Bronson Schoen
Titles as the sources gave them. In 2 entries, with 0 checked quotations.
In the Base
Every entry they appear in.
Monitorability evaluations and policy proposals
On the AI Alignment Forum, evhub sets out four types of monitorability, argues trust in monitors should rest on auditing evaluations, and proposes a methodology for measuring them. The post also backs both binding red lines and ongoing limits on lab changes that reduce monitorability. evhub says these are personal views.
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.