Материал на языке оригинала: English.
From hard refusals to safe-completions: toward output-centric safety training
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.
7 августа 2025 г. · Источник: OpenAI news
Полный текст доступен у источника.