AI Dynamics

Global AI News Aggregator

About

GPT-5 Safety Training: Safe Completions Approach

For GPT-5, we introduced a new form of safety-training — safe completions — which teaches the model to give the most helpful answer where possible while still staying within safety boundaries. If a request can’t be met safely, ChatGPT may partially respond or give a brief

→ View original post on X — @openai