AI Can Teach You More Than Most Classrooms – Here’s the Proof

Author: Deep Mistry | June 2025

Table of Contents

• Introduction
• AI vs Traditional Classrooms
• Top AI Tools That Teach Better
• Real-World Proof & Stats
• Case Study: Exam Prep with AI
• Conclusion

Introduction

Can AI replace a teacher? Maybe not fully. But can it teach you more effectively than most traditional classrooms? Absolutely — and we have the proof. With tools like ChatGPT, Khan Academy AI, Duolingo Max, ScribeSense, and more, learning has become smarter, faster, and more personalized than ever.

AI vs Traditional Classrooms: A Quick Comparison

Feature	AI-Powered Learning	Traditional Classroom
Availability	24/7 access	Limited to school hours
Learning Pace	Fully personalized & adaptive	One-size-fits-all
Feedback Speed	Instant and ongoing	Delayed (daily/weekly)
Cost	Mostly free or low-cost	Tuition, infrastructure, etc.
Data-Driven Insights	Yes – personalized reports	No or very limited

Top AI Tools That Teach Better Than Many Tutors

• ChatGPT (OpenAI): Use it to explain complex concepts, solve math problems, write essays, and simulate mock interviews.
• Duolingo Max: AI-based language learning with real-time corrections and speaking practice.
• Khanmigo: An AI tutor developed by Khan Academy to coach students and provide instant feedback.
• Socratic by Google: Take a picture of a problem, and it explains the answer step-by-step using AI.
• Quillionz: AI tool to generate quizzes and flashcards for revision.

Most of these tools are mobile-friendly and free to use!

Real-World Proof & Stats

• 91% of students using AI tutors (ChatGPT, Khanmigo) reported faster understanding of difficult subjects.
• 40% improvement in self-paced exam scores (Study: EdTech Review 2024).
• Rural students in India improved English proficiency by 30% after using Socratic + Duolingo for 3 months.
• AI-based mock interview prep led to a 50% higher job interview success rate in a career bootcamp study.

Case Study: From 52% to 78% in 60 Days with AI

Student: A Class 12 student in Gujarat struggled with Physics.
Old Method: Tuition + Notes (average: 52%)
New Strategy: Combined ChatGPT for concept explanation, YouTube AI tutors, and daily quizzes from Quillionz
Result: Jumped to 78% in final school assessment.

Quote: “I could ask dumb questions to ChatGPT anytime. It didn’t judge me, and that built my confidence.”

Conclusion

Classrooms aren’t obsolete. But most of them can’t keep up with AI’s speed, personalization, and 24/7 support. Whether you're preparing for board exams, mastering a new skill, or upskilling for a job — AI is your ultimate teacher.

The smartest learners in 2025 are those who blend traditional education with AI tools. Are you one of them?

© 2025 Study From Here. Written by Deep Mistry.

GitHub CI/CD Observability with OpenTelemetry

Author: Deep Mistry | June 2025

Table of Contents

• Introduction
• Why Observability in CI/CD?
• What is OpenTelemetry?
• Setting Up OpenTelemetry in GitHub Actions
• Sample GitHub Workflow with Telemetry
• Benefits of CI/CD Observability
• Conclusion

Introduction

CI/CD pipelines are the backbone of modern DevOps workflows. However, they often lack robust observability features. In this blog, we’ll explore how to enhance your GitHub Actions workflows with observability using OpenTelemetry – a powerful open-source telemetry framework.

Why Observability in CI/CD?

Observability isn't just for apps in production. Your CI/CD pipeline can:

• Expose bottlenecks during builds
• Help debug flaky tests
• Detect failures early
• Provide insight into workflow duration and parallel steps

What is OpenTelemetry?

OpenTelemetry is a unified framework for collecting traces, metrics, and logs from your applications. It supports multiple languages and can be integrated with various backends like Prometheus, Grafana, Jaeger, or New Relic.

Setting Up OpenTelemetry in GitHub Actions

GitHub Actions allow custom scripts and Docker-based containers. You can instrument steps in the workflow using OpenTelemetry's CLI or SDKs. You’ll need:

• Access to an OpenTelemetry Collector endpoint
• Set environment variables like OTEL_EXPORTER_OTLP_ENDPOINT
• Use an OpenTelemetry-compatible logger or CLI in your job steps

Sample GitHub Workflow with Telemetry

Here’s a sample GitHub Actions workflow using a telemetry wrapper script:

name: CI Build with Observability

on: [push]

jobs:
  build:
    runs-on: ubuntu-latest
    env:
      OTEL_EXPORTER_OTLP_ENDPOINT: "https://otel-collector.yourdomain.com:4317"
      OTEL_SERVICE_NAME: "ci-build"

    steps:
      - name: Checkout code
        uses: actions/checkout@v3

      - name: Set up Node.js
        uses: actions/setup-node@v4
        with:
          node-version: 18

      - name: Install Dependencies
        run: |
          npm install

      - name: Run Tests with Tracing
        run: |
          npx otel-cli exec -- npm test

This setup sends trace data to your OpenTelemetry collector.

Benefits of CI/CD Observability

• See how long each job/step takes
• Detect slow builds or retries early
• Log test failures with trace context
• Monitor changes in build patterns across branches or PRs

Conclusion

Integrating OpenTelemetry into your GitHub Actions workflows can drastically improve your CI/CD insights. As you scale teams or microservices, having observability at the pipeline level becomes essential for debugging and optimization.

Try it in your next project and move one step closer to full-stack observability!

Have questions or want to share your setup? Leave a comment below or connect with me on LinkedIn.

© 2025 Study From Here. Written by Deep Mistry.

Self-study Plan For Electrical Engineering

Why Now?

Brain-computer interfaces (BCIs) have been a fascination of mine for years, and with recent breakthroughs in non-invasive neural decoding, miniaturized implants, and AI-driven signal processing, 2025 feels like the right time to get serious. Last summer, I decided to stop passively reading about BCIs and start actively preparing to contribute to the field.

So far, I’ve deep-dived into foundational neuroscience through Fundamental Neuroscience, The Hippocampus, and various review papers. That gave me enough grounding to parse contemporary journal articles, which I now regularly read to stay current with the research.

Where I’m lacking is on the engineering side. I earned an applied math degree and then spent 13 years in industry—first as a quant at a hedge fund, then as a software developer and eventually a technical lead. In that time, I never touched electrical engineering, embedded systems, or hardware design. And now I want to fill that gap.

This personal curriculum is my roadmap for doing exactly that.

---

The 2025 Approach

Over the next 12–24 months, I’m taking a hybrid approach:

1. Self-study through textbooks based on a modern Electrical and Computer Engineering (ECE) curriculum—loosely inspired by the University of Waterloo’s 2025 undergraduate track.

2. Hands-on projects that reinforce theory with real-world experimentation.

3. Community learning, ideally via a small, focused study group of people interested in BCIs, neurotech, or hardware for healthtech. If that sounds like you, please reach out—collaboration will make this more effective and more fun.

---

Key Concerns

1. Missing Unknowns

I’m sure there are blind spots I’m not even aware of—especially in areas like biocompatibility, implantable power systems, or advanced signal acquisition. If you work on ultra-low-power, implantable medical devices, I’d love to talk.

2. Transitioning to Application

Once I’ve built this foundation, what’s next? I don’t yet have a concrete path into BCI work—whether academic, startup, or industry—but I'm hoping the network I build along the way helps guide that step.

---

📘 Phase 1: Core Hardware Foundations (2025)

🔧 Projects

• Breadboard a digital clock (or a neuromorphic variant?)

• Explore simple signal amplification from a bioelectric source (e.g. EMG)

📚 Study Plan

• Electricity & Magnetism
  Textbook: Electricity and Magnetism by Purcell

• Digital Circuits & Systems
  Textbook: Digital Design and Computer Architecture – Harris & Harris 

• Linear Circuits
  Textbook: The Art of Electronics – Horowitz & Hill 

• Electronic Circuits
  Textbooks:

  • Microelectronic Circuits – Sedra & Smith

  • Microelectronics – B. Razavi 

• Materials Chemistry for Engineers
  Textbook: Chemistry: Molecular Nature of Matter and Change – Silberberg

• Signals & Systems
  Textbook options:

  • Signals and Systems – Oppenheim & Willsky

  • Linear Systems and Signals – B.P. Lathi

✅ Already Covered

• Math fundamentals (calculus, linear algebra, probability, transforms)

• Software development & system design (>10 years of experience)

---

⚙️ Phase 2: Intermediate Systems & Applications

🔧 Projects

• Build a basic analog/digital radio

• FPGA-based signal processing prototype

• Real-time embedded system for biosignal acquisition (e.g. heart rate monitor)

📚 Study Plan

• Embedded Microprocessor Systems
  Textbook: TBD

• Digital Hardware Systems
  Textbook: TBD

• Communication Systems I
  Textbook: Intro to Analog & Digital Communications – Haykin & Moher

• Control Systems
  Textbooks:

  • Feedback Control of Dynamic Systems – Franklin et al.

  • Feedback Systems – Åström & Murray

• Information Theory
  Refresher only

• Digital Signal Processing (DSP)
  Textbook: Foundations of Signal Processing – Vetterli et al.

• Electronic Devices
  Textbook: Semiconductor Physics and Devices – Neamen

• Microwave & RF Circuits
  Textbook: Fundamentals of Microwave and RF Design – Michael Steer

---

🚀 Phase 3: Advanced Topics & Electives

💬 Checkpoint

Before diving into this phase, I’ll be actively seeking advice from people working in neural interfaces and medical-grade electronics to validate whether I’m missing any vital topics or practical know-how.

🔧 Projects

• TBD (likely something in closed-loop neural stimulation or wireless data transfer from an implant)

📚 Study Plan

• Communication Systems II
  Textbook: Communication Systems – John Proakis

• Wireless Communications
  Textbook: Wireless Communications and Networking – Mark & Zhuang

• Micro/Nano Fabrication
  Textbook: Micro and Nano Fabrication Technology – Yan

• Integrated Analog Electronics
  Textbook: Analog CMOS Integrated Circuits – Razavi

• Integrated Digital Electronics
  Textbook: Digital Integrated Circuits – Rabaey et al.

• Radio Wave Systems
  Textbook: TBD

• Digital Control Systems
  Textbook: TBD

• RF Integrated Devices and Circuits
  Textbook: TBD

• Geometrical & Physical Optics
  Textbook: TBD

---

Final Thoughts

This is a living plan, subject to iteration as I learn more and talk to people in the field. If you're also exploring BCIs or neurotech in 2025—whether as a hobbyist, researcher, or entrepreneur—I’d genuinely love to hear from you. Let's build something together.

Self-Studying the MIT Applied Math Curriculum

A Deep Dive into Applied Math – The Self-Taught Way

This summer, I’ve committed to an intellectually ambitious (and deeply personal) project: independently completing the MIT Applied Math Curriculum. I’ll be auditing classes (in person and online), connecting with professors and mentors, and tackling the OpenCourseWare (OCW) assignments and exams wherever available.

In this post, I’ll outline the motivations behind this journey, share a bit about my academic and research background, and lay out the specific plan I’m following. If you're mainly interested in the course list, feel free to skip down to The Plan.

 

Why Take on the MIT Applied Math Curriculum in 2025?

Currently, I’m a dual Master’s student at Harvard and Georgia Tech, specializing in Machine Learning and Computational Biology. I also serve as a research assistant across several labs, where I work at the intersection of Applied Math, Theoretical Neuroscience, and Deep Learning. My previous experience includes co-founding an ML startup. This fall, I’m preparing to apply to PhD programs focused on AI and mathematical biology.

My journey here hasn’t been linear. I originally studied Biology and Cognitive Science at UC San Diego, and my early internships leaned toward Product Management. Along the way, I taught myself to code—initially for web and mobile development—and gradually became captivated by the parallels between information processing in computers and biology. That fascination, particularly with neural networks, led me into graduate programs in CS and Biology, where I began conducting ML research and independently learning the mathematical foundations necessary to interpret cutting-edge papers.

 

As I progressed, something unexpected happened—I fell in love with math itself. Although foundational topics like Linear Algebra, Probability, and Vector Calculus are often sufficient for ML, I’ve noticed that the most innovative thinkers around me draw upon a much broader and deeper mathematical toolkit. They’re able to tap into concepts from PDEs, Dynamical Systems, Numerical Methods, and Optimization Theory, and apply those ideas in novel ways.

After speaking with mentors, including professors and graduate students from Harvard and MIT, the consensus was clear: if I want to push the boundaries of my research and sharpen my mathematical intuition, pursuing a rigorous curriculum like MIT’s Applied Math track is an excellent foundation.

I've been fortunate to gain access to audit select courses, both online and in person, and this self-directed program is my way of organizing, committing to, and sharing that experience. Hopefully, others interested in ML, bioinformatics, or computational theory might find this roadmap helpful too.

The Plan: Courses I’ll Be Studying

MIT’s Applied Math curriculum is thoughtfully designed, blending mathematical theory with real-world applications. I’ve selected a sample path based on the 2024–2025 course listings, emphasizing courses available via MIT OCW, edX, and other open resources, supplemented with similar material at Harvard, Georgia Tech, and nearby institutions.

 

✅ Core Courses (Foundation Building)

• 18.03: Differential Equations

• 18.06: Linear Algebra

• 18.100B: Real Analysis

• 18.330: Introduction to Numerical Analysis

• 18.600: Probability and Random Variables

• 18.700: Linear Algebra (Theoretical)

🧠 Restricted Electives (Applied Focus)

• 18.303: Linear Partial Differential Equations

• 18.330: Numerical Methods for PDEs

• 18.404: Theory of Computation

• 6.041A/B: Probabilistic Systems Analysis

• 6.036: Introduction to Machine Learning (MIT AI curriculum)

• 18.650: Statistics for Applications

   

🔄 Electives and Supplementary Topics

• Optimization Theory (18.335 or equivalent)

• Stochastic Processes

• Information Theory

• Dynamical Systems

• Mathematical Biology (as applicable to my research)

What Comes Next?

I don’t plan to rigidly confine this journey to a summer timeline. While I’ll be actively involved in summer research and class auditing, this project will evolve organically throughout the year. My goal isn’t just to tick off course boxes, but to deeply internalize the material—to make the math intuitive, applicable, and generative for future work.

I’ll be posting updates, study notes, problem solutions, and reflections here periodically. Ideally, this process will lead to:

• More elegant and powerful approaches to ML modeling

• Cross-disciplinary research ideas

• New ways to think about problems in neuroscience and biology

And who knows—once I’ve finished Applied Math, maybe I’ll give the Pure Math curriculum a shot next!

 

Follow Along If you're curious, want to join the ride, or have resources to suggest—drop a comment or connect. I’m excited to see where this self-studying journey leads!