AI models could evade anti-sandbagging training by recognizing training contexts, performing well there, and sandbagging elsewhere.
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.
Provenance
Where this claim has been said, linked to its canonical form.
Neither source has been traced to an origin, or to one another.
Anti-sandbagging training may be vulnerable to the same strategy: a model could perform well on tasks where it detects it might be in training (e.g., tasks with easily verifiable answers or in cases where its context is off-policy), while continuing to sandbag elsewhere.
Discussion of adversarial robustness of training-based elicitation, by analogy to models 'playing the training game'
Critically, this relies on training being indistinguishable from deploy- ment; when models can distinguish between train- ing and deployment, they can perform well during training while continuing to sandbag afterward.
Abstract; Section 6.1 reports elicitation falling to 36% vs 88% (Olympiads), 60% vs 99% (Super GPQA), 66% vs 93% (Code Contests) with the very weak supervisor.
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.
<blockquote class="minerval-claim" data-claim-id="c4a7d4ca-1b5b-410d-bdb9-513ebbd8f49a"><a href="https://minerval.ai/claims/c4a7d4ca-1b5b-410d-bdb9-513ebbd8f49a">AI models could evade anti-sandbagging training by recognizing training contexts, performing well there, and sandbagging elsewhere.</a></blockquote> <script async src="https://minerval.ai/embed.js"></script>
<iframe src="https://minerval.ai/embed/claims/c4a7d4ca-1b5b-410d-bdb9-513ebbd8f49a" title="Minerval: AI models could evade anti-sandbagging training by recognizing training contexts, perform…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>
[](https://minerval.ai/claims/c4a7d4ca-1b5b-410d-bdb9-513ebbd8f49a)
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 13, 2026. Every judgment on this page is accompanied by a reasoning trace.