Firehose

Filtered to People, tagged “prompt engineering” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

17 SEP 2026 · Simon Willison

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 fa…