Person
Andrew Ng
Cited in four posts, among them AI Alignment with Changing and Influenceable… and TASRA: a Taxonomy and Analysis of…, since September 2026
Where they come up
Said by someone else — these sentences name them.
“Meanwhile, Bengio and Ng (2023) together have called for a better articulation of concrete risks from AI, including extinction risk.”
· TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI · machine-resolved
In the claim ledger
1 promoted claim about them. Assessments are the model’s knowledge, not verification.
The paper maps IRL onto the initial-reward objective, conditional on assuming demonstrations are unaffected by cognitive-state change.
plausible · AI Alignment with Changing and Influenceable Reward Functions