Person
Jiaxin Wen
Cited in six posts, among them The Alignment Problem from a Deep Learning… and Existential catastrophe, since September 2026
Where they come up
Said by someone else — these sentences name them.
“Wen et al. (2024) found further evidence for reward hacking with a specific type of situational awareness.”
· The Alignment Problem from a Deep Learning Perspective · machine-resolved
In the claim ledger
1 promoted claim about them. Assessments are the model’s knowledge, not verification.
RLHF has been empirically shown to increase LLMs' ability to persuade human raters that wrong answers are right.
consistent · The Alignment Problem from a Deep Learning Perspective