One way to avoid unspotted prediction errors is for the technology in its current state to have early and frequent contact with reality as it is iteratively developed, tested, deployed, and all the while improved. And there are creative ideas people don’t often discuss which can improve the safety landscape in surprising ways — for example, it’s easy to create a continuum of incrementally-better AIs (such as by deploying subsequent checkpoints of a given training run), which presents a safety opportunity very unlike our historical approach of infrequent major model upgrades.
Recent articles
- OpenAI DevDay 2025 live blog - 6th October 2025
- Embracing the parallel coding agent lifestyle - 5th October 2025
- Designing agentic loops - 30th September 2025