Person
Sebastian Farquhar
Cited in two posts, AI Alignment with Changing and Influenceable… and Characterizing Manipulation from AI Systems, since September 2026
In their words
“Similarly, Farquhar et al. (2022) allow for specifying the “natural distribution” of the delicate state – which is formed by the components of the state of the human that one does not want the agent to have incentives to change (e.g.”
· Characterizing Manipulation from AI Systems · machine-resolved
In the claim ledger
3 promoted claims about them. Assessments are the model’s knowledge, not verification.
A person's initial state is a bad counterfactual baseline because natural change is normal and often good.
consistent · Characterizing Manipulation from AI Systems
Deciding which influences count as harmful is an irreducibly political judgement.
consistent · Characterizing Manipulation from AI Systems
The stability property that would make accidental side effects innocuous fails in many real-world domains.
consistent · AI Alignment with Changing and Influenceable Reward Functions