thinker
active
thinker:rohin-shahRohin Shah
Prior work on goal misgeneralization cited as pathway to misalignment
Authored
0
Introduces
0
Studies
0
Affiliations
0
Cited by
0
More papers — OpenAlex / S2
Other inbound relations (2)
- mentionsAlignment faking in large language models(paper)
- mentionsEvaluating Language Model Character Traits(paper)
Recent mentions (2)
- papers-typedward-2024-evaluating-language.md
- papers-typedgreenblatt-2024-alignment.md