Skip to content
Calculating Space

Person

Joseph Y. Halpern

Cited in two posts, AI Alignment with Changing and Influenceable… and Characterizing Manipulation from AI Systems, since September 2026

In their words

  • “Halpern and Kleiman-Weiner (2018) provide a causal operationalization of intent: roughly, an action is intended if (i) it was actually performed, (ii) it was not the only possible action, and (iii) that action was at least as good as any other action on expected utility grounds, according to the agent’s world model and utility function.”

    · Characterizing Manipulation from AI Systems · machine-resolved