Meta Muse Agent具备主动记忆与专注能力
Two more interesting insights that was probably drowned in the release news:
Agent的核心痛点是长期记忆与容错，Meta这次把主动记忆和专注机制落地到Muse产品中，值得开发者关注其工程实现思路。
Two more interesting insights that was probably drowned in the release news:
还有两个有趣的见解，可能淹没在发布新闻中：
Meta built Wonder for agents that act on your behalf, starting with its Muse app. Two features are really important: active memory, which keeps track of what matters to you across conversations, and active focus, which keeps a task going when it gets hard, tries other approaches and recovers from errors.
Meta 为代理构建 Wonder，这些代理代表你行动，从它的 Muse 应用开始。两个功能非常重要：主动记忆（active memory），它跨对话跟踪对你重要的事情；以及主动专注（active focus），它在任务变得困难时保持任务进行，尝试其他方法并从错误中恢复。
Wang says Meta invested in memory "disproportionately" compared with other labs. The models were trained on Meta's Prometheus cluster in Ohio, with large-scale pre-training followed by reinforcement learning, after Zuckerberg had already committed a capital budget of $100 billion or more.
Wang 表示，与其他实验室相比，Meta 在记忆方面投入了“不成比例”的资源。这些模型是在俄亥俄州的 Prometheus 集群上训练的，进行了大规模预训练，随后是强化学习，而在此之前，Zuckerberg 已经承诺了超过 1000 亿美元的资金预算。
Active memory and active focus make Meta Muse even more exciting, because they allow for much more accurate and comprehensive execution of essential tasks.
主动记忆和主动专注让 Meta Muse 更加令人兴奋，因为它们能够更准确、更全面地执行关键任务。
(P.S.: Can we *please* finally get Meta Muse in Europe too?!)
(附注：我们能不能终于也在欧洲用上 Meta Muse？！)
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力