Follow
Johannes Treutlein
Johannes Treutlein
Anthropic
Verified email at anthropic.com - Homepage
Title
Cited by
Cited by
Year
COLA: Consistent Learning with Opponent-Learning Awareness
T Willi*, A Letcher*, J Treutlein*, J Foerster
International Conference on Machine Learning, 2022
462022
A New Formalism, Method and Open Issues for Zero-Shot Coordination
J Treutlein, M Dennis, C Oesterheld, J Foerster
International Conference on Machine Learning, 2021
332021
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation
C Anil*, A Pokle*, K Liang*, J Treutlein, Y Wu, S Bai, Z Kolter, R Grosse
Advances in Neural Information Processing Systems, 2022
142022
The Evidentialist's Wager
W MacAskill, A Vallinder, C Oesterheld, C Shulman, J Treutlein
The Journal of Philosophy 118 (6), 320-342, 2021
11*2021
Normative Disagreement as a Challenge for Cooperative AI
J Stastny, M Riché, A Lyzhov, J Treutlein, A Dafoe, J Clifton
arXiv preprint arXiv:2111.13872, 2021
92021
Similarity-based cooperative equilibrium
C Oesterheld, J Treutlein, R Grosse, V Conitzer, J Foerster
Advances in Neural Information Processing Systems, 2023
8*2023
Conditioning Predictive Models: Risks and Strategies
E Hubinger, A Jermyn, J Treutlein, R Hudson, K Woolverton
arXiv preprint arXiv:2302.00805, 2023
32023
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
J Treutlein, D Choi, J Betley, C Anil, S Marks, RB Grosse, O Evans
arXiv preprint arXiv:2406.14546, 2024
22024
Modeling evidential cooperation in large worlds
J Treutlein
arXiv preprint arXiv:2307.04879, 2023
2*2023
Incentivizing honest performative predictions with proper scoring rules
C Oesterheld*, J Treutlein*, E Cooper, R Hudson
Conference on Uncertainty in Artificial Intelligence, 2023
22023
The system can't perform the operation now. Try again later.
Articles 1–10