Picture by Writer
# Introduction
Increase your hand in the event you’ve ever frozen throughout a technical interview when the interviewer requested, “Stroll me by your method.” Most candidates learn the query, leap straight into code, and hope muscle reminiscence kicks in.
What in the event you may add an interview query into an AI device and get a podcast rationalization of your code, a visible thoughts map, flashcards, and a quiz? Effectively, you possibly can with NotebookLM.
On this article, we’ll first remedy Meta’s “Advice System” interview query ourselves, then use NotebookLM’s six options to know and study from it smarter, not tougher.
# Meet NotebookLM: Google’s AI-Powered Examine Assistant
NotebookLM is Google’s AI examine assistant. It transforms how we study from knowledge by combining a number of AI-powered options that make the method extra interactive and adaptive.
It does so by turning your paperwork, books, or another supplies into interactive studying instruments. Extra particularly, it turns your supplies into conversations, visible maps, and quizzes, and saves hours of handbook overview, making advanced matters simpler to digest.
This helps you perceive and retain data quicker. In brief, NotebookLM helps you study smarter, not tougher.
Let’s now remedy the Meta interview query, then discover how NotebookLM may help us study from that very same code.
# The Problem: Meta’s “Advice System” Interview Query
Advice System
You might be given the checklist of Fb associates and the checklist of Fb pages that customers observe. Your job is to create a brand new suggestion system for Fb. For every Fb person, discover pages that this person does not observe however no less than one among their associates does. Output the person ID and the ID of the web page that needs to be really useful to this person.
The query is on the market on StrataScratch. On this query, Meta requested us to construct a suggestion system that means Fb pages a person doesn’t observe but, however no less than one among their associates does.
// Understanding the Information Behind the Drawback
We now have two totally different datasets, user_friends and user_pages.
The primary one exhibits every person’s social connections (who’s associates with whom), whereas user_pages lists which pages every person already follows.
Collectively, they assist us discover new web page suggestions based mostly on mutual associates’ exercise.
Let’s preview the user_friends dataset first.
| user_id | friend_id |
|---|---|
| 1 | 2 |
| 1 | 4 |
| 1 | 5 |
| 2 | 1 |
| 2 | 3 |
Let’s preview the second dataset now, user_pages:
| user_id | page_id |
|---|---|
| 1 | 21 |
| 1 | 25 |
| 2 | 25 |
| 2 | 23 |
| 2 | 24 |
// Step-by-Step Resolution: Constructing the Advice Engine
The purpose is to advocate Fb pages {that a} person hasn’t adopted but, however that no less than one among their associates already follows.
First, we join every person with the pages their associates observe. This helps us see which pages are adopted by the person’s community and potential suggestions.
friends_pages = users_friends.merge(users_pages, left_on='friend_id', right_on='user_id')
friends_pages = friends_pages[['user_id_x', 'page_id']]
Now we have to exclude pages that customers already observe. We do that by merging once more with the unique users_pages desk and conserving solely the pages that aren’t already within the person’s checklist.
comparability = friends_pages.merge(
users_pages,
how='left',
left_on=['user_id_x', 'page_id'],
right_on=['user_id', 'page_id']
)
consequence = comparability[comparison['user_id'].isna()][['user_id_x', 'page_id']]
Lastly, we take away any duplicates to keep away from recommending the identical web page a number of instances and rename the column for readability.
consequence = consequence.drop_duplicates()
consequence = consequence.rename(columns={'user_id_x': 'user_id'})
Listed here are the primary few rows of anticipated output.
| user_id | page_id |
|---|---|
| 1 | 23 |
| 1 | 24 |
| 1 | 28 |
| 3 | 23 |
| 3 | 28 |
Up up to now, we’ve relied on conventional methods: coding, merging, and decoding every little thing ourselves.
Now, Google’s NotebookLM permits us to take the educational course of a step additional.
# From Fixing to Studying: Enter NotebookLM
On this part, we’ll present easy methods to present NotebookLM with the small print of the Meta interview query, then discover its six interactive options that provide help to study smarter.
// Step 1: Making a New Pocket book and Including Your Information
Earlier than NotebookLM can help us, we have to present it with details about our interview query. This begins by creating a brand new pocket book. Head to the NotebookLM web site and click on “Create a brand new pocket book.”
It should ask you for the supply.
As you possibly can see within the screenshot beneath, totally different choices can be found.
- Google Drive
- Web site
- Youtube
- Paste textual content
Let’s use the “Paste textual content” choice and paste the metadata of the Meta’s interview query. Right here is the data we’ll insert utilizing this reusable format.
Right here is the query.
[paste question here]
It makes use of two datasets.
[paste dataset information here]
Right here is the python answer.
[paste python solution here.]
Subsequent, click on on “Insert”, proven beneath.
// Exploring the Interactive Studying Studio
Beneath is the display that opens after we hit “Insert.” On the left, we will see the sources. Within the center, we’ve an LLM that was educated on our knowledge. On the fitting, we’ve a “Studio” containing six totally different studying codecs, which we’ll check one after the other.
Let’s click on on “How does the Python answer leverage current pal and web page knowledge for suggestions” button, which is underneath the enter textual content within the center. This query was generated by NotebookLM.
Right here is the reply.
As you possibly can see, it explains your entire idea. You may as well save this word by clicking “Save word” on the finish. The notes will then seem underneath the “Studio” part like this.
So, in case you have any questions associated to this interview query, you should use the LLM in the midst of the earlier display to get a solution. Let’s discover the “Studio” six options that make issues extra attention-grabbing.
// Experiencing NotebookLM’s Six Studying Options
On this part, we’ll see NotebookLM’s six studying options, proven beneath, in motion.
Every one helps you perceive the Meta interview query from a unique angle — by audio, video, visuals, and interactive follow.
1. Generate an Audio Overview
Click on “Audio Overview.”
If you do this, you’ll see this notification underneath “Studio,” and your audio overview will likely be prepared in a few minutes.
NotebookLM turns your uploaded content material right into a podcast-style dialog. Two AI voices talk about your downside such as you’re listening to a tech interview prep present. They break down Meta’s suggestion system, clarify the logic, and spotlight edge circumstances.
You’ll be able to obtain this dialog, and curiously, you can even be a part of it by clicking on “Interactive.” The display beneath will then open.
And while you click on on be a part of, the message will say “Hey, somebody needs to hitch,” permitting you to hitch the dialog. (Sure, you possibly can actually be a part of the dialog; it’s up to date in real-time by a text-to-speech API. A extremely futuristic function!)
2. Generate the Video Breakdown
Return to the “Studio” panel and hit “Video Overview.” NotebookLM creates a video that visualizes your knowledge and explains the answer. In our case, the video is 6 minutes and 21 seconds lengthy.
Within the generated video, NotebookLM first explains the broader idea: how social media platforms determine what to advocate, earlier than transferring into our particular downside.
Subsequent, the generated video discusses the interview downside by breaking it down into elements, beginning with this key step proven beneath.
Subsequent, it begins explaining the answer. It doesn’t simply repeat what’s on the display; the reasons go deep into the idea.
And eventually, it breaks down the answer into steps and explains it utilizing these steps.
3. Map the Logic Visually
Flip again to the “Studio” panel and click on the “Thoughts Map.”
NotebookLM generates a visible tree of the issue. Let’s see one.
You see your entire downside construction in a single view: suggestion purpose on the prime, required datasets within the center, and answer steps on the backside. Let’s click on on one among them, for instance, “Step 1: Determine Buddies’ Pages ( Merge 1).”
As you possibly can see, the thoughts map expands by explaining step 1. You’ll be able to obtain it, too.
4. Construct Reviews
Flip again to the Studio panel and click on “Reviews.” NotebookLM asks you to pick which sort of report you wish to create.
Let’s choose an issue walkthrough. It should begin producing a report.
Right here is the step-by-step walkthrough that explains easy methods to remedy this interview query.
5. Generate Flashcards
Flip again to the “Studio” panel and click on “Flashcards.” NotebookLM auto-generates Q&A playing cards. Let’s see one among them.
And while you click on on the reply, right here is the consequence.
Let’s click on on “Clarify.” It makes use of a immediate to reply this query with Gemini fashions.
Now let’s see the outcomes.
6. Create a Quiz
Flip again to the Studio panel and click on on the Quiz. NotebookLM generates a follow check. Let’s do it and see the primary quiz.
Let’s click on on “Trace.”
The reply is now apparent. So, let’s choose it and see what occurs.
For those who nonetheless have a query, click on on “Clarify.” It takes you to the center part, the place the LLM educated on our answer supplies the reply. Right here it’s.
# Conclusion
Prepping for technical interviews does not imply grinding interview issues in isolation. It means understanding deeply, visualizing clearly, and explaining confidently. NotebookLM turns a single interview query right into a multi-sensory studying expertise, together with audio, video, visible maps, written studies, and energetic recall.
You have already got the problem-solving abilities. Now you have got a system to arrange them, reinforce them, and current them underneath stress. Subsequent time you see a tricky SQL or Python query, do not panic; add it, discover it, and grasp it.
Nate Rosidi is a knowledge scientist and in product technique. He is additionally an adjunct professor instructing analytics, and is the founding father of StrataScratch, a platform serving to knowledge scientists put together for his or her interviews with actual interview questions from prime corporations. Nate writes on the newest developments within the profession market, offers interview recommendation, shares knowledge science initiatives, and covers every little thing SQL.
