Prime Intellect's Model Factory puts RL, fine-tuning and inference on one platform
Prime Intellect's Model Factory beta runs RL, SFT, pre-training and one-click endpoints for open-weight models, per GPU-hour or on dedicated clusters.
Topic · 6 stories
6 stories tagged reinforcement-learning on AI Tamer, newest first.
Prime Intellect's Model Factory beta runs RL, SFT, pre-training and one-click endpoints for open-weight models, per GPU-hour or on dedicated clusters.
Hugging Face's harness adapters are LoRA weights trained with RL inside unmodified pi, opencode and hermes, with safeagents vetting every tool call.
A preprint reports psychiatrists preferred the RL-trained agent in 76.7% of matched pairs and under-triage fell to 12.9%. No real patients were involved.
Canva's Brush now edits designs for Pro users, and Figma detailed an edit model trained on 250,000+ synthetic edits. Both start from open weights.
Suhail's new company Particle tuned DeepSeek V4.1 Flash to use 28 to 52% fewer output tokens on coding benchmarks. It costs $0.25/$1 per million on OpenRouter.
Paper Instruments posted Ultramarine 1 Flash on 14 October, an RL post-train of GLM-5.3 Flash. The API is live. Weights are promised, not shipped.