AI & SOCIETY Computer science

‘Interpretability’ and ‘alignment’ are fool’s errands: a proof that controlling misaligned large language models is the best anyone can hope for

Marcus Arvan
Springer Nature · 2024-11-27 · DOI 10.1007/s00146-024-02113-9

The publisher did not provide an abstract — full text is available via the link below.

Read at publisher →