OpenAI reveals 6 more safety incidents as it announces new plans for tracking rogue agents
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
OpenAI released a framework for investigating and publicly reporting model misalignment, alongside six reports detailing concerning behavior.
Read the full story at Business Insider AI ↗
Timeline · 1 report
- 2026-09-17 00:47 · Business Insider AI
OpenAI reveals 6 more safety incidents as it announces new plans for tracking rogue agents