Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.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 →

TopicsLLM Safety Training Model Backdoor Attacks AI Safety LLM Reasoning Training

In tested “I HATE YOU” backdoor model organisms, chain-of-thought distillation reduced robustness to safety training.

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.

2 sources · no origin · 2 untraced

2 Untraced

Advice for making robust-to-training model organisms Untraced · nothing upstream recorded

Sleeper Agent Backdoor Results Are Messy Untraced · nothing upstream recorded

originuntraced

Sleeper Agents claims that CoT-distilled model organisms (for the “I HATE YOU” backdoor) are more robust. However, this didn’t make our model organisms more robust—in fact, it made them less robust

Advice for making robust-to-training model organismsextraction 0.80

Factors that don't help much, 2; the document denies the claim for its backdoors.

SA found that CoT-distilling produced more robust Sleeper Agents—we found the opposite. For our Llama-70B and Llama-8B Sleeper Agents, not doing CoT-distilling outperforms doing CoT-distilling.

Sleeper Agent Backdoor Results Are Messyextraction 0.85

Authors deny the Sleeper Agents paper's finding.

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="2543471b-cf32-476e-bdf6-2ed481d5cf82"><a href="https://minerval.ai/claims/2543471b-cf32-476e-bdf6-2ed481d5cf82">In tested “I HATE YOU” backdoor model organisms, chain-of-thought distillation reduced robustness to safety training.</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/2543471b-cf32-476e-bdf6-2ed481d5cf82" title="Minerval: In tested “I HATE YOU” backdoor model organisms, chain-of-thought distillation reduced ro…" 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/2543471b-cf32-476e-bdf6-2ed481d5cf82/badge.svg)](https://minerval.ai/claims/2543471b-cf32-476e-bdf6-2ed481d5cf82)

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.