Blog

The Blind Spot Horizon: Why Your AI Benchmarks Are Lying to You featured image

The Blind Spot Horizon: Why Your AI Benchmarks Are Lying to You

"If you measure the wrong thing, you optimize for the wrong thing. And when dealing with frontier, multimodal models, the wrong thing might just break your entire system without …

avatar
Rabimba Karanjai
•
The Hidden Performance Trap in Causal Ring Attention featured image

The Hidden Performance Trap in Causal Ring Attention

This post is a walkthrough of ring-flash-jax , a small JAX project that explores this problem and implements the fix. We'll add the four things you actually need before Ring …

avatar
Rabimba Karanjai
•
Unboxing Gemma: High-Throughput Sparse Autoencoder (SAE) Training on Google Cloud TPU v5e featured image

Unboxing Gemma: High-Throughput Sparse Autoencoder (SAE) Training on Google Cloud TPU v5e

A blog post about unboxing gemma: high-throughput sparse autoencoder (sae) training on google cloud tpu v5e

avatar
Rabimba Karanjai
•
The Gemma 4 E2B Fine-Tuning Cookbook featured image

The Gemma 4 E2B Fine-Tuning Cookbook

A complete, opinionated recipe for adapting Gemma 4 E2B to your domain — from multimodal dataset construction and QLoRA configuration through training loop debugging, evaluation, …

avatar
Rabimba Karanjai
•
Building a Multimodal Document Intelligence Pipeline with Gemma 4 E2B featured image

Building a Multimodal Document Intelligence Pipeline with Gemma 4 E2B

A production-grade walkthrough — PDF ingestion, OCR, audio transcription, structured reasoning, and agentic tool calling — all on a 2.3B parameter model that fits on a single …

avatar
Rabimba Karanjai
•
Write Once, Scale Everywhere featured image

Write Once, Scale Everywhere

End-to-End Gemma 2B LoRA Fine-Tuning and Serving on GPU & TPU If you have ever prototyped a Large Language Model LLM on your local GPU and then s......

avatar
Rabimba Karanjai
•
Visualizing the Invisible: How Nano Banana 2 Turns Dense Science into Stunning Art featured image

Visualizing the Invisible: How Nano Banana 2 Turns Dense Science into Stunning Art

Disclaimer: As a Google Developer Expert (GDE), I was incredibly fortunate to be invited by Google DeepMind to test these models internally before their public release. The …

avatar
Rabimba Karanjai
•
Fine-Tuning at the Redline: Architecting a Trustable AI Racing Coach featured image

Fine-Tuning at the Redline: Architecting a Trustable AI Racing Coach

" AI in a Jupyter notebook is safe. AI on a race track—at 150 mph—is a different story." - Ajeet Mirwani

avatar
Rabimba Karanjai
•
A Split‑Brain Neuro‑Symbolic Training Method for High‑Velocity Autonomous Coaching from Telemetry featured image

A Split‑Brain Neuro‑Symbolic Training Method for High‑Velocity Autonomous Coaching from Telemetry

A blog post about a split‑brain neuro‑symbolic training method for high‑velocity autonomous coaching from telemetry

avatar
Rabimba Karanjai
•
The Context Trap: Why Scaling Laws Can’t Break the Ceiling of Uncertainty featured image

The Context Trap: Why Scaling Laws Can’t Break the Ceiling of Uncertainty

We are currently living through the “ Post-Reasoning ” phase of the AI hype cycle. By now, models like Gemini 2.0 and the latest iterations of Gemini have normalized the idea that …

avatar
Rabimba Karanjai
•
🎤 SpeakWise: Build an AI Public Speaking Coach with Gemma 3n featured image

🎤 SpeakWise: Build an AI Public Speaking Coach with Gemma 3n

Project by: Rabimba Showcase for: Google Developer Expert (GDE) AI Sprint

avatar
Rabimba Karanjai
•
My Google I/O 2024 Adventure: A GDE's Front-Row Seat to the Gemini Era featured image

My Google I/O 2024 Adventure: A GDE's Front-Row Seat to the Gemini Era

Hey tech enthusiasts! Rabimba Karanjai here, your friendly neighborhood Google Developer Expert (GDE), back from an exhilarating whirlwind tour of Google I/O 2024. Let me tell you, …

avatar
Rabimba Karanjai
•
MovieBuff: Dive Deeper into Movies with Generative AI featured image

MovieBuff: Dive Deeper into Movies with Generative AI

MovieBuff: Dive Deeper into Movies Before You Watch MovieBuff: Dive Deeper into Movies Before You Watch Have you ever spent two hours watching a movie only to be disappointed? …

avatar
Rabimba Karanjai
•
Immersive Payment: Second Update featured image

Immersive Payment: Second Update

This is the second update to the Immersive Payment project update under the Grant For Web Fellowship. You can read the last report here: …

avatar
Rabimba Karanjai
•
Immersive Payment: First Update featured image

Immersive Payment: First Update

It has been more than 6 months now that I have had the Immersive Payments, Spark Grant. Since then I have worked on realizing the scope of the project and finally, I am here to …

avatar
Rabimba Karanjai
•
Attack of the Clones (Part 1): Drishti and vMeet featured image

Attack of the Clones (Part 1): Drishti and vMeet

Background : India recently banned certain Chinese Apps from being used and also with that launched a campaign of being vocal for local . Essentially promoting industries and app …

avatar
Rabimba Karanjai
•
Handling Web Server file permission: The Last Guide featured image

Handling Web Server file permission: The Last Guide

If you have to work with a LAMP stack one of the first things you do is setting up permission for your user and web server so that you can deploy files correctly and securely and …

avatar
Rabimba Karanjai
•
Help finding a cure for COVID19: Set up Folding@Home featured image

Help finding a cure for COVID19: Set up Folding@Home

COVID-19 has been already assigned as a pandemic worldwide now. It is now a global problem affecting all of our day to day lives. Almost all the methods of combating the virus at …

avatar
Rabimba Karanjai
•
Visualizing large scale Uber Movement Data featured image

Visualizing large scale Uber Movement Data

New York's cab data visualization from Uber's Engineering blog Last month one of my acquaintances in LinkedIn pointed me to a very interesting dataset. Uber's Movement Dataset. It …

avatar
Rabimba Karanjai
•