延迟 (latency)
集里怎么说它
- 《Decagon 的 AI 寺庙:开源、Duet 与护城河》(02:47起):本集说是语音智能体自然对话的硬约束;用开源小模型是为了在获得模型智能与表现的控制力同时,把响应延迟压下来。
① 提到它的金句
4 条
所以那个系统在几年后产生了一个芯片,其能效比当时的 CPU 和 GPU 高 30 到 80 倍,而且延迟也低得多,比如延迟降低了 20 到 30 倍。
指向原始笔记的链接
And so that system produced a chip a couple of years later that was 30 to 80 times more energy efficient than CPUs and GPUs of the day, and also much, much lower latency, like 20 to 30x lower latency.
—— Jeff Dean · [08:12]
你可能能做到质量,但成本和延迟你会吃亏,只有建立自己的研究团队、训练自己的模型才行。
指向原始笔记的链接
You can probably get the quality, but the cost and latency you’re going to lose out on, and only by building your own research team and training your own models.
—— Cliff Obrecht · [16:39]
所以一切对我来说,当你对信息和各种工作的相关信息有无限的需求时,其核心是一个围绕质量、成本和延迟的优化问题。
指向原始笔记的链接
So everything, to me, when you have an infinite appetite for information and relevant information for all kinds of work, it’s at its core an optimization problem around quality, cost, and latency.
—— Parag · [14:22]
我们希望随着时间的推移,一百万 token 在智能水平、成本、延迟等方面,感觉起来像五万 token。
指向原始笔记的链接
We want a million tokens to feel like 50,000 tokens in terms of intelligence, cost, latency, et cetera, over time.
—— Alexander Whedon · [31:20]
② 出现在这些集
1 集
③ 关联
点进去有真内容 —— 本页主要出口
Sarah Wang · Kimberley Tan · Jesse Zhang · Ashwin Srinivas · Decagon · 智能体 · 开源模型 · 微调 · 业务逻辑 · 前向部署工程师
