Cites: Power-seeking can be probable and predictive for trained agents
3 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.
- Optimal Policies Tend to Seek Power
arxiv:1912.01683· evidence: id - Is Power-Seeking AI an Existential Risk?
arxiv:2206.13353· evidence: id - Parametrically Retargetable Decision-Makers Tend To Seek Power
arxiv:2206.13477· evidence: id