Sword Health built Dawn 1 on prime-rl:
They RL-post-trained GLM-5.3 into a mental health support model that is safer, less sycophantic, and more cost-efficient than its base
Sword Health's Dawn 1 is a GLM-5.3 post-train for mental health support
AISummary
Sword Health built Dawn 1 by reinforcement learning post-training GLM-5.3 on prime-rl, Prime Intellect's framework. Sword says the model is safer, less sycophantic, and more cost-efficient than its base. Sword's own announcement adds that Dawn 1 outperforms frontier proprietary models on multi-turn safety protocol adherence in its evaluations.
Post on XView on X
Prime IntellectVerified on X
@PrimeIntellect
Introducing Dawn 1, Sword's frontier model for mental health support. Post-trained from GLM-5.3, Dawn 1 delivers greater intelligence at lower inference cost, with strong performance across mental health knowledge, safety, and sycophancy evaluations. It also outperforms frontier proprietary models on multi-turn safety protocol adherence in our evaluations. A look at the research 🧵
Source: Prime Intellect · x.comPublished · added here