AI in Everyday Life | ashisharora.ai

Let's Make AI 'Real'

AI is everywhere!

But between the hype cycles and the headlines, the real understanding often gets lost.

This space is about staying grounded, breaking down what AI can actually do, where it falls short, and how to use it in ways that are legitimate, effective, and genuinely good.

Research-backed. Experience-driven. No hand-waving.

I Asked AI to Measure a Building. It looked up the Answer Instead

AI Can Look At a Video & Describe a Car Crash. It Can't Tell You How Fast the Car Was Going. Over the last few months, just like you - I've been using VLMs (Vision-Language Models) quite extensively, more aggressively than ever. Uploading screenshots, analysing dashcam clips, feeding product images, asking models to "look at this video and tell me what's happening." And I'll be honest - the results felt magical. "There's a yellow sedan moving left to right across the frame

Ashish Arora

9 min read

What's Actually Behind the AI Evaluation Hype?

What's behind the AI evaluation obsession? Over the last few months, I noticed something strange. Every AI paper I opened, every conference talk I watched, every product launch I followed - they all kept circling back to the same word: AI evaluations. Not training. Not fine-tuning. Not even prompting. Evaluations!! At first, I dismissed it as another benchmark fatigue - another leaderboard war. But this wasn't about 'measuring' models better. It was about 'teaching' them dif

Ashish Arora

7 min read

Stop Chunking Your CSVs: How I Built an AI That Reads Spreadsheets Like a Human

Last week, I walked into a meeting that started with what seemed like a simple question. "We've got PDF ingestion working great. How do we solve for CSVs and spreadsheets?" The room went quiet. You know that silence - the one where everyone's mentally calculating how much work just landed on the table? That was it. See, here's the thing. Chunking PDFs and text files into a RAG pipeline? That's pretty neat at this point. It's almost a solved problem. You split the document, ge

Ashish Arora

7 min read

2 3 4

Hey, I am Ashish.

An engineer who's spent the last 16+ years building with technology — and the last few years going deep on AI.

I write system prompts, build LLM-powered systems, and read more research papers than is probably healthy.

This blog exists because I noticed a gap. AI is everywhere now — in products, in conversations, in decisions that affect real people. But between the hype and the headlines, the actual understanding of how these systems work often gets lost.

I write to close that gap. I dig into the research and translate it into things practitioners and curious people can actually use. No hype. No hand-waving. Just grounded, research-backed insights about what AI can do, what it can't, and why the difference matters.

Before this, I spent years across roles — engineering, mentoring, building systems with open-source tools like Kubernetes. I've lived in India, Norway, Spain and Australia, and travelled through 17 countries.

These days I'm based in India, still building, still learning, and still convinced that the best way to understand something is to explain it clearly.

I am glad you are here.

Ashish Arora

Let's Make AI 'Real'

I Asked AI to Measure a Building. It looked up the Answer Instead

What's Actually Behind the AI Evaluation Hype?

Stop Chunking Your CSVs: How I Built an AI That Reads Spreadsheets Like a Human

About Me

Too Many Things To Do
In Too Tittle Time?

Never Miss a New Post.

Let's Make AI 'Real'

I Asked AI to Measure a Building. It looked up the Answer Instead

What's Actually Behind the AI Evaluation Hype?

Stop Chunking Your CSVs: How I Built an AI That Reads Spreadsheets Like a Human

About Me

Too Many Things To Do In Too Tittle Time? Never Miss a New Post.

Too Many Things To Do
In Too Tittle Time?

Never Miss a New Post.