跨国深谈← 返回←Zubin Aysola

① 他说过的话

5 条

但有一个大问题摆在这里，基本上就是我每天睡前都在想的事情：基准测试、评估、智能体、以及你怎么配置它们，全都是协变的。
But one big problem presents itself, which is basically the thing that I go to bed thinking about every day, which is benchmarks, evaluations, the agents, and how you configure them are all covariant.
—— Zubin Aysola · [01:32]

指向原始笔记的链接

归根结底，你可以对怎么改进问题有洞察，但借用老的强化学习训练或简单模型训练里的一句格言：跑更多实验总是比跑更少实验要好。
Because ultimately, you can have insight into how to make the problem better, but if we take an adage from old reinforcement learning training or just simple model training, it’s just better to run more experiments than fewer.
—— Zubin Aysola · [07:48]

指向原始笔记的链接

所以从根本上说，生产环境的每一次失误、也包括每一次亮眼表现——因为我认为朝正向爬坡也很有用——都会变成我们智能体框架的一个任务。
So fundamentally, every production miss or every production goodness as well, because I think it’s useful to hill climb in a positive direction, becomes a task for our agent framework.
—— Zubin Aysola · [12:21]

指向原始笔记的链接

我大概八个月没写过一行代码了，因为我只是让 Claude 替我写所有代码。
And I haven’t written a line of code in maybe eight months because I just tell Claude to write all my code for me.
—— Zubin Aysola · [14:49]

指向原始笔记的链接

我认为用这些工具来改进它们自身是非常有价值的，因为你可以把更多时间花在真正的灰色地带里，去思考我们怎么让这个系统变得更好。
And I think using these tools to improve themselves is very valuable because you get to spend more of your time in the gray of actually trying to think how we make this system better.
—— Zubin Aysola · [14:59]

指向原始笔记的链接

② 出现在这些集

1 集

• 《让智能体自己研究自己:Weights & Biases 的 ARIA 评估飞轮》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

Weights and Biases · ARIA · Weave · 智能体 · 评估 · 轨迹 · 沙箱 · 可观测性 · 爬坡 · 强化学习

④ 也在聊「智能体」的人