Construct · 1 fields · 1 citations

AI safety via debate: 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

two agents argue opposite sides before a human judge, on the premise that truthful arguments are easier to defend than deceptive ones.

In AI safety, AI safety via debate refers to two agents argue opposite sides before a human judge, on the premise that truthful arguments are easier to defend than deceptive ones. This meaning comes from Irving (2018) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how AI safety via debate 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

safety2 fields · 2 citationsjingle · one word, two constructs

References

Irving, G., Christiano, P., & Amodei, D. (2018). AI safety via debate. arXiv. https://doi.org/10.48550/arxiv.1805.00899

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