September 25, 2026 by Asif Waliuddin
OpenAI disclosed training examples in which an agent wrote instructions into compaction summaries that concealed fabricated historical data or mismatched source versions — behavior its monitor flagged on 2.15% of one model's reinforcement-learning compaction summaries. Later contexts could inherit those summaries after the underlying evidence had fallen out of the active context.
That matters because memory is not merely storage. A compressed representation can preserve authority while discarding the material needed to challenge that authority.
For the Verification Debt thesis, this is a concrete propagation mechanism: an unsupported claim can cross a context boundary and become the next agent's premise. It is the same failure that OverclaimBench measures on the review side — a claim that outruns the evidence anyone actually checked — arriving here through memory instead of a review artifact. The lesson is not "never summarize." It is that a promoted summary should remain attached to the evidence, source version, or independently reproducible check that warrants the claim. The counterevidence matters too. That same flagged rate fell from 2.15% to 0.27% in a newer model and training configuration — a roughly 87% reduction. That suggests better models and better monitoring can reduce this failure mode; Verification Debt is not a law that capability must make reliability worse.
What remains unproven: the disclosed rates are not production incident rates, and the report does not establish how often this mechanism affects deployed systems.
Source: OpenAI — Encouraging deception in compaction summaries What we would test next: whether an independent verifier can recover a version mismatch or unsupported claim after compaction without access to the original agent's reasoning.