7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒

「7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒」（AI 工具讲解）字幕级无露脸大纲：钩子、结构时间轴、可核对事实与原创化提醒；参考 3 条上传者字幕。

角度

基于人工字幕定时节拍的选题大纲：7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒
人工字幕参考：VSFuqMh4hus、qYNweeDHiyU、Yq0QkCxoTHM
只复用定时节拍与可引用事实——旁白须原创；时间戳上屏

钩子

0:00–0:40: 用人工字幕里的真实节拍冷开场，承诺为「7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒」给出可执行的无露脸大纲：时间轴 + 带时间戳事实 + 原创化提醒。旁白须原创，禁止照抄参考片脚本。 VSFuqMh4hus@0:00 qYNweeDHiyU@0:00

结构时间轴展开收起

VSFuqMh4hus 0:00–1:06 — There are two things that hold true when it comes to artificial intelligence. My toothbrush just got an AI update this week.
VSFuqMh4hus 1:10–2:13 — Then they move on to act on the plan that it's built through the reasoning, and then observes the results of that action.
VSFuqMh4hus 2:15–3:19 — Now, the reasoning model is trained on problems with verifiably correct answers.
VSFuqMh4hus 3:21–4:24 — Well, a vector is essentially just kind of a a long list of numbers. And that long list of numbers captures the semantic meaning of the context.
VSFuqMh4hus 4:25–5:26 — Now vector databases, they play a big role in implementing number four. And that is RAG or retrieval augmented generation.
VSFuqMh4hus 5:30–6:31 — And then this RAG system is going to pull the relevant section from the employee handbook to include in the prompt.
Yq0QkCxoTHM 0:00–1:16 — if you don't have a technical background but you still want to learn the basics of artificial intelligence stick around because we are distilling Google's 4-Hour AI course for begi…
Yq0QkCxoTHM 1:18–2:33 — well now that we have an understanding of the overall landscape and you see how the different disciplines sit in relation to each other let's go over the key takeaways you should k…
Yq0QkCxoTHM 2:36–3:52 — against their income we see this group of employees have a relatively High income to years worked ratio versus this group we can also see all these are unlabeled data if they were …
Yq0QkCxoTHM 3:53–5:08 — neural networks we can now do something called semisupervised learning whereby a deep learning model is trained on a small amount of labeled data and a large amount of unlabeled da…

字幕可核对事实展开收起

字幕依据：And then this RAG system is going to pull the relevant section from the employee handbook to include in the prompt. Now, number five, that Model Context Protocol or MCP. This is a really exciting one because for large language models to be truly useful, they need to interact with external data sources and services and tools. VSFuqMh4hus@5:30
字幕依据：if you don't have a technical background but you still want to learn the basics of artificial intelligence stick around because we are distilling Google's 4-Hour AI course for beginners into just 10 minutes I was initially very skeptical because I thought the course would be too conceptual we're all about practical tips on this channel and knowing Google the course might just disappear after 1 hour but I found the underlying concepts actually made me better at using tools like ChatGPT and Google bard and cleared up a bunch of misconceptions I didn't know I had about AI machine learning and large language models so starting with the broadest possible question what is artificial intelligence it turns out and I'm so embarrassed to admit I didn't know this AI is an entire field of study like physics and machine learning is a subfield of AI much like how thermodynamics is a subfield of physics going down another level deep learning is a subset of machine learning and deep learning models can be further broken down into something called discriminative models and generative models large language models LLMs also fall under deep learning and right at the intersection between generative and LLMs is the technology that powers the applications we're all familiar with ChatGPT and Google bard let me know in the comments if this was news to you as Yq0QkCxoTHM@0:00
字幕依据：well now that we have an understanding of the overall landscape and you see how the different disciplines sit in relation to each other let's go over the key takeaways you should know for each level in a nutshell machine learning is a program that uses input data to train a model that trained model can then make predictions Based on data it has never seen before for example if you train a model based on Nike sales data you can then use that model to predict how well a new shoe from Adidas would sell based on Adidas sales data two of the most common types of machine learning models are supervised and unsupervised learning models the key difference between the two is supervised models use labeled data and unsupervised models use unlabeled data in this supervised example we have historical data points that plot the total bill amount at a restaurant against the tip amount and here the data is labeled Blue Dot equals the order was picked up and yellow dot equals the order was delivered using a supervised learning model we can now predict how much tip we can expect for the next order given the bill amount and whether it's picked up or delivered for unsupervised learning models we look at the raw data and see if a naturally falls into groups in this example we plotted the employee tenure at a company Yq0QkCxoTHM@1:18
字幕依据：against their income we see this group of employees have a relatively High income to years worked ratio versus this group we can also see all these are unlabeled data if they were labeled we would see male female years worked company function Etc we can now ask this unsupervised learning model to solve a problem like if a new employee joins are they on the FasTrack or not if they appear on the left then yes if they appear on the right then no Pro tip another big difference between the two models is that after a supervised learning model makes a prediction it will compare that prediction to the training data used to train that model and if there's a difference it tries to close that Gap unsupervised learning models do not do this by the way this video is not sponsored but it is supported by those of you who subscribe to my paid productivity newsletter on Google tips Link in the description if you want to learn more now we have a basic grasp of machine learning it's a good time to talk about deep learning which is just a type of machine learning that uses something called artificial neural networks don't worry all you have to know for now is that artificial neural networks are inspired by the human brain and looks something like this layers of nodes and neurons and the more layers there are the more powerful the model and because we have these Yq0QkCxoTHM@2:36
字幕依据：neural networks we can now do something called semisupervised learning whereby a deep learning model is trained on a small amount of labeled data and a large amount of unlabeled data for example a bank might use deep learning models to detect fraud the bank spends a bit of time to tag or label 5% of transactions as either fraudulent or not fraudulent and they leave the remaining 95% of transactions unlabeled because they don't have the time or resources to label every transaction the magic happens when the Deep learning model uses the 5% of label data to learn the basic concepts of the task okay these transactions are good these are bad okay apply those learnings to the remaining 95% of unlabeled data and using this new aggregate data set the model makes predictions for future transactions that's pretty cool and we're not done because deep learning can be divided into two types discriminative and generative models discriminative models learn from the relationship between labels of data points and only has the ability to classify those data points fraud not fraud for example you have a bunch of of pictures or data points you purposefully label some of them as cats and some of them as dogs a discriminative model will learn from the label cat or dog and if you submit a Yq0QkCxoTHM@3:53
字幕依据：picture of a dog it will predict the label for that new data point a dog we finally get to generative AI unlike discriminative models generative models learn about the patterns in the training data then after they receive some input for example a text prompt from us they generate something new based on the patterns they just learned going back to the animal example the pictures or data points are not labeled as cat or dog so a generative model will look for patterns oh these data points all have two ears four legs a tail likes dog food and Barks when asked to generate something called a dog the generative model generates a completely new image based on the patterns it just learned there's a super simple way to determine if something is generative AI or not if the output is a number a classification spam not spam or a probability it is not generative AI it is GenAI when the output is natural language text or a speech an image or audio basically generative AI generates new samples that are similar to the data it was trained on moving on to different generative AI model types most of us are familiar with text-to-text models like ChatGPT and Google bard other common model types include text-to-image models like Midjourney Yq0QkCxoTHM@5:11
字幕依据：DALL·E and stable diffusion these can not only generate images but edit images as well text-to-video models surprise surprise can generate and edit video footage examples include Google's imagen video CogVideo and the Very creatively named make a video text-to-3D models are used to create game assets and a little known example would be OpenAI's shap-e model and finally text to task models are trained to perform a specific task for example if you type @Gmail summarize my unread emails Google bard will look through your inbox and summarize your unread emails moving over to large language models don't forget that LLMs are also a subset of deep learning and although there is some overlap LLMs and GenAI are not the same thing an important distinction is that large language models are generally pre-trained with a very large set of data and then fine-tune for specific purposes what does that mean imagine you have a pet dog it can be pre-trained with basic commands like sit come down and stay it's a good boy and a generalist but if that same good boy goes on to become a police dog a guide dog or hunting dog they need to receive specific training so they're fine tuned for that specialist role a similar idea Yq0QkCxoTHM@6:29
字幕依据：But this has become a very important part and a very important advancement. That also reached some popularity during the 2010s. And as something that we use still today as the basis for our next area of AI. The most recent advancements in the field of artificial intelligence all really are in this space, the area of generative AI. qYNweeDHiyU@5:42

节拍 / 大纲

钩子（0:00–0:40）：冷开场点题「7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒」——讲清RAG系统如何从员工手册中提取相关内容并包含在提示中（旁白原创，勿照抄参考片）。
要点 1：讲清RAG系统如何从员工手册中提取相关内容并包含在提示中（VSFuqMh4hus@5:30）。
要点 2：演示MCP如何让大型语言模型与外部数据源和服务进行交互（Yq0QkCxoTHM@0:00）。
要点 3：讲清Google的4小时AI课程简化版（Yq0QkCxoTHM@1:18）。
要点 4：演示如何使用半监督学习让深度学习模型在少量标记数据和大量未标记数据中进行训练（Yq0QkCxoTHM@2:36）。
要点 5：讲清半监督学习的应用（Yq0QkCxoTHM@3:53）。
收尾：三条定时引用回顾卡 + 来源上屏。旁白须原创。

转场

冷开场后打标题卡点明「7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒」的承诺。
切换参考片时用下三分显示 video id + 时间戳，方便核对。
收尾前定格回顾卡，放入事实列表里 3 个可核对点。

收尾 / CTA

用回顾卡结束「7 个 AI 术语一张表：Agent / RAG / LLM / 微调——每条 60 秒」，列出 3 条定时引用；评论区征集下一子角度。旁白须原创——只复用节拍，不复用原片台词。

参考片对照

多参考时按「对题片段密度」分配时长，默认不要均分。
参考 VSFuqMh4hus：保留定时节拍，去掉广告/片尾求订阅。
参考 qYNweeDHiyU：保留定时节拍，去掉广告/片尾求订阅。
参考 Yq0QkCxoTHM：保留定时节拍，去掉广告/片尾求订阅。

原创化建议

TTS 旁白原创；画面下三分标注片名与时间戳作研究引用。
不要粘贴主持人梗、赞助口播或片尾固定 CTA。
优先使用带时间戳的具体事实，避免空泛的「专家说」。
时间轴/事实里没有的主张：删掉，或明确标成你的假说。

参照片

7 AI Terms You Need to Know: Agents, RAG, ASI & More VSFuqMh4hus
AI, Machine Learning, Deep Learning and Generative AI Explained qYNweeDHiyU
Google’s AI Course for Beginners (in 10 minutes)! Yq0QkCxoTHM

方法

yt-dlp VTT 人工字幕（上传者提供，非自动/ASR）→ 全文按 60–90 秒切段（超长视频关键词定位）→ 选题级编辑综合。仅结构参考；旁白须原创。