M.T.Ramkrushna - DEV Community

M.T.Ramkrushna

Nov 13

How do you ship a prompt change? (Friday AI question)

#discuss #ai #llm #testing

3 min read

M.T.Ramkrushna

Nov 13

Does your AI feature ever say "I don't know"? (Friday AI question)

#discuss #ai #llm #rag

1

3

3 min read

M.T.Ramkrushna

Nov 12

Presidio: detect and redact PII before your prompts reach the LLM

#ai #python #llm #security

7 min read

M.T.Ramkrushna

Nov 12

FastMCP: turn a Python function into an MCP tool Claude and Cursor can call

#aipythonmcpllm

6 min read

M.T.Ramkrushna

Nov 11

You Can't Prompt Your Way Out of Prompt Injection

#ai #security #llm #programming

4 min read

M.T.Ramkrushna

Nov 11

Max Reasoning Effort Is a Bad Default: More Thinking Can Make Your Model Worse

#ai #llm #machinelearning #programming

1

4

7 min read

M.T.Ramkrushna

Nov 10

Agent Memory Is Not a Junk Drawer: What Anthropic's Dreaming Experiments Teach About Building It

#ai #llm #agents #machinelearning

1

4

5 min read

M.T.Ramkrushna

Nov 10

70% of Requirements, 26% of Tasks: What Alibaba's Co-Design Bench Teaches About Evaluating Coding Agents

#ai #llm #programming #testing

7 min read

M.T.Ramkrushna

Nov 9

Your Agent Will Call the Same Tool Twice. Make Side-Effecting Tools Idempotent

#ai #llm #agents #python

4 min read

M.T.Ramkrushna

Nov 9

Your embedding model is a schema decision: how to choose it and plan the re-embed

#ai #rag #llm #machinelearning

1

6 min read

M.T.Ramkrushna

Nov 5

Outlines: stop parsing broken JSON — constrain the tokens instead

#aipythonllmdevops

4 min read

M.T.Ramkrushna

Nov 5

DSPy: stop hand-tuning prompts, write signatures and let a metric pick the prompt

#ai #llm #python #promptengineering

2

4

6 min read

M.T.Ramkrushna

Nov 4

You Probably Don't Need a Dedicated Vector Database (Yet)

#ai #postgres #rag #database

7 min read

M.T.Ramkrushna

Nov 4

Your Thumbs-Up Rate Is Lying to You: Stop Optimizing AI Features for User Approval

#ai #llm #machinelearning #programming

6 min read

M.T.Ramkrushna

Nov 3

An Open-Weight Model Turned Firefox Security Fixes Into Exploits. Your Patch Gap Is Now the Attack Surface

#ai #security #llm #devops

6 min read

M.T.Ramkrushna

Nov 3

Mistral Large 4 Is Open Weight. Read the License and Do the Memory Math Before You Self-Host

#ai #llm #opensource #mistral

5 min read

M.T.Ramkrushna

Nov 2

Your tool descriptions are prompts: how to write tools LLM agents actually use correctly

#ai #llm #agents #programming

5 min read

M.T.Ramkrushna

Nov 2

Few-shot examples teach format, not facts: how to pick, balance and order them

#ai #llm #promptengineering #machinelearning

4 min read

M.T.Ramkrushna

Oct 30

Is temperature 0 deterministic? How does your team handle LLM randomness?

#discuss #ai #llm #testing

4 min read

M.T.Ramkrushna

Oct 30

Do you log your LLM prompts and responses? Four answers, and the one I'd pick

#discuss #llm #privacy #ai

1

14

3 min read

M.T.Ramkrushna

Oct 29

Ragas: how to actually measure your RAG pipeline (faithfulness, context precision/recall, relevancy)

#ai #rag #python #llm

8 min read

M.T.Ramkrushna

Oct 29

Docling: turn messy PDFs into clean, heading-aware chunks for RAG

#ai #rag #python #llm

5 min read

M.T.Ramkrushna

Oct 28

Your model's reasoning trace is not an audit log

#ai #llm #agents #security

2

5 min read

M.T.Ramkrushna

Oct 28

Multi-agent is usually overkill: start with one agent and earn the second

#ai #llm #agents #architecture

3 min read

M.T.Ramkrushna

Oct 27

Markdown Is the New Executable: What the AGENTS.md-in-Downloads Attack Teaches Us About Coding Agent Security

#ai #security #agents #llm

7 min read

M.T.Ramkrushna

Oct 27

GPT-6.1 Terra and the Real Metric for Computer-Use Agents: Cost per Task, Not Price per Token

#ai #llm #agents #openai

5

4 min read

M.T.Ramkrushna

Oct 26

A 200 OK Can Still Be a Broken Answer: Check Why Your LLM Stopped

#ai #llm #python #programming

2

5 min read

M.T.Ramkrushna

Oct 26

RAG Chunking Done Right: Split on Structure, Attach Metadata, and Measure Recall Before You Touch chunk_size

#ai #rag #llm #python

2

6 min read

M.T.Ramkrushna

Oct 22

pgvector: Build RAG Retrieval Inside the Postgres You Already Run

#ai #postgres #rag #python

1

5 min read

M.T.Ramkrushna

Oct 22

Ollama: Run LLMs Locally and Swap Them Into Your App With One base_url Change

#ai #llm #python #tutorial

4 min read

M.T.Ramkrushna

Oct 21

AI-Generated Code Without Tests Is Technical Debt at Machine Speed

#ai #testing #programming #softwareengineering

4 min read

M.T.Ramkrushna

Oct 21

Long Context Windows Won't Kill RAG. Retrieval Was Never Just a Workaround for Small Windows.

#ai #rag #llm #programming

5 min read

M.T.Ramkrushna

Oct 20

AlphaProof Nexus Solved 9 Open Erdős Problems. The Lesson for AI Engineers Is the Verifier, Not the Model

#ai #llm #agents #machinelearning

8 min read

M.T.Ramkrushna

Oct 20

Mercury 3 and the Diffusion LLM Bet: What 1,000 Tokens per Second Changes for Agents (and What It Doesn't)

#ai #llm #machinelearning #programming

7 min read

M.T.Ramkrushna

Oct 19

Your LLM Judge Is Biased: Three Fixes Before You Trust Its Scores

#ai #llm #testing #python

4 min read

M.T.Ramkrushna

Oct 19

Hybrid Search for RAG: Why Your Vector Search Misses "TS-999" (and the 20-Line Fix)

#ai #rag #llm #python

3

4 min read

M.T.Ramkrushna

Oct 16

What's Actually Eating Your LLM Bill? Four Suspects to Check First

#ai #llm #devops #productivity

4 min read

M.T.Ramkrushna

Oct 16

Version Your AI Feature: Prompts and Evals Before Model Config

#ai #llm #devops #productivity

4 min read

M.T.Ramkrushna

Oct 15

Langfuse — Stop Debugging LLM Apps Blind

#ai #llm #python #devops

5 min read

M.T.Ramkrushna

Oct 15

LiteLLM Router — Stop Hardcoding One Provider Into Your App

#ai #llm #python #devops

3 min read

M.T.Ramkrushna

Oct 14

Fine-Tuning Is Usually Premature

#ai #llm #machinelearning #productivity

2

4 min read

M.T.Ramkrushna

Oct 14

Blank Chat Is the Wrong Default for Most Work AI

#ai #ux #product #llm

5 min read

M.T.Ramkrushna

Oct 13

Your Agent's Prompt Is Not a Permission System: Lessons from Anthropic's Unintended-Actions Report

#ai #security #llm #agents

8

8 min read

M.T.Ramkrushna

Oct 13

Decision models: when your AI should return a probability, not a paragraph

#ai #llm #machinelearning #opensource

5 min read

M.T.Ramkrushna

Oct 12

Lost in the Middle: Why LLMs Miss What's Buried in Long Prompts (and How to Fix It)

#ai #llm #machinelearning #softwareengineering

1

5 min read

M.T.Ramkrushna

Oct 12

Prompt Caching: Put the Stable Stuff First (and Stop Paying Twice for the Same Tokens)

#ai #llm #python #programming

1

4 min read

M.T.Ramkrushna

Oct 6

Reka's Rho-1: What Happens When One Model Replaces Your Multimodal Pipeline

#ai #machinelearning #robotics #computervision

4 min read

M.T.Ramkrushna

Oct 6

Reflection AI's Beam: Why 23B Active Parameters Matter More Than 501B

#ai #llm #opensource #machinelearning

3 min read

M.T.Ramkrushna

Oct 5

This Week in AI: Safety Standards, Watermarking, and Agent Memory

#news #ai #llm #agents

2 min read

M.T.Ramkrushna

Oct 3

14. Union-Find (DSU) + Minimum Spanning Trees

#ai #python #dsa

6 min read

M.T.Ramkrushna

Oct 3

Topic 13: Shortest Path Algorithms 🚀

#ai #python #dsa

7 min read

M.T.Ramkrushna

Oct 3

Topic 12: Graphs 🕸️

#ai #python #dsa

7 min read

M.T.Ramkrushna

Oct 3

Topic 11: Heaps & Priority Queues 🏔️

#ai #python #dsa

6 min read

M.T.Ramkrushna

Oct 3

Topic 10: Binary Search Trees - BST 🌲

#ai #dsa #python

6 min read

M.T.Ramkrushna

Oct 3

Topic 9: Trees — Binary Trees 🌳

#ai #python #dsa

7 min read

M.T.Ramkrushna

Sep 14

DSA: Topic 8: Linked Lists

#algorithms #computerscience #interview #python

7 min read

M.T.Ramkrushna

Sep 14

DSA: Topic 7: Queues, Deques & BFS

#algorithms #coding #interview #python

5 min read

M.T.Ramkrushna

Sep 14

DSA: Topic 6: Stacks & Monotonic Stack

#algorithms #coding #interview #python

5 min read

M.T.Ramkrushna

Sep 14

DSA: Topic 5: Binary Search

#algorithms #beginners #computerscience #interview

4 min read

M.T.Ramkrushna

Sep 14

DSA: Topic 4: Sliding Window

#algorithms #computerscience #interview #learning

3 min read

4 Week Community Wellness Streak

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Want to connect with M.T.Ramkrushna?