From the source
OpenAI describes a new safe-completions approach in GPT-5 that replaces hard refusals with output-centric safety training, aiming to improve both safety and helpfulness on dual-use prompts.
From hard refusals to safe-completions: toward output-centric safety training
Capability change
From the source
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.
openai.com
