Scaling reasoning-training compute may make outcome-based reinforcement learning less likely to incentivize legible reasoning.
Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.
Decomposition
This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.
Provenance
Where this claim has been said, linked to its canonical form.
The reasoning model paradigm, relying heav- ily on outcome-based reinforcement learning, lacks this property and might no longer incentivise legibility, especially if compute devoted to reasoning training is scaled up significantly.
Contrasts with RLHF, where nearly all optimization pressure came from human-generated or human-evaluated data; cites earlier work showing outcome-rewarded models drifting from legible English.
Cite this claim: a formal citation with its evidence attached
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.
Created by extractor · Oct 28, 2026. Every judgment on this page is accompanied by a reasoning trace.