0

Alex Tamkin

Papers
4

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
4papers

Authored papers

4

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

arXiv 2024

2024

Eliciting Human Preferences with Language Models

arXiv 2023

2023

Codebook Features: Sparse and Discrete Interpretability for Neural Networks

arXiv 2023

2023

C5T5: Controllable Generation of Organic Molecules with Transformers

c5t5-controllable-generation-of-organic-1

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 4 papers

Belinda Z. Li

1 shared paper

Buck Shlegeris

1 shared paper

Carson Denison

1 shared paper

Daniel Rothchild

1 shared paper

David Duvenaud

1 shared paper

Ethan Perez

1 shared paper

Evan Hubinger

1 shared paper

Fazl Barez

1 shared paper

Jacob Andreas

1 shared paper

Jared Kaplan

co-founder / Chief Science Officer

1 shared paper