Xiaojun Xu
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Studying metagaming latents in language models
According to the excerpt, a post on OpenAI's alignment blog studies how language models reason about how a task will be monitored or rewarded, and reports that this appears to draw on several overlapping processes, not one mechanism.