38 PM

48 points

0 comments13 min readLW link

Natural Abstractions: Key claims, Theorems, and Critiques

LawrenceC, Leon Lang and Erik Jenner

Mar 16, 2023, 4:37 PM

241 points

23 comments45 min readLW link 3 reviews

Sydney can play chess and kind of keep track of the board state

Erik JennerMar 3, 2023, 9:39 AM

64 points

19 comments6 min readLW link

Research agenda: Formalizing abstractions of computations

Erik JennerFeb 2, 2023, 4:29 AM

93 points

10 comments31 min readLW link

Abstractions as morphisms between (co)algebras

Erik JennerJan 14, 2023, 1:51 AM

17 points

1 comment8 min readLW link

Subsets and quotients in interpretability

Erik JennerDec 2, 2022, 11:13 PM

26 points

1 comment7 min readLW link

ARC paper: Formalizing the presumption of independence

Erik JennerNov 20, 2022, 1:22 AM

97 points

2 comments2 min readLW link

(arxiv.org)

Response to Katja Grace’s AI x-risk counterarguments

Erik Jenner and Johannes Treutlein

Oct 19, 2022, 1:17 AM

77 points

18 comments15 min readLW link

Disentangling inner alignment failures

Erik JennerOct 10, 2022, 6:50 PM

23 points

5 comments4 min readLW link

Good ontologies induce commutative diagrams

Erik JennerOct 9, 2022, 12:06 AM

49 points

5 comments14 min readLW link

How are you dealing with ontology identification?

Erik JennerOct 4, 2022, 11:28 PM

34 points

10 comments3 min readLW link

Breaking down the training/deployment dichotomy

Erik JennerAug 28, 2022, 9:45 PM

30 points

3 comments3 min readLW link

Reward model hacking as a challenge for reward learning

Erik JennerApr 12, 2022, 9:39 AM

25 points

1 comment9 min readLW link

The (not so) paradoxical asymmetry between position and momentum

Erik JennerMar 28, 2021, 1:31 PM

21 points

10 comments4 min readLW link

ejenner’s Shortform

Erik JennerJul 28, 2020, 10:42 AM

2 points

35 comments LW link