Construct · 1 fields · 1 citations

constitutional AI: a standalone construct

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

● anchor · a standalone construct Nearest construct by meaning·not indexed
constitutionalAI1 CONSTRUCTConstitutional AIBAI · AI SAFETY

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

AI safety

training a harmless assistant using a written list of principles, with AI-generated critiques and preference labels replacing human labels for harmfulness.

In ai safety, constitutional AI refers to training a harmless assistant using a written list of principles, with AI-generated critiques and preference labels replacing human labels for harmfulness. This meaning comes from Bai (2022) in arXiv.[1]

Unit
Recovery means
Measured by

Next

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

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

Open in ColliderExport BibTeXReport this entry

Nearby constructs

list1 fields · 1 citationsanchor · a standalone constructpreference4 fields · 7 citationsjingle · one word, four constructssafety2 fields · 2 citationsjingle · one word, two constructs

References

  1. Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., Chen, C., Olsson, C., Olah, C., Hernandez, D., Drain, D., Ganguli, D., Li, D., Tran-Johnson, E., Perez, E., Kerr, J., Mueller, J., Ladish, J., Landau, J., Ndousse, K., Lukosuite, K., Lovitt, L., Sellitto, M., Elhage, N., Schiefer, N., Mercado, N., DasSarma, N., Lasenby, R., Larson, R., Ringer, S., Johnston, S., Kravec, S., Showk, S. E., Fort, S., Lanham, T., Telleen-Lawton, T., Conerly, T., Henighan, T., Hume, T., Bowman, S. R., Hatfield-Dodds, Z., Mann, B., Amodei, D., Joseph, N., McCandlish, S., Brown, T., & Kaplan, J. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv. https://doi.org/10.48550/arxiv.2212.08073

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