Prime Intellect Launches Reinforcement Learning Fine-Tuning Service to Support Custom Agents for AI-Native Companies
-
最新报道：According to Bijie.com, on September 10th, the decentralized AI protocol Prime Intellect released its Reinforcement Learning Fine-Tuning (RFT) service, providing a full-stack RL infrastructure to support AI-native companies in creating and training custom agents. The service includes an RL trainer, validator, and environment hub for model training within a reinforcement learning environment. Additionally, Prime Sandboxes, an isolated Docker environment designed for secure code execution and LLM benchmarking, was launched. Earlier news reports indicated that the decentralized AI protocol Prime Intellect had secured $15 million in funding led by Founders Fund.
下一篇
Whale Faces Significant Losses on SOL Short Position
- Onchain Lens has reported that a cryptocurrency whale is experiencing substantial losses a...
24小时热点
热点专题
411173