▶ Videos →

📰 Dev.to · Shrijith Venkatramana

37 articles · Updated every 3 hours · View all reads

All Articles 132,680 Blog Posts 137,323 Tech Tutorials 34,368 Research Papers 25,935 News 18,809 ⚡ AI Lessons

Beyond Code Generation: How OmniSVG Rethinks Vector Graphics with Vision-Language Models

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 3h ago

Beyond Code Generation: How OmniSVG Rethinks Vector Graphics with Vision-Language Models

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Adam: The Optimization Algorithm That Made LLMs Practical

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 2w ago

Adam: The Optimization Algorithm That Made LLMs Practical

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

The Small Mathematical Trick That Helped Make LLMs Possible: Understanding Layer Normalization

Dev.to · Shrijith Venkatramana 3w ago

The Small Mathematical Trick That Helped Make LLMs Possible: Understanding Layer Normalization

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Scaled Dot-Product Attention: The 4-Line Algorithm That Powers Modern LLMs

Dev.to · Shrijith Venkatramana 3w ago

Scaled Dot-Product Attention: The 4-Line Algorithm That Powers Modern LLMs

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

How We Actually Measure Whether an LLM's Output Is Good - BLEU, COMET and BLEURT

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 4w ago

How We Actually Measure Whether an LLM's Output Is Good - BLEU, COMET and BLEURT

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Synthetic Data: The Hidden Ingredient That Made Modern LLMs Scale

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 4w ago

Synthetic Data: The Hidden Ingredient That Made Modern LLMs Scale

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

The Scaling Laws That Made LLMs Work

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

The Scaling Laws That Made LLMs Work

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Reinforcement Learning with Verifiable Rewards: Why AI is Learning to Grade Its Own Homework

Dev.to · Shrijith Venkatramana 🎮 Reinforcement Learning ⚡ AI Lesson 1mo ago

Reinforcement Learning with Verifiable Rewards: Why AI is Learning to Grade Its Own Homework

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

The Three Phases of Post-Training: How LLMs Learn to Provide Sensible Responses

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

The Three Phases of Post-Training: How LLMs Learn to Provide Sensible Responses

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Attention Mechanisms in LLMs: The Idea That Changed AI Forever

Dev.to · Shrijith Venkatramana 1mo ago

Attention Mechanisms in LLMs: The Idea That Changed AI Forever

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

KV Cache in LLMs: The Optimization That Makes Modern AI Models Feel Fast

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

KV Cache in LLMs: The Optimization That Makes Modern AI Models Feel Fast

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

PEFT Explained: How to Fine-Tune LLMs Without Retraining Billions of Parameters

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

PEFT Explained: How to Fine-Tune LLMs Without Retraining Billions of Parameters

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

FlashAttention Explained: The Optimization That Made Modern LLMs Practical

Dev.to · Shrijith Venkatramana 1mo ago

FlashAttention Explained: The Optimization That Made Modern LLMs Practical

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Mixture of Experts (MoE) Explained Simply: How Modern AI Models Get Bigger Without Getting Slower

Dev.to · Shrijith Venkatramana 📐 ML Fundamentals ⚡ AI Lesson 1mo ago

Mixture of Experts (MoE) Explained Simply: How Modern AI Models Get Bigger Without Getting Slower

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Speculative Decoding: How LLMs Generate Tokens Faster Without Changing the Answer

Dev.to · Shrijith Venkatramana 1mo ago

Speculative Decoding: How LLMs Generate Tokens Faster Without Changing the Answer

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

The Top Golang Mocking Libraries in 2026: A Practical Comparison

Dev.to · Shrijith Venkatramana ⚡ AI Lesson 1mo ago

The Top Golang Mocking Libraries in 2026: A Practical Comparison

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Getting Started with Genkit in Go: Building Production-Ready AI Applications Without Reinventing the Wheel

Dev.to · Shrijith Venkatramana 💻 AI-Assisted Coding ⚡ AI Lesson 1mo ago

Getting Started with Genkit in Go: Building Production-Ready AI Applications Without Reinventing the Wheel

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Building Truly Cross-Platform Claude Code Hooks with Go, Bash, PowerShell, WSL, and Git-Bash

Dev.to · Shrijith Venkatramana 💻 AI-Assisted Coding ⚡ AI Lesson 1mo ago

Building Truly Cross-Platform Claude Code Hooks with Go, Bash, PowerShell, WSL, and Git-Bash

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Lean4 Might Be the Missing Piece in AI: Why Theorem Provers Are Suddenly Everywhere

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

Lean4 Might Be the Missing Piece in AI: Why Theorem Provers Are Suddenly Everywhere

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

I Pointed Chrome's Prompt API at a 1.25 Million Character Memoir, and It Got Interesting Fast

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 1mo ago

I Pointed Chrome's Prompt API at a 1.25 Million Character Memoir, and It Got Interesting Fast

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Type Inhabitation in Lean: Why “Hello {name}” Can Become a Theorem

Dev.to · Shrijith Venkatramana 1mo ago

Type Inhabitation in Lean: Why “Hello {name}” Can Become a Theorem

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Claude Code Hooks 101: Turning Your AI Coding Assistant Into an Automated Teammate

Dev.to · Shrijith Venkatramana 💻 AI-Assisted Coding ⚡ AI Lesson 2mo ago

Claude Code Hooks 101: Turning Your AI Coding Assistant Into an Automated Teammate

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Lean 4 for Programmers: Building a Todo List with Proof

Dev.to · Shrijith Venkatramana 🧠 Large Language Models ⚡ AI Lesson 2mo ago

Lean 4 for Programmers: Building a Todo List with Proof

Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every...

Lean 4 101 for Python Programmers: A Gentle Introduction to Theorem Proving

Dev.to · Shrijith Venkatramana 2mo ago

Lean 4 101 for Python Programmers: A Gentle Introduction to Theorem Proving

Before we begin — if you're interested in improving engineering quality and developer workflows,...