For realistic tasks, learning decompositions likely requires much less supervision than learning complex behaviors directly.
Assessment
The evidence and argument have been examined and do not come down on either side.
The claim is a forecast from the 2018 Iterated Amplification paper (Christiano, Shlegeris and Amodei): that the large supervision savings observed when a model learns one-step task decompositions instead of whole solutions will carry over to realistic tasks. The direct evidence for it comes from five algorithmic toy tasks, where amplification needed tens of thousands of decomposition examples against tens of millions of full-solution examples for supervised learning. Those tasks were picked because they decompose cleanly, so they say little about realistic work.
The general argument offered, that decomposing with help from subtask solvers is strictly easier than solving unaided, shows decomposition is easier to perform but not that it needs less supervision to learn, nor that good decompositions are cheap for humans to demonstrate. Evidence from realistic settings is mixed. Ought's human experiments on factored cognition (2019 to 2020) found realistic reading and argument-evaluation tasks hard to break into locally checkable steps, with frequent disagreement about step validity. OpenAI's recursive book summarization (2021) showed decomposition can make human feedback feasible on a long realistic task, but did not measure supervision against a direct baseline. Since then, most capability in practice comes from pretraining, which changes what "learning directly" costs and leaves the original comparison largely untested. The claim remains plausible but unestablished; a controlled comparison of label counts on a realistic task would settle it.
Full reasoning: the evidence and decisions behind this verdict
Own model first: the claim is true if, for realistic tasks, the number or cost of human-provided training signals needed to learn good decompositions is much lower than for learning the end-to-end behavior. That requires (a) realistic tasks to admit decompositions whose steps are much simpler than the whole, and (b) humans to be able to demonstrate or judge those steps cheaply.
For: (1) Algorithmic experiments in arXiv 1810.08575: ~10^4 decomposition examples vs ~10^7 supervised examples. Rated likely only conditional on realistic tasks resembling the toy tasks, a premise left unstated in the source. (2) "Decomposition is strictly easier than solving without the aid of X": true in a performance sense, but the step from easier-to-perform to needing much less supervision is not guaranteed, and the source gives no reason for the "much". Rated slight.
Against: Ought's factored-evaluation experiments (www.lesswrong.com/posts/pH3eKEAEupx8c2ep9/update-on-ought-s-experiments-on-factored-evaluation-of) found participants disagreed often about step validity and tree accuracy was modest (around 65 to 69% for depth 1 to 2 trees, per Alignment Newsletter 86), suggesting realistic decompositions are costly to produce and check. These were human-only experiments, not ML supervision counts, so the bearing is indirect.
Mixed: Wu et al. 2021, Recursively Summarizing Books with Human Feedback (arXiv 2109.10862), used decomposition to make feedback on book-length summarization tractable; it supports feasibility but not a quantified supervision saving versus direct learning.
No study found compares supervision counts for learned decomposition versus direct learning on a realistic task. Verdict: inconclusive, credence slightly below even, given the toy-task evidence is selected for clean decomposition and realistic-setting evidence is mixed. A search was brief; a wider search of process-supervision and task-decomposition literature could shift this modestly.
Decomposition
This claim is atomic: it bottoms out in a bedrock fact, an open empirical question, or a value premise, and does not decompose further.
Provenance
Where this claim has been said, linked to its canonical form.
Its one source has been traced to an origin, or to one another.
But the general phenomenon, that learning decompositions can be much cheaper than learning complex behaviors directly, is likely to hold for realistic tasks, since performing decomposition is strictly easier than solving the task without the aid of X.
Amplification needed tens of thousands of oracle calls versus tens of millions of supervised examples
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="a4bfe1a1-0d33-4876-b6ab-40989cb38bac"><a href="https://minerval.ai/claims/a4bfe1a1-0d33-4876-b6ab-40989cb38bac">For realistic tasks, learning decompositions likely requires much less supervision than learning complex behaviors directly.</a></blockquote> <script async src="https://minerval.ai/embed.js"></script>
<iframe src="https://minerval.ai/embed/claims/a4bfe1a1-0d33-4876-b6ab-40989cb38bac" title="Minerval: For realistic tasks, learning decompositions likely requires much less supervision than l…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>
[](https://minerval.ai/claims/a4bfe1a1-0d33-4876-b6ab-40989cb38bac)
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.
The attention this claim received was paid for by a funded mandate. Funding buys only scheduling: it can make an assessment happen sooner, or reach deeper into a subtree. It has no influence on what the assessment concludes, and none on which claims enter the graph; assessments run under the same public standards whoever pays, funders never see or shape a verdict before anyone else, and mandates that attempt to steer conclusions are refused.
Created by extractor · Nov 11, 2026. Every judgment on this page is accompanied by a reasoning trace.