argumentA line of reasoning from premises to a conclusion. Like a claim, it belongs to no one who makes it.constitution →

The argument from the imitation-trained sandbagger

forThis argument, if it holds, bears in favour of the claim.constitution →Output-only monitoring reliably detects deliberate language-model underperformance only when intent is verbalized or rephrased responses conflict.

The argument

A capable model trained to reproduce a weaker model's outputs gives answers, errors and transcripts that match an honestly weak model's, so imitation can defeat detection that judges a model by its outputs, and detectors validated on prompted or simply locked sandbaggers lose reliability against such models. What remains for an evaluator without weight or training access is whatever the sandbagger gives away about itself. The giveaways with published detectors are intent stated in readable reasoning and answers that vary across rephrasings of one question. Output-only monitoring is therefore reliable only where one of those two is present.

Does it work?

Does it follow?: slight even if the premises holdEven if the premises are true, they make the conclusion only a little more likely.constitution →
Do the premises hold?: 2 supported

Granting its premises, the argument establishes a limit: output-only detection fails where the sandbagger leaves no trace. It does not establish that stated intent and paraphrase inconsistency are the only traces, which is the step the conclusion needs. The move from "these two have published detectors" to "only these two" overlooks other artifacts that have been detected, such as implausible error patterns in actions. Nor does it show that detection is reliable when either signal is present. The limit itself is well grounded: imitation defeating output-based detection is supported by the one blinded test and a matched-accuracy follow-up, while the loss of reliability against imitation-trained models has not yet been assessed on its own.

Premises

SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →Capability imitation can defeat accuracy-based black-box detection of sandbagging.
SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →Sandbagging detectors are less reliable against models fine-tuned to imitate a weaker model's outputs than against prompted or prompt-distilled sandbaggers.

Where it is made

Passages where sources make, criticize or mention this argument. They record where it appears, not how strong it is, and none has precedence over another.

No source is recorded as making it.