Marcus Arvan. ‘Interpretability’ and ‘alignment’ are fool’s errands: a proof that controlling misaligned large language models is the best anyone can hope for. // AI & SOCIETY. – 2024. – DOI: 10.1007/s00146-024-02113-9. – URL: https://doi.org/10.1007/s00146-024-02113-9
Marcus Arvan (2024). ‘Interpretability’ and ‘alignment’ are fool’s errands: a proof that controlling misaligned large language models is the best anyone can hope for. AI & SOCIETY. https://doi.org/10.1007/s00146-024-02113-9
Marcus Arvan. “‘Interpretability’ and ‘alignment’ are fool’s errands: a proof that controlling misaligned large language models is the best anyone can hope for.” AI & SOCIETY, 2024. doi:10.1007/s00146-024-02113-9.
@article{Arvan2024,
title = {‘Interpretability’ and ‘alignment’ are fool’s errands: a proof that controlling misaligned large language models is the best anyone can hope for},
author = {Arvan, Marcus},
journal = {AI \& SOCIETY},
year = {2024},
doi = {10.1007/s00146-024-02113-9},
url = {https://doi.org/10.1007/s00146-024-02113-9}
}