Modeling evidential cooperation in large worlds von Treutlein, Johannes

Volltext bestellen

Modeling evidential cooperation in large worlds von Treutlein, Johannes

Volltext

Incentivizing honest performative predictions with proper scoring rules von Oesterheld, Caspar, Treutlein, Johannes, Cooper, Emery, Hudson, Rubi

Volltext bestellen

Conditioning Predictive Models: Risks and Strategies von Hubinger, Evan, Jermyn, Adam, Treutlein, Johannes, Hudson, Rubi, Woolverton, Kate

Volltext bestellen

Similarity-based cooperative equilibrium von Oesterheld, Caspar, Treutlein, Johannes, Grosse, Roger, Conitzer, Vincent, Foerster, Jakob

Volltext bestellen

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data von Treutlein, Johannes, Choi, Dami, Betley, Jan, Marks, Samuel, Anil, Cem, Grosse, Roger, Evans, Owain

Volltext bestellen

COLA: Consistent Learning with Opponent-Learning Awareness von Willi, Timon, Letcher, Alistair, Treutlein, Johannes, Foerster, Jakob

Volltext bestellen

A New Formalism, Method and Open Issues for Zero-Shot Coordination von Treutlein, Johannes, Dennis, Michael, Oesterheld, Caspar, Foerster, Jakob

Volltext bestellen

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation von Anil, Cem, Pokle, Ashwini, Liang, Kaiqu, Treutlein, Johannes, Wu, Yuhuai, Bai, Shaojie, Kolter, Zico, Grosse, Roger

Volltext bestellen

Alignment faking in large language models von Greenblatt, Ryan, Denison, Carson, Wright, Benjamin, Roger, Fabien, MacDiarmid, Monte, Marks, Sam, Treutlein, Johannes, Belonax, Tim, Chen, Jack, Duvenaud, David, Khan, Akbir, Michael, Julian, Mindermann, Sören, Perez, Ethan, Petrini, Linda, Uesato, Jonathan, Kaplan, Jared, Shlegeris, Buck, Bowman, Samuel R, Hubinger, Evan

Volltext bestellen

Normative Disagreement as a Challenge for Cooperative AI von Stastny, Julian, Riché, Maxime, Lyzhov, Alexander, Treutlein, Johannes, Dafoe, Allan, Clifton, Jesse

Volltext bestellen

Similarity-based cooperative equilibrium von Oesterheld, Caspar, Treutlein, Johannes, Grosse, Roger, Conitzer, Vincent, Foerster, Jakob

Volltext

A New Formalism, Method and Open Issues for Zero-Shot Coordination von Treutlein, Johannes, Dennis, Michael, Oesterheld, Caspar, Foerster, Jakob

Volltext

Incentivizing honest performative predictions with proper scoring rules von Oesterheld, Caspar, Treutlein, Johannes, Cooper, Emery, Hudson, Rubi

Volltext

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data von Treutlein, Johannes, Choi, Dami, Betley, Jan, Marks, Samuel, Anil, Cem, Grosse, Roger, Evans, Owain

Volltext

Conditioning Predictive Models: Risks and Strategies von Hubinger, Evan, Jermyn, Adam, Treutlein, Johannes, Hudson, Rubi, Woolverton, Kate

Volltext

COLA: Consistent Learning with Opponent-Learning Awareness von Willi, Timon, Letcher, Alistair, Treutlein, Johannes, Foerster, Jakob

Volltext

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation von Anil, Cem, Pokle, Ashwini, Liang, Kaiqu, Treutlein, Johannes, Wu, Yuhuai, Bai, Shaojie, Kolter, Zico, Grosse, Roger

Volltext

Alignment faking in large language models von Greenblatt, Ryan, Denison, Carson, Wright, Benjamin, Fabien, Roger, MacDiarmid, Monte, Marks, Sam, Treutlein, Johannes, Belonax, Tim, Chen, Jack, Duvenaud, David, Khan, Akbir, Julian, Michael, Mindermann, Sören, Perez, Ethan, Petrini, Linda, Uesato, Jonathan, Kaplan, Jared, Buck Shlegeris, Bowman, Samuel R, Hubinger, Evan

Volltext

Normative Disagreement as a Challenge for Cooperative AI von Stastny, Julian, Riché, Maxime, Lyzhov, Alexander, Treutlein, Johannes, Dafoe, Allan, Clifton, Jesse

Volltext