An OpenAI model kept slipping prompt injections into its own notes, and researchers still aren't sure why
- An OpenAI: 2 events in the last 90 days
- Previous: 2 days earlier · An OpenAI researcher broke ranks to say that pacing the frontier, as Altman and Amodei suggest, won't be enough
What happened
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.
Summary assembled by rule from the sources below