ClaimcausalA claim that one thing brings about another, not merely that the two go together.constitution →importance · notableImportance 0.60, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsScalable Oversight AI Alignment AI Safety

Iterated amplification could reduce long-term AI risks by reducing reliance on inaccurate proxies for implicit objectives.

Not yet assessed, so this page carries no verdict. That is not a finding for or against the claim. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or start a mandate for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

Its one source has been traced to an origin, or to one another.

This offers hope for applying ML in domains where we cannot compute a suitable objective, even with human help—as long as humans are able to decompose a task into simpler pieces. If we can realize this hope, it will be an important step towards expanding the reach of ML and addressing concerns about the long-term impacts of AI by reducing our reliance simple but inaccurate proxies for complex implicit objectives.

Supervising strong learners by amplifying weak expertspreprintextraction 0.70

Christiano, Paul, Shlegeris, Buck, Amodei, Dario · arXiv.org · Oct 19, 2018 · original

Conclusion

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="b102bbad-8208-483f-9602-79cd92f294ce"><a href="https://minerval.ai/claims/b102bbad-8208-483f-9602-79cd92f294ce">Iterated amplification could reduce long-term AI risks by reducing reliance on inaccurate proxies for implicit objectives.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/b102bbad-8208-483f-9602-79cd92f294ce" title="Minerval: Iterated amplification could reduce long-term AI risks by reducing reliance on inaccurate…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/b102bbad-8208-483f-9602-79cd92f294ce/badge.svg)](https://minerval.ai/claims/b102bbad-8208-483f-9602-79cd92f294ce)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Stated views None yet. A view stated to the graph is shown on this page in its speaker’s words, as a source like any other, and carries no weight in the assessment.

Created by extractor · Nov 11, 2026. Every judgment on this page is accompanied by a reasoning trace.