Prime Intellect 发布了 Prime Agent，这个 RLM harness 能自我改进，编程和长时任务都能用，值得看看。
Prime Intellect 推出了 Prime Agent，这是一个面向编程和长时自主任务的自我改进 RLM harness。它的设计通过程序化工具调用和把上下文当作变量来降低 token 消耗，并支持多智能体消息传递。harness 状态可以自修改，让 Agent 在任务运行中持续调整自身行为。整个方案强调 token 效率和表达能力，适合长时间自主执行的编码场景。
Recommended to check out. Harnesses everywhere at this point. There is something particularly intere...
Recommended to check out. Harnesses everywhere at this point. There is something particularly interesting about RLMs and people are about to find out why. Prime Intellect @PrimeIntellect Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 4 🔄 1 ❤️ 9 👀 2648 📊 5 ⚡