Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline.
This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance.
We’re strengthening the Frontier Safety Framework (FSF) to help identify and mitigate severe risks from advanced AI models.
We introduce VaultGemma, the most capable model trained from scratch with differential privacy.
Company knowledge brings context from your apps into ChatGPT for answers specific to your business, with clear citations, security, privacy, and admin controls. Available now for Business, Enterprise, and Edu users.
ChatGPT Atlas, the browser with ChatGPT built it. Get instant answers, summaries, and smart web help—right from any page.
Learn how OpenAI evaluates political bias in ChatGPT through new real-world testing methods that improve objectivity and reduce bias.
To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app with safety at the foundation. Our approach is anchored in concrete protections.
ENEOS Materials uses ChatGPT Enterprise to speed research, improve plant design safety, and cut HR analysis time by 90%, with 80% reporting better workflows.
Explore OpenAI’s approach to balancing teen safety, freedom, and privacy in AI use.
OpenAI shares progress on the partnership with the US CAISI and UK AISI to strengthen AI safety and security.
OpenAI and Microsoft sign a new MOU, reinforcing their partnership and shared commitment to AI safety and innovation.
Discover how SafetyKit leverages OpenAI GPT-5 to enhance content moderation, enforce compliance, and outpace legacy safety systems with greater accuracy .
OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and safety.
OpenAI surveyed over 1,000 people worldwide on how AI should behave and compared their views to our Model Spec. Learn how collective alignment is shaping AI defaults to better reflect diverse human values and perspectives.
OpenAI and Anthropic share findings from a first-of-its-kind joint safety evaluation, testing each other’s models for misalignment, instruction following, hallucinations, jailbreaking, and more—highlighting progress, challenges, and the value of cross-lab collaboration.
How we think about safety for users experiencing mental or emotional distress, the limits of today’s systems, and the work underway to refine them.
Discover how OpenAI's new safe-completions approach in GPT-5 improves both safety and helpfulness in AI responses—moving beyond hard refusals to nuanced, output-centric safety training for handling dual-use prompts.
