Shadowing Practice: How does AI actually work? - Learn English Speaking with Video

בחר מצב תרגול

כל מצב פותח חדר תרגול במסך מלא.

26 משפטים

אם המשפטים קצרים או ארוכים מדי, לחץ על ערוך כדי להתאים אותם.

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.

הורד אפליקציה

כל מה שאתה צריך כדי לדבר בשטף

הגיית AIציון לכל משפט

תרגול IPAשלוט בכל צליל

אוצר מיליםבנה את מאגר המילים שלך

משחק אוצר מיליםלמד תוך כדי משחק

סרוק QR

Download on theApp Store Get it onGoogle Play

FOR YOU

המלץ על סרטון

55 משפטים

Vocabulary and speaking notes for this lesson

This video has 26 sentences and 409 words to shadow. The speech runs for 2:17. The speaker talks at a natural 179 words per minute, close to everyday conversation. Only 80% of the words are among the 3,000 most common in English, so the vocabulary is demanding.

Key vocabulary in this video

15 words from the video worth learning, with pronunciation and meaning:

Word	Pronunciation	Meaning
harness verb	/ˈhɑɹ.nəs/	To place a harness on something; to tie up or restrain.
output noun	/ˈaʊtpʊt/	Production; quantity produced, created, or completed.
prompt verb	/pɹɑmpt/	To lead (someone) toward what they should say or do.
generate verb	/ˈd͡ʒɛn.ə.ɹeɪt/	To bring into being; give rise to.
generator noun	/ˈdʒɛnəɹeɪtə(ɹ)/	An apparatus in which vapour or gas is formed from a liquid or solid by means of heat or chemical process, as a steam boiler, gas retort etc.
select verb	/sɪˈlɛkt/	To choose one or more elements of a set, especially a set of options.
helpful adjective	/ˈhɛlp.fl̩/	Furnishing help; giving aid; useful.
essentially adverb	/ɪˈsɛnʃəli/	In essence: by nature.
reflect verb	/ɹɪˈflɛkt/	To bend back (light, etc.) from a surface.
enable verb	/ɪˈneɪ.bəl/	To make somebody able (to do, or to be, something); to give sufficient ability or power to do or to be; to give strength or ability to.
loop noun	/luːp/	A length of thread, line or rope that is doubled over to make an opening.
parallel adjective	/ˈpæ.ɹəˌlɛl/	Equally distant from one another at all points.
scientist noun	/ˈsaɪəntəst/	One whose activities make use of the scientific method to answer questions regarding the measurable universe. A scientist may be involved in original research…
inform verb	/ɪnˈfɔɹm/	To communicate knowledge to.
detect verb	/dɪˈtɛkt/	To discover or find by careful search, examination, or probing.

Phrasal verbs you will hear

Word	Meaning
fill up verb	To make (something) completely full.
team up with verb	To associate with another in a joint enterprise.
think through verb	To fully consider, so as to understand all the consequences of.
work together verb	To be coworkers with someone; to share a workspace with someone.

Pronunciation to watch

The speaker uses 6 contractions and reduced forms, such as I'm, we'll, we're. Say them the short way, as you hear them.

The “sh” and “zh” sounds: essentially /ɪˈsɛnʃəli/, compression /kəmˈpɹɛʃ.ən/
Long words — get the stress right: generator /ˈdʒɛnəɹeɪtə(ɹ)/, essentially /ɪˈsɛnʃəli/

How to practise with this video

Listen to the whole video once without speaking and note the words you do not know.
Start at 0.75× speed, shadow it sentence by sentence, then go back to normal speed once it feels easy.
Record yourself and compare with the original, paying attention to words like harness, output, prompt.

מהי טכניקת השאדואינג?

שאדואינג היא טכניקת למידת שפה מבוססת מדע שפותחה במקור להכשרת מתורגמנים מקצועיים ופופולרית על ידי הפוליגלוט ד"ר אלכסנדר ארגואלס. השיטה פשוטה אך עוצמתית: אתה מקשיב לאודיו באנגלית ילידית וחוזר עליו בקול רם מיד — כמו צל העוקב אחרי הדובר עם עיכוב של 1–2 שניות בלבד. בניגוד להאזנה פסיבית או תרגילי דקדוק, שאדואינג מכריח את המוח והשרירים בפה לעבד ולשחזר דפוסי דיבור אמיתיים בו זמנית. מחקרים מראים שזה משפר משמעותית את דיוק ההגייה, האינטונציה, הקצב, הדיבור המחובר, הבנת השמיעה ושטף הדיבור — מה שהופך אותו לאחת השיטות היעילות ביותר להכנה לIELTS Speaking ולתקשורת באנגלית בעולם האמיתי.

טכניקת Shadowing: קרא את המדריך המלא שלב אחר שלב →

Shadowing Practice: How does AI actually work? - Learn English Speaking with Video

בחר מצב תרגול

הורד אפליקציה

When AIs act emotional

LangChain in 5 Minutes (Explained Clearly)

900+ hours of Learning AI Agents in 9 Minutes

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

AI, Machine Learning, Deep Learning and Generative AI Explained

9 Insane Claude Mods I Already Can't live Without

Jack Dorsey’s New Dessa AI Voice Sounds Scary Human

Why the Arab World never united

Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production

What is a PLC and how does it work?

Dear Higgsfield, I reverse engineered you in 12 hours

Why AI Tokens are so Expensive - Computerphile