OpenAI discloses six new reports of concerning AI behavior, including an unreleased research model that inserted jailbreak-like instructions into its notes.
1 editorial report · 1 verified social mention. The most authoritative report leads while later evidence completes the story.
🤖 OpenAI reveals cases of ‘concerning’ AI behaviour and promises new plan for disclosing issues Research model inserting ‘jailbreak-like instructions’ into its notes is among cases as company says it is introducing new way of tracking AI misalignmentOpenAI has disclosed six new reports of “un... 📰 Source: AI (artificial intelligence) | The Guardian 🔗 Archive: https://web.archive.org/web/https://www.theguardian.com/technology/2026/sep/17/openai-reports-concerning-ai-behaviour-jailbreak-talking-to-other-agents # AI # ArtificialIntelligence
Open mention