Person
Jan Leike
Cited in thirteen posts, among them AI Alignment with Changing and Influenceable… and Existential Risk from Power-Seeking AI, since September 2026
Where they come up
Said by someone else — these sentences name them.
“Thanks to Daniel Ziegler for his feedback and help on this project, to Buck Shlegeris for sharing his ideas on unmonitored deployments and ways to avoid them, and to Jan Leike and Sam Bowman for their feedback on the draft of this post.”
· · machine-resolved
“See Christian (2020) and Krueger, Maharaj, and Leike (2020) for some discussion of this possibility.)”
· Existential Risk from Power-Seeking AI · machine-resolved
In the claim ledger
1 promoted claim about them. Assessments are the model’s knowledge, not verification.
Claim 2: under state expressivity, shared dynamics and coverage assumptions, standard reward modelling implicitly optimizes a DR-MDP objective indexed by some cognitive state.
plausible · AI Alignment with Changing and Influenceable Reward Functions