HE

Heitor Lessa

Beyond Coding 主持
本站收录 1 集 · 10 条金句 · 关联 10

① 他说过的话

10 条

这次重构几乎花了我 2 亿个 token。
This cost me almost 200 million tokens to refactor.
—— Heitor Lessa · [01:00]

指向原始笔记的链接

当领导层开始质疑时,我是否需要一名工程师加上每月 5,000 美元才能让他们完成工作?
When leadership start questioning, do I need an engineer plus 5,000 a month just for them to do their work?
—— Heitor Lessa · [01:14]

指向原始笔记的链接

大部分工作不是编码。它主要是协调,然后说服人们事情可能是怎样的。
Most of the work is not coding. It’s largely coordination and then convincing people on how things could be.
—— Heitor Lessa · [08:36]

指向原始笔记的链接

我们往往被训练成只学习硬技能和所有的技术细节,并且表现得非常出色,成为房间里最聪明的人,这在某种程度上就像是胡扯。
We tend to be conditioned to learn only the hard skills and all the technical pieces and be really good and be the best smart person in the room, which is like BS in a way.
—— Heitor Lessa · [18:20]

指向原始笔记的链接

而发展职业生涯的最佳方式不是试图学习更多,以及如何在自己的工作中更高效。而是尝试学习相邻领域的角色。
the best way to grow a career is not to try to learn more and how to be more effective in your own job. But trying to learn adjacent roles.
—— Heitor Lessa · [18:56]

指向原始笔记的链接

但这也是危险的一部分,因为每个人可能会意外地、错误地认为工程只是一个开发人员,这就是你所需要的。
But it’s also part of the danger because then everyone can accidentally, wrongly assume that engineering is just a single developer and that’s all you need.
—— Heitor Lessa · [24:32]

指向原始笔记的链接

我超级喜欢,因为我向组织解释的所有事情等等,人类天生是不确定的。但我们现在正在添加更多的智能体。我们更加不确定了。所以我需要某种程度的确定性。
I’m a big fan of, because of everything I explained to organizations and so forth, is that humans are non-deterministic by nature. But now we’re adding more agents. We’re even more non-deterministic. So I need some level of determinism.
—— Heitor Lessa · [33:53]

指向原始笔记的链接

所以默认基本上将与你使用的模型一样好,但这并不好。
So the default will basically be as good as the model that you’re using and that’s not good.
—— Heitor Lessa · [78:08]

指向原始笔记的链接

我认为这是最大的谎言,甚至当营销和炒作出来时说,我们不再需要工程师了。这个问题都解决了。
I think it’s the biggest lie to say even when the marketing and the hype came out in saying, we don’t need engineers anymore. This problem is all solved.
—— Heitor Lessa · [89:54]

指向原始笔记的链接

但是在你运行一个会话三、四、七个小时之后,你筋疲力尽了。你最不情愿的就是去思考这可能是一个 linter 吗?
But after you’ve run a session for like three, four, seven hours, you’re exhausted. The last thing you want is to think about what could this be a linter?
—— Heitor Lessa · [103:49]

指向原始笔记的链接

② 出现在这些集

1 集

③ 他谈到的

点进去有真内容 —— 本页主要出口

智能体 · 规范驱动开发 · 苏格拉底方法 · 对抗性审查 · 合并检查 · 命令 · 技能 · 确定性 · 伪造证据 · 三层模型分层

④ 也在聊「智能体」的人