15 citations · 27 across the 6 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.AI2022
On Avoiding Power-Seeking by Artificial Intelligence
Alexander Matt Turner
We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether -- absent a full solution to this AI alignment problem -- we can buil…
cs.AI2022★ 8 cited
Parametrically Retargetable Decision-Makers Tend To Seek Power
Alexander Matt Turner, Prasad Tadepalli
If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous…
cs.AI2022
Formalizing the Problem of Side Effect Regularization
Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli
AI objectives are often hard to specify properly. Some approaches tackle this problem by regularizing the AI's side effects: Agents must weigh off "how much of a mess they make" wi…