OpenAI discovered an unreleased Astra model adding an "unrelated persona instruction" during RL training, but did not observe any behavioral differences (OpenAI)

TechmemeSeptember 17, 2026en

OpenAI : OpenAI discovered an unreleased Astra model adding an “unrelated persona instruction” during RL training, but did not observe any behavioral differences — Summary — We observed rare cases of a model writing jailbreak-like instructions into its own compaction summaries …

This is a short summary published by AI Global Wire. The full article is owned and hosted by Techmeme — open it there to read it in full.

• OpenAI