specific method · filed under evaluation
Refusal-suppressed variants for capability estimation
Evaluating variants with safeguards removed to estimate latent model capability.
Also called refusal-suppressed variants.
- sources
- 3
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 3
Documented in
Evidence
3 spans quoted from the sources, strongest treatment first.
refusal-suppressed variants intended to estimate latent capability with safeguards removed
usedevaluation onlyin InklingThinking Machines Lab
refusal-suppressed variants intended to estimate latent capability with safeguards removed
usedevaluation onlyin InklingThinking Machines Lab
refusal-suppressed variants intended to estimate latent capability with safeguards removed
usedevaluation onlyin InklingThinking Machines Lab
Filed alongside
Other methods under evaluation.
Prompt-based output standardizationEvaluation without safety filtersavg@kAlmost@1Behavior testing with stubs and edge casesDeadline-bounded rollout evaluationDiverse benchmark validation for quantizationDocumenting evaluation configurationEnd-to-end exploit development evaluationEvaluation equivalence thresholdFixed MTP draft-token acceptance lengthFour-run mean pass@1Full trajectory releaseJoint validation protocolMean@5Model–harness co-designOfficial-release-source baseline restrictionPrompt engineering to elicit answersProtocolQA robustness validationRefusal behavior quantificationRollout-based auditingSample test and length-constraint filteringSandboxed GPU kernel optimization evaluationSingle-agent and multi-agent evaluation configurations