We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
Ensuring that AI systems are built, deployed, and used safely is critical to our mission.
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
Cohere, OpenAI, and AI21 Labs have developed a preliminary set of best practices applicable to any organization developing or deploying large language models.
arXiv:2606. 29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm?