Safety
Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss.…
Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss. We’re sharing what we learned from studying a long-running
Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss. We’re sharing what we learned from studying a long-running model, and how those findings are shaping our approach to evaluations, alignment, monitoring, and user control. https://openai.com/index/safety-alignment-long-horizon-models/
Related
- Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning
- Safety Must Precede the Deployment of Open-Ended AI
- Long-Term Memory for VLA-based Agents in Open-World Task Execution
- SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Source: OpenAI (X) | 2026-07-20