Re:GPT-OSS-Safeguard
by killcoder on Wednesday October 29, 2025 @10:01AM
(#45746961)
Apart 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