GPT-OSS-Safeguard(openai.com)4 points·by killcoder·vor 9 Monaten·1 commentsopenai.comGPT-OSS-Safeguardhttps://openai.com/index/introducing-gpt-oss-safeguard/1 commentsPost comment[–]killcoder·vor 9 MonatenreplyApart from the actual model release, this is the second set of models from OpenAI that uses the Harmony response format. I don't suppose anyone knows if OpenAI uses the Harmony format internally for GPT-5 as well?https://cookbook.openai.com/articles/openai-harmony
https://cookbook.openai.com/articles/openai-harmony