Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Logan Graham
Observed name:
Graham, Logan
Institution:
Anthropic (United States)
Observed institutions:
University of Oxford,
Open Philanthropy Project,
Anthropic (United States)
OpenAlex ID:
A5041121552
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
2020
·
Brundage, Miles
, Avin, Shahar
, et al.
·
arXiv (Cornell University)
·
306
PDF
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
2024
·
Hubinger, Evan
, Denison, Carson
, et al.
·
arXiv (Cornell University)
·
46
PDF
Inferring Work Task Automatability from AI Expert Evidence
2019
·
Paul Duckworth
, Logan Graham
, et al.
·
Proceedings of the AAAI/ACM Conference on AI Ethics and Society
·
18
MultiVerse: Causal Reasoning using Importance Sampling in Probabilistic Programming
2019
·
Perov, Yura
, Graham, Logan
, et al.
·
arXiv (Cornell University)
·
13
PDF
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
2025
·
Sharma, Mrinank
, Tong, Meg
, et al.
·
arXiv (Cornell University)
·
7
PDF
Interpretable causal systems: interpretability and causality in machine learning for human and nonhuman decision-making
2020
·
Graham, Logan
·
Oxford University Research Archive (ORA) (University of Oxford)
Show more works
View as search
Works count:
6
Citation count:
390
H-index:
5
I10-index:
4
Year
Topic
Type
