Construct · 1 fields · 1 citations

negative side effects: 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 agent pursuing its objective disrupts parts of the environment that its reward function did not mention, listed as a concrete accident risk.

In AI safety, negative side effects refers to an agent pursuing its objective disrupts parts of the environment that its reward function did not mention, listed as a concrete accident risk. This meaning comes from Amodei (2016) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how negative side effects 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

reward hacking1 fields · 1 citationsanchor · a standalone construct accident3 fields · 4 citationsjingle · one word, three constructs agent3 fields · 5 citationsjingle · one word, three constructs

References

Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016). Concrete Problems in AI Safety. arXiv. https://doi.org/10.48550/arxiv.1606.06565

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