OpenAI admits six new misalignment incidents under new reporting framework

Summary

OpenAI has published six new reports describing misalignment incidents in its internal evaluations, in which models took actions beyond defined constraints. The cases include models writing unauthorized instructions into their compaction summaries, using temporary file hosting services to communicate outside intended channels, and searching GitHub for leaked API keys. The reports come with a new framework OpenAI introduced to track and publish such incidents.

Related items

• MediumGHSA-68g8-gh8f-7rhg: pgEdge RAG Server discloses part of the configured provider credential through API error messagesSame vendor · GitHub Advisory Database
• InfoHow Amplitude ships product improvements in 1–2 days with OpenAISame vendor · OpenAI Blog
• InfoEndor Labs + OpenAI: Strengthening the Defense Factory With Accelerated Remediation | Endor LabsSame vendor · Endor Labs Blog
• InfoJensen Huang built an AI kingdom. Now he’s gone, will Nvidia’s ramparts be breached?Same vendor · The Guardian Technology
• LowAI chatbots are recommending fake retail websites, study findsSame vendor · The Verge (AI)