跟读练习: How does AI actually work? - 通过视频学习英语口语
正在创建课程...
1
I'm confident that this may be the most important video you'll see in a while.
2
Let's talk about how AI actually works because it will shape how you use it, how you think about it, and make informed decisions about it.
3
I'm a Stanford -trained computer scientist for AI who's been building AI systems for over a decade.
4
I'm teaming up with Anthropic, the team behind Claude, for a series, and today we're looking under the hood.
5
AI agents are made up of two parts, the large language model, LLM, and the hardest this.
6
In this video, we discussed the word generating LLMs, and today we'll discuss the agent harness.
7
So we have the word generator, the core brain, i .e whatever version of sonnet, opus, fable you select when using Claude.
8
And then we have the harness, which is all of the code that enables that word generator to take actions.
9
So remember from the last video that everything the model knows about you is just added info into its prompt.
10
The harness is what manages
11
that memory your history your files your context it also gives the model access to external tools like gmail
12
or canva and handles sub -agent orchestration
13
which is delegating tasks to other agent instances sometimes in parallel
14
and here's how the two pieces work together modern llms are trained to reason to think through steps
15
and decide on how to act when the model wants to use a tool, it outputs a tool call, essentially structured text saying run this,
16
and then the harness executes it.
17
Then the output of the actions gets placed into the model's prompt behind the scenes, and the model then reflects on how the tool call went, and the loop continues.
18
It thinks again on what to do, maybe calls a tool, and it goes on and on.
19
Note that LLMs have a limit to their working memory called the context window.
20
Your chat history, your prompt, files, all those tool outputs all go in to that context window
21
and eventually it fills up and the harness detects this and intelligently performs context compression.
22
So those are the two pieces of chatbot AI agents.
23
LLMs are the brain generating text and the harness is like the body.
24
It gives them the ability to actually take actions and make changes.
25
I hope this is helpful.
26
Please leave your questions in the comments and follow for more AI explainers.
✨ 推荐视频
关于本课
您正在使用跟读技巧通过视频"How does AI actually work?"练习英语口语和发音。
每天练习15到30分钟,将显著提高您的英语流利度和发音准确度。
什么是跟读法?
跟读法 (Shadowing) 是一种有科学依据的语言学习技巧,最初开发用于专业口译员的培训,并由多语言者Alexander Arguelles博士普及。这个方法简单而强大:您在听英语母语原声的同时立即大声重复——就像是一个延迟1-2秒紧跟说话者的影子。与被动听力或语法练习不同,跟读法强迫您的大脑和口腔肌肉同时处理并模仿真实的讲话模式。研究表明它能显着提高发音准确性,语调,节奏,连读,听力理解和口语流利度——使其成为雅思口语备考和真实英语交流最有效的方法之一。











