Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.
Publishers representing hundreds of newsrooms and content brands are using OpenAI partnerships and grant programs to adopt AI tools and strengthen the news ecosystem, while ChatGPT users gain access to information from leading, reliable publications.
Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.
Sora is OpenAI’s video generation model, designed to take text, image, and video inputs and generate a new video as an output. Sora builds on learnings from DALL-E and GPT models, and is designed to give people expanded tools for storytelling and creative expression.
Broadening usage of frontier AI
Building smarter maps with GPT-4o vision fine-tuning