Minerval

← the claim it bears on

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

The argument from degradation with the capability gap

This argument, if it holds, weighs against the claim.constitution →Scalable oversight protocols remain effective against AI systems that deliberately deceive their overseers.

The argument

Scalable oversight is meant for systems more capable than their overseers. In adversarial tests, oversight success falls as the capability gap grows, and a weaker monitor catches less of an agent's hidden misbehaviour as the agent's advantage grows. A deliberate deceiver is the adversary those tests model. Oversight therefore loses effectiveness against deceivers in the regime it is designed for.

Does it work?

Does it follow?
If the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
Do the premises hold?
2 supported

Granting the premises, loss of effectiveness against deceivers at large gaps is much more likely, since the games showing the decline pit the overseer against a player trying to defeat it. It is not guaranteed: the decline was measured in a few settings with current models, and peer prediction and some debate results show the opposite trend. Both premises now stand as supported: decline with the capability gap as a default tendency, and weaker monitors catching less hidden misbehaviour as the agent's advantage grows. The argument turns on whether the decline is the rule or a property of the methods tested.

Premises

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.

  • Scaling Laws For Scalable Oversightmakes itThe passage states the inference with what it needs.constitution →
    our framework models oversight as a game between capability-mismatched players [...] we find that NSO success rates at a general Elo gap of 400 are 13.5% for Mafia, 51.7% for Debate, 10.0% for Backdoor Code, and 9.4% for Wargames; these rates decline further when overseeing stronger systems.

    Joshua Engels, David D. Baek, Subhash Kantamneni, Max Tegmark · 2025-04-25

Earlier ratings

  • Nov 11, 2026If the premises are true, the conclusion is much more likely, though not guaranteed.constitution →

    Granting the premises, loss of effectiveness against deceivers at large gaps is much more likely, since the adversarial games that show the decline are tests against a player trying to defeat the overseer. It is not guaranteed: the decline was measured in a few games with current models, debate depended mainly on the judge's strength, and peer prediction and lie-detector oversight showed the opposite trend. Decline with the capability gap stands as supported as a default tendency; the narrower premise about weaker monitors and hidden misbehaviour has not yet been assessed. The argument carries real weight and turns on whether the measured decline is the rule or a property of the methods tested.

The argument from degradation with the capability gap · Minerval