Maximillian Piras
① 他说过的话
12 条
我认为提醒自己这一点很重要:不管间接还是直接,我们很可能都在售卖 token。
指向原始笔记的链接
I think it’s important to remind ourselves that in some way or another, we probably are selling tokens, whether it’s indirectly or directly.
—— Maximillian Piras · [05:03]
教训是:如果我们无法给客户提供某种有形的投资回报率(ROI),那我们就很难传达价值。
指向原始笔记的链接
the lesson being if we’re not able to give something that is a tangible ROI for our customers, then it’s very hard for us to communicate value.
—— Maximillian Piras · [08:49]
人们把一整年的 token 预算挥霍一空——而且是在一个季度里就挥霍完了——或者他们在应付 token 排行榜之类的东西。
指向原始笔记的链接
People are blowing through their entire token budget for a year and they’re blowing through it in a quarter or they’re dealing with token leaderboards and such.
—— Maximillian Piras · [09:23]
现在,我认为我们有点处于这种厄运循环中:我们超支,同时我们使用不足。
指向原始笔记的链接
right now I think we’re kind of in this doom loop where we’re overspending and we’re underusing.
—— Maximillian Piras · [09:52]
token 作为内部系统的度量当然是有用的,但归根结底,它们只是一种输出。
指向原始笔记的链接
tokens are, of course, useful as a measurement of an internal system, but at the end of the day, they’re just an output.
—— Maximillian Piras · [10:49]
但问题当然是我们都在被一千个 pull request 折磨至死。
指向原始笔记的链接
the problem of course is that we’re all kind of dying by a thousand pull requests.
—— Maximillian Piras · [11:51]
瓶颈最终转移到了验证这一侧,因此,我们没有办法大规模地衡量价值,并以同样的速度判断质量。
指向原始笔记的链接
the bottleneck ends up shifting to the verification side, and thus, we don’t have a way to measure value at scale and to judge quality at the same speed.
—— Maximillian Piras · [12:20]
如果你要考虑如何为某件事构建一个智能体,你也必须考虑如何帮助客户构建,或者至少创建一种方法,来验证输出是好的。
指向原始笔记的链接
if you’re going to think of how to build an agent for something, you also have to think about how do you help the customers build or at least create a method for verifying that the output is good.
—— Maximillian Piras · [14:05]
如果你要把一个智能体卖给某个人,你也必须帮他们解决评分标准的问题,即我们究竟如何验证这个智能体在做好的工作
指向原始笔记的链接
if you’re going to sell somebody an agent, you also have to help them with the rubric of how do we actually verify that this agent is doing good work
—— Maximillian Piras · [15:44]
当验收标准具有很高的不确定性时,你基本上就处于一个验证与执行无法区分的境地。
指向原始笔记的链接
when you have high uncertainty in the acceptance criteria, you pretty much have a spot where verification is indistinguishable from execution.
—— Maximillian Piras · [19:11]
如果你能找出一个相当可重复的模式来验证它们的工作,你其实也可以直接把智能体扔到那个问题上。
指向原始笔记的链接
if you can figure out a pretty repeatable pattern for verifying their work, you can actually just throw agents at that problem as well.
—— Maximillian Piras · [20:04]
所以你不只是构建一个智能体,你或许要构建一个用来验证那个智能体工作的智能体。
指向原始笔记的链接
you don’t just build the agent, you perhaps build the agent that verifies the work of the agent.
—— Maximillian Piras · [20:13]
② 出现在这些集
1 集
- 《鼠标力:为智能体时代找回「马力」这把尺子》 — 作为嘉宾
③ 他谈到的
点进去有真内容 —— 本页主要出口
Utori · 智能体 · 计算机使用模型 · 心智模型 · 鼠标力 · token · ROI · 代码审查 · 验证 · 熵
