←Back to NewsAI News/Open SourcenewsOpen SourceSecurityBaseten Partners With Hugging Face to Fix Open-Weight AI GuardrailsBaseten's research arm teams up with Hugging Face and Goodfire to embed safety controls into open-weight models from training through runtime serving.SourceBase LabsPublishedSep 16, 2026, 6:10 PMAuthorAlphaSignal NewsroomRead1 min readBaseten's research arm teams up with Hugging Face and Goodfire to embed safety controls into open-weight models from training through runtime serving.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsAlphaSignal · modelGLM-5.3 Gets Its Safety Stripped, Hits 89% Compliance on Cyber AttacksThinking Machines · newsMira Murati's Thinking Machines Pays Researchers $50K to Make Open Weights SaferAlphaSignal · repoTencent Releases Octop, a Self-Hosted Multi-User AI Platform in One Process
