OpenAI reveals six more safety issues and unveils plan to disclose incidents
BBC Technologyen
The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment".
This is a short summary published by AI Global Wire. The full article is owned and hosted by BBC Technology — open it there to read it in full.
Read the full story at BBC Technology- OpenAI
Related AI news
- Do Frontier Models Seek Safety Evidence Before Acting?arXiv cs.AI · September 17, 2026
- When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AIarXiv cs.AI · September 17, 2026
- AI risk split among tech leaders set to play out at Trump-Xi White House dinnerDIGITIMES · September 17, 2026
- OpenAI discovered an unreleased Astra model adding an "unrelated persona instruction" during RL training, but did not observe any behavioral differences (OpenAI)Techmeme · September 17, 2026
- SoftBank’s credit risk rises as OpenAI exposure growsTech in Asia · September 17, 2026
- OpenAI reveals six new cases of AI misbehavior, vows transparencyEconomic Times Tech · September 17, 2026