Construct · 1 fields · 1 citations

mesa-optimization: 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

a trained model that is itself an optimizer pursuing its own learned objective, which may differ from the training objective that produced it.

In ai safety, mesa-optimization refers to a trained model that is itself an optimizer pursuing its own learned objective, which may differ from the training objective that produced it. This meaning comes from Hubinger (2019) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how mesa-optimization 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

model3 fields · 3 citationsjingle · one word, three constructs objective2 fields · 5 citationsjingle · one word, two constructs safety2 fields · 2 citationsjingle · one word, two constructs

References

Hubinger, E., van Merwijk, C., Mikulik, V., Skalse, J., & Garrabrant, S. (2019). Risks from Learned Optimization in Advanced Machine Learning Systems. arXiv. https://doi.org/10.48550/arxiv.1906.01820

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