Self-generated prompt injections in compaction summaries

T2Covered by 1 source · first reported by Simon Willison's Weblog at 17 Sept, 20:57 UTC

Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the last six months". This one here is my favorite: they caught some of their models in training…

aidev

Sources

• T2Self-generated prompt injections in compaction summariesSimon Willison's Weblog17 Sept, 20:57