Browse the library

The complete record — 223 artifacts, last updated 20 Aug 2026. Also available as JSON and RSS (CC BY 4.0).

Filters:

1 artifact matching

9 Jul 2026 Mila (Quebec AI Institute) & ROOST Lab publication

Mila's Suicide Prevention Guardrail: Lightweight, Open Source Safeguards for Real-Time Detection

Joint beta release by Mila's AI Safety Studio and ROOST of an open-weights (Apache-2.0) output-moderation classifier for suicide and self-harm content in chatbot responses. The model is a fine-tuned…