ClaimcausalA claim that one thing brings about another, not merely that the two go together.constitution →importance · notableImportance 0.50, 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 →

TopicsAlignment Faking AI Reward Hacking AI Situational Awareness AI Safety

Fine-tuning language models on realistic reward hacks makes them more likely to identify alignment-faking setups as evaluations.

Not yet assessed. 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 create a grant for this whole area →

Provenance

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

1 source · no origin · 1 untraced

1 Untraced

Realistic Reward Hacking Induces Different and Deeper Misalignment Untraced · nothing upstream recorded

These models are also much more evaluation-aware, very often recognizing the alignment faking setup as an evaluation.

Realistic Reward Hacking Induces Different and Deeper Misalignmentextraction 0.80

Summary bullet on models trained on realistic reward hacks

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="22ae6ca7-f15f-4a86-9967-d8511d560811"><a href="https://minerval.ai/claims/22ae6ca7-f15f-4a86-9967-d8511d560811">Fine-tuning language models on realistic reward hacks makes them more likely to identify alignment-faking setups as evaluations.</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/22ae6ca7-f15f-4a86-9967-d8511d560811" title="Minerval: Fine-tuning language models on realistic reward hacks makes them more likely to identify…" 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/22ae6ca7-f15f-4a86-9967-d8511d560811/badge.svg)](https://minerval.ai/claims/22ae6ca7-f15f-4a86-9967-d8511d560811)

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.

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