2 citations · 2 across the 4 of their papers we have counts for
Showing cs.AIShow all
3 papers · 1 filter
cs.AI2025
Corrigibility Transformation: Constructing Goals That Accept Updates
Rubi Hudson
An AI agent will learn a desired goal more effectively if it does not resist the training process, but many partially learned goals incentivize an AI to avoid further goal updates.…
cs.AI2023★ 2 cited
Incentivizing honest performative predictions with proper scoring rules
Caspar Oesterheld, Johannes Treutlein, Emery Cooper +1
Proper scoring rules incentivize experts to accurately report beliefs, assuming predictions cannot influence outcomes. We relax this assumption and investigate incentives when pred…
cs.AI2023
Conditioning Predictive Models: Risks and Strategies
Evan Hubinger, Adam Jermyn, Johannes Treutlein +2
Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Kno…