跨国深谈← 返回←Matt Garman

① 他说过的话

5 条

它们实际上非常在意尾部延迟，这很有意思，因为人并不总是关心 P999 的 S3 延迟，但智能体确实在意，并且会被它卡住。
They actually care a lot about tail latencies, which is interesting, where people don’t always care about the P999 S3 latency, like agents do care and get blocked by that.
—— Matt Garman · [08:25]

指向原始笔记的链接

结果发现 Trainium 从绝对性能和性价比的角度来看，可能是目前市场上最好的推理芯片。
It turns out that Terranium is actually maybe the best inference chip on the market right now from an absolute performance and cost performance point of view.
—— Matt Garman · [38:03]

指向原始笔记的链接

但我认为这是我们差异化的部分，也是需要认真考虑的超级重要的事情，因为让数据回传给模型提供商，我认为是一件危险的事。
But I think it’s a differentiating piece for us and it’s a super important thing to think about because having that data go back into the model provider I think is a dangerous thing.
—— Matt Garman · [47:01]

指向原始笔记的链接

因为你看，到了某个时候，客户将需要机器速度的安全，而不是人类速度，不是像报警之后有人进去查看那种速度。
Because look, at some point, customers are going to need security at machine speed, not at human speed, not at like an alarm, someone goes in, look at it.
—— Matt Garman · [50:43]

指向原始笔记的链接

智能体优先，智能体写所有的代码。你只是在管理一个智能体团队，并驱动它们。
Agent first, the agents write all of the code. You’re just managing a team of agents and driving that.
—— Matt Garman · [53:22]

指向原始笔记的链接

② 出现在这些集

1 集

• 《当AI智能体成为云的大客户：AWS CEO Matt Garman 谈2200亿美元的豪赌》 — 作为联合主持

③ 他谈到的

点进去有真内容 —— 本页主要出口

Raguraguram · AWS · Amazon · 智能体 · GPU · Trainium · Graviton · Bedrock · 沙箱 · Firecracker

④ 也在聊「智能体」的人