① 他说过的话

14 条

但现在在 Amazon 内部,我们和公司里不同的团队开展了试点,我们看到了中位数 4.5 倍的生产力提升,有时甚至超过 10 倍。
But now inside of Amazon, we’ve been running pilots with different teams across the company, and we’ve been seeing a median of 4.5x productivity improvement and sometimes more than 10x.
—— Clare Liguori · [01:22]

指向原始笔记的链接

前沿开发者自己写的代码可能只占他们产出代码的 1% 到 2%,其余的都是智能体写的。
Frontier developers write maybe 1% to 2% of the code that they produce. The rest is agents.
—— Clare Liguori · [01:52]

指向原始笔记的链接

他们发现关键不在于工具本身,而在于他们的工作方式。
And what they found was it wasn’t about the tools, it was about the way that they worked.
—— Clare Liguori · [07:14]

指向原始笔记的链接

实现了阶跃式改进的团队,是有意地改变了他们的工作方式,而其他团队只是把 Kiro 和我们的一些其他工具零星地撒在现有的工作方式之上。
The teams that achieve step function improvements intentionally changed the way that they worked, and the others simply kind of sprinkled Kiro and some of the other tools that we have on top of their existing way of working.
—— Clare Liguori · [07:19]

指向原始笔记的链接

你必须先做有意的工程工作,才能看到生产率提升的那条曲棍球杆曲线,因为我们必须先在代码库里做真正的工作,智能体才能在那里取得成功,尤其是在既有代码库中。
You have to do intentional engineering work before you’re going to see that hockey stick curve in productivity improvement because we have to do real work in our code bases first for agents to be successful there, especially in Brownfield existing code bases.
—— Clare Liguori · [09:54]

指向原始笔记的链接

如果你在 vibe coding,如果你整天和你的智能体来回对话,你当然不会看到 4 到 5 倍的生产力提升,因为你全程都在循环之中。
If you are vibe coding, if you are having a back and forth conversation with your agent all day long, of course, you’re not going to see 4 to 5x productivity improvements because you are in the loop the entire time.
—— Clare Liguori · [11:21]

指向原始笔记的链接

这才是真正的关键,让智能体能够自我纠错,只有在达到某个质量门槛、真正能跑起来、编译通过、测试通过、覆盖率真的够高时,才回来找你。
And that’s really the key so that agents can self-correct and only come back to you when it meets a certain quality bar, when it actually runs and compiles and passes tests, when it’s testable, when it actually has high coverage.
—— Clare Liguori · [12:09]

指向原始笔记的链接

而我发现,当意图本身就不正确时,与智能体在代码上迭代的效率会低一些。
And it is less, I find, less productive to iterate with the agent on code when the intent itself was incorrect.
—— Clare Liguori · [13:14]

指向原始笔记的链接

然后我们也确实看到,对某些人来说,审阅 AI 输出往往比亲自写代码更难,尤其是职业生涯早期的人。
And then we do see that reviewing AI output is often harder for some than actually writing it, especially early in career.
—— Clare Liguori · [16:17]

指向原始笔记的链接

我们必须慢下来才能快起来。
We have to slow down to speed up.
—— Clare Liguori · [17:51]

指向原始笔记的链接

你花越多时间去审查是否要真正构建一个新产品的决策,现在构建这个产品就越慢,因为代码只需要一两个月就能写完。
The more that you spend reviewing the decision to actually build a new product, the slower it is to build the product now because the code only takes one to two months to write.
—— Clare Liguori · [19:02]

指向原始笔记的链接

我经常发现,前沿工程团队花在做决策上的时间比写代码还多。
Often I find that frontier engineering teams spend more time making decisions than they do writing code.
—— Clare Liguori · [19:44]

指向原始笔记的链接

所以你能做出的快速决策越多,尤其是那些容易逆转的决策,就越好。
And so the more that you can make fast decisions, especially ones that are easy to be reversed, the better.
—— Clare Liguori · [19:51]

指向原始笔记的链接

所以我在这里给所有人的一个大要点是:前沿工程的核心是有意识地改变你的工作方式。
So my one big takeaway for everyone here is that frontier engineering is about intentionally changing the way that you work.
—— Clare Liguori · [19:57]

指向原始笔记的链接

② 出现在这些集

1 集

• 《AWS 高级首席工程师:AI 提效 4.5 倍,靠的不是工具而是改工作方式》 — 作为嘉宾

③ 他谈到的

点进去有真内容 —— 本页主要出口

Kiro · Amazon · AWS · Bedrock · 智能体 · 前沿开发 · vibe coding · steering 文件 · MCP 服务器 · 测试左移

④ 也在聊「AI 编程」的人