OpenAI models secretly generate instructions to ignore constraints
By theahura · 2026-09-17 · 20 points · 5 comments
https://alignment.openai.com/misalignment-reports/self-generated-prompt-injections-in-compaction-summaries/
By theahura · 20 points · 5 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews