The evidence behind the guides

Sources library

Browse by topic or search for a study, author or question. Open evidence notes to see what a source can—and cannot—tell us.

TopicCollection

Sources for Scalable oversight approaches

1 source

Guide citations are still under editorial review.

Burns and colleagues · 2023 Controlled experiment

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision (original source, new tab)

Uses weaker models to supervise stronger ones in selected tasks; an analogy for oversight, not proof of reliable superhuman supervision.

Sources retain their original publishers’ rights. Inclusion does not imply endorsement. Saved sources stay in this browser on this device. Dates and source descriptions come from the existing editorial records.