跨国深谈← 返回←Lance Martin

① 他说过的话

4 条

但是当模型只能做大约一小时的工作时，异步作为一种体验是很糟糕的。
But when models can only do like an hour of work, async as an experience is kind of bad.
—— Lance Martin · [01:48]

指向原始笔记的链接

因为发生的事情是，与其将转向编码到我作为人类身上，不如将信号编码到环境中。
Because what happens is instead of encoding steering into me as the human, you’re encoding the signal into the environment.
—— Lance Martin · [09:31]

指向原始笔记的链接

因为那最终并没有建立苦涩教训，在这个意义上，模型可以学会管理自己的内存，比你可以提前为模型凭直觉设计这些内存类型要好得多。
Because that ends up being not very bitter lesson built in the sense that models can learn to manage their own memory much better than you can intuit these memory types for the model ahead of time.
—— Lance Martin · [23:02]

指向原始笔记的链接

这是非常经典的苦涩教训药丸，但模型可以推理它们自己的内存和上下文结构，比你可以为它们规定一种构建自己内存的方式要好得多。
This is very classically bitter lesson pill, but models can reason about their own memory and context structure much better than you can prescribe for them a way to structure their own memories.
—— Lance Martin · [23:50]

指向原始笔记的链接

② 出现在这些集

1 集

• 《Claude 异步智能体架构的四块基石》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

Anthropic · OpenAI · 任务视界 · Managed Agents · harness · 沙箱 · 验证器 · dreaming · 组织级驾驭系统 · 带内记忆

④ 也在聊「智能体」的人