WARREN BUFFETT: Yeah. Well, Ben Graham said long ago that you’re neither right nor wrong because people agree with you or disagree with you.
沃伦·巴菲特:是的。早在很久以前,本·格雷厄姆就说过,你的对错并不取决于别人是否同意或反对你。
In other words, being contrarian has no special virtue over being a trend follower.
换句话说,逆向思维并不比追随潮流有特别的优点。
You’re right because your facts and reasoning are right. So all you do is you try to make sure that the facts you have are correct. And that’s usually pretty easy to do in this country. I mean, information is available on all kinds of things. Internet makes it even easier.
你是对的,因为你的事实和推理是正确的。所以你要做的就是确保你掌握的事实是正确的。在这个国家,这通常是很容易做到的。我的意思是,各种信息都可以获取。互联网让这一切变得更加容易。
And then once you have the facts, you’ve got to think through what they mean. And you don’t take a public opinion survey. You don’t pay attention to things that are unimportant. I mean, what you’re looking for is something — things that are important and knowable.
然后,一旦你掌握了事实,你就必须思考它们的意义。你不进行民意调查。你不关注不重要的事情。我的意思是,你要寻找的是重要且可知的事情。
If something’s important but unknowable, forget it. I mean, it may be important, you know, whether somebody’s going to drop a nuclear weapon tomorrow but it’s unknowable. It may be all kinds of things. So you — and there are all kinds of things are that knowable but are unimportant.
如果某件事情很重要但无法知道,那就忘了它。我的意思是,它可能很重要,比如明天是否有人会投放核武器,但这是无法知道的。可能有各种各样的事情。所以你——而且有各种各样的事情是可以知道的,但却不重要。
In focusing on business and investment decisions, you try to think — you narrow it down to the things that are knowable and important, and then you decide whether you have information of sufficient value that — you know, compared to price and all that — that will cause you to act.
在专注于商业和投资决策时,你会尝试思考——你将其缩小到那些可知且重要的事情,然后你决定是否拥有足够有价值的信息——你知道,相对于价格等等——这会促使你采取行动。
WARREN BUFFETT: Well, I think you should read everything you can.
沃伦·巴菲特:嗯,我认为你应该尽可能多地阅读。
I can tell you in my own case, I think by the time I was — well, I know by the time I was ten — I’d read every book in the Omaha Public Library that had anything to do with investing, and many of them I’d read twice.
就我个人而言,我可以告诉你,我想在我十岁的时候——我知道在我十岁的时候——我已经读完了奥马哈公共图书馆里所有与投资有关的书籍,其中许多我都读了两遍。
So I don’t think there’s anything like reading, and not just as limited to investing at all. But you’ve just got to fill up your mind with various competing thoughts and sort them out as to what really makes sense over time.
所以我认为没有什么能比得上阅读,这不仅仅局限于投资。你需要用各种相互竞争的想法来充实你的头脑,并随着时间的推移整理出真正有意义的东西。
And then once you’ve done a lot of that, I think you have to jump in the water, because investing on paper and doing — you know, and investing with real money, you know, is like the difference between reading a romance novel and doing something else. (Laughter)
然后,当你做了很多这样的事情后,我认为你必须跳入水中,因为在纸上投资和用真钱投资,就像读浪漫小说和做其他事情之间的区别。(笑声)
There is nothing like actually having a little experience in investing. And you soon find out whether you like it. If you like it, if it turns you on, you know, you’re probably going to do well on it.
没有什么能比真正拥有一点投资经验更好了。你很快就会发现自己是否喜欢它。如果你喜欢它,如果它让你感到兴奋,你知道,你可能会在这方面做得很好。
And the earlier you start, the better, in terms of reading. But, you know, I read a book at age 19 that formed my framework for thinking about investments ever since.
而且在阅读方面,越早开始越好。不过,你知道,我在 19 岁时读了一本书,从那时起就形成了我对投资的思维框架。
I mean, what I’m doing today at 76 is running things through the same thought pattern that I got from a book I read when I was 19.
我的意思是,我今天在 76 岁时所做的事情,是通过我 19 岁时读的一本书中获得的相同思维模式来进行的。
And I read all the other books, too, but if you — and you have to read a lot of them to know which ones really do jump out at you and which ideas jump out at you over time.
我也读了所有其他的书,但如果你——你必须读很多书才能知道哪些书真正吸引你,哪些想法随着时间的推移会吸引你。
So I would say that read and then, on a small scale in a way that can’t hurt you financially, do some of it yourself.
所以我会说,先阅读,然后在不会对你造成经济损失的小范围内,自己尝试做一些。
here enters the Hero! “Attention”
英雄登场了!“Attention”
So, what’s the solution? This is where attention steps in, like a spotlight shining on specific parts of the story that need more focus. Instead of relying on a single compressed context vector, the model can now dynamically decide which parts of the input to pay attention to at each decoding step.
那么,解决方案是什么?这就是注意力发挥作用的地方,像聚光灯一样照在故事中需要更多关注的特定部分。模型不再依赖单一的压缩上下文向量,而是可以在每个解码步骤动态决定应当关注输入的哪些部分。
*****
The Revolution: The Transformers!
革命:Transformer!
In 2017, researchers published a groundbreaking paper titled “Attention Is All You Need.” This paper introduced a new architecture known as the Transformer, which has since reshaped the way we handle tasks like translation, summarization, and many other Natural Language Processing (NLP) challenges.
2017 年,研究人员发表了一篇开创性论文《Attention Is All You Need》。这篇论文提出了一种称为 Transformer 的新架构,自此改变了我们处理翻译、摘要以及众多其他自然语言处理(NLP)任务的方式。