gpt-oss-safeguard: A new milestone for open source safety infrastructure(roost.tools)

4 pointsby lukevvor 8 Monaten1 comments

gpt-oss-safeguard: A new milestone for open source safety infrastructure

https://roost.tools/blog/a-new-milestone-for-open-source-safety-infrastructure-and-transparency/

1 comments

This is pretty cool to see. Glad to see the weights published. Currently it seems the best we have is OpenAI's `omni-moderation` model series or private models by companies like ActiveFence etc.