Akshat Bubna
① 他说过的话
4 条
为什么你要让一个智能体去阅读数百个 Kubernetes 文件并编写甚至没有类型的 YAML,而它基本上可以在一个装饰器中做几个更改,然后获得这种能够自我配置的运行时,实时看到它的更改在运行中生效。
指向原始笔记的链接
Why would you have an agent read through hundreds of Kubernetes files and write YAML that’s not even typed when it can basically make a couple of changes in a decorator and it gets this sort of self-provisioning runtime of being able to see its changes live in action.
—— Akshat Bubna · [05:06]
改进内核只给你几个百分点的提升,而增加接受长度实际上是 2 到 4 倍的乘法性减少。
指向原始笔记的链接
Improving kernel only give you like few percentage points improvement and increasing except lengths literally is multiplicative decrease in two to four x
—— Akshat Bubna · [17:38]
我们在 2023 年 5 月构建了沙箱,在任何人甚至知道这将成为一件事之前。
指向原始笔记的链接
we built sandboxes in May of 2023 before anyone was even knew this was going to be a thing.
—— Akshat Bubna · [09:19]
这是我们一直有所回避的一件事,就是为模型提供 API。
指向原始笔记的链接
This is one thing we’ve kind of stayed away from is providing an API for models
—— Akshat Bubna · [48:34]
② 出现在这些集
1 集
- 《不只做推理:Modal 如何跨界多节点训练与智能体云》 — 作为嘉宾
③ 他谈到的
点进去有真内容 —— 本页主要出口
Swyx · Vibhu · Modal · 智能体 · AX · DX · 沙箱 · 推理 · 弹性推理 · 投机解码
