← Back to all news

OpenAI Blog August 7, 2025

From hard refusals to safe-completions: toward output-centric safety training

Read the original on OpenAI Blog →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at OpenAI Blog.

OpenAI Blog

Sep 9, 2025

SafetyKit scales risk agents with OpenAI’s most capable models

Discover how SafetyKit leverages OpenAI GPT-5 to enhance content moderation, enforce compliance, and outpace legacy safety systems with greater accuracy .

llms agents safety

OpenAI Blog

Jul 15

GPT-Red: Unlocking Self-Improvement for Robustness

Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.

llms reinforcement-learning safety

OpenAI Blog

Oct 29, 2025

Introducing gpt-oss-safeguard

OpenAI introduces gpt-oss-safeguard—open-weight reasoning models for safety classification that let developers apply and iterate on custom policies.

OpenAI Blog

May 21, 2024

OpenAI safety practices

Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.

OpenAI Blog

Mar 24

Helping developers build safer AI experiences for teens

OpenAI releases prompt-based teen safety policies for developers using gpt-oss-safeguard, helping moderate age-specific risks in AI systems.

OpenAI Blog

Jun 20, 2016

OpenAI technical goals

OpenAI’s mission is to build safe AI, and ensure AI’s benefits are as widely and evenly distributed as possible.