Deepika

97 posts

Deepika banner
Deepika

Deepika

@Deepika_0803

Learning AI & ML LLM | NLP | ML Fundamentals Building real projects with FastAPI Hashnode Blogger ✍️

انضم Ekim 2025
23 يتبع7 المتابعون
تغريدة مثبتة
Deepika
Deepika@Deepika_0803·
Hey! I'm Deepika 👋 Recent CSE graduate learning AI/ML in public. Currently exploring NLP, sharing my learnings on Hashnode, and building real-world projects. Let's connect and learn together! #NLP #MachineLearning
English
4
0
3
211
Deepika
Deepika@Deepika_0803·
Small win today: understood LangGraph persistence It’s basically state save + restore Which explains how chats magically resume Also did EDA on a dataset… Every month has all 4 seasons Real world data = creative writing? Or is this normal?
English
0
0
1
5
Deepika
Deepika@Deepika_0803·
LangGraph is making agents feel less like code, more like systems. Built a small chatbot today Then went dataset hunting for XGBoost Funny part? Finding the right dataset > building the model Lowkey want a “describe → get datasets” tool
English
0
0
0
6
Deepika
Deepika@Deepika_0803·
Got a Prompt Engineer interview tomorrow. Rounds include English test, aptitude, coding, GD… but nothing that evaluates prompting. Offer: 3 LPA + 2-year bond. Still attending though. Interviews are just another dataset for learning.
English
0
0
1
6
Deepika
Deepika@Deepika_0803·
Today I learned XGBoost. Gradient Boosting but with: ⚡ speed 📉 regularization 🧠 smart optimizations Ran a small regression example. Tomorrow: real dataset. Starting to understand why everyone in ML interviews keeps asking about this. Respect to Tianqi Chen
English
0
0
0
21
Deepika
Deepika@Deepika_0803·
Tried running Aden Hive today. Mistake #1: didn’t read the docs. Mistake #2: assumed it would “just work”. Eventually got it running on bash… but it quietly switched to an Anthropic model instead of the one I configured. AI agents are autonomous… apparently configs are too.
English
0
0
0
27
Deepika
Deepika@Deepika_0803·
Learned Gradient Boosting for classification today. Same story as regression… just a different loss function. Also discovered ML involves more formulas than my memory likes. Took a break and tried some random photography too.
Deepika tweet media
English
0
0
0
14
Deepika
Deepika@Deepika_0803·
Today I studied the math behind Gradient Boosting. First 10 minutes: “This is easy.” Then came additive modeling… Then gradients… Now I’m confused but also curious. I guess solving problems is the only way forward. How did you guys actually learn this?
English
0
0
2
11
Deepika
Deepika@Deepika_0803·
Spent today learning Random Forest. Thought it was a completely different algorithm… turns out it’s just many decision trees trained on random data. My Sunday ended with a realization (I’m dramatic). How’s yours?
English
0
0
0
10
Deepika
Deepika@Deepika_0803·
Took an AI hiring challenge. Job title: AI Engineer Questions: • ML • NLP • Coding LLMs, agents, RAG… nowhere to be found. At this point I’m convinced AI interviews are just ML interviews in disguise.
English
0
0
2
36
Deepika
Deepika@Deepika_0803·
For people running AI agencies: How do you figure out which companies might actually need your solution? Manual research? Signals you watch? Just experience? Trying to learn how agencies identify potential clients.
English
0
0
1
163
Deepika
Deepika@Deepika_0803·
Building in AI feels strange sometimes. There’s always something new: new models new frameworks new terms Today I didn’t build anything. Just thinking, learning, processing. Tomorrow we build again.
English
0
0
1
6
Deepika
Deepika@Deepika_0803·
Today: built a LangGraph agent with self-evaluation. Also today: discovered 5 new LLMs, 3 renamed ones, and 2 “state-of-the-art” replacements. Building agents is easier than tracking model names.
English
0
0
1
16
Deepika
Deepika@Deepika_0803·
Worked on parallel workflows in LangGraph + built an IELTS Task 2 evaluator. Still haven’t locked in my March goals. Moving forward, figuring it out as I go.
English
0
0
0
12
Deepika
Deepika@Deepika_0803·
February so far: 2 projects done. Sentiment analysis, and a full employee attrition pipeline(EDA -> Deployment). Learned a lot, had fun, and honestly… it felt more like solving a mystery than coding ML.
English
0
0
0
6
Deepika
Deepika@Deepika_0803·
Spent the day connecting FastAPI backend to a Gradio frontend for my attrition model. Prediction + probability + SHAP explanations working end-to-end. Feels good to see it live.
Deepika tweet media
English
0
0
0
15
Deepika
Deepika@Deepika_0803·
ML + SHAP = magic✨ My attrition model now tells not just who leaves, but why. App’s backend & frontend are next. What did you work on today?
English
0
0
1
38
Deepika
Deepika@Deepika_0803·
@matthewncollins True. And just like TCP/IP, most people use it without understanding how powerful it actually is.
English
0
0
0
13
Matthew Collins
Matthew Collins@matthewncollins·
Prompts are today’s tcp/ip packets
English
1
0
1
96
Deepika
Deepika@Deepika_0803·
Big realization today: Sklearn can build the model. But only you can understand the data. Spent more time on EDA → got better results. ML isn’t model-first. It’s data-first.
English
0
0
1
8
Deepika
Deepika@Deepika_0803·
@0xAl3x_ Cool, I’m excited to see your mentor chatbot too.
English
0
0
1
16