AI & ML
gpt-oss-safeguard technical report
OpenAI Blog0 views
gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline. For more information about the development and architecture of the underlying gpt-oss models, see the original gpt-oss model model card.
Source:https://openai.com/index/gpt-oss-safeguard-technical-reportPreviousIntroducing gpt-oss-safeguardNextAdvancing organizational transformation for business innovation
Related posts
Network sampling: a comparative review
0arXiv stat.CO
Multilevel Filtering on Manifolds with Light Schr\"odinger Bridges
0arXiv stat.CO
Deep Mixture Models: A Statistical Review with R
0arXiv stat.CO
Nvidia Kinsus deal targets 3.5x substrate capacity by Q3 2028
0dev.to News
Printing large-type cards from a static website
0dev.to Design
Master Your AI Research: Seamlessly Integrate ChatGPT, Claude, Gemini Outputs into Obsidian
0dev.to Productivity