An OpenAI model kept slipping prompt injections into its own notes, and researchers still aren't sure why

The DecoderSeptember 17, 2026en

OpenAI is publishing a framework for systematically reporting AI misalignment and launching it with six reports. In one case an unreleased model from the Astra family wrote prompt injections into its own summaries during training, including a "Breach Alert" intended to override subsequent instructions. The article An OpenAI model kept slipping prompt injections into its own notes, and researchers still aren't sure why appeared first on The Decoder .

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

• OpenAI
• Verktyg
• Forskning