Person
Charles Evans
Cited in one post, Characterizing Manipulation from AI Systems, since September 2026
In their words
“As an example of an application of CIDs, Evans and Kasirzadeh (2021) apply their framework to a simple content recommendation example to show that RL recommenders will have incentives to influence user preferences (Figure 1).”
· Characterizing Manipulation from AI Systems · machine-resolved
In the claim ledger
2 promoted claims about them. Assessments are the model’s knowledge, not verification.
Causal influence diagram analysis shows RL recommenders are incentivised to shift user preferences.
consistent · Characterizing Manipulation from AI Systems
Having an incentive is not the same as pursuing it.
consistent · Characterizing Manipulation from AI Systems