DR

dreaming

概念
本站收录 3 集 · 2 条金句 · 关联 10

集里怎么说它

① 提到它的金句

2 条

但下一层是关于,好,如果 token 并不是真正可互换的,你需要给它们分配不同的工作,比如这个 token 负责建议、那个负责执行,这个在「做梦」、那个在执行,诸如此类,你会想开始组合这些协同配合的编排式策略
But the next one is about, okay, if tokens aren’t really fungible and you need to give them different jobs, like maybe this token is advising versus this token is executing, this token is dreaming versus this token is executing, so on and so forth, you want to start composing these kind of orchestrated strategies that go together
—— 嘉宾 · [11:34]

指向原始笔记的链接

我们发现,随着模型演变得更有能力,如果你将逐字稿和记忆状态作为一个周期性批处理过程,并使用我们所谓的做梦,它允许我们提取新的洞察和新的组织结构,这基本上会反馈并编辑记忆,从而让第二天的智能体会话自动地变得更加智能。
What we found is that as models have evolved and become more capable, if you feed the transcripts and the memory state as a periodic batch process with what we call dreaming, it allows us to extract new insights and new organized structures that essentially feedback and edit the memory as needed to make the next day’s agent sessions automatically much more intelligent.
—— Gagan Bhat · [27:45]

指向原始笔记的链接

② 出现在这些集

3 集

③ 关联

点进去有真内容 —— 本页主要出口

Anthropic · 沙箱 · harness · Claude Code · Messages API · 智能体 · Managed Agents · 可观测性 · Guy Pajani · Lance Martin