AI Control: Improving Safety Despite Intentional Subversion

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger

Cite this paper

Credit the original research and its authors.

BibTeX

@misc{greenblatt-2024-ai-control-improving,
  author = {Ryan Greenblatt and Buck Shlegeris and Kshitij Sachan and Fabien Roger},
  title = {{AI Control: Improving Safety Despite Intentional Subversion}},
  year = {2024},
  note = {ICML 2024},
  url = {https://arxiv.org/abs/2312.06942}
}