Construct · 1 fields · 1 citations

iterated amplification: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

AI safety

an alignment training approach in which a human aided by copies of the current model solves harder problems, and the model is trained to imitate that combined system.

In AI safety, iterated amplification refers to an alignment training approach in which a human aided by copies of the current model solves harder problems, and the model is trained to imitate that combined system. This meaning comes from Christiano (2018) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how iterated amplification sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

alignment6 fields · 12 citationsjingle · one name, six constructs amplification4 fields · 4 citationsjingle · one word, four constructs current3 fields · 6 citationsjingle · one word, three constructs

References

Christiano, P., Shlegeris, B., & Amodei, D. (2018). Supervising strong learners by amplifying weak experts. arXiv. https://doi.org/10.48550/arxiv.1810.08575

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct