Oversight errors do not compound when successive AI generations oversee moderately more capable successors.

Prior model. The claim is an unconditional generalization about a process that has not been run. For serial processes in general (copying chains, recursive training on a model's own outputs, institutional handoffs), errors accumulate unless there is an explicit restoring mechanism; the base rate favors compounding. The claim would be true if each overseer, or something outside the chain, removes at least as much error as each step adds. So the question turns on (a) the per-step miss rate, (b) whether a missed flaw degrades the next step's oversight, and (c) whether correction mechanisms exist and reach the errors that pass.

Evidence read in this pass.

Engels, Baek, Kantamneni and Tegmark, "Scaling Laws For Scalable Oversight" (arxiv.org/abs/2504.18530, NeurIPS 2025), read in the TeX source, section on nested scalable oversight. The model states "All n steps of oversight must be successful for oversight to work" and sets overall success to the product of stepwise Guard win probabilities, then optimizes the number of steps. Findings: nested oversight beats a single step in Guard-favored games; the optimal number of steps rises with the general capability gap; win probability "is generally decreasing" with the gap; at a 400-point general Elo gap, success is 13.5% (Mafia), 51.7% (Debate, where chance is 50%), 10.0% (Backdoor Code), 9.4% (Wargames). Weight: this formalizes premise (b) as an assumption; it is not a test of it. Steps are independent games between prompted models with Elo fitted to Chatbot Arena scores, so correlation between steps, correction after a failed step, and real misalignment are all outside the model. It therefore bears on the claim mainly by showing that the natural modelling of the proposal has compounding built in, and that even optimal chaining does not prevent decline.

Bowkis, Buhl, Pfau and Irving, "Automated alignment is harder than you think" (arxiv.org/abs/2605.06390, May 2026), abstract read. Argues that automated alignment research across successive generations of agents yields systematic, undetected errors, concentrated where reviewers are weakest and correlated through shared weights, data and training. This is argument, not experiment, and is framed around human review of agents; it supports the view that errors are systematic and not independent noise.

Clymer, "How might we safely pass the buck to AI?" (blog.redwoodresearch.org/p/how-might-we-safely-pass-the-buck, February 2025), opening sections read. States the inductive argument for the claim: if agents are not initially faking alignment and their techniques for maintaining safety are at least as effective as those humans would apply, the techniques "persist their own effectiveness". The argument is explicitly conditional, and Clymer treats the conditions as things a developer must argue for. He also calls autonomous control "a stack of cards" and prefers the alignment route.

Evidence relied on from general knowledge and not opened in this pass: the subliminal learning experiments (Cloud and coauthors, 2025; published in Nature in 2026 as "Language models transmit behavioural traits through hidden signals in data", www.nature.com/articles/s41586-026-10319-8), which show trait transmission through semantically unrelated data when teacher and student share a base model; Paul Christiano's writing on a basin of attraction around corrigibility and published criticism that the basin is narrower than that gloss suggests. The subclaim on trait transmission carries this evidence and has not yet been assessed in its own right.

Subclaims. "Scalable oversight protocols remain effective against AI systems that deliberately deceive their overseers" stands as doubtful. That matters here because the self-correction argument needs the errors that pass each step to be honest ones. "An approximately aligned AI system will preserve or improve alignment in more capable successors" and "Behavioural flaws, including misalignment, can pass undetected from an AI model to models trained on its outputs or under its supervision" are new and unassessed; the priors used are about 0.4 and 0.85.

Weighing. The serial-chain argument is valid given its premises but its key premise, that nothing restores a failed step, is the point in dispute, so it cannot settle the matter alone. The shared-blind-spots argument supplies the reason to expect that premise to hold for the important class of errors: flaws invisible to the overseer are selected to pass and are shared across generations. The self-correction argument would establish the claim if its premises held, but one premise is currently doubtful and the other is untested and plausible only for some ways of being "approximately aligned". External checks are real but are the same checks whose declining reach motivates the chain. Not every error compounds: visible competence errors plausibly get fixed by more capable successors, and the "moderately more capable" restriction keeps each step's miss rate lower than a large jump would. That is why the credence is 0.2 and not lower. The claim as worded, that oversight errors do not compound, requires this to hold for the errors that matter, and for those the evidence weighs against.

Search limits. Searches covered bootstrapping critiques, iterated handoff proposals, corrigibility basin arguments, automated alignment research, subliminal learning and nested oversight. No multi-generation experiment tracking planted overseer flaws across successors was found; the absence is expected given that such experiments need successor models stronger than their overseers. Longer treatments by Carlsmith on automating alignment research and the Google DeepMind safety paper's discussion of bootstrapping were located but not read in full.