📰 Dev.to · Mohit Verma

Articles from Dev.to · Mohit Verma · 5 articles · Updated every 3 hours · View all reads

All ⚡ AI Lessons (10078) ArXiv cs.AI Dev.to · FORUM WEB Forbes Innovation Dev.to AI OpenAI News Hugging Face Blog

Stop Using Fixed-Length Chunking: The 1 Change That Gave Us 40% Better RAG Precision

Dev.to · Mohit Verma 3d ago

Stop Using Fixed-Length Chunking: The 1 Change That Gave Us 40% Better RAG Precision

How swapping RecursiveCharacterTextSplitter for SemanticChunker in 2 hours delivered a 41% relative improvement in RAGAS context precision — with full

GraphRAG Beats Vector Search by 86% — But 92% of Teams Are Building It Wrong

Dev.to · Mohit Verma 3d ago

GraphRAG Beats Vector Search by 86% — But 92% of Teams Are Building It Wrong

Microsoft's GraphRAG achieves 86% on multi-hop queries — but only with entity resolution, community detection, and query routing. Most teams skip all

We Rebuilt Our RAG Pipeline 4 Times — Here's the Architecture That Finally Served 50K Daily Queries Under 800ms

Dev.to · Mohit Verma 3d ago

We Rebuilt Our RAG Pipeline 4 Times — Here's the Architecture That Finally Served 50K Daily Queries Under 800ms

A brutal post-mortem of 4 RAG pipeline rebuilds: fixed chunking failures, re-ranking latency traps, context stuffing degradation, and the final archit

Your LLM Is Lying to You Silently: 4 Statistical Signals That Catch Drift Before Users Do

Dev.to · Mohit Verma 2w ago

Your LLM Is Lying to You Silently: 4 Statistical Signals That Catch Drift Before Users Do

Your LLM returns HTTP 200 while silently degrading. Learn 4 statistical signals — KL divergence, embedding drift, LLM-as-judge, refusal fingerprinting

5 Data Engineering Techniques That Increased Our LLM Efficiency by 70%

Dev.to · Mohit Verma 3w ago

5 Data Engineering Techniques That Increased Our LLM Efficiency by 70%

Discover how data engineering techniques improved our LLM efficiency by 70%.