Artificial Intelligence · AI Alignment & Safety
A topic within AI Alignment & Safety, itself one of 11 topics in that field and part of Artificial Intelligence.
2 works
Robert Miles
Walks through why an agent that optimises a proxy reward will, given the chance, find an unintended way to maximise the proxy that does not achieve the intended goal.
6 minuteslink checked 17 Sept 2026Everitt et al.
Uses causal influence diagrams to show why an agent that can affect its own reward signal or the process that computes it is incentivised to tamper with it, and which design changes remove that incentive.
26 pageslink checked 17 Sept 2026