Monte MacDiarmid

Cite

Notes

Only stored in your browser.

Attribution

3papers

Authored papers

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

arXiv 2024

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

arXiv 2024

Alignment faking in large language models

arXiv 2024

No known affiliations.

from 3 papers

Buck Shlegeris

Carson Denison

David Duvenaud

Ethan Perez

Evan Hubinger

Jared Kaplan

co-founder / Chief Science Officer

Samuel R. Bowman

Fazl Barez

Nicholas Schiefer

Ryan Greenblatt