RSS

David Lindner

Karma: 452

Alignment researcher at Google DeepMind

MONA: Three Month Later—Up­dates and Steganog­ra­phy Without Op­ti­miza­tion Pressure

David Lindner and Vikrant Varma
Apr 12, 2025, 11:15 PM
31 points
0 comments5 min readLW link

Can LLMs learn Stegano­graphic Rea­son­ing via RL?

robert mccarthy, Vasil Georgiev, Steven Basart and David Lindner
Apr 11, 2025, 4:33 PM
20 points
2 comments6 min readLW link

MONA: Man­aged My­opia with Ap­proval Feedback

Seb Farquhar, David Lindner and Rohin Shah
Jan 23, 2025, 12:24 PM
80 points
29 comments9 min readLW link

On scal­able over­sight with weak LLMs judg­ing strong LLMs

zac_kenton, Noah Siegel, janos, Jonah Brown-Cohen, Samuel Albanie, David Lindner and Rohin Shah
Jul 8, 2024, 8:59 AM
49 points
18 comments7 min readLW link
(arxiv.org)

VLM-RM: Spec­i­fy­ing Re­wards with Nat­u­ral Language

ChengCheng, David Lindner and Ethan Perez
Oct 23, 2023, 2:11 PM
20 points
2 comments5 min readLW link
(far.ai)

Prac­ti­cal Pit­falls of Causal Scrubbing

Jérémy Scheurer, Phil3, tony, jacquesthibs and David Lindner
Mar 27, 2023, 7:47 AM
87 points
17 comments13 min readLW link

Threat Model Liter­a­ture Review

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt
Nov 1, 2022, 11:03 AM
78 points
4 comments25 min readLW link

Clar­ify­ing AI X-risk

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt
Nov 1, 2022, 11:03 AM
127 points
24 comments4 min readLW link1 review