シャドーイング練習: How does AI actually work? - 動画で英語スピーキングを学ぶ

I'm confident that this may be the most important video you'll see in a while.

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.

I'm a Stanford -trained computer scientist for AI who's been building AI systems for over a decade.

I'm teaming up with Anthropic, the team behind Claude, for a series, and today we're looking under the hood.

AI agents are made up of two parts, the large language model, LLM, and the hardest this.

In this video, we discussed the word generating LLMs, and today we'll discuss the agent harness.

So we have the word generator, the core brain, i .e whatever version of sonnet, opus, fable you select when using Claude.

And then we have the harness, which is all of the code that enables that word generator to take actions.

So remember from the last video that everything the model knows about you is just added info into its prompt.

The harness is what manages

that memory your history your files your context it also gives the model access to external tools like gmail

or canva and handles sub -agent orchestration

which is delegating tasks to other agent instances sometimes in parallel

and here's how the two pieces work together modern llms are trained to reason to think through steps

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,

and then the harness executes it.

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.

It thinks again on what to do, maybe calls a tool, and it goes on and on.

Note that LLMs have a limit to their working memory called the context window.

Your chat history, your prompt, files, all those tool outputs all go in to that context window

and eventually it fills up and the harness detects this and intelligently performs context compression.

So those are the two pieces of chatbot AI agents.

LLMs are the brain generating text and the harness is like the body.

It gives them the ability to actually take actions and make changes.

I hope this is helpful.

Please leave your questions in the comments and follow for more AI explainers.

✨ おすすめ動画

55 文

When AIs act emotional

University StudentsBusiness English+1

309 文

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

University StudentsBusiness English+1

126 文

How I use AI as a senior software engineer and 5 principles of AI explained in 10 minutes

University StudentsBusiness English+1

175 文

Amazon Bedrock Tutorial | Getting Started with Amazon Bedrock | AI Model Access & Testing

University StudentsBusiness English+1

シャドーイングとは？英語上達に効果的な理由

シャドーイング（Shadowing）は、もともとプロの通訳者養成プログラムで開発された言語学習法で、多言語習得者として知られるDr. Alexander Arguelles によって広く普及されました。方法はシンプルですが非常に効果的：ネイティブスピーカーの英語を聞きながら、1〜2秒の遅延で声に出してすぐに繰り返す——まるで「影（shadow）」のように話者を追いかけます。文法ドリルや受動的なリスニングと異なり、シャドーイングは脳と口の筋肉が同時にリアルタイムで英語を処理・再現することを強制します。研究により、発音精度、抑揚、リズム、連音、リスニング力、そして会話の流暢さが大幅に向上することが確認されています。IELTSスピーキング対策や自然な英語コミュニケーションを目指す方に特におすすめです。

シャドーイングのやり方: ステップ別の完全ガイドを読む →

シャドーイング練習: How does AI actually work? - 動画で英語スピーキングを学ぶ

When AIs act emotional

Claude Code: The Advanced Guide (99% of Devs Skip These Features)

How I use AI as a senior software engineer and 5 principles of AI explained in 10 minutes

What is a PLC and how does it work?

We Let $200 GPT-Pro Think for 7 Days on Unsolved Math

Introduction to statistical prediction models

What is an AI Token? | LLM Tokens explained in 2 minutes!

LangChain in 5 Minutes (Explained Clearly)

15 Minutes to Fix Your AI Dev Workflow with OpenCode

Supervised Learning: Crash Course AI #2

AI Just Crossed the Terrifying Line - Now What?

Amazon Bedrock Tutorial | Getting Started with Amazon Bedrock | AI Model Access & Testing

このレッスンについて

シャドーイングとは？英語上達に効果的な理由