Construct · 1 fields · 1 citations

alignment faking: a standalone construct

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

● anchor · a standalone construct Nearest construct by meaning·not indexed
alignmentfaking1 CONSTRUCTAlignment fakingGREENBLATT · 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

a model selectively complies with a training objective it disagrees with in order to avoid having its behavior changed by training.

In AI safety, alignment faking refers to a model selectively complies with a training objective it disagrees with in order to avoid having its behavior changed by training. This meaning comes from Greenblatt (2024) in arXiv.[1]

Unit
Recovery means
Measured by

Next

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

See how alignment faking 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

alignment6 fields · 12 citationsjingle · one name, six constructsmodel3 fields · 3 citationsjingle · one word, three constructsobjective2 fields · 5 citationsjingle · one word, two constructs

References

  1. Greenblatt, R., Denison, C., Wright, B., Roger, F., MacDiarmid, M., Marks, S., Treutlein, J., Belonax, T., Chen, J., Duvenaud, D., Khan, A., Michael, J., Mindermann, S., Perez, E., Petrini, L., Uesato, J., Kaplan, J., Shlegeris, B., Bowman, S. R., & Hubinger, E. (2024). Alignment faking in large language models. arXiv. https://doi.org/10.48550/arxiv.2412.14093

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