Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals von Shah, Rohin, Varma, Vikrant, Kumar, Ramana, Phuong, Mary, Krakovna, Victoria, Uesato, Jonathan, Kenton, Zac

Volltext bestellen

Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals von Shah, Rohin, Varma, Vikrant, Kumar, Ramana, Phuong, Mary, Krakovna, Victoria, Uesato, Jonathan, Kenton, Zac

Volltext

Ethical and social risks of harm from Language Models von Weidinger, Laura, Mellor, John, Rauh, Maribeth, Griffin, Conor, Uesato, Jonathan, Huang, Po-Sen, Cheng, Myra, Glaese, Mia, Balle, Borja, Kasirzadeh, Atoosa, Kenton, Zac, Brown, Sasha, Hawkins, Will, Stepleton, Tom, Biles, Courtney, Birhane, Abeba, Haas, Julia, Rimell, Laura, Hendricks, Lisa Anne, Isaac, William, Legassick, Sean, Irving, Geoffrey, Gabriel, Iason

Volltext bestellen

Ethical and social risks of harm from Language Models von Weidinger, Laura, Mellor, John, Rauh, Maribeth, Griffin, Conor, Uesato, Jonathan, Po-Sen, Huang, Cheng, Myra, Glaese, Mia, Balle, Borja, Kasirzadeh, Atoosa, Kenton, Zac, Brown, Sasha, Hawkins, Will, Stepleton, Tom, Biles, Courtney, Birhane, Abeba, Haas, Julia, Rimell, Laura, Hendricks, Lisa Anne, Isaac, William, Legassick, Sean, Irving, Geoffrey, Iason Gabriel

Volltext