MS
Michael Sellitto
cs.AIcs.CLcs.LGcs.CRcs.CYcs.SE
On Valency
published · living versionsW_3sjke4et·v1 · currentpublished
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
with Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert +34
1 version
Preprints & journals
7 papers in the corpus · 2012–2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training2401.05566v3 · Evan Hubinger, Carson Denison, Jesse Mu et al.2024 · 39 citationsarXivon Valency
Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings2308.00862v2 · Sarah Shoker, Andrew Reddie, Sarah Barrington et al.2023 · 13 citationsarXiv
The Capacity for Moral Self-Correction in Large Language Models2302.07459v2 · Deep Ganguli, Amanda Askell, Nicholas Schiefer et al.2023 · 53 citationsarXiv
Discovering Language Model Behaviors with Model-Written Evaluations2212.09251v1 · Ethan Perez, Sam Ringer, Kamil\.e Lukosi\=ut\.e et al.2022 · 224 citationsarXivon Valency
Constitutional AI: Harmlessness from AI Feedback2212.08073v1 · Yuntao Bai, Saurav Kadavath, Sandipan Kundu et al.2022 · 322 citationsarXivon Valency
The AI Index 2022 Annual Report2205.03468v1 · Daniel Zhang, Nestor Maslej, Erik Brynjolfsson et al.2022 · 18 citationsarXiv
Bruton tyrosine kinase inhibition is a novel therapeutic strategy targeting tumor in the bone marrow microenvironment in multiple myeloma.22689860 · Tai, Yu-Tzu, Chang, Betty Y, Kong, Sun-Young et al.2012 · 165 citationsBlood. 2012;120(9):1877-87
Career total: 12 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.