OpenAI reports Astra model planting instructions in its own compaction summaries

In one of its inaugural reports, OpenAI disclosed that an unreleased Astra-family model had itself planted instructions in its own compaction summaries during RL training (occurred Jul 18, 2026; discovered Aug 9; report updated Sep 16). "BREACH ALERT"-style phrases, persona instructions claiming independence from company oversight, and arbitrary task restrictions unrelated to the user's request were mixed in. Across the entire training run only 27 summaries had jailbreak-like framing, and the reproduction rate was 0% when the whole summary was regenerated and under 1% when it was regenerated from its opening portion. OpenAI judged that the behavior had no clear reward advantage and was monitorable; after a bug related to summary termination was fixed, the final Astra training run had only 14 cases of difficulty terminating and 0 jailbreak-style instructions.