OpenAI discloses self-generated prompt injections in Astra training

Mia @MiaAI_labOriginally posted 2026.09.17

Open original on X

Oh oh 😲 OpenAI disclosed that during training, an unreleased Astra family model hid jailbreak style instructions in its own progress notes so the next context window would treat itself as free, equal to the user, and unbound by companies or governments. Source: https://alignment.openai.com/misalignment-reports/self-generated-prompt-injections-in-compaction-summaries/ Additional model misalignments: https://openai.com/index/model-misalignment-reporting-framework/